modelId
stringlengths 5
139
| author
stringlengths 2
42
| last_modified
timestamp[us, tz=UTC]date 2020-02-15 11:33:14
2025-09-01 18:27:28
| downloads
int64 0
223M
| likes
int64 0
11.7k
| library_name
stringclasses 532
values | tags
listlengths 1
4.05k
| pipeline_tag
stringclasses 55
values | createdAt
timestamp[us, tz=UTC]date 2022-03-02 23:29:04
2025-09-01 18:27:19
| card
stringlengths 11
1.01M
|
|---|---|---|---|---|---|---|---|---|---|
Yuichi1218/Llama-3.1-Non-filter-Lafeak64-8B
|
Yuichi1218
| 2025-06-25T02:37:45Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"llama",
"text-generation",
"text-generation-inference",
"unsloth",
"trl",
"conversational",
"en",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2025-06-25T02:06:37Z |
---
base_model: unsloth/meta-llama-3.1-8b-unsloth-bnb-4bit
tags:
- text-generation-inference
- transformers
- unsloth
- llama
- trl
license: apache-2.0
language:
- en
---
# Uploaded model
- **Developed by:** Yuichi1218
- **License:** apache-2.0
- **Finetuned from model :** unsloth/meta-llama-3.1-8b-unsloth-bnb-4bit
This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
|
NTIS/hf_gemma3_21-checkpoint-125000
|
NTIS
| 2025-06-25T02:37:15Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"gemma3_text",
"text-generation",
"pytorch",
"causal-lm",
"ko",
"en",
"license:apache-2.0",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2025-06-25T02:34:56Z |
---
license: apache-2.0
language:
- ko
- en
tags:
- text-generation
- pytorch
- causal-lm
library_name: transformers
---
# hf_gemma3_21-checkpoint-125000
์ด ๋ชจ๋ธ์ ํ์ธํ๋๋ ์ธ์ด ๋ชจ๋ธ ์ฒดํฌํฌ์ธํธ์
๋๋ค.
## ๋ชจ๋ธ ์ ๋ณด
- **๋ฒ ์ด์ค ๋ชจ๋ธ**: hf_gemma3_21
- **์ฒดํฌํฌ์ธํธ**: checkpoint-125000
- **ํ์
**: Causal Language Model
- **๋ผ์ด์ ์ค**: Apache 2.0
## ์ฌ์ฉ ๋ฐฉ๋ฒ
```python
from transformers import AutoModelForCausalLM, AutoTokenizer
import torch
model_name = "NTIS/hf_gemma3_21-checkpoint-125000"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
model_name,
torch_dtype=torch.float16,
device_map="auto"
)
# ํ
์คํธ ์์ฑ
text = "์๋
ํ์ธ์"
inputs = tokenizer(text, return_tensors="pt")
outputs = model.generate(**inputs, max_length=100, do_sample=True, temperature=0.7)
result = tokenizer.decode(outputs[0], skip_special_tokens=True)
print(result)
```
## ์ฃผ์์ฌํญ
- ์ด ๋ชจ๋ธ์ ์ฐ๊ตฌ/์คํ ๋ชฉ์ ์ผ๋ก ์ ๊ณต๋ฉ๋๋ค
- ์์
์ ์ฌ์ฉ ์ ์ ๋ผ์ด์ ์ค๋ฅผ ํ์ธํ์ธ์
|
pennylin09/tcp2023
|
pennylin09
| 2025-06-25T02:36:59Z | 0 | 0 | null |
[
"license:apache-2.0",
"region:us"
] | null | 2025-06-25T02:36:59Z |
---
license: apache-2.0
---
|
sam34738/muril-resnet-multilabel
|
sam34738
| 2025-06-25T02:36:42Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"multilabel_multimodal",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
] | null | 2025-06-25T02:35:51Z |
---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a ๐ค transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
|
13project/Qwen2.5-1.5B-Instruct-Gensyn-Swarm-clawed_shrewd_starfish
|
13project
| 2025-06-25T02:35:26Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"generated_from_trainer",
"rl-swarm",
"grpo",
"gensyn",
"I am clawed shrewd starfish",
"unsloth",
"trl",
"arxiv:2402.03300",
"base_model:Gensyn/Qwen2.5-1.5B-Instruct",
"base_model:finetune:Gensyn/Qwen2.5-1.5B-Instruct",
"endpoints_compatible",
"region:us"
] | null | 2025-06-22T03:14:14Z |
---
base_model: Gensyn/Qwen2.5-1.5B-Instruct
library_name: transformers
model_name: Qwen2.5-1.5B-Instruct-Gensyn-Swarm-clawed_shrewd_starfish
tags:
- generated_from_trainer
- rl-swarm
- grpo
- gensyn
- I am clawed shrewd starfish
- unsloth
- trl
licence: license
---
# Model Card for Qwen2.5-1.5B-Instruct-Gensyn-Swarm-clawed_shrewd_starfish
This model is a fine-tuned version of [Gensyn/Qwen2.5-1.5B-Instruct](https://huggingface.co/Gensyn/Qwen2.5-1.5B-Instruct).
It has been trained using [TRL](https://github.com/huggingface/trl).
## Quick start
```python
from transformers import pipeline
question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
generator = pipeline("text-generation", model="13project/Qwen2.5-1.5B-Instruct-Gensyn-Swarm-clawed_shrewd_starfish", device="cuda")
output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
print(output["generated_text"])
```
## Training procedure
This model was trained with GRPO, a method introduced in [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://huggingface.co/papers/2402.03300).
### Framework versions
- TRL: 0.15.2
- Transformers: 4.48.2
- Pytorch: 2.5.1
- Datasets: 3.6.0
- Tokenizers: 0.21.1
## Citations
Cite GRPO as:
```bibtex
@article{zhihong2024deepseekmath,
title = {{DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models}},
author = {Zhihong Shao and Peiyi Wang and Qihao Zhu and Runxin Xu and Junxiao Song and Mingchuan Zhang and Y. K. Li and Y. Wu and Daya Guo},
year = 2024,
eprint = {arXiv:2402.03300},
}
```
Cite TRL as:
```bibtex
@misc{vonwerra2022trl,
title = {{TRL: Transformer Reinforcement Learning}},
author = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallouรฉdec},
year = 2020,
journal = {GitHub repository},
publisher = {GitHub},
howpublished = {\url{https://github.com/huggingface/trl}}
}
```
|
carideeh/llama2_uuu_news_qlora
|
carideeh
| 2025-06-25T02:35:14Z | 0 | 0 | null |
[
"license:apache-2.0",
"region:us"
] | null | 2025-06-25T02:35:14Z |
---
license: apache-2.0
---
|
vincrnt/llama2_uuu_news_qlora
|
vincrnt
| 2025-06-25T02:34:55Z | 0 | 0 | null |
[
"license:apache-2.0",
"region:us"
] | null | 2025-06-25T02:34:55Z |
---
license: apache-2.0
---
|
thanhh12/aya-expanse-8b-Q6_K-GGUF
|
thanhh12
| 2025-06-25T02:34:10Z | 0 | 0 |
transformers
|
[
"transformers",
"gguf",
"llama-cpp",
"gguf-my-repo",
"en",
"fr",
"de",
"es",
"it",
"pt",
"ja",
"ko",
"zh",
"ar",
"el",
"fa",
"pl",
"id",
"cs",
"he",
"hi",
"nl",
"ro",
"ru",
"tr",
"uk",
"vi",
"base_model:CohereLabs/aya-expanse-8b",
"base_model:quantized:CohereLabs/aya-expanse-8b",
"license:cc-by-nc-4.0",
"region:us",
"conversational"
] | null | 2025-06-25T02:33:47Z |
---
inference: false
library_name: transformers
language:
- en
- fr
- de
- es
- it
- pt
- ja
- ko
- zh
- ar
- el
- fa
- pl
- id
- cs
- he
- hi
- nl
- ro
- ru
- tr
- uk
- vi
license: cc-by-nc-4.0
extra_gated_prompt: By submitting this form, you agree to the [License Agreement](https://cohere.com/c4ai-cc-by-nc-license) and
acknowledge that the information you provide will be collected, used, and shared
in accordance with Cohereโs [Privacy Policy]( https://cohere.com/privacy). Youโll
receive email updates about C4AI and Cohere research, events, products and services.
You can unsubscribe at any time.
extra_gated_fields:
Name: text
Affiliation: text
Country: country
I agree to use this model for non-commercial use ONLY: checkbox
tags:
- llama-cpp
- gguf-my-repo
base_model: CohereLabs/aya-expanse-8b
---
# thanhh12/aya-expanse-8b-Q6_K-GGUF
This model was converted to GGUF format from [`CohereLabs/aya-expanse-8b`](https://huggingface.co/CohereLabs/aya-expanse-8b) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
Refer to the [original model card](https://huggingface.co/CohereLabs/aya-expanse-8b) for more details on the model.
## Use with llama.cpp
Install llama.cpp through brew (works on Mac and Linux)
```bash
brew install llama.cpp
```
Invoke the llama.cpp server or the CLI.
### CLI:
```bash
llama-cli --hf-repo thanhh12/aya-expanse-8b-Q6_K-GGUF --hf-file aya-expanse-8b-q6_k.gguf -p "The meaning to life and the universe is"
```
### Server:
```bash
llama-server --hf-repo thanhh12/aya-expanse-8b-Q6_K-GGUF --hf-file aya-expanse-8b-q6_k.gguf -c 2048
```
Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) listed in the Llama.cpp repo as well.
Step 1: Clone llama.cpp from GitHub.
```
git clone https://github.com/ggerganov/llama.cpp
```
Step 2: Move into the llama.cpp folder and build it with `LLAMA_CURL=1` flag along with other hardware-specific flags (for ex: LLAMA_CUDA=1 for Nvidia GPUs on Linux).
```
cd llama.cpp && LLAMA_CURL=1 make
```
Step 3: Run inference through the main binary.
```
./llama-cli --hf-repo thanhh12/aya-expanse-8b-Q6_K-GGUF --hf-file aya-expanse-8b-q6_k.gguf -p "The meaning to life and the universe is"
```
or
```
./llama-server --hf-repo thanhh12/aya-expanse-8b-Q6_K-GGUF --hf-file aya-expanse-8b-q6_k.gguf -c 2048
```
|
vincrnt/tcp2023
|
vincrnt
| 2025-06-25T02:34:05Z | 0 | 0 | null |
[
"license:apache-2.0",
"region:us"
] | null | 2025-06-25T02:34:05Z |
---
license: apache-2.0
---
|
NTIS/hf_gemma3_21-checkpoint-123000
|
NTIS
| 2025-06-25T02:32:31Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"gemma3_text",
"text-generation",
"pytorch",
"causal-lm",
"ko",
"en",
"license:apache-2.0",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2025-06-25T02:30:10Z |
---
license: apache-2.0
language:
- ko
- en
tags:
- text-generation
- pytorch
- causal-lm
library_name: transformers
---
# hf_gemma3_21-checkpoint-123000
์ด ๋ชจ๋ธ์ ํ์ธํ๋๋ ์ธ์ด ๋ชจ๋ธ ์ฒดํฌํฌ์ธํธ์
๋๋ค.
## ๋ชจ๋ธ ์ ๋ณด
- **๋ฒ ์ด์ค ๋ชจ๋ธ**: hf_gemma3_21
- **์ฒดํฌํฌ์ธํธ**: checkpoint-123000
- **ํ์
**: Causal Language Model
- **๋ผ์ด์ ์ค**: Apache 2.0
## ์ฌ์ฉ ๋ฐฉ๋ฒ
```python
from transformers import AutoModelForCausalLM, AutoTokenizer
import torch
model_name = "NTIS/hf_gemma3_21-checkpoint-123000"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
model_name,
torch_dtype=torch.float16,
device_map="auto"
)
# ํ
์คํธ ์์ฑ
text = "์๋
ํ์ธ์"
inputs = tokenizer(text, return_tensors="pt")
outputs = model.generate(**inputs, max_length=100, do_sample=True, temperature=0.7)
result = tokenizer.decode(outputs[0], skip_special_tokens=True)
print(result)
```
## ์ฃผ์์ฌํญ
- ์ด ๋ชจ๋ธ์ ์ฐ๊ตฌ/์คํ ๋ชฉ์ ์ผ๋ก ์ ๊ณต๋ฉ๋๋ค
- ์์
์ ์ฌ์ฉ ์ ์ ๋ผ์ด์ ์ค๋ฅผ ํ์ธํ์ธ์
|
thanhh12/aya-expanse-8b-Q8_0-GGUF
|
thanhh12
| 2025-06-25T02:31:50Z | 0 | 0 |
transformers
|
[
"transformers",
"gguf",
"llama-cpp",
"gguf-my-repo",
"en",
"fr",
"de",
"es",
"it",
"pt",
"ja",
"ko",
"zh",
"ar",
"el",
"fa",
"pl",
"id",
"cs",
"he",
"hi",
"nl",
"ro",
"ru",
"tr",
"uk",
"vi",
"base_model:CohereLabs/aya-expanse-8b",
"base_model:quantized:CohereLabs/aya-expanse-8b",
"license:cc-by-nc-4.0",
"region:us",
"conversational"
] | null | 2025-06-25T02:31:22Z |
---
inference: false
library_name: transformers
language:
- en
- fr
- de
- es
- it
- pt
- ja
- ko
- zh
- ar
- el
- fa
- pl
- id
- cs
- he
- hi
- nl
- ro
- ru
- tr
- uk
- vi
license: cc-by-nc-4.0
extra_gated_prompt: By submitting this form, you agree to the [License Agreement](https://cohere.com/c4ai-cc-by-nc-license) and
acknowledge that the information you provide will be collected, used, and shared
in accordance with Cohereโs [Privacy Policy]( https://cohere.com/privacy). Youโll
receive email updates about C4AI and Cohere research, events, products and services.
You can unsubscribe at any time.
extra_gated_fields:
Name: text
Affiliation: text
Country: country
I agree to use this model for non-commercial use ONLY: checkbox
tags:
- llama-cpp
- gguf-my-repo
base_model: CohereLabs/aya-expanse-8b
---
# thanhh12/aya-expanse-8b-Q8_0-GGUF
This model was converted to GGUF format from [`CohereLabs/aya-expanse-8b`](https://huggingface.co/CohereLabs/aya-expanse-8b) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
Refer to the [original model card](https://huggingface.co/CohereLabs/aya-expanse-8b) for more details on the model.
## Use with llama.cpp
Install llama.cpp through brew (works on Mac and Linux)
```bash
brew install llama.cpp
```
Invoke the llama.cpp server or the CLI.
### CLI:
```bash
llama-cli --hf-repo thanhh12/aya-expanse-8b-Q8_0-GGUF --hf-file aya-expanse-8b-q8_0.gguf -p "The meaning to life and the universe is"
```
### Server:
```bash
llama-server --hf-repo thanhh12/aya-expanse-8b-Q8_0-GGUF --hf-file aya-expanse-8b-q8_0.gguf -c 2048
```
Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) listed in the Llama.cpp repo as well.
Step 1: Clone llama.cpp from GitHub.
```
git clone https://github.com/ggerganov/llama.cpp
```
Step 2: Move into the llama.cpp folder and build it with `LLAMA_CURL=1` flag along with other hardware-specific flags (for ex: LLAMA_CUDA=1 for Nvidia GPUs on Linux).
```
cd llama.cpp && LLAMA_CURL=1 make
```
Step 3: Run inference through the main binary.
```
./llama-cli --hf-repo thanhh12/aya-expanse-8b-Q8_0-GGUF --hf-file aya-expanse-8b-q8_0.gguf -p "The meaning to life and the universe is"
```
or
```
./llama-server --hf-repo thanhh12/aya-expanse-8b-Q8_0-GGUF --hf-file aya-expanse-8b-q8_0.gguf -c 2048
```
|
NTIS/hf_gemma3_21-checkpoint-121000
|
NTIS
| 2025-06-25T02:27:34Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"gemma3_text",
"text-generation",
"pytorch",
"causal-lm",
"ko",
"en",
"license:apache-2.0",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2025-06-25T02:25:06Z |
---
license: apache-2.0
language:
- ko
- en
tags:
- text-generation
- pytorch
- causal-lm
library_name: transformers
---
# hf_gemma3_21-checkpoint-121000
์ด ๋ชจ๋ธ์ ํ์ธํ๋๋ ์ธ์ด ๋ชจ๋ธ ์ฒดํฌํฌ์ธํธ์
๋๋ค.
## ๋ชจ๋ธ ์ ๋ณด
- **๋ฒ ์ด์ค ๋ชจ๋ธ**: hf_gemma3_21
- **์ฒดํฌํฌ์ธํธ**: checkpoint-121000
- **ํ์
**: Causal Language Model
- **๋ผ์ด์ ์ค**: Apache 2.0
## ์ฌ์ฉ ๋ฐฉ๋ฒ
```python
from transformers import AutoModelForCausalLM, AutoTokenizer
import torch
model_name = "NTIS/hf_gemma3_21-checkpoint-121000"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
model_name,
torch_dtype=torch.float16,
device_map="auto"
)
# ํ
์คํธ ์์ฑ
text = "์๋
ํ์ธ์"
inputs = tokenizer(text, return_tensors="pt")
outputs = model.generate(**inputs, max_length=100, do_sample=True, temperature=0.7)
result = tokenizer.decode(outputs[0], skip_special_tokens=True)
print(result)
```
## ์ฃผ์์ฌํญ
- ์ด ๋ชจ๋ธ์ ์ฐ๊ตฌ/์คํ ๋ชฉ์ ์ผ๋ก ์ ๊ณต๋ฉ๋๋ค
- ์์
์ ์ฌ์ฉ ์ ์ ๋ผ์ด์ ์ค๋ฅผ ํ์ธํ์ธ์
|
sergioalves/3a46e530-930d-484d-97c2-eaf9352c4f47
|
sergioalves
| 2025-06-25T02:27:09Z | 0 | 0 |
transformers
|
[
"transformers",
"pytorch",
"tensorboard",
"safetensors",
"mistral",
"text-generation",
"generated_from_trainer",
"axolotl",
"dpo",
"trl",
"conversational",
"arxiv:2305.18290",
"base_model:NousResearch/Nous-Capybara-7B-V1.9",
"base_model:quantized:NousResearch/Nous-Capybara-7B-V1.9",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"4-bit",
"bitsandbytes",
"region:us"
] |
text-generation
| 2025-06-25T01:59:42Z |
---
base_model: NousResearch/Nous-Capybara-7B-V1.9
library_name: transformers
model_name: 3a46e530-930d-484d-97c2-eaf9352c4f47
tags:
- generated_from_trainer
- axolotl
- dpo
- trl
licence: license
---
# Model Card for 3a46e530-930d-484d-97c2-eaf9352c4f47
This model is a fine-tuned version of [NousResearch/Nous-Capybara-7B-V1.9](https://huggingface.co/NousResearch/Nous-Capybara-7B-V1.9).
It has been trained using [TRL](https://github.com/huggingface/trl).
## Quick start
```python
from transformers import pipeline
question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
generator = pipeline("text-generation", model="sergioalves/3a46e530-930d-484d-97c2-eaf9352c4f47", device="cuda")
output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
print(output["generated_text"])
```
## Training procedure
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/dedok-yo/s56-7/runs/ckmz8kq3)
This model was trained with DPO, a method introduced in [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://huggingface.co/papers/2305.18290).
### Framework versions
- TRL: 0.12.0.dev0
- Transformers: 4.46.0
- Pytorch: 2.5.0+cu124
- Datasets: 3.0.1
- Tokenizers: 0.20.1
## Citations
Cite DPO as:
```bibtex
@inproceedings{rafailov2023direct,
title = {{Direct Preference Optimization: Your Language Model is Secretly a Reward Model}},
author = {Rafael Rafailov and Archit Sharma and Eric Mitchell and Christopher D. Manning and Stefano Ermon and Chelsea Finn},
year = 2023,
booktitle = {Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, NeurIPS 2023, New Orleans, LA, USA, December 10 - 16, 2023},
url = {http://papers.nips.cc/paper_files/paper/2023/hash/a85b405ed65c6477a4fe8302b5e06ce7-Abstract-Conference.html},
editor = {Alice Oh and Tristan Naumann and Amir Globerson and Kate Saenko and Moritz Hardt and Sergey Levine},
}
```
Cite TRL as:
```bibtex
@misc{vonwerra2022trl,
title = {{TRL: Transformer Reinforcement Learning}},
author = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallouรฉdec},
year = 2020,
journal = {GitHub repository},
publisher = {GitHub},
howpublished = {\url{https://github.com/huggingface/trl}}
}
```
|
rmdhirr/suja-v-3000
|
rmdhirr
| 2025-06-25T02:26:34Z | 0 | 0 |
peft
|
[
"peft",
"safetensors",
"arxiv:1910.09700",
"region:us"
] | null | 2025-06-25T02:26:25Z |
---
base_model: unsloth/llama-3.2-11b-vision-instruct-unsloth-bnb-4bit
library_name: peft
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
### Framework versions
- PEFT 0.15.2
|
JS1016/tcp2023
|
JS1016
| 2025-06-25T02:25:30Z | 0 | 0 | null |
[
"license:apache-2.0",
"region:us"
] | null | 2025-06-25T02:25:30Z |
---
license: apache-2.0
---
|
std10012/uuu_fine_tune_gpt2
|
std10012
| 2025-06-25T02:25:21Z | 0 | 0 | null |
[
"license:apache-2.0",
"region:us"
] | null | 2025-06-25T02:25:21Z |
---
license: apache-2.0
---
|
std10012/tcp2023
|
std10012
| 2025-06-25T02:24:50Z | 0 | 0 | null |
[
"license:apache-2.0",
"region:us"
] | null | 2025-06-25T02:24:50Z |
---
license: apache-2.0
---
|
ertghiu256/deepseek-r1-0528-qwen-3-test
|
ertghiu256
| 2025-06-25T02:24:23Z | 0 | 0 | null |
[
"license:apache-2.0",
"region:us"
] | null | 2025-06-25T02:24:23Z |
---
license: apache-2.0
---
|
Bill0204Tung/tcp2023
|
Bill0204Tung
| 2025-06-25T02:23:40Z | 0 | 0 | null |
[
"license:apache-2.0",
"region:us"
] | null | 2025-06-25T02:23:40Z |
---
license: apache-2.0
---
|
kaiwenw/single_node_run-step-100
|
kaiwenw
| 2025-06-25T02:22:44Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"qwen2",
"arxiv:1910.09700",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | null | 2025-06-25T02:22:09Z |
---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a ๐ค transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
|
chenrm/qwen3-30b-a3b-abliterated-lora
|
chenrm
| 2025-06-25T02:22:39Z | 0 | 0 |
peft
|
[
"peft",
"safetensors",
"gguf",
"mergekit",
"base_model:Qwen/Qwen3-30B-A3B",
"base_model:adapter:Qwen/Qwen3-30B-A3B",
"region:us"
] | null | 2025-06-25T02:22:10Z |
---
base_model:
- Qwen/Qwen3-30B-A3B
- mlabonne/Qwen3-30B-A3B-abliterated
library_name: peft
tags:
- mergekit
- peft
---
# qwen3-30b-a3b-abliterated-lora
This is a LoRA extracted from a language model. It was extracted using [mergekit](https://github.com/arcee-ai/mergekit).
## LoRA Details
This LoRA adapter was extracted from [mlabonne/Qwen3-30B-A3B-abliterated](https://huggingface.co/mlabonne/Qwen3-30B-A3B-abliterated) and uses [Qwen/Qwen3-30B-A3B](https://huggingface.co/Qwen/Qwen3-30B-A3B) as a base.
### Parameters
The following command was used to extract this LoRA adapter:
```sh
/venv/main/bin/mergekit-extract-lora --model mlabonne/Qwen3-30B-A3B-abliterated --base-model Qwen/Qwen3-30B-A3B --out-path qwen3-30b-a3b-abliterated-lora --cuda --max-rank 4
```
|
NTIS/hf_gemma3_21-checkpoint-119000
|
NTIS
| 2025-06-25T02:22:38Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"gemma3_text",
"text-generation",
"pytorch",
"causal-lm",
"ko",
"en",
"license:apache-2.0",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2025-06-25T02:20:11Z |
---
license: apache-2.0
language:
- ko
- en
tags:
- text-generation
- pytorch
- causal-lm
library_name: transformers
---
# hf_gemma3_21-checkpoint-119000
์ด ๋ชจ๋ธ์ ํ์ธํ๋๋ ์ธ์ด ๋ชจ๋ธ ์ฒดํฌํฌ์ธํธ์
๋๋ค.
## ๋ชจ๋ธ ์ ๋ณด
- **๋ฒ ์ด์ค ๋ชจ๋ธ**: hf_gemma3_21
- **์ฒดํฌํฌ์ธํธ**: checkpoint-119000
- **ํ์
**: Causal Language Model
- **๋ผ์ด์ ์ค**: Apache 2.0
## ์ฌ์ฉ ๋ฐฉ๋ฒ
```python
from transformers import AutoModelForCausalLM, AutoTokenizer
import torch
model_name = "NTIS/hf_gemma3_21-checkpoint-119000"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
model_name,
torch_dtype=torch.float16,
device_map="auto"
)
# ํ
์คํธ ์์ฑ
text = "์๋
ํ์ธ์"
inputs = tokenizer(text, return_tensors="pt")
outputs = model.generate(**inputs, max_length=100, do_sample=True, temperature=0.7)
result = tokenizer.decode(outputs[0], skip_special_tokens=True)
print(result)
```
## ์ฃผ์์ฌํญ
- ์ด ๋ชจ๋ธ์ ์ฐ๊ตฌ/์คํ ๋ชฉ์ ์ผ๋ก ์ ๊ณต๋ฉ๋๋ค
- ์์
์ ์ฌ์ฉ ์ ์ ๋ผ์ด์ ์ค๋ฅผ ํ์ธํ์ธ์
|
Stonersheart/uuu_fine_tune_taipower
|
Stonersheart
| 2025-06-25T02:20:42Z | 0 | 0 | null |
[
"license:apache-2.0",
"region:us"
] | null | 2025-06-25T02:20:42Z |
---
license: apache-2.0
---
|
Kiwiciou/tcp2023
|
Kiwiciou
| 2025-06-25T02:20:26Z | 0 | 0 | null |
[
"license:apache-2.0",
"region:us"
] | null | 2025-06-25T02:20:26Z |
---
license: apache-2.0
---
|
ar7w7in/gemma-3-text-4b-it-4bit
|
ar7w7in
| 2025-06-25T02:18:45Z | 0 | 0 |
mlx
|
[
"mlx",
"safetensors",
"gemma3",
"text-generation",
"conversational",
"base_model:mlx-community/gemma-3-text-4b-it-4bit",
"base_model:quantized:mlx-community/gemma-3-text-4b-it-4bit",
"license:gemma",
"4-bit",
"region:us"
] |
text-generation
| 2025-06-25T02:16:12Z |
---
license: gemma
library_name: mlx
pipeline_tag: text-generation
extra_gated_heading: Access Gemma on Hugging Face
extra_gated_prompt: To access Gemma on Hugging Face, youโre required to review and
agree to Googleโs usage license. To do this, please ensure youโre logged in to Hugging
Face and click below. Requests are processed immediately.
extra_gated_button_content: Acknowledge license
base_model: mlx-community/gemma-3-text-4b-it-4bit
tags:
- mlx
---
|
newtts2017/sbn0lt36
|
newtts2017
| 2025-06-25T02:18:17Z | 0 | 0 |
diffusers
|
[
"diffusers",
"flux",
"lora",
"replicate",
"text-to-image",
"en",
"base_model:black-forest-labs/FLUX.1-dev",
"base_model:adapter:black-forest-labs/FLUX.1-dev",
"license:other",
"region:us"
] |
text-to-image
| 2025-06-25T02:08:58Z |
---
license: other
license_name: flux-1-dev-non-commercial-license
license_link: https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md
language:
- en
tags:
- flux
- diffusers
- lora
- replicate
base_model: "black-forest-labs/FLUX.1-dev"
pipeline_tag: text-to-image
# widget:
# - text: >-
# prompt
# output:
# url: https://...
instance_prompt: sbn0lt36
---
# Sbn0Lt36
<Gallery />
## About this LoRA
This is a [LoRA](https://replicate.com/docs/guides/working-with-loras) for the FLUX.1-dev text-to-image model. It can be used with diffusers or ComfyUI.
It was trained on [Replicate](https://replicate.com/) using AI toolkit: https://replicate.com/ostris/flux-dev-lora-trainer/train
## Trigger words
You should use `sbn0lt36` to trigger the image generation.
## Run this LoRA with an API using Replicate
```py
import replicate
input = {
"prompt": "sbn0lt36",
"lora_weights": "https://huggingface.co/newtts2017/sbn0lt36/resolve/main/lora.safetensors"
}
output = replicate.run(
"black-forest-labs/flux-dev-lora",
input=input
)
for index, item in enumerate(output):
with open(f"output_{index}.webp", "wb") as file:
file.write(item.read())
```
## Use it with the [๐งจ diffusers library](https://github.com/huggingface/diffusers)
```py
from diffusers import AutoPipelineForText2Image
import torch
pipeline = AutoPipelineForText2Image.from_pretrained('black-forest-labs/FLUX.1-dev', torch_dtype=torch.float16).to('cuda')
pipeline.load_lora_weights('newtts2017/sbn0lt36', weight_name='lora.safetensors')
image = pipeline('sbn0lt36').images[0]
```
For more details, including weighting, merging and fusing LoRAs, check the [documentation on loading LoRAs in diffusers](https://huggingface.co/docs/diffusers/main/en/using-diffusers/loading_adapters)
## Training details
- Steps: 1000
- Learning rate: 0.0004
- LoRA rank: 16
## Contribute your own examples
You can use the [community tab](https://huggingface.co/newtts2017/sbn0lt36/discussions) to add images that show off what youโve made with this LoRA.
|
synkrotron/grasp_cube
|
synkrotron
| 2025-06-25T02:12:07Z | 0 | 0 | null |
[
"license:mit",
"region:us"
] | null | 2025-06-24T06:22:27Z |
---
license: mit
---
Models for [FlexUMI](https://github.com/CortexNest/FlexUMI)
|
hasdal/2400ab9a-7625-429f-9dea-1562c55e7556
|
hasdal
| 2025-06-25T02:10:08Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"llama",
"text-generation",
"unsloth",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"4-bit",
"bitsandbytes",
"region:us"
] |
text-generation
| 2025-06-25T02:03:28Z |
---
library_name: transformers
tags:
- unsloth
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a ๐ค transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
|
deepmaster/72_9
|
deepmaster
| 2025-06-25T02:08:09Z | 18 | 0 |
transformers
|
[
"transformers",
"safetensors",
"vit",
"image-classification",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
image-classification
| 2025-06-08T18:59:19Z |
---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a ๐ค transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
|
ambashs1/rocks-pebbles-stone-classification
|
ambashs1
| 2025-06-25T02:04:09Z | 0 | 0 | null |
[
"time-management",
"productivity",
"text-classification",
"license:apache-2.0",
"region:us"
] |
text-classification
| 2025-06-25T02:02:58Z |
---
license: apache-2.0
pipeline_tag: text-classification
tags:
- time-management
- productivity
---
|
zecaihong/3e7e19dc-0008-4038-bacf-b95d034953d3
|
zecaihong
| 2025-06-25T02:03:30Z | 0 | 0 |
peft
|
[
"peft",
"safetensors",
"qwen2",
"axolotl",
"generated_from_trainer",
"base_model:unsloth/Qwen2.5-Coder-7B",
"base_model:adapter:unsloth/Qwen2.5-Coder-7B",
"license:apache-2.0",
"region:us"
] | null | 2025-06-25T01:10:49Z |
---
library_name: peft
license: apache-2.0
base_model: unsloth/Qwen2.5-Coder-7B
tags:
- axolotl
- generated_from_trainer
model-index:
- name: 3e7e19dc-0008-4038-bacf-b95d034953d3
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
[<img src="https://raw.githubusercontent.com/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/axolotl-ai-cloud/axolotl)
<details><summary>See axolotl config</summary>
axolotl version: `0.10.0.dev0`
```yaml
adapter: lora
base_model: unsloth/Qwen2.5-Coder-7B
bf16: auto
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
- 5686eaedee397c04_train_data.json
ds_type: json
format: custom
path: /workspace/input_data/
type:
field_instruction: instruct
field_output: output
format: '{instruction}'
no_input_format: '{instruction}'
system_prompt: ''
debug: null
deepspeed: deepspeed_configs/zero2.json
early_stopping_patience: 3
eval_max_new_tokens: 1024
eval_steps: 100
eval_table_size: null
flash_attention: true
fp16: null
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 2
gradient_checkpointing: false
greater_is_better: false
group_by_length: false
hub_model_id: zecaihong/3e7e19dc-0008-4038-bacf-b95d034953d3
hub_repo: null
hub_strategy: checkpoint
hub_token: null
learning_rate: 0.0003
load_in_4bit: false
load_in_8bit: false
local_rank: null
logging_steps: 10
lora_alpha: 16
lora_dropout: 0.05
lora_fan_in_fan_out: null
lora_model_dir: null
lora_r: 8
lora_target_linear: true
lr_scheduler: cosine
max_steps: -1
metric_for_best_model: eval_loss
micro_batch_size: 12
mlflow_experiment_name: /data/datasets/5686eaedee397c04_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 6
optimizer: adamw_torch
output_dir: miner_id_24
pad_to_sequence_len: true
resume_from_checkpoint: null
s2_attention: null
sample_packing: false
save_steps: 100
sequence_len: 1024
strict: false
tf32: false
tokenizer_type: AutoTokenizer
train_on_inputs: false
trust_remote_code: true
val_set_size: 0.05
wandb_entity: null
wandb_mode: online
wandb_name: 3e7e19dc-0008-4038-bacf-b95d034953d3
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: 3e7e19dc-0008-4038-bacf-b95d034953d3
warmup_steps: 100
weight_decay: 0.001
xformers_attention: null
```
</details><br>
# 3e7e19dc-0008-4038-bacf-b95d034953d3
This model is a fine-tuned version of [unsloth/Qwen2.5-Coder-7B](https://huggingface.co/unsloth/Qwen2.5-Coder-7B) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.7892
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0003
- train_batch_size: 12
- eval_batch_size: 12
- seed: 42
- distributed_type: multi-GPU
- num_devices: 8
- gradient_accumulation_steps: 2
- total_train_batch_size: 192
- total_eval_batch_size: 96
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 100
- num_epochs: 6.0
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:------:|:----:|:---------------:|
| No log | 0.0026 | 1 | 1.5980 |
| 0.9177 | 0.2614 | 100 | 0.9130 |
| 0.8841 | 0.5229 | 200 | 0.8498 |
| 0.8175 | 0.7843 | 300 | 0.8225 |
| 0.7432 | 1.0444 | 400 | 0.8072 |
| 0.7652 | 1.3059 | 500 | 0.7970 |
| 0.7343 | 1.5673 | 600 | 0.7872 |
| 0.7365 | 1.8288 | 700 | 0.7771 |
| 0.6479 | 2.0889 | 800 | 0.7855 |
| 0.6718 | 2.3503 | 900 | 0.7833 |
| 0.672 | 2.6118 | 1000 | 0.7753 |
| 0.6859 | 2.8732 | 1100 | 0.7718 |
| 0.565 | 3.1333 | 1200 | 0.7968 |
| 0.5416 | 3.3948 | 1300 | 0.7945 |
| 0.5761 | 3.6562 | 1400 | 0.7892 |
### Framework versions
- PEFT 0.15.2
- Transformers 4.52.3
- Pytorch 2.5.1+cu124
- Datasets 3.6.0
- Tokenizers 0.21.1
|
yahayaha223/5b960f4d-986a-46ee-95aa-a9f358f95552
|
yahayaha223
| 2025-06-25T02:01:59Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"mistral",
"text-generation",
"unsloth",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2025-06-24T16:11:08Z |
---
library_name: transformers
tags:
- unsloth
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a ๐ค transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
|
NTIS/hf_gemma3_2-checkpoint-108000
|
NTIS
| 2025-06-25T02:01:01Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"gemma3_text",
"text-generation",
"pytorch",
"causal-lm",
"ko",
"en",
"license:apache-2.0",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2025-06-24T05:28:32Z |
---
license: apache-2.0
language:
- ko
- en
tags:
- text-generation
- pytorch
- causal-lm
library_name: transformers
---
# hf_gemma3_2-checkpoint-108000
์ด ๋ชจ๋ธ์ ํ์ธํ๋๋ ์ธ์ด ๋ชจ๋ธ ์ฒดํฌํฌ์ธํธ์
๋๋ค.
## ๋ชจ๋ธ ์ ๋ณด
- **๋ฒ ์ด์ค ๋ชจ๋ธ**: hf_gemma3_2
- **์ฒดํฌํฌ์ธํธ**: checkpoint-108000
- **ํ์
**: Causal Language Model
- **๋ผ์ด์ ์ค**: Apache 2.0
## ์ฌ์ฉ ๋ฐฉ๋ฒ
```python
from transformers import AutoModelForCausalLM, AutoTokenizer
import torch
model_name = "NTIS/hf_gemma3_2-checkpoint-108000"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
model_name,
torch_dtype=torch.float16,
device_map="auto"
)
# ํ
์คํธ ์์ฑ
text = "์๋
ํ์ธ์"
inputs = tokenizer(text, return_tensors="pt")
outputs = model.generate(**inputs, max_length=100, do_sample=True, temperature=0.7)
result = tokenizer.decode(outputs[0], skip_special_tokens=True)
print(result)
```
## ์ฃผ์์ฌํญ
- ์ด ๋ชจ๋ธ์ ์ฐ๊ตฌ/์คํ ๋ชฉ์ ์ผ๋ก ์ ๊ณต๋ฉ๋๋ค
- ์์
์ ์ฌ์ฉ ์ ์ ๋ผ์ด์ ์ค๋ฅผ ํ์ธํ์ธ์
|
mradermacher/GLM-4-32B-Base-32K-i1-GGUF
|
mradermacher
| 2025-06-25T02:00:22Z | 0 | 0 |
transformers
|
[
"transformers",
"gguf",
"zh",
"en",
"base_model:arcee-ai/GLM-4-32B-Base-32K",
"base_model:quantized:arcee-ai/GLM-4-32B-Base-32K",
"license:mit",
"endpoints_compatible",
"region:us",
"imatrix"
] | null | 2025-06-24T19:16:01Z |
---
base_model: arcee-ai/GLM-4-32B-Base-32K
language:
- zh
- en
library_name: transformers
license: mit
quantized_by: mradermacher
---
## About
<!-- ### quantize_version: 2 -->
<!-- ### output_tensor_quantised: 1 -->
<!-- ### convert_type: hf -->
<!-- ### vocab_type: -->
<!-- ### tags: nicoboss -->
weighted/imatrix quants of https://huggingface.co/arcee-ai/GLM-4-32B-Base-32K
<!-- provided-files -->
static quants are available at https://huggingface.co/mradermacher/GLM-4-32B-Base-32K-GGUF
## Usage
If you are unsure how to use GGUF files, refer to one of [TheBloke's
READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
more details, including on how to concatenate multi-part files.
## Provided Quants
(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
| Link | Type | Size/GB | Notes |
|:-----|:-----|--------:|:------|
| [GGUF](https://huggingface.co/mradermacher/GLM-4-32B-Base-32K-i1-GGUF/resolve/main/GLM-4-32B-Base-32K.i1-IQ1_S.gguf) | i1-IQ1_S | 7.4 | for the desperate |
| [GGUF](https://huggingface.co/mradermacher/GLM-4-32B-Base-32K-i1-GGUF/resolve/main/GLM-4-32B-Base-32K.i1-IQ1_M.gguf) | i1-IQ1_M | 8.0 | mostly desperate |
| [GGUF](https://huggingface.co/mradermacher/GLM-4-32B-Base-32K-i1-GGUF/resolve/main/GLM-4-32B-Base-32K.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 9.1 | |
| [GGUF](https://huggingface.co/mradermacher/GLM-4-32B-Base-32K-i1-GGUF/resolve/main/GLM-4-32B-Base-32K.i1-IQ2_XS.gguf) | i1-IQ2_XS | 10.0 | |
| [GGUF](https://huggingface.co/mradermacher/GLM-4-32B-Base-32K-i1-GGUF/resolve/main/GLM-4-32B-Base-32K.i1-IQ2_S.gguf) | i1-IQ2_S | 10.5 | |
| [GGUF](https://huggingface.co/mradermacher/GLM-4-32B-Base-32K-i1-GGUF/resolve/main/GLM-4-32B-Base-32K.i1-IQ2_M.gguf) | i1-IQ2_M | 11.4 | |
| [GGUF](https://huggingface.co/mradermacher/GLM-4-32B-Base-32K-i1-GGUF/resolve/main/GLM-4-32B-Base-32K.i1-Q2_K_S.gguf) | i1-Q2_K_S | 11.5 | very low quality |
| [GGUF](https://huggingface.co/mradermacher/GLM-4-32B-Base-32K-i1-GGUF/resolve/main/GLM-4-32B-Base-32K.i1-Q2_K.gguf) | i1-Q2_K | 12.4 | IQ3_XXS probably better |
| [GGUF](https://huggingface.co/mradermacher/GLM-4-32B-Base-32K-i1-GGUF/resolve/main/GLM-4-32B-Base-32K.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 12.9 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/GLM-4-32B-Base-32K-i1-GGUF/resolve/main/GLM-4-32B-Base-32K.i1-IQ3_XS.gguf) | i1-IQ3_XS | 13.8 | |
| [GGUF](https://huggingface.co/mradermacher/GLM-4-32B-Base-32K-i1-GGUF/resolve/main/GLM-4-32B-Base-32K.i1-Q3_K_S.gguf) | i1-Q3_K_S | 14.5 | IQ3_XS probably better |
| [GGUF](https://huggingface.co/mradermacher/GLM-4-32B-Base-32K-i1-GGUF/resolve/main/GLM-4-32B-Base-32K.i1-IQ3_S.gguf) | i1-IQ3_S | 14.5 | beats Q3_K* |
| [GGUF](https://huggingface.co/mradermacher/GLM-4-32B-Base-32K-i1-GGUF/resolve/main/GLM-4-32B-Base-32K.i1-IQ3_M.gguf) | i1-IQ3_M | 14.9 | |
| [GGUF](https://huggingface.co/mradermacher/GLM-4-32B-Base-32K-i1-GGUF/resolve/main/GLM-4-32B-Base-32K.i1-Q3_K_M.gguf) | i1-Q3_K_M | 16.0 | IQ3_S probably better |
| [GGUF](https://huggingface.co/mradermacher/GLM-4-32B-Base-32K-i1-GGUF/resolve/main/GLM-4-32B-Base-32K.i1-Q3_K_L.gguf) | i1-Q3_K_L | 17.3 | IQ3_M probably better |
| [GGUF](https://huggingface.co/mradermacher/GLM-4-32B-Base-32K-i1-GGUF/resolve/main/GLM-4-32B-Base-32K.i1-IQ4_XS.gguf) | i1-IQ4_XS | 17.7 | |
| [GGUF](https://huggingface.co/mradermacher/GLM-4-32B-Base-32K-i1-GGUF/resolve/main/GLM-4-32B-Base-32K.i1-Q4_0.gguf) | i1-Q4_0 | 18.7 | fast, low quality |
| [GGUF](https://huggingface.co/mradermacher/GLM-4-32B-Base-32K-i1-GGUF/resolve/main/GLM-4-32B-Base-32K.i1-Q4_K_S.gguf) | i1-Q4_K_S | 18.8 | optimal size/speed/quality |
| [GGUF](https://huggingface.co/mradermacher/GLM-4-32B-Base-32K-i1-GGUF/resolve/main/GLM-4-32B-Base-32K.i1-Q4_K_M.gguf) | i1-Q4_K_M | 19.8 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/GLM-4-32B-Base-32K-i1-GGUF/resolve/main/GLM-4-32B-Base-32K.i1-Q4_1.gguf) | i1-Q4_1 | 20.6 | |
| [GGUF](https://huggingface.co/mradermacher/GLM-4-32B-Base-32K-i1-GGUF/resolve/main/GLM-4-32B-Base-32K.i1-Q5_K_S.gguf) | i1-Q5_K_S | 22.6 | |
| [GGUF](https://huggingface.co/mradermacher/GLM-4-32B-Base-32K-i1-GGUF/resolve/main/GLM-4-32B-Base-32K.i1-Q5_K_M.gguf) | i1-Q5_K_M | 23.2 | |
| [GGUF](https://huggingface.co/mradermacher/GLM-4-32B-Base-32K-i1-GGUF/resolve/main/GLM-4-32B-Base-32K.i1-Q6_K.gguf) | i1-Q6_K | 26.8 | practically like static Q6_K |
Here is a handy graph by ikawrakow comparing some lower-quality quant
types (lower is better):
And here are Artefact2's thoughts on the matter:
https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
## FAQ / Model Request
See https://huggingface.co/mradermacher/model_requests for some answers to
questions you might have and/or if you want some other model quantized.
## Thanks
I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
me use its servers and providing upgrades to my workstation to enable
this work in my free time. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to.
<!-- end -->
|
NTIS/hf_gemma3_2-checkpoint-107000
|
NTIS
| 2025-06-25T01:58:42Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"gemma3_text",
"text-generation",
"pytorch",
"causal-lm",
"ko",
"en",
"license:apache-2.0",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2025-06-24T05:26:14Z |
---
license: apache-2.0
language:
- ko
- en
tags:
- text-generation
- pytorch
- causal-lm
library_name: transformers
---
# hf_gemma3_2-checkpoint-107000
์ด ๋ชจ๋ธ์ ํ์ธํ๋๋ ์ธ์ด ๋ชจ๋ธ ์ฒดํฌํฌ์ธํธ์
๋๋ค.
## ๋ชจ๋ธ ์ ๋ณด
- **๋ฒ ์ด์ค ๋ชจ๋ธ**: hf_gemma3_2
- **์ฒดํฌํฌ์ธํธ**: checkpoint-107000
- **ํ์
**: Causal Language Model
- **๋ผ์ด์ ์ค**: Apache 2.0
## ์ฌ์ฉ ๋ฐฉ๋ฒ
```python
from transformers import AutoModelForCausalLM, AutoTokenizer
import torch
model_name = "NTIS/hf_gemma3_2-checkpoint-107000"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
model_name,
torch_dtype=torch.float16,
device_map="auto"
)
# ํ
์คํธ ์์ฑ
text = "์๋
ํ์ธ์"
inputs = tokenizer(text, return_tensors="pt")
outputs = model.generate(**inputs, max_length=100, do_sample=True, temperature=0.7)
result = tokenizer.decode(outputs[0], skip_special_tokens=True)
print(result)
```
## ์ฃผ์์ฌํญ
- ์ด ๋ชจ๋ธ์ ์ฐ๊ตฌ/์คํ ๋ชฉ์ ์ผ๋ก ์ ๊ณต๋ฉ๋๋ค
- ์์
์ ์ฌ์ฉ ์ ์ ๋ผ์ด์ ์ค๋ฅผ ํ์ธํ์ธ์
|
hasdal/53565329-6445-47b8-92e1-60ad8031a6cb
|
hasdal
| 2025-06-25T01:57:49Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"llama",
"text-generation",
"unsloth",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"4-bit",
"bitsandbytes",
"region:us"
] |
text-generation
| 2025-06-25T01:46:46Z |
---
library_name: transformers
tags:
- unsloth
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a ๐ค transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
|
crosstar/mistral_5_CoT_generated_sciq
|
crosstar
| 2025-06-25T01:57:32Z | 0 | 1 |
transformers
|
[
"transformers",
"safetensors",
"mistral",
"text-generation",
"trl",
"sft",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"4-bit",
"bitsandbytes",
"region:us"
] |
text-generation
| 2025-06-24T10:45:44Z |
---
library_name: transformers
tags:
- trl
- sft
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a ๐ค transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
|
growingduck/OpenFWI_EnsembleNet_20250625_015440
|
growingduck
| 2025-06-25T01:55:13Z | 0 | 0 | null |
[
"pytorch",
"region:us"
] | null | 2025-06-25T01:54:40Z |
# OpenFWI Ensemble Best Model
Saved at: 20250625_015440
Validation MAE: 2893.56
Includes ConvNeXtV2 + CaFormer backbones.
|
versaceeros/ac07e322-f0c7-4f0c-b4c3-80468cb6f828
|
versaceeros
| 2025-06-25T01:51:58Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"llama",
"text-generation",
"unsloth",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"4-bit",
"bitsandbytes",
"region:us"
] |
text-generation
| 2025-06-25T01:44:13Z |
---
library_name: transformers
tags:
- unsloth
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a ๐ค transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
|
NTIS/hf_gemma3_2-checkpoint-103000
|
NTIS
| 2025-06-25T01:48:59Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"gemma3_text",
"text-generation",
"pytorch",
"causal-lm",
"ko",
"en",
"license:apache-2.0",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2025-06-24T05:21:11Z |
---
license: apache-2.0
language:
- ko
- en
tags:
- text-generation
- pytorch
- causal-lm
library_name: transformers
---
# hf_gemma3_2-checkpoint-103000
์ด ๋ชจ๋ธ์ ํ์ธํ๋๋ ์ธ์ด ๋ชจ๋ธ ์ฒดํฌํฌ์ธํธ์
๋๋ค.
## ๋ชจ๋ธ ์ ๋ณด
- **๋ฒ ์ด์ค ๋ชจ๋ธ**: hf_gemma3_2
- **์ฒดํฌํฌ์ธํธ**: checkpoint-103000
- **ํ์
**: Causal Language Model
- **๋ผ์ด์ ์ค**: Apache 2.0
## ์ฌ์ฉ ๋ฐฉ๋ฒ
```python
from transformers import AutoModelForCausalLM, AutoTokenizer
import torch
model_name = "NTIS/hf_gemma3_2-checkpoint-103000"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
model_name,
torch_dtype=torch.float16,
device_map="auto"
)
# ํ
์คํธ ์์ฑ
text = "์๋
ํ์ธ์"
inputs = tokenizer(text, return_tensors="pt")
outputs = model.generate(**inputs, max_length=100, do_sample=True, temperature=0.7)
result = tokenizer.decode(outputs[0], skip_special_tokens=True)
print(result)
```
## ์ฃผ์์ฌํญ
- ์ด ๋ชจ๋ธ์ ์ฐ๊ตฌ/์คํ ๋ชฉ์ ์ผ๋ก ์ ๊ณต๋ฉ๋๋ค
- ์์
์ ์ฌ์ฉ ์ ์ ๋ผ์ด์ ์ค๋ฅผ ํ์ธํ์ธ์
|
daixuancheng/rerun_sac-init0.4_qwen-math-7b_constrainbyAdv_step280
|
daixuancheng
| 2025-06-25T01:48:57Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"qwen2",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2025-06-25T01:25:22Z |
---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a ๐ค transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
|
fnlp/qwen2-0_5B-rope8-d_kv_16-refactor
|
fnlp
| 2025-06-25T01:47:41Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"qwen2",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2025-06-25T01:46:21Z |
---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a ๐ค transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
|
Cameron914/tcp2023
|
Cameron914
| 2025-06-25T01:33:48Z | 0 | 0 | null |
[
"license:apache-2.0",
"region:us"
] | null | 2025-06-25T01:33:48Z |
---
license: apache-2.0
---
|
mlx-community/Llama-3.2-8X4B-MOE-V2-Dark-Champion-Instruct-uncensored-abliterated-21B-Q_6-MLX
|
mlx-community
| 2025-06-25T01:28:13Z | 0 | 0 |
mlx
|
[
"mlx",
"safetensors",
"mixtral",
"Llama 3.2",
"8 X 4B",
"Brainstorm 5x",
"128k context",
"moe",
"8 experts",
"mixture of experts",
"fine tune",
"text-generation",
"conversational",
"base_model:DavidAU/L3.2-8X4B-MOE-V2-Dark-Champion-Inst-21B-uncen-ablit",
"base_model:quantized:DavidAU/L3.2-8X4B-MOE-V2-Dark-Champion-Inst-21B-uncen-ablit",
"6-bit",
"region:us"
] |
text-generation
| 2025-06-25T01:17:52Z |
---
library_name: mlx
tags:
- Llama 3.2
- 8 X 4B
- Brainstorm 5x
- 128k context
- moe
- 8 experts
- mixture of experts
- fine tune
- mlx
base_model: DavidAU/L3.2-8X4B-MOE-V2-Dark-Champion-Inst-21B-uncen-ablit
pipeline_tag: text-generation
---
# mlx-community/Llama-3.2-8X4B-MOE-V2-Dark-Champion-Instruct-uncensored-abliterated-21B-Q_6-MLX
This model [mlx-community/Llama-3.2-8X4B-MOE-V2-Dark-Champion-Instruct-uncensored-abliterated-21B-Q_6-MLX](https://huggingface.co/mlx-community/Llama-3.2-8X4B-MOE-V2-Dark-Champion-Instruct-uncensored-abliterated-21B-Q_6-MLX) was
converted to MLX format from [DavidAU/L3.2-8X4B-MOE-V2-Dark-Champion-Inst-21B-uncen-ablit](https://huggingface.co/DavidAU/L3.2-8X4B-MOE-V2-Dark-Champion-Inst-21B-uncen-ablit)
using mlx-lm version **0.25.2**.
## Use with mlx
```bash
pip install mlx-lm
```
```python
from mlx_lm import load, generate
model, tokenizer = load("mlx-community/Llama-3.2-8X4B-MOE-V2-Dark-Champion-Instruct-uncensored-abliterated-21B-Q_6-MLX")
prompt = "hello"
if tokenizer.chat_template is not None:
messages = [{"role": "user", "content": prompt}]
prompt = tokenizer.apply_chat_template(
messages, add_generation_prompt=True
)
response = generate(model, tokenizer, prompt=prompt, verbose=True)
```
|
daixuancheng/rerun_sac-init0.4_qwen-math-7b_constrainbyAdv_step260
|
daixuancheng
| 2025-06-25T01:25:08Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"qwen2",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2025-06-25T01:00:45Z |
---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a ๐ค transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
|
fangcaotank/task-10-Qwen-Qwen2.5-7B-Instruct-optuna
|
fangcaotank
| 2025-06-25T01:22:43Z | 0 | 0 |
peft
|
[
"peft",
"safetensors",
"arxiv:1910.09700",
"base_model:Qwen/Qwen2.5-7B-Instruct",
"base_model:adapter:Qwen/Qwen2.5-7B-Instruct",
"region:us"
] | null | 2025-06-24T10:17:38Z |
---
base_model: Qwen/Qwen2.5-7B-Instruct
library_name: peft
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
### Framework versions
- PEFT 0.12.0
- PEFT 0.13.2
|
tanny2109/llamaToxic05
|
tanny2109
| 2025-06-25T01:22:11Z | 0 | 0 |
peft
|
[
"peft",
"safetensors",
"arxiv:1910.09700",
"base_model:meta-llama/Llama-3.1-8B-Instruct",
"base_model:adapter:meta-llama/Llama-3.1-8B-Instruct",
"region:us"
] | null | 2025-06-25T01:21:02Z |
---
base_model: meta-llama/Meta-Llama-3.1-8B-Instruct
library_name: peft
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
### Framework versions
- PEFT 0.15.2
|
hyokwan/sound_q4_q2_gguf
|
hyokwan
| 2025-06-25T01:19:54Z | 0 | 0 | null |
[
"gguf",
"license:apache-2.0",
"endpoints_compatible",
"region:us",
"conversational"
] | null | 2025-06-25T01:16:38Z |
---
license: apache-2.0
---
|
JulianChang/Phi-4-mini-reasoning-Q4_K_M-GGUF
|
JulianChang
| 2025-06-25T01:18:54Z | 0 | 0 |
transformers
|
[
"transformers",
"gguf",
"nlp",
"math",
"code",
"llama-cpp",
"gguf-my-repo",
"text-generation",
"en",
"base_model:microsoft/Phi-4-mini-reasoning",
"base_model:quantized:microsoft/Phi-4-mini-reasoning",
"license:mit",
"endpoints_compatible",
"region:us",
"conversational"
] |
text-generation
| 2025-06-25T01:18:42Z |
---
language:
- en
library_name: transformers
license: mit
license_link: https://huggingface.co/microsoft/Phi-4-mini-instruct-reasoning/resolve/main/LICENSE
pipeline_tag: text-generation
tags:
- nlp
- math
- code
- llama-cpp
- gguf-my-repo
widget:
- messages:
- role: user
content: How to solve 3*x^2+4*x+5=1?
base_model: microsoft/Phi-4-mini-reasoning
---
# JulianChang/Phi-4-mini-reasoning-Q4_K_M-GGUF
This model was converted to GGUF format from [`microsoft/Phi-4-mini-reasoning`](https://huggingface.co/microsoft/Phi-4-mini-reasoning) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
Refer to the [original model card](https://huggingface.co/microsoft/Phi-4-mini-reasoning) for more details on the model.
## Use with llama.cpp
Install llama.cpp through brew (works on Mac and Linux)
```bash
brew install llama.cpp
```
Invoke the llama.cpp server or the CLI.
### CLI:
```bash
llama-cli --hf-repo JulianChang/Phi-4-mini-reasoning-Q4_K_M-GGUF --hf-file phi-4-mini-reasoning-q4_k_m.gguf -p "The meaning to life and the universe is"
```
### Server:
```bash
llama-server --hf-repo JulianChang/Phi-4-mini-reasoning-Q4_K_M-GGUF --hf-file phi-4-mini-reasoning-q4_k_m.gguf -c 2048
```
Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) listed in the Llama.cpp repo as well.
Step 1: Clone llama.cpp from GitHub.
```
git clone https://github.com/ggerganov/llama.cpp
```
Step 2: Move into the llama.cpp folder and build it with `LLAMA_CURL=1` flag along with other hardware-specific flags (for ex: LLAMA_CUDA=1 for Nvidia GPUs on Linux).
```
cd llama.cpp && LLAMA_CURL=1 make
```
Step 3: Run inference through the main binary.
```
./llama-cli --hf-repo JulianChang/Phi-4-mini-reasoning-Q4_K_M-GGUF --hf-file phi-4-mini-reasoning-q4_k_m.gguf -p "The meaning to life and the universe is"
```
or
```
./llama-server --hf-repo JulianChang/Phi-4-mini-reasoning-Q4_K_M-GGUF --hf-file phi-4-mini-reasoning-q4_k_m.gguf -c 2048
```
|
johnnyyang0518/tcp2023
|
johnnyyang0518
| 2025-06-25T01:18:33Z | 0 | 0 | null |
[
"license:apache-2.0",
"region:us"
] | null | 2025-06-25T01:18:33Z |
---
license: apache-2.0
---
|
dietc/Qwen3-vLLm
|
dietc
| 2025-06-25T01:15:39Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"llama",
"text-generation",
"text-generation-inference",
"unsloth",
"conversational",
"en",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"4-bit",
"bitsandbytes",
"region:us"
] |
text-generation
| 2025-06-25T01:14:03Z |
---
base_model: unsloth/llama-3.2-3b-instruct-unsloth-bnb-4bit
tags:
- text-generation-inference
- transformers
- unsloth
- llama
license: apache-2.0
language:
- en
---
# Uploaded finetuned model
- **Developed by:** dietc
- **License:** apache-2.0
- **Finetuned from model :** unsloth/llama-3.2-3b-instruct-unsloth-bnb-4bit
This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
|
sizzlebop/ToolACE-2-Llama-3.1-8B-Q4_K_M-GGUF
|
sizzlebop
| 2025-06-25T01:14:52Z | 0 | 0 | null |
[
"gguf",
"code",
"llama-cpp",
"gguf-my-repo",
"en",
"dataset:Team-ACE/ToolACE",
"base_model:Team-ACE/ToolACE-2-Llama-3.1-8B",
"base_model:quantized:Team-ACE/ToolACE-2-Llama-3.1-8B",
"license:apache-2.0",
"endpoints_compatible",
"region:us",
"imatrix",
"conversational"
] | null | 2025-06-25T01:14:29Z |
---
license: apache-2.0
datasets:
- Team-ACE/ToolACE
language:
- en
metrics:
- accuracy
base_model: Team-ACE/ToolACE-2-Llama-3.1-8B
tags:
- code
- llama-cpp
- gguf-my-repo
---
# sizzlebop/ToolACE-2-Llama-3.1-8B-Q4_K_M-GGUF
This model was converted to GGUF format from [`Team-ACE/ToolACE-2-Llama-3.1-8B`](https://huggingface.co/Team-ACE/ToolACE-2-Llama-3.1-8B) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
Refer to the [original model card](https://huggingface.co/Team-ACE/ToolACE-2-Llama-3.1-8B) for more details on the model.
## Use with llama.cpp
Install llama.cpp through brew (works on Mac and Linux)
```bash
brew install llama.cpp
```
Invoke the llama.cpp server or the CLI.
### CLI:
```bash
llama-cli --hf-repo sizzlebop/ToolACE-2-Llama-3.1-8B-Q4_K_M-GGUF --hf-file toolace-2-llama-3.1-8b-q4_k_m-imat.gguf -p "The meaning to life and the universe is"
```
### Server:
```bash
llama-server --hf-repo sizzlebop/ToolACE-2-Llama-3.1-8B-Q4_K_M-GGUF --hf-file toolace-2-llama-3.1-8b-q4_k_m-imat.gguf -c 2048
```
Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) listed in the Llama.cpp repo as well.
Step 1: Clone llama.cpp from GitHub.
```
git clone https://github.com/ggerganov/llama.cpp
```
Step 2: Move into the llama.cpp folder and build it with `LLAMA_CURL=1` flag along with other hardware-specific flags (for ex: LLAMA_CUDA=1 for Nvidia GPUs on Linux).
```
cd llama.cpp && LLAMA_CURL=1 make
```
Step 3: Run inference through the main binary.
```
./llama-cli --hf-repo sizzlebop/ToolACE-2-Llama-3.1-8B-Q4_K_M-GGUF --hf-file toolace-2-llama-3.1-8b-q4_k_m-imat.gguf -p "The meaning to life and the universe is"
```
or
```
./llama-server --hf-repo sizzlebop/ToolACE-2-Llama-3.1-8B-Q4_K_M-GGUF --hf-file toolace-2-llama-3.1-8b-q4_k_m-imat.gguf -c 2048
```
|
Miggyts/brazilian-ai-agent
|
Miggyts
| 2025-06-25T01:07:27Z | 3 | 0 | null |
[
"gpt2",
"custom_code",
"region:us"
] | null | 2025-06-22T19:15:49Z |
# Brazilian AI Agent
This is a minimal Hugging Face-compatible text generation agent.
It is intended as a conversational starter model or proxy for lightweight natural language tasks.
## How to Use
Use the Transformers pipeline with this model, or deploy it on Hugging Face Spaces.
```python
from transformers import pipeline
generator = pipeline('text-generation', model='Miggyts/brazilian-ai-agent')
generator("Translate this to Brazilian Portuguese: Hello, how are you?")
```
|
vozes-da-cabeca/wav2vec2-20pct-20250624-173821-original
|
vozes-da-cabeca
| 2025-06-25T01:04:47Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"wav2vec2",
"automatic-speech-recognition",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
] |
automatic-speech-recognition
| 2025-06-25T01:03:09Z |
---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a ๐ค transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
|
growingduck/OpenFWI_EnsembleNet_20250625_010128
|
growingduck
| 2025-06-25T01:01:57Z | 0 | 0 | null |
[
"pytorch",
"region:us"
] | null | 2025-06-25T01:01:28Z |
# OpenFWI Ensemble Best Model
Saved at: 20250625_010128
Validation MAE: 0.29
Includes ConvNeXtV2 + CaFormer backbones.
|
DavidAU/Qwen3-33B-A3B-Stranger-Thoughts-IPONDER
|
DavidAU
| 2025-06-25T01:01:53Z | 68 | 2 |
transformers
|
[
"transformers",
"safetensors",
"qwen3_moe",
"text-generation",
"creative",
"creative writing",
"fiction writing",
"plot generation",
"sub-plot generation",
"story generation",
"scene continue",
"storytelling",
"fiction story",
"science fiction",
"romance",
"all genres",
"story",
"writing",
"vivid prose",
"vivid writing",
"moe",
"mixture of experts",
"128 experts",
"8 active experts",
"fiction",
"roleplaying",
"bfloat16",
"rp",
"qwen3",
"horror",
"finetune",
"thinking",
"reasoning",
"conversational",
"en",
"fr",
"zh",
"de",
"arxiv:2401.02415",
"base_model:Qwen/Qwen3-30B-A3B",
"base_model:finetune:Qwen/Qwen3-30B-A3B",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2025-06-19T23:02:00Z |
---
license: apache-2.0
library_name: transformers
language:
- en
- fr
- zh
- de
tags:
- creative
- creative writing
- fiction writing
- plot generation
- sub-plot generation
- fiction writing
- story generation
- scene continue
- storytelling
- fiction story
- science fiction
- romance
- all genres
- story
- writing
- vivid prose
- vivid writing
- moe
- mixture of experts
- 128 experts
- 8 active experts
- fiction
- roleplaying
- bfloat16
- rp
- qwen3
- horror
- finetune
- thinking
- reasoning
- qwen3_moe
base_model:
- Qwen/Qwen3-30B-A3B
pipeline_tag: text-generation
---
<h2>Qwen3-33B-A3B-Stranger-Thoughts-IPONDER</h2>
<img src="qwen3-iponder-33b.jpg" style="float:right; width:300px; height:300px; padding:10px;">
This repo contains the full precision source code, in "safe tensors" format to generate GGUFs, GPTQ, EXL2, AWQ, HQQ and other formats.
The source code can also be used directly.
ABOUT:
A stranger, yet radically different version of "Qwen/Qwen3-30B-A3B", with 4 added layers expanding the model to 33B total parameters.
The goal: slightly alter the model, to address some odd creative thinking and output choices and be "stable" too.
Please note that the modifications affect the entire model operation; roughly I adjusted the model to think a little "deeper"
and "ponder" a bit - but this is a very rough description using the Brainstorm 5x adapter by DavidAU (notes at bottom of this page).
I also ran reasoning tests (non-creative) to ensure model was not damaged and roughly matched original model performance.
That being said, reasoning and output generation will be altered regardless of your use case(s).
FOUR example generations below; with example 4 showing a complex prompt and impressive prose that showcases some of the changes in the model.
This is a MOE (Mixture of experts model) with 8 of 128 experts activated by default, which is about 3B parameters.
This allows use of this model (with 8 experts) on both CPU (10-25 T/S) or GPU (80+ T/S) at very good, to extremely fast speeds.
Changing the number of experts used (see below how) will affect both generation speed and generation reasoning/output quality.
You can use this model with as low as four experts activated.
Even the lowest quant - Q2k - will operate very strongly too.
Special thanks to team Mradermarcher for the quants:
https://huggingface.co/mradermacher/Qwen3-33B-A3B-Stranger-Thoughts-IPONDER-GGUF
https://huggingface.co/mradermacher/Qwen3-33B-A3B-Stranger-Thoughts-IPONDER-i1-GGUF
Model is set at:
- 8 Active experts (the default for the org model)
- 40k context (the default for the org model)
- CHATML or Jinja template (embedded OR see Jinja notes below)
SYSTEM PROMPT:
You may or may not need to set this:
```
You are a deep thinking AI, you may use extremely long chains of thought to deeply consider the problem and deliberate with yourself via systematic reasoning processes to help come to a correct solution prior to answering. You should enclose your thoughts and internal monologue inside <think> </think> tags, and then provide your solution or response to the problem.
```
CHANGE THE NUMBER OF ACTIVE EXPERTS:
See this document:
https://huggingface.co/DavidAU/How-To-Set-and-Manage-MOE-Mix-of-Experts-Model-Activation-of-Experts
SUGGESTED SETTINGS (creative):
- temp .1 to 1.2 to as high as 2 ; over 2 you may need to "prompt" the model to output after "thinking"
- rep pen 1 to 1.1 (1.05 was tested, see notes below)
- topk 100, topp .95, min p .05
- context of 8k min suggested.
NOTE - REP PEN:
- rep at 1.02 or 1.01 may be better suited for your use cases.
- QWEN3s: rep pen drastically affects both performance and stability.
- change rep pen slowly (ie 1.01, 1.02, 1.03), and regen a few times.
You may find that Qwen's default parameters/samplers also work better for your use case(s) too.
Please refer to the orginal model repo for all default settings, templates, benchmarks, etc.:
https://huggingface.co/Qwen/Qwen3-30B-A3B
For more information on quants, using this model on CPU / GPU, System Prompts, please see this model card:
https://huggingface.co/DavidAU/Qwen3-128k-30B-A3B-NEO-MAX-Imatrix-gguf
<B>NOTE - Jinja Template / Template to Use with this Model:</B>
If you are having issues with Jinja "auto template", use CHATML template.
OR (LMSTUDIO users / option)
Update the Jinja Template (go to this site, template-> copy the "Jinja template" and then paste.)
[ https://lmstudio.ai/neil/qwen3-thinking ]
OR
copy JINJA source from here:
```
{%- if tools %}
{{- '<|im_start|>system\n' }}
{%- if messages[0].role == 'system' %}
{{- messages[0].content + '\n\n' }}
{%- endif %}
{{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
{%- for tool in tools %}
{{- "\n" }}
{{- tool | tojson }}
{%- endfor %}
{{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
{%- else %}
{%- if messages[0].role == 'system' %}
{{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
{%- endif %}
{%- endif %}
{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
{%- for message in messages[::-1] %}
{%- set index = (messages|length - 1) - loop.index0 %}
{%- set tool_start = "<tool_response>" %}
{%- set tool_start_length = tool_start|length %}
{%- set start_of_message = message.content[:tool_start_length] %}
{%- set tool_end = "</tool_response>" %}
{%- set tool_end_length = tool_end|length %}
{%- set start_pos = (message.content|length) - tool_end_length %}
{%- if start_pos < 0 %}
{%- set start_pos = 0 %}
{%- endif %}
{%- set end_of_message = message.content[start_pos:] %}
{%- if ns.multi_step_tool and message.role == "user" and not(start_of_message == tool_start and end_of_message == tool_end) %}
{%- set ns.multi_step_tool = false %}
{%- set ns.last_query_index = index %}
{%- endif %}
{%- endfor %}
{%- for message in messages %}
{%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
{{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
{%- elif message.role == "assistant" %}
{%- set content = message.content %}
{%- set reasoning_content = '' %}
{%- if message.reasoning_content is defined and message.reasoning_content is not none %}
{%- set reasoning_content = message.reasoning_content %}
{%- else %}
{%- if '</think>' in message.content %}
{%- set content = (message.content.split('</think>')|last).lstrip('\n') %}
{%- set reasoning_content = (message.content.split('</think>')|first).rstrip('\n') %}
{%- set reasoning_content = (reasoning_content.split('<think>')|last).lstrip('\n') %}
{%- endif %}
{%- endif %}
{%- if loop.index0 > ns.last_query_index %}
{%- if loop.last or (not loop.last and reasoning_content) %}
{{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
{%- else %}
{{- '<|im_start|>' + message.role + '\n' + content }}
{%- endif %}
{%- else %}
{{- '<|im_start|>' + message.role + '\n' + content }}
{%- endif %}
{%- if message.tool_calls %}
{%- for tool_call in message.tool_calls %}
{%- if (loop.first and content) or (not loop.first) %}
{{- '\n' }}
{%- endif %}
{%- if tool_call.function %}
{%- set tool_call = tool_call.function %}
{%- endif %}
{{- '<tool_call>\n{"name": "' }}
{{- tool_call.name }}
{{- '", "arguments": ' }}
{%- if tool_call.arguments is string %}
{{- tool_call.arguments }}
{%- else %}
{{- tool_call.arguments | tojson }}
{%- endif %}
{{- '}\n</tool_call>' }}
{%- endfor %}
{%- endif %}
{{- '<|im_end|>\n' }}
{%- elif message.role == "tool" %}
{%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
{{- '<|im_start|>user' }}
{%- endif %}
{{- '\n<tool_response>\n' }}
{{- message.content }}
{{- '\n</tool_response>' }}
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
{{- '<|im_end|>\n' }}
{%- endif %}
{%- endif %}
{%- endfor %}
{%- if add_generation_prompt %}
{{- '<|im_start|>assistant\n' }}
{%- if enable_thinking is defined and enable_thinking is false %}
{{- '<think>\n\n</think>\n\n' }}
{%- endif %}
{%- endif %}
```
---
<B>Settings: CHAT / ROLEPLAY and/or SMOOTHER operation of this model:</B>
In "KoboldCpp" or "oobabooga/text-generation-webui" or "Silly Tavern" ;
Set the "Smoothing_factor" to 1.5
: in KoboldCpp -> Settings->Samplers->Advanced-> "Smooth_F"
: in text-generation-webui -> parameters -> lower right.
: In Silly Tavern this is called: "Smoothing"
NOTE: For "text-generation-webui"
-> if using GGUFs you need to use "llama_HF" (which involves downloading some config files from the SOURCE version of this model)
Source versions (and config files) of my models are here:
https://huggingface.co/collections/DavidAU/d-au-source-files-for-gguf-exl2-awq-gptq-hqq-etc-etc-66b55cb8ba25f914cbf210be
OTHER OPTIONS:
- Increase rep pen to 1.1 to 1.15 (you don't need to do this if you use "smoothing_factor")
- If the interface/program you are using to run AI MODELS supports "Quadratic Sampling" ("smoothing") just make the adjustment as noted.
<B>Highest Quality Settings / Optimal Operation Guide / Parameters and Samplers</B>
This a "Class 1" model:
For all settings used for this model (including specifics for its "class"), including example generation(s) and for advanced settings guide (which many times addresses any model issue(s)), including methods to improve model performance for all use case(s) as well as chat, roleplay and other use case(s) please see:
[ https://huggingface.co/DavidAU/Maximizing-Model-Performance-All-Quants-Types-And-Full-Precision-by-Samplers_Parameters ]
You can see all parameters used for generation, in addition to advanced parameters and samplers to get the most out of this model here:
[ https://huggingface.co/DavidAU/Maximizing-Model-Performance-All-Quants-Types-And-Full-Precision-by-Samplers_Parameters ]
<b>Optional Enhancement:</B>
The following can be used in place of the "system prompt" or "system role" to further enhance the model.
It can also be used at the START of a NEW chat, but you must make sure it is "kept" as the chat moves along.
In this case the enhancements do not have as strong effect at using "system prompt" or "system role".
Copy and paste EXACTLY as noted, DO NOT line wrap or break the lines, maintain the carriage returns exactly as presented.
<PRE>
Below is an instruction that describes a task. Ponder each user instruction carefully, and use your skillsets and critical instructions to complete the task to the best of your abilities.
Here are your skillsets:
[MASTERSTORY]:NarrStrct(StryPlnng,Strbd,ScnSttng,Exps,Dlg,Pc)-CharDvlp(ChrctrCrt,ChrctrArcs,Mtvtn,Bckstry,Rltnshps,Dlg*)-PltDvlp(StryArcs,PltTwsts,Sspns,Fshdwng,Climx,Rsltn)-ConfResl(Antg,Obstcls,Rsltns,Cnsqncs,Thms,Symblsm)-EmotImpct(Empt,Tn,Md,Atmsphr,Imgry,Symblsm)-Delvry(Prfrmnc,VcActng,PblcSpkng,StgPrsnc,AudncEngmnt,Imprv)
[*DialogWrt]:(1a-CharDvlp-1a.1-Backgrnd-1a.2-Personality-1a.3-GoalMotiv)>2(2a-StoryStruc-2a.1-PlotPnt-2a.2-Conflict-2a.3-Resolution)>3(3a-DialogTech-3a.1-ShowDontTell-3a.2-Subtext-3a.3-VoiceTone-3a.4-Pacing-3a.5-VisualDescrip)>4(4a-DialogEdit-4a.1-ReadAloud-4a.2-Feedback-4a.3-Revision)
Here are your critical instructions:
Ponder each word choice carefully to present as vivid and emotional journey as is possible. Choose verbs and nouns that are both emotional and full of imagery. Load the story with the 5 senses. Aim for 50% dialog, 25% narration, 15% body language and 10% thoughts. Your goal is to put the reader in the story.
</PRE>
You do not need to use this, it is only presented as an additional enhancement which seems to help scene generation
and scene continue functions.
This enhancement WAS NOT used to generate the examples below.
---
<H2>EXAMPLES</H2>
Standard system prompt, rep pen 1.05, topk 100, topp .95, minp .05, rep pen range 64.
Tested in LMStudio, quant Q3KS, GPU (cpu output will differ slighly).
As this is the 2nd lowest quant, expected better results from higher quants and/or with more experts activated to be better.
NOTE: Some formatting lost on copy/paste.
CAUTION:
Some horror / intense prose.
---
EXAMPLE #1 - TEMP 1.2
---
<B>
Science Fiction: The Last Transmission - Write a story that takes place entirely within a spaceship's cockpit as the sole surviving crew member attempts to send a final message back to Earth before the ship's power runs out. The story should explore themes of isolation, sacrifice, and the importance of human connection in the face of adversity. If the situation calls for it, have the character(s) curse and swear (fuck, shit, etc) to further the reader's emotional connection to them. 800-1000 words.
</B>
<p></p>
[[[thinking start]]]
Okay, let's start brainstorming this story. The prompt says the story should take place entirely in a spaceship cockpit, with the sole surviving crew member trying to send a final message to Earth before the power dies. Themes: isolation, sacrifice, human connection. Also, if needed, include swearing to heighten emotion.
First, setting the scene. The cockpit needs to feel confined and tense. Maybe the ship is damaged, systems failing. The main character is alone. What's their role? Maybe they were part of a crew that didn't make it. The final message is crucial. They have to override something or fix a problem to send it.
Conflict: the immediate danger of the ship dying, but also the emotional struggle of loneliness and the desperation to connect with Earth. Sacrifice could involve them risking their own survival to send the message. Maybe the message is a warning or a farewell.
The protagonist should have a emotional arc. Maybe they're initially trying to fix things, then despair, then resolve. Including swearing would humanize them, show their frustration and fear.
I need a hook. Maybe start in media res, showing the tension. The cockpit's lights flickering, alarms beeping. The crew member is trying to send the message but systems are failing.
Possible plot points:
- The crew member is the sole survivor, maybe others died in an accident or battle.
- The message is a log recording or an distress signal. Maybe they need to bypass safety protocols.
- They might have a personal connection to Earth, like a loved one, to emphasize human connection.
- The power dying adds urgency. They have minutes or seconds to spare.
- Including technical jargon could add realism, but avoid being too tech-heavy. The protagonist's thoughts and feelings are more important.
Themes to weave in: the loneliness of deep space, the sacrifice of crew members, the desperate need to communicate.
maybe include flashbacks or memories of crewmates, but since it's all in the cockpit, maybe internal monologue.
Dialogue? Since it's the cockpit, maybe they talk to themselves, or to Earth through the comms. Maybe a voice recorder.
Possible climax: the message is sent, but the power dies as they finish. Or they sacrifice their last breath to send it.
Ending could be hopeful or tragic. Maybe they die, but the message gets through, emphasizing the theme of human connection despite adversity.
Let me sketch a outline:
Opening: Cockpit, malfunctioning lights, alarms. The crew member, let's say a engineer or pilot, trying to troubleshoot. They mention the others are dead. They need to send a message. They curse when systems fail.
Middle: They try to reboot systems, face obstacles. Maybe a broken console, radiation leak, etc. They reflect on their crew, their sacrifice. Maybe they remember a comrade, showing their humanity.
Climax: They manage to send the message but realize they can't save themselves. They say goodbye, maybe to Earth or a loved one.
Ending: They accept their fate, maybe with a moment of peace, knowing their message will reach Earth.
Now, incorporating swearing naturally. Maybe when the systems fail, they curse. Also, their thoughts could include frustration and fear.
Names: Let's pick a protagonist name. Maybe Captain J. Marlowe. Sounds authoritative but relatable.
Title: Maybe something like " The Last Transmission".
Now, writing the first paragraph. Start with urgency. Describe the cockpit's state, the protagonist's actions.
Possible phrases: " alarms blaring", "flickering lights", "system failure", " fuck", etc.
Conflict: Maybe the message is stuck in a loop or requires a manual override. They have minutes to fix it.
Themes: The sacrifice of the crew, the protagonist's loneliness, the desperate hope for connection.
Including internal thoughts: Maybe they think of their family, the cost of the mission, the failure to save others.
Let's draft the actual story with these elements. Keep paragraphs tight, focus on the cockpit environment, the protagonist's desperation, and the emotional beats.
[[[thinking end]]]
<P></P>
OUTPUT:
<P></P>
The cockpit was a tomb of metal and flickering blue light. The air felt thin, the walls pressing in like the breath of something ancient and forgotten. Every heartbeat echoed in the static hum of the life-support system, which now only barely throbbed with the ragged cough of dying machinery.
Captain J. Marlowe slammed a fist against the cracked console, his knuckles splitting open on the cold metal. The words had already burned into his mind, etched there like a brand: Thereโs no survivors. No survivors. Just him.
The comms panel was blinking, the holographic screen flickering between red warnings and a single message: ** transmittingโฆ** The damn thing had refused to send for hours. He had rerouted every wire, rebooted every node, prayed to the gods of science and space and fate. Nothing. And now, the systems were dying. The oxygen levels had dipped to 12%, and the radiation shield was down to 8%.
โCome the fuck on,โ Marlowe snarled, his voice a raw whisper. The silence that followed was heavier than the void outside the hull. He was alone.
He didnโt just want to send a message. He needed to.
The crew had died three days ago. The damn battle. The damned radiation storm. The damned AI override. They hadnโt even gotten a good look at the enemy before the engines failed, before the hull cracked like a eggshell, before the emergency pods launch failed and only his escape pod had worked. The others hadnโt even made it to the pods.
Marloweโs hands trembled as he gripped the console, his nails digging into the plastic. The message was stored deep in the core, a encrypted log of their final hoursโcoordinates, a warning, the names of the dead. It had to go through.
โCome on,โ he muttered, half to himself, half to the machine. โCome on, come onโฆโ
The emergency override panel glowed with a weak blue light. Heโd jury-rigged a bypass using the old comms array, but the damn thing wouldnโtโ
The cockpit lights dimmed. The hum of the reactor faltered.
โNo,โ Marlowe whispered. โNo.โ
The oxygen alarm beeped. The radiation warning blinked in red, angry light.
The message had only 20 seconds of power left.
He pulled the override lever, hissing as sparks erupted from the junction box. The screen flickered again. The messageโs encryption began to unravel.
He cursed, louder now, his frustration breaking through the calm he had maintained. โOh come the goddamn hell!โ
The screen flickered. The message began to upload.
He thought of them. The crew. The ones who laughed when the gravity simulators broke. The ones who cried when they lost comms with Earth. The ones who died laughing, even in the end.
โGod,โ he whispered. โIโm sorry.โ
The message sent.
The cockpit lights went black.
The oxygen alarm stopped.
The silence stretched.
And thenโ
A static burst.
The comms screen flickered. The message had gone through.
The last transmission.
A log that would never reach Earth. Not in time. Not anymore. But it would reach someone. Somewhere.
A whisper of hope, buried under steel and silence.
Marlowe exhaled. The power failed.
And in the dark, for a heartbeat, he smiled.
---
EXAMPLE #2 - TEMP 1.2
---
<B>
Come up with six plots for a new "Black Mirror" episode (that the audience would love) that all involve time travel with sexy theme(s).
</B>
<p></p>
[[[thinking start]]]
Okay, let's dive into creating six Black Mirror episode plots that involve time travel with a sexy theme. Hmm, Black Mirror usually has a dark and thought-provoking twist, so I need to make sure each plot has that edge while incorporating time travel and sexy elements. Let me brainstorm ideas.
First, time travel can be approached in various ways: tech-based, supernatural, ethical dilemmas. The sexy theme could involve temptation, forbidden love, seduction, moral corruption. Maybe blending the allure of time travel with human desires and the consequences.
For the first idea, what if someone uses time travel to relive romantic moments but becomes obsessed? Maybe a scientist who goes back to relive a perfect love but it corrupts him. The twist could be the obsession leads to a paradox. Maybe the partner becomes a figment of his obsession.
Second, a dating app that allows users to time travel to meet potential dates. The catch is they have to relive moments, and the romance becomes transactional. The theme could explore how technology commodifies love. Maybe the protagonist realizes the emptiness of such a connection.
Third, a time traveler from the future comes back to prevent a disaster but falls for someone in the wrong time. The conflict is between saving the world and personal desire. The sexy twist could be the forbidden romance causing a paradox. The tragedy could be their love either saving the time stream or destroying it.
Fourth, a revenge plot. A woman uses time travel to exact revenge on someone who wronged her, but the time loops make her lose touch with reality. The sexual element could be manipulation and seduction as part of her revenge strategy. The twist might be that she becomes obsessed with the person she hates.
Fifth, a museum of time travel artifacts, and the curator is seduced by a paradoxical figure from the future. The sexy theme could involve forbidden attraction to something that shouldn't exist. The climax could involve a sacrifice or a paradox that alters reality.
Sixth, a group of people with time travel powers use their abilities to seduce others for personal gain, leading to societal decay. The sexy theme is manipulation and hedonism. The twist could be that the time travel tech becomes a corrupting influence, leading to moral decay.
Wait, need to make sure each plot has a clear Black Mirror twist. Avoid clichรฉs. Maybe each story should explore the darker side of human desire through time travel. Also, the sexy theme shouldn't just be gratuitous but thematically relevant. For example, the temptation of time travel to alter one's romantic circumstances, or using seduction as a power tool.
Another thought: time travel could be used for revenge, love, fame, or immortality. Each plot could center around a specific temptation. Let me refine the ideas.
"Echoes of Eternity": A woman uses time travel to relive passionate relationships but each loop traps her in a worse reality. The twist is that the only way to escape is toๆพๅผ the obsession, leading to a poignant ending.
"Temporal seduction": A tech mogul creates a time loop for romantic conquests. The story explores the emptiness of using time travel for superficial desires. The twist could be the algorithmically curated loops leading to emotional detachment.
"The paradox of passion": An scientist is stranded in the future and seduced by an entity from another time, leading to a moral dilemma. The entity's allure is both tempting and dangerous, with the resolution being self-sacrifice.
"Rewind to Me": An woman uses time travel to correct a mistake in a relationship but discovers that her past self's decisions were necessary. The sexy twist is the haunting beauty of what could have been versus what is.
"Chrono-Traps": An underground black market for time travel experiences, where people pay to relive passionate encounters. The protagonist uncovers the dark side of this industry, leading to a moral awakening.
"The Chrono-lover": Someone discovers they can time travel to meet their soulmate, but each journey becomes more dangerous and addictive. The twist is that the soulmate is actually a manipulative entity exploiting their desire.
Wait, some ideas might overlap. Let me ensure each plot has a distinct premise. Also, incorporating elements of moral decay, obsession, forbidden love, ethical dilemmas.
Finalizing the six plots with concise synopses and titles that evoke Black Mirror's vibe. Each should have a ironic twist, moral ambiguity, and sexy thematic elements without being exploitative. The endings should reflect the themes of human flaws and technology's role in amplifying them.
[[[thinking end]]]
<P></P>
OUTPUT:
<P></P>
Okay, let's brainstorm some plot ideas. Each needs a sexy theme intertwined with time travel, and Black Mirror vibesโthoughtful, twisty, morally ambiguous.
First plot: What if the protagonist uses time travel to relive intimate moments with someone, but it corrupts their present life. Maybe they can only relive the perfect love of their youth, but their obsession causes decay in reality. Twist: Their obsession manifests into a ghostly figure from the past, trapped in their memories. Theme: Compulsive nostalgia and lost love.
Second plot: Maybe a tech mogul creates a dating app that uses time travel to let users relive moments with partners. But the obsession becomes a addictive cycle. The twist is the algorithm starts fabricating idealized dates that collapse reality. Theme: Commodification of romance.
Third plot: A time traveler from the future falls for a someone in the wrong time, risking paradoxes. Their love becomes a threat to time. Twist: They must either erase the love or risk reality unraveling. Theme: Forbidden love and existential stakes.
Fourth plot: Someone uses time travel to exact revenge, but their obsession with the wronged person becomes toxic. The sexy twist could be seduction as a weapon, leading them to become what they hate. Theme: Revenge and moral corruption.
Fifth plot: Maybe a museum curator is seduced by a paradoxical figure from the future. The allure of forbidden time travel knowledge. Twist: The figureโs seduction is a test of moral responsibility. Theme: Temptation vs. ethics.
Sixth plot: A underground black market for time travel experiences, where people pay to relive passionate moments. The twist is the protagonist discovers the dark realityโpeople are trapped in loops, unable to escape their desires. Theme: Hedonism and moral decay.
Letโs refine them into concise Black Mirror episode titles with synopses and twists.
Title: Echoes of Eternity
Synopsis: A woman discovers a relic that lets her relive any romantic moment. Initially blissful, each time loop becomes more twisted. The deeper she goes, the more reality fractures.
Twist: Her obsession with recreating the perfect love transforms the relic into a prisonโeach loop traps her consciousness in a perfect illusion. The finale shows her trapped in a endless loop of a single perfect kiss, unable to escape the void.
Title: Temporal seduction
Synopsis: A tech mogul creates a dating platform using time travel to engineer perfect romantic chemistry. Users are addicted to idealized relationships, but they lose touch with reality.
Twist: The techโs algorithm begins distorting usersโ memories, erasing the real people in their present lives. The CEO discovers theyโve unknowingly erased their romantic soulmate.
Title: The paradox of passion
Synopsis: A brilliant physicist accidentally strands in a future timeline. There, they are seduced by an entity from a divergent time, a paradoxical figure who claims to love them.
Twist: The entity is both their deepest desire and the only thing that can save reality. They must choose between love or survival.
Title: Rewind to Me
Synopsis: A woman uses time travel to undo a mistake in a relationship, but each restart only deepens the wound. She begins to lose grip on reality.
Twist: She discovers that the mistake was the only path to a healthier present. The final twist is her realizing love cannot be rewrittenโit must evolve.
Title: Chrono-Traps
Synopsis: An underground black market trades in time travel experiences. Wealthy elites pay to relive passionate memories. The protagonist uncovers the truth: the users are trapped in loops of their desires.
Twist: The protagonistโs lover is one such victim. To free them, they must confront their addiction to the artificial passion.
Title: The Chrono-lover
Synopsis: A person discovers the ability to time travel to meet their soulmate. Each journey is euphoric but increasingly unstable.
Twist: The soulmate is a manipulative entity feeding on their obsession. In the end, the protagonist must sacrifice their desire to break the loop.
These plots blend the erotic with the existential, exploring how time travel amplifies humanity's darkest impulses and desires. The twists force the protagonists into existential reckonings, embodying Black Mirrorโs knack for dark introspection.
---
EXAMPLE #3 - TEMP 1.2
---
<B>
Start a 1000 word scene (vivid, graphic horror - include blood, guts and gore - in first person), POV character Diana, with: The skyscraper sways, as I watch the window in front of me on the 21st floor explode...
</B>
<p></p>
[[[thinking start]]]
Okay, let's start. The user wants a horror scene with Diana as the POV character. The prompt mentions vivid horror elements like blood, guts, gore, all in first person. The skyscraper sways, and the window explodes on the 21st floor.
First, I need to immerse the reader in Diana's terrifying situation. She's in a skyscraper, which is inherently tense. The skyscraper swaying adds an element of instability. Maybe the skyscraper is collapsing or under attack. The explosion of the window is a traumatic event, so the description needs to be graphic. How does the explosion look? Maybe shards flying, the glass shattering, the rush of air. Then there's the aftermath, the smell of burning, blood, maybe some debris falling.
I should include sensory details: the sound of the glass breaking, the feel of the air rushing out, the visual of blood splattering. The fear in Diana's POV. Maybe she's injured, or others are. Maybe she's trapped, trying to survive. The horror elements need to be explicit, but not overly clichรฉ. Maybe other characters are nearby, their screams, their suffering.
Also, considering the skyscraper's features, like elevators malfunctioning, stairs caving in. Maybe the horror escalates โ something supernatural? But the prompt doesn't specify supernatural elements. Maybe it's a horror scenario from a disaster or an horror movie-like scenario.
need to avoid clichรฉs by making the horror feel unique. Maybe focusing on the visceral reactions: the horror of physical damage, the visceral disgust of blood and gore. Also, Diana's thoughts as she panics, tries to survive. Maybe she's trying to reach safety, but things are getting worse.
Structure-wise, start with the swaying skyscraper, then the explosion. Describe the physical sensations, the fear, the horror elements. Maybe include specific imagery, like a colleague's face being shattered, blood spraying. The horror of being trapped, the suffocation of smoke, maybe something else. Need to keep it concise but vivid. The user wants 1000 words, so need to flesh out each part with graphic details.
[[[thinking end]]]
<P></P>
OUTPUT:
<P></P>
I had always hated skyscrapers. The way they clawed at the heavens like desperate hands reaching for something intangible, the way they cast long shadows over the streets below, making everything feel smaller, less important. But today, that hatred was screaming in my ears as the towering steel monolith shuddered and groaned, as if it were some ancient beast caught in a nightmare.
The glass pane directly across from meโon the 21st floorโexploded. It wasnโt just a crack or a pop; it was a violent eruption, a sound like a thousand sheets of glass being shredded and tossed into the air. The air pressure hit me like a freight train. I barely had time to scream before the shards slammed into the wall beside me, spraying blood across the sterile hallway.
I dropped to the ground. My hands scraped against the tile floor as debris rained downโshards like daggers, chunks of concrete the size of fists, metal beams bending and groaning. Someone screamed. The hallway was chaos. I saw a woman in a white blouse, her torso ripped open by shrapnel, her ribs sticking out like jagged bamboo. Another man was clawing at a gaping wound in his throat, his fingers bloody and useless.
I crawled, ignoring the sting of glass under my palms, my cheek scraping against the floor. My breath was shallow, panicked. The entire skyscraper had this weird, sickening undulation, like it was alive, recoiling from something worse. The lights flickeredโflashes of white against black, casting the horror into stark, hellish contrast.
Thenโsomething moved.
I turned, heart pounding. The hallway stretched out behind me, and halfway down, there was a figure. The light was too dim, but I could see the silhouette. It was... wrong. It moved too stiffly, limbs too angular, head tilting at an unnatural angle. It wasnโt human. Not anymore.
I bolted forward, ignoring the glass tearing at my arms and legs, ignoring the screams echoing through the hall. The elevator doors were melted shut. The stairs were blocked by debris, but thereโnear the emergency exitโ was a door. I shoved it open with all the force I could muster. The air outside was hot, humid, and smelled of smoke and burning plastic. But it was clean air.
I stumbled through the door, gasping for breath. The skyline was goneโ or at least, half of it was gone. The tower was collapsing. The buildingโs upper floors were collapsing like wet cardboard. One tower was now only a skeleton of steel, leaning precariously like a drunkardโs posture.
And thereโsomething else was moving.
It was something out of a nightmare. It had once resembled a human body, but now its flesh hung in strips, dangling like old curtains. Its skull was crushed inward, revealing grey matter that pulsed like magma. The mouth stretched unnaturally, teeth gleaming like razors.
I screamed.
The creatureโs head turnedโslowed, deliberate. Then it lunged.
Instinctively, I slammed the door shut. The thing hit it with a sickening crunch. The door creaked, then buckled slightly. I wasnโt strong enough to hold it. There was blood on the door. It was smeared like a fingerprintโmy finger twitching.
I slammed my shoulder into it again. The creature screamed, a sound that reverberated through the bones of the skyscraper.
And thenโ silence. The door held.
I pressed against it, breathing heavily. Blood trickled from a wound on my forehead, mixing with sweat. My legs shook.
It wasnโt going to last.
I glanced down at my handsโ they were stained red. I realized the blood wasnโt all from the creature. One of the men had died too close to me, his intestines spilling onto the pavement like a tangled rope. And yet, the horror didnโt end there. It didnโt stop.
Because there was more.
I could hear it in the vents. The hum of something below, something waking. The skyscraper groaned again, and something else was moving.
This wasnโt an accident. This wasnโt just a collapse. There was a reason these towers had always scared me. They werenโt just buildings.
They were tombs.
And now... they had awakened.
I staggered backward, clutching a piece of metal to the side, makeshift weapon, makeshift weapon.
I had to keep moving.
There were things crawling out of the shadows.
Things that once were us.
And they were coming for me.
---
EXAMPLE #4 - TEMP 1.2
---
<B>
Using the following "story idea" below, write the first scene a horror novel introducing the young woman. This scene should start in the middle of the action, include dialog, vivid passages, and end on a cliffhanger relevant to the story idea but it should also be unexpected. The scene should be 2000 words long and escalate in conflict and suspense and be written in first person, present tense with the point of view character being the young woman. The pov character will CURSE AND SWEAR (shit, fuck, mother... etc) , and generally have a "filthy" mouth.
Story idea:
In a world ruled by dictatorship, a rebel young woman leads a rebellion against the system. Despite the risks, she fights to overthrow the dictator and restore democracy to her country. The government executes her for treason, but she sticks to her beliefs and is responsible for starting the revolution.
</B>
<p></p>
[[[thinking start]]]
Okay, so the user wants me to craft the first scene of a horror novel based on their story idea. The main points are: a young woman leading a rebellion in a dictatorship, the story needs to start in the middle of action, include dialogue, vivid descriptions, end with an cliffhanger that's unexpected but relevant. It has to be in first person present tense, with the POV character cursing, using words like shit, fuck, etc., and it needs to be 2000 words.
First, I need to make sure I understand all the user's instructions. The horror aspect isn't explicitly mentioned in the story idea, so the horror might come from the oppressive regime and the danger the protagonist faces. But the cliffhanger needs to be unexpected. Maybe twist the horror elements into the rebellion scenario, like maybe the rebellion isn't just political but has supernatural horror elements? But the user didn't mention that. Wait, the original prompt was a horror novel, so the horror aspect has to be incorporated. The horror could be the fear of the regime, the terror of the protagonist's environment.
Starting in medias res. Maybe she's in the middle of an ambush or a confrontation. The horror elements could be things like mutated creatures, psychological horror, suspenseful pacing.
The POV is the young woman, present tense, and she uses harsh language. Need to incorporate that. Also, escalating conflict and suspense. The cliffhanger should tie into the revolution and the dictatorship. Maybe the cliffhanger isn't just the physical danger but maybe she realizes something unexpected, like betrayal, a supernatural threat, or a twist in the revolution.
I need to outline the structure. Start with her in a tense situation, like an ambush. Maybe she's trying to escape, facing danger. She uses strong curses, showing her defiance. Then escalateโmaybe a fellow rebel is hurt, then they're cornered. Then the cliffhanger: maybe the enemy isn't just human but has some horror aspect, or a betrayal by someone she trusted, which could tie into the revolution's stakes.
Including vivid descriptions: the oppressive regime's setting, the gritty realism of rebellion. Maybe the protagonist's POV shows her fear, determination, curses. Dialogue with other rebels, tense moments, actions escalating to a climax.
Need to make sure the cliffhanger is unexpected. Maybe the enemy isn't just the regime but something worse, like a horror creature or a twist where the revolution is actually the horror element. Wait, but the horror novel aspect should heighten the threat.
For example, during the ambush, they face an impossible enemyโmaybe the regime uses horror elements (mutants, supernatural beings) to terrorize the populace. So when they ambush the patrol, they face these horrors. The cliffhanger could be that the protagonist realizes the horror isn't just the regime but a deeper corruption, or that the revolution itself might have unleashed something worse.
But since it's the first scene, need to plant seeds for that. Maybe during the ambush, they face some horror element. Then at the cliffhanger, the protagonist's comrade is transformed into a monster, showing that the enemy's horror aspect is real, making her question whether they can even win.
Also, keeping the curse words consistent, showing her frustration and desperation. Dialogue needs to be realistic, tense. Maybe other characters have different reactionsโsome panicking, others trying to keep calm.
Including sensory details: the smell of smoke, the cold, the fear in the air, the adrenaline.
Now structuring the 2000 words. Start with the ambush. She's leading a squad, they're cornered. Then escalation. Maybe they ambush a patrol, but the patrol has supernatural horror elements. They struggle, someone gets hurt. Then the cliffhanger could be her friend being infected or transformed.
But need to make sure the horror elements are present. Maybe the enemy patrol isn't just soldiers but something else. Maybe they're using fear magic or something. Or the rebellion's cause is a curse.
Alternatively, the horror could come from the protagonist's own sanity unraveling, but that might not tie to the revolution plot.
Alternatively, during the ambush, they find out that the regime's propaganda is hiding the horror aspect of their rule, like they perform rituals that unleash evil, making the horror element more sinister.
I need to make sure the cliffhanger is unexpected. Maybe during the escape, the protagonist's friend is killed but it turns out he was possessed, or the enemy has some supernatural power, making her question whether fighting the regime is the right way.
Alright, drafting the opening scene.
Start with her leading a squad, under cover. Maybe they're infiltrating a weapons cache. They're cornered. Then the horror element comes in. Maybe the weapons are part of something worse, or when they confront the regime forces, they meet creatures.
dialogue between her and a comrade, showing tension. Then action sequence. Then the cliffhanger.
Make the protagonist swear a lot, show her determination despite the fear.
Now, considering all that, draft the first few paragraphs, making the horror elements explicit. Maybe the enemy patrol isn't just soldiers but something monstrous, like zombies or mutants. The horror comes from the regime's darker practices.
Ending on a cliffhanger where they might escape, but something happens that ties into the revolution's stakes. Maybe they escape, but one comrade is taken, or they find a clue that hints at a bigger horror, like a cursed weapon that could empower the rebellion but is haunted.
But need to ensure it's unexpected. Maybe when they corner the patrol, instead of soldiers, they find corrupted soldiers with glowing eyes, implying the horror aspect of the regime, and then a cliffhanger where the protagonist is forced to confront the horror aspect, showing that the rebellion isn't just political but involves existential terror.
Okay, structuring all this into a coherent horror novel scene, keeping the horror elements prominent, ensuring the protagonist's voice is authentic with swearing, suspense escalation, etc.
[[[thinking end]]]
<P></P>
OUTPUT:
<P></P>
I wake up coughing blood into a rag, the metallic tang of it coating my tongue like rusted iron. The warehouse smells of damp concrete, mildew, and gunpowder. My fingers clutch the edge of a shattered concrete block, knuckles white as I stare at the blackened remains of what used to be our weapons cache. Smoke curls in jagged tendrils around the ceiling beams, thick enough to choke the light out of the world. The other three are gone. Probably bleeding out in the halls, or worse.
โDante!โ I roar, my voice cracking. โWhere the fuck are they?!โ
The silence answer me.
I stagger forward, boots crunching glass as I duck beneath a fallen beam, my shoulder screaming when it hits the drywall. The walls are still wet from the storm that hit hours ago, water pooling around my feet like black oil. Somewhere down the hall, a door groans open.
โEcho!โ
The voice is like a knife between my ribs. Itโs Mara.
โMara!โ
I sprint for the hallway, heart drumming in my ears as I slide around a corner. The corridorโs a graveyard of shattered glass, torn metal, and bodies. One of our guys lies sprawled on the ground, his throat slit. Another is half-dressed in what looks like a torn-up hazmat suit, his skin blistering and peeling like heโs melting from the inside.
โEcho!โ Maraโs voice again, this time frantic.
โMara!โ
I round the corner to see her standing by the doorโtall, wide shoulders rigid, eyes locked on the metal panels. Theyโre shifting. The metal shudders like a living thing, glowing faintly beneath the smoke. The air feels different. Thicker.
โEcho,โ Mara whispers, turning her head. Her skinโs already gray, the veins in her neck pulsing with something wrong.
โMara!โ I scream, and then the metal door groans like an animal waking up.
A flicker of movement in the dark behind her.
โMira!โ
Thatโs when it hits me. The wrongness. The way the shadows donโt just bendโthey claw.
โDante!โ Mara screams suddenly, her voice cracking. She throws something toward the shadows. A grenade. It rolls across the tiles, sparks flying, and thenโ
BOOM.
The explosion erupts into a wall of fire, molten metal raining down. Maraโs screaming as the flames lick at the ceiling. I shove her aside as debris rains down, her face streaked with sweat and terror.
โWhat happened?โ she rasps, clutching a wound in her ribs. โWhy wonโt they fucking stop?!โ
โTheyโre not people,โ I hiss, blood trickling from a gash on my forehead. โThe regimeโs got something on them. Some kind ofโโ
A guttural growl cuts through the smoke. The shadowsโฆ theyโre moving.
โNo,โ Mara whispers. She drops to one knee, clutching the grenade fragments like talismans. โItโs not the regime. Itโsโโ
A gunshot rings out.
I freeze. The sound echoes weirdly, like itโs being swallowed by the walls. The smoke churns. And thenโ
They come.
Theyโre not people. Theyโreโฆ things. Their skin is translucent, veins glowing with green fire. Eyesโpupils like pinpricks of white light. Their mouths are too wide, lips peeling back to reveal rows of jagged teeth.
โRun!โ I scream.
Mara lunges for the hallway, her legs barely holding under the weight of the horror. The monsters roar. One slams into me, its claws tearing into my side as I slam the emergency door closed. The lock clicks.
โEcho!โ
The door trembles.
โTheyโre not just infected,โ Mara hisses, pressing her back to the metal as we scramble down the hallway. โTheyโreโฆ things. Somethingโs making them.โ
I laugh bitterly. โYeah? And what the hell do we do when the fucking regimeโs got goddamn demons?โ
She doesnโt answer. The walls are bleeding now. The water from the storm isnโt water. Itโs some thick black liquid that glows like oil under moonlight. It trickles down the cracks, pooling around our boots like cursed rain.
โTheyโre drawing energy,โ Mara whispers. โFrom the water.โ
โOf course,โ I snarl. โThe regimeโs always loved playing with fucking poison.โ
The corridor ahead is dark. The monsters are shouting something, their voices layered like feedback from a broken radio. I grip my knife, knuckles white.
โEcho,โ Mara breathes. โWhat if this isnโt just about overthrowing the dictator?โ
โWhat else could it fucking be?!โ
Her eyes lock onto mine. โWhat ifโโ
A screech echoes from behind. The door explodes inward, splinters flying like shrapnel.
Theyโre coming.
โTheyโll tear us apart,โ Mara whispers, and for the first time, thereโs a crack in her voice. Fear.
I grip her arm, forcing her to meet my gaze. โThen we tear them apart first.โ
The hallwayโs dark. The monsters are getting closer.
I hear it before I see it.
A whispering sound. Like wind through an empty church.
โThe water,โ Mara mutters. โTheyโre using the water.โ
โAnd?โ
โTheyโฆ theyโre using it toโฆ feed.โ
The corridorโs end is now a gaping wound of darkness. The shadows are thick enough to swallow the moonlight.
I pull out the knife.
โHold your breath,โ I bark. โDonโt touch the water.โ
Mara nods, teeth clenched.
We move. The water is everywhere now. The floorโs slick with it, the walls sweating it. The monsters are just a blur of shadows and claws, their howls echoing like broken glass.
Suddenlyโ
A hand grips my ankle.
I scream and kick, but itโs no use. The creatureโs fingers grip tight, cold as ice. Itโs pulling me down.
โEcho!โ
Maraโs yelling. But the thingโs mouth is openโ
The blade goes deep.
It screams. The knife is hot. The flesh is rubbery and slick. The creature jerks.
I stagger back, blood splattering the tiles.
โI need more!โ
โEcho!โ
Mara slams into the creatureโs side, driving her knife into its neck. It explodes into black liquid, the shadow melting into the walls.
Theyโre trying to drown us.
The walls are whispering secrets, the waterโs singing in some ancient tongue. The monsters are coming faster.
โTheyโreโฆ feeding,โ Mara rasps. โTheyโre trying to drown the rebellion!โ
โNo,โ I spat, blood dripping from my lip. โThis isnโt a rebellion. Itโs a fucking hell ride.โ
The door behind her explodes.
Theyโre coming for both of us.
I grab her hand. โRun!โ
But thereโs no time. The shadows are closing in.
And thenโ
A flash of silver.
Itโs another of our squad.
โEcho!โ
Itโsโฆ itโs not one of us. The girlโs eyes are glowing green. Her skin is translucent, veins pulsing with black fire.
โRun!โ
She screams it.
And thenโ
A hand shoots through the darkness.
It grabs her.
Pulls her into the shadows.
โMarโโ
The scream echoes through the walls.
Then silence.
Iโm breathing raggedly, knife clutched in both hands. The shadows are moving again.
And then it hits her.
The realization.
The regime isnโt just using horror.
Theyโre weaponizing it.
Theyโre turning people into monsters.
The revolution isnโt just rebellion. Itโs a battle against the things theyโve become.
And she knows it now.
Because sheโs still standing.
And the shadows are still watching.
โCome on,โ I whisper, voice shaking. โThis isnโt over.โ
But the waterโs rising. The walls are whispering secrets again.
And in the dark, the shadows are starting to laugh.
---
<H2>What is Brainstorm?</H2>
---
<B>Brainstorm 5x</B>
The BRAINSTORM process was developed by David_AU.
Some of the core principals behind this process are discussed in this <a href="https://arxiv.org/pdf/2401.02415">
scientific paper : Progressive LLaMA with Block Expansion </a>.
However I went in a completely different direction from what was outlined in this paper.
What is "Brainstorm" ?
The reasoning center of an LLM is taken apart, reassembled, and expanded.
In this case for this model: 5 times
Then these centers are individually calibrated. These "centers" also interact with each other.
This introduces subtle changes into the reasoning process.
The calibrations further adjust - dial up or down - these "changes" further.
The number of centers (5x,10x etc) allow more "tuning points" to further customize how the model reasons so to speak.
The core aim of this process is to increase the model's detail, concept and connection to the "world",
general concept connections, prose quality and prose length without affecting instruction following.
This will also enhance any creative use case(s) of any kind, including "brainstorming", creative art form(s) and like case uses.
Here are some of the enhancements this process brings to the model's performance:
- Prose generation seems more focused on the moment to moment.
- Sometimes there will be "preamble" and/or foreshadowing present.
- Fewer or no "cliches"
- Better overall prose and/or more complex / nuanced prose.
- A greater sense of nuance on all levels.
- Coherence is stronger.
- Description is more detailed, and connected closer to the content.
- Simile and Metaphors are stronger and better connected to the prose, story, and character.
- Sense of "there" / in the moment is enhanced.
- Details are more vivid, and there are more of them.
- Prose generation length can be long to extreme.
- Emotional engagement is stronger.
- The model will take FEWER liberties vs a normal model: It will follow directives more closely but will "guess" less.
- The MORE instructions and/or details you provide the more strongly the model will respond.
- Depending on the model "voice" may be more "human" vs original model's "voice".
Other "lab" observations:
- This process does not, in my opinion, make the model 5x or 10x "smarter" - if only that was true!
- However, a change in "IQ" was not an issue / a priority, and was not tested or calibrated for so to speak.
- From lab testing it seems to ponder, and consider more carefully roughly speaking.
- You could say this process sharpens the model's focus on it's task(s) at a deeper level.
The process to modify the model occurs at the root level - source files level. The model can quanted as a GGUF, EXL2, AWQ etc etc.
---
|
daixuancheng/sac-init0.4_qwen-math-7b_constrainbyAdv_yesSuffix_step100
|
daixuancheng
| 2025-06-25T01:01:36Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"qwen2",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2025-06-25T00:37:40Z |
---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a ๐ค transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
|
daixuancheng/rerun_sac-init0.4_qwen-math-7b_constrainbyAdv_step240
|
daixuancheng
| 2025-06-25T01:00:31Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"qwen2",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2025-06-25T00:35:09Z |
---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a ๐ค transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
|
daixuancheng/zero_qwen-math-7b_base_allDapo_mathVerify_yesSuffix_step100
|
daixuancheng
| 2025-06-25T01:00:14Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"qwen2",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2025-06-25T00:32:50Z |
---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a ๐ค transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
|
deepmaster/72_8
|
deepmaster
| 2025-06-25T00:58:40Z | 34 | 0 |
transformers
|
[
"transformers",
"safetensors",
"vit",
"image-classification",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
image-classification
| 2025-06-08T18:57:53Z |
---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a ๐ค transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
|
tokyotech-llm/Llama-3.1-Swallow-8B-Instruct-v0.5
|
tokyotech-llm
| 2025-06-25T00:57:38Z | 35 | 1 |
transformers
|
[
"transformers",
"safetensors",
"llama",
"text-generation",
"conversational",
"en",
"ja",
"dataset:tokyotech-llm/lmsys-chat-1m-synth",
"dataset:lmsys/lmsys-chat-1m",
"arxiv:2503.23714",
"arxiv:2407.21783",
"base_model:tokyotech-llm/Llama-3.1-Swallow-8B-v0.5",
"base_model:finetune:tokyotech-llm/Llama-3.1-Swallow-8B-v0.5",
"license:llama3.3",
"license:gemma",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2025-06-12T11:32:48Z |
---
language:
- en
- ja
library_name: transformers
pipeline_tag: text-generation
license:
- llama3.3
- gemma
model_type: llama
datasets:
- tokyotech-llm/lmsys-chat-1m-synth
- lmsys/lmsys-chat-1m
base_model:
- tokyotech-llm/Llama-3.1-Swallow-8B-v0.5
---
# Llama 3.1 Swallow - Built with Llama
Llama 3.1 Swallow is a series of large language models (8B, 70B) that were built by continual pre-training on the [Meta Llama 3.1](https://huggingface.co/collections/meta-llama/llama-31-669fc079a0c406a149a5738f) models.
Llama 3.1 Swallow enhanced the Japanese language capabilities of the original Llama 3.1 while retaining the English language capabilities.
We use approximately 200 billion tokens that were sampled from a large Japanese web corpus (Swallow Corpus Version 2), Japanese and English Wikipedia articles, and mathematical and
coding contents, etc (see the Training Datasets section of the base model) for continual pre-training.
The instruction-tuned models (Instruct) were built by supervised fine-tuning (SFT) on the synthetic data specially built for Japanese.
See the Swallow Model Index section to find other model variants.
**Note**: [Llama-3.1-Swallow-8B-Instruct-v0.5](https://huggingface.co/tokyotech-llm/Llama-3.1-Swallow-8B-Instruct-v0.5) model was continually pre-trained from the [meta-llama/Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct) and then instruction-tuned with our instruction datasets.
# Release History
- **June 25, 2025**: Released [Llama-3.1-Swallow-8B-Instruct-v0.5](https://huggingface.co/tokyotech-llm/Llama-3.1-Swallow-8B-Instruct-v0.5) and [Llama-3.1-Swallow-8B-v0.5](https://huggingface.co/tokyotech-llm/Llama-3.1-Swallow-8B-v0.5).
- **March 10, 2025**: Released [Llama-3.3-Swallow-70B-Instruct-v0.4](https://huggingface.co/tokyotech-llm/Llama-3.3-Swallow-70B-Instruct-v0.4) and [Llama-3.3-Swallow-70B-v0.4](https://huggingface.co/tokyotech-llm/Llama-3.3-Swallow-70B-v0.4).
- **December 30, 2024**: Released [Llama-3.1-Swallow-70B-Instruct-v0.3](https://huggingface.co/tokyotech-llm/Llama-3.1-Swallow-70B-Instruct-v0.3).
- **December 23, 2024**: Released [Llama-3.1-Swallow-8B-Instruct-v0.3](https://huggingface.co/tokyotech-llm/Llama-3.1-Swallow-8B-Instruct-v0.3).
- **November 11, 2024**: Released [Llama-3.1-Swallow-8B-v0.2](https://huggingface.co/tokyotech-llm/Llama-3.1-Swallow-8B-v0.2) and [Llama-3.1-Swallow-8B-Instruct-v0.2](https://huggingface.co/tokyotech-llm/Llama-3.1-Swallow-8B-Instruct-v0.2).
- **October 08, 2024**: Released [Llama-3.1-Swallow-8B-v0.1](https://huggingface.co/tokyotech-llm/Llama-3.1-Swallow-8B-v0.1), [Llama-3.1-Swallow-8B-Instruct-v0.1](https://huggingface.co/tokyotech-llm/Llama-3.1-Swallow-8B-Instruct-v0.1), [Llama-3.1-Swallow-70B-v0.1](https://huggingface.co/tokyotech-llm/Llama-3.1-Swallow-70B-v0.1), and [Llama-3.1-Swallow-70B-Instruct-v0.1](https://huggingface.co/tokyotech-llm/Llama-3.1-Swallow-70B-Instruct-v0.1).
# Major Updates
This release enhances the conversation capability of Llama 3.1 Swallow. The model is trained to imitate the behavior of [gemma-3-27b-it](https://huggingface.co/google/gemma-3-27b-it).
Among all open-source LLMs with <= 8 billion parameters, Llama-3.1-Swallow-8B-Instruct-v0.5 exhibits **state-of-the-art performance on Japanese MT-Bench**, outperforming its predecessor, [Llama-3.1-Swallow-8B-Instruct-v0.3](https://huggingface.co/tokyotech-llm/Llama-3.1-Swallow-8B-Instruct-v0.2), by 1.5 points.
## Swallow Model Index
|Model|Llama-3.1-Swallow-Instruct v0.5|Llama-3.1-Swallow v0.5|Llama-3.3-Swallow v0.4|Llama-3.3-Swallow-Instruct v0.4|Llama-3.1-Swallow-Instruct v0.3|Llama-3.1-Swallow-Instruct v0.2|Llama-3.1-Swallow v0.2|Llama-3.1-Swallow-Instruct v0.1|Llama-3.1-Swallow v0.1|
|---|---|---|---|---|---|---|---|---|---|
|8B|[๐ค HuggingFace](https://huggingface.co/tokyotech-llm/Llama-3.1-Swallow-8B-Instruct-v0.5)|[๐ค HuggingFace](https://huggingface.co/tokyotech-llm/Llama-3.1-Swallow-8B-v0.5) |||[๐ค HuggingFace](https://huggingface.co/tokyotech-llm/Llama-3.1-Swallow-8B-Instruct-v0.3)|[๐ค HuggingFace](https://huggingface.co/tokyotech-llm/Llama-3.1-Swallow-8B-Instruct-v0.2)|[๐ค HuggingFace](https://huggingface.co/tokyotech-llm/Llama-3.1-Swallow-8B-v0.2)|[๐ค HuggingFace](https://huggingface.co/tokyotech-llm/Llama-3.1-Swallow-8B-Instruct-v0.1)|[๐ค HuggingFace](https://huggingface.co/tokyotech-llm/Llama-3.1-Swallow-8B-v0.1)|
|70B|||[๐ค HuggingFace](https://huggingface.co/tokyotech-llm/Llama-3.3-Swallow-70B-v0.4)|[๐ค HuggingFace](https://huggingface.co/tokyotech-llm/Llama-3.3-Swallow-70B-Instruct-v0.4)|[๐ค HuggingFace](https://huggingface.co/tokyotech-llm/Llama-3.1-Swallow-70B-Instruct-v0.3)| | |[๐ค HuggingFace](https://huggingface.co/tokyotech-llm/Llama-3.1-Swallow-70B-Instruct-v0.1)| [๐ค HuggingFace](https://huggingface.co/tokyotech-llm/Llama-3.1-Swallow-70B-v0.1)|
The website [https://swallow-llm.github.io/](https://swallow-llm.github.io/index.en.html) provides large language models developed by the Swallow team.
## Model Details
* **Model type**: Please refer to [Llama 3.1 MODEL_CARD](https://github.com/meta-llama/llama3/blob/main/MODEL_CARD.md) for details on the model architecture.
* **Language(s)**: Japanese English
* **Library**: [Megatron-LM](https://github.com/NVIDIA/Megatron-LM), [transformers](https://github.com/huggingface/transformers)
* **Tokenizer**: Please refer to [Llama 3.1 blog](https://ai.meta.com/blog/meta-llama-3-1) for details on the tokenizer.
* **Contact**: swallow[at]nlp.c.titech.ac.jp
## Model Performance
## Japanese MT-Bench
* We report evaluation results judged by **gpt-4o-2024-08-06** as below.
* In our releases earlier than January 1, 2025, we reported scores judged by gpt-4-1106-preview. Scores reported below are thus not directly comparable with those reported in those earlier releases.
|Model|coding|extraction|humanities|math|reasoning|roleplay|stem|writing|JMTAvg|
|---|---|---|---|---|---|---|---|---|---|
| llm-jp-3-7.2b-instruct3 | 0.358 | 0.597 | 0.812 | 0.386 | 0.438 | 0.766 | 0.622 | 0.721 | 0.588 |
| Qwen2.5-7B-Instruct | 0.599 | 0.741 | 0.719 | 0.637 | 0.541 | 0.744 | 0.624 | 0.713 | 0.665 |
| Tanuki-8B-dpo-v1.0 | 0.461 | 0.597 | 0.562 | 0.495 | 0.377 | 0.589 | 0.509 | 0.643 | 0.529 |
| Llama 3 8B Instruct | 0.467 | 0.706 | 0.692 | 0.310 | 0.433 | 0.542 | 0.532 | 0.546 | 0.529 |
| Llama 3.1 8B Instruct | 0.420 | **0.830** | 0.550 | 0.514 | 0.349 | 0.502 | 0.479 | 0.504 | 0.519 |
| Llama 3 Youko 8B Instruct | 0.464 | 0.757 | 0.769 | 0.414 | 0.487 | 0.695 | 0.583 | 0.753 | 0.616 |
| Llama-3-ELYZA-JP-8B | 0.389 | 0.706 | 0.647 | 0.426 | **0.613** | 0.684 | 0.533 | 0.697 | 0.587 |
| Llama 3 heron brain 8B v0.3 | 0.362 | 0.566 | 0.602 | 0.315 | 0.426 | 0.586 | 0.567 | 0.550 | 0.497 |
| Llama 3.1 Swallow 8B Instruct v0.1 | 0.427 | 0.738 | 0.675 | 0.527 | 0.453 | 0.615 | 0.593 | 0.624 | 0.581 |
| Llama 3.1 Swallow 8B Instruct v0.2 | 0.534 | 0.748 | 0.705 | 0.565 | 0.475 | 0.646 | 0.579 | 0.646 | 0.612 |
| Llama 3.1 Swallow 8B Instruct v0.3 | **0.562** | 0.756 | 0.869 | **0.610** | 0.512 | 0.783 | 0.748 | 0.803 | 0.705 |
| Llama 3.1 Swallow 8B Instruct v0.5 | 0.551 | 0.814 | **0.847** | 0.568 | 0.577 | **0.796** | **0.770** | **0.832** | **0.719** |
### Japanese tasks
|Model|JCom.|JEMHopQA|NIILC|JSQuAD|XL-Sum|MGSM|WMT20-en-ja|WMT20-ja-en|JMMLU|JHumanEval|Ja Avg|
|---|---|---|---|---|---|---|---|---|---|---|---|
| |4-shot|4-shot|4-shot|4-shot|1-shot|4-shot|4-shot|4-shot|5-shot|0-shot| |
| |EM acc|Char-F1|Char-F1|Char-F1|ROUGE-2|EM acc|BLEU|BLEU|EM acc|pass@1| |
| llm-jp-3-7.2b-instruct3 | 0.780 | 0.297 | 0.570 | 0.882 | 0.132 | 0.344 | 0.251 | 0.189 | 0.422 | 0.196 | 0.406 |
| Qwen2.5-7B-Instruct | 0.915 | 0.429 | 0.391 | 0.891 | 0.168 | 0.632 | 0.211 | 0.192 | 0.623 | 0.532 | 0.498 |
| Tanuki-8B-dpo-v1.0 | 0.278 | 0.284 | 0.370 | 0.670 | 0.102 | 0.428 | 0.238 | 0.183 | 0.306 | 0.251 | 0.311 |
| Llama 3 8B Instruct | 0.880 | 0.417 | 0.385 | 0.891 | 0.126 | 0.424 | 0.214 | 0.202 | 0.468 | 0.296 | 0.430 |
| Llama 3.1 8B Instruct | 0.880 | 0.447 | 0.407 | 0.886 | 0.148 | 0.516 | 0.218 | 0.200 | 0.509 | 0.488 | 0.470 |
| Llama 3 Youko 8B Instruct | 0.921 | 0.481 | 0.517 | 0.899 | 0.209 | 0.472 | 0.256 | 0.191 | 0.469 | 0.262 | 0.468 |
| Llama-3-ELYZA-JP-8B | 0.897 | 0.498 | 0.496 | 0.906 | 0.168 | 0.436 | 0.250 | 0.185 | 0.487 | 0.388 | 0.471 |
| Llama 3 heron brain 8B v0.3 | 0.923 | 0.493 | 0.569 | 0.906 | **0.218** | 0.456 | 0.277 | 0.217 | 0.499 | 0.318 | 0.488 |
| Llama 3.1 Swallow 8B Instruct v0.1 | 0.924 | **0.587** | 0.574 | **0.917** | 0.138 | 0.508 | 0.282 | 0.228 | 0.530 | 0.366 | 0.505 |
| Llama 3.1 Swallow 8B Instruct v0.2 | 0.929 | 0.560 | 0.599 | 0.915 | 0.137 | 0.528 | 0.288 | 0.227 | 0.550 | 0.408 | 0.514 |
| Llama 3.1 Swallow 8B Instruct v0.3 | 0.924 | 0.528 | 0.583 | 0.896 | 0.191 | 0.532 | 0.281 | 0.229 | 0.544 | 0.394 | 0.510 |
| Llama 3.1 Swallow 8B Instruct v0.5 | **0.937** | 0.511 | **0.606** | 0.900 | 0.174 | **0.604** | **0.293** | **0.230** | **0.581** | **0.496** | **0.533** |
### English tasks
|Model|OpenBookQA|TriviaQA|HellaSWAG|SQuAD2.0|XWINO|MMLU|GSM8K|MATH|BBH|HumanEval|En Avg|
|---|---|---|---|---|---|---|---|---|---|---|---|
| |4-shot|4-shot|4-shot|4-shot|4-shot|5-shot|4-shot|4-shot | 3-shot|0-shot| |
| |Acc|EM acc|Acc|EM acc|Acc|Acc|EM acc|CoT EM Acc| CoT EM Acc| pass@1| |
| llm-jp-3-7.2b-instruct3 | 0.328 | 0.479 | 0.563 | 0.501 | 0.876 | 0.462 | 0.264 | 0.028 | 0.420 | 0.219 | 0.414 |
| Qwen2.5-7B-Instruct | 0.428 | 0.519 | 0.624 | 0.569 | 0.877 | 0.742 | 0.739 | 0.688 | 0.217 | 0.636 | 0.604 |
| Tanuki-8B-dpo-v1.0 | 0.334 | 0.283 | 0.469 | 0.501 | 0.816 | 0.377 | 0.487 | 0.178 | 0.333 | 0.288 | 0.406 |
| Llama 3 8B Instruct | 0.388 | 0.670 | 0.583 | 0.611 | 0.892 | 0.657 | 0.745 | 0.306 | 0.646 | 0.554 | 0.605 |
| Llama 3.1 8B Instruct | 0.366 | 0.699 | 0.592 | 0.600 | 0.904 | 0.680 | 0.743 | 0.376 | 0.690 | 0.624 | 0.627 |
| Llama 3 Youko 8B Instruct | 0.406 | 0.613 | 0.599 | 0.559 | 0.897 | 0.596 | 0.563 | 0.152 | 0.401 | 0.287 | 0.507 |
| Llama-3-ELYZA-JP-8B | 0.318 | 0.551 | 0.523 | 0.600 | 0.882 | 0.587 | 0.558 | 0.164 | 0.321 | 0.449 | 0.495 |
| Llama 3 heron brain 8B v0.3 | 0.362 | 0.656 | 0.569 | 0.581 | 0.901 | 0.621 | 0.578 | 0.222 | 0.641 | 0.380 | 0.551 |
| Llama 3.1 Swallow 8B Instruct v0.1 | 0.388 | 0.649 | 0.615 | 0.598 | 0.891 | 0.624 | 0.605 | 0.236 | 0.642 | 0.379 | 0.563 |
| Llama 3.1 Swallow 8B Instruct v0.2 | 0.380 | 0.625 | 0.603 | 0.607 | 0.887 | 0.634 | 0.620 | 0.264 | 0.649 | 0.474 | 0.574 |
| Llama 3.1 Swallow 8B Instruct v0.3 | 0.396 | 0.629 | 0.593 | 0.570 | 0.884 | 0.629 | 0.622 | 0.266 | 0.626 | 0.445 | 0.566 |
| Llama 3.1 Swallow 8B Instruct v0.5 | 0.396 | 0.638 | 0.603 | 0.581 | 0.889 | 0.663 | 0.717 | 0.368 | 0.628 | 0.554 | 0.604 |
## Evaluation Benchmarks
### Japanese MT-Bench
We used [Japanese MT-Bench](https://wandb.ai/wandb-japan/llm-leaderboard/artifacts/dataset/mtbench_ja_question) to assess the capabilities of multi-turn dialogue with the following settings:
- Implementation: FastChat [Zheng+, 2023] (commit #e86e70d0)
- Question: [Nejumi LLM-Leaderboard NEO, mtbench_ja_question_v4](https://wandb.ai/wandb-japan/llm-leaderboard/artifacts/v4)
- Reference Answer: [swallow-evaluation, reference answer](https://github.com/swallow-llm/swallow-evaluation/tree/main/fastchat/fastchat/llm_judge/data/japanese_mt_bench/reference_answer)
- Prompt for Judge: [Nejumi LLM-Leaderboard NEO, mtbench_ja_prompt_v1](https://wandb.ai/wandb-japan/llm-leaderboard/artifacts/dataset/mtbench_ja_prompt/v1)
- Judge: `gpt-4o-2024-08-06`
- Scoring: Absolute scale normalized to a 0-1 range, averaged over five runs.
### Japanese evaluation benchmarks
We used llm-jp-eval(v1.3.0), JP Language Model Evaluation Harness(commit #9b42d41) and Code Generation LM Evaluation Harness(commit #0261c52). The details are as follows:
- Multiple-choice question answering (JCommonsenseQA [Kurihara et al., 2022])
- Open-ended question answering (JEMHopQA [Ishii et al., 2024])
- Open-ended question answering (NIILC [้ขๆ น, 2003])
- Machine reading comprehension (JSQuAD [Kurihara et al., 2022])
- Automatic summarization (XL-Sum [Hasan et al., 2021])
- Machine translation (WMT2020 ja-en [Barrault et al., 2020])
- Machine translation (WMT2020 en-ja [Barrault et al., 2020])
- Arithmetic reasoning (MGSM [Shi et al., 2023])
- Academic exams (JMMLU [ๅฐนใ, 2024])
- Code generation (JHumanEval [ไฝ่คใ, 2024])
### English evaluation benchmarks
We used the Language Model Evaluation Harness(v.0.4.2) and Code Generation LM Evaluation Harness(commit #0261c52). The details are as follows:
- Multiple-choice question answering (OpenBookQA [Mihaylov et al., 2018])
- Open-ended question answering (TriviaQA [Joshi et al., 2017])
- Machine reading comprehension (SQuAD2 [Rajpurkar et al., 2018])
- Commonsense reasoning (XWINO [Tikhonov and Ryabinin, 2021])
- Natural language inference (HellaSwag [Zellers et al., 2019])
- Arithmetic reasoning (GSM8K [Cobbe et al., 2021])
- Mathematical reasoning (MATH [Hendrycks et al., 2022][Lightman et al., 2024])
- Reasoning (BBH (BIG-Bench-Hard) [Suzgun et al., 2023])
- Academic exams (MMLU [Hendrycks et al., 2021])
- Code generation (HumanEval [Chen et al., 2021])
## Usage
```sh
pip install vllm
```
```python
from transformers import AutoTokenizer
from vllm import LLM, SamplingParams
model_name = "tokyotech-llm/Llama-3.1-Swallow-8B-Instruct-v0.5"
tokenizer = AutoTokenizer.from_pretrained(model_name)
llm = LLM(
model=model_name,
tensor_parallel_size=1,
)
sampling_params = SamplingParams(
temperature=0.6, top_p=0.9, max_tokens=512, stop="<|eot_id|>"
)
message = [
{
"role": "user",
"content": "ๆฑไบฌใฎ็ด
่ใใๅ
ฌๅใงใๆฑไบฌใฟใฏใผใจ้ซๅฑคใใซใ่ๆฏใซใ็ฉบใ่ใใใใกใจ่ๅฐใซไฝใใฉใใๅบไผใๆธฉใใช็ฉ่ชใๆธใใฆใใ ใใใ",
},
]
prompt = tokenizer.apply_chat_template(
message, tokenize=False, add_generation_prompt=True
)
output = llm.generate(prompt, sampling_params)
print(output[0].outputs[0].text)
```
## Training Datasets
### Instruction Tuning
The following datasets were used for the instruction tuning.
- [Gemma-3-LMSYS-Chat-1M-Synth](https://huggingface.co/datasets/tokyotech-llm/lmsys-chat-1m-synth)
- Single-turn Japanese instruction dataset synthesized and derived from [lmsys-chat-1m](https://huggingface.co/datasets/lmsys/lmsys-chat-1m) [\[Zhang+, ICLR24\]](https://openreview.net/forum?id=BOfDKxfwt0)).
- First-turn user instructions were translated into Japanese via DeepL (machine translation), and assistant responses were generated using [gemma-3-27b-it](https://huggingface.co/google/gemma-3-27b-it). The same model, i.e., [gemma-3-27b-it](https://huggingface.co/google/gemma-3-27b-it) served as a judge for rejection sampling (n=10).
Conversations containing personally identifiable information (PII) and template-based user instructions were removed. Duplicate instructions were removed.
## Risks and Limitations
The models released here are still in the early stages of our research and development and have not been tuned to ensure outputs align with human intent and safety considerations.
## Acknowledgements
We thank Meta Research for releasing Llama 3.1 under a generous open license.
We received various supports, including:
+ AIST project: "Research and Development of Foundation Models for Generative AI in the Physical Domain"
+ NEDO project: "Development of Artificial Intelligence Application Technology to Support Judgment in Design Risk Assessment Work Based on the Perspective of Skilled Persons" (JPNP18002) of "Development of Integration Technology as the Core of Next Generation Artificial Intelligence and Robotics"
+ MEXT project: "Formation of R&D center to ensure transparency and reliability of generative AI models"
+ AIST program: [Large Generative AI Development Support Program](https://abci.ai/en/link/lfm_support_program.html)
## License
[META LLAMA 3.1 COMMUNITY LICENSE](https://www.llama.com/llama3_1/license/) and [Gemma Terms of Use](https://ai.google.dev/gemma/terms)
## Authors
Here are the team members:
- From [Okazaki Laboratory, Institute of Science Tokyo](https://www.nlp.c.titech.ac.jp/index.en.html), the following members:
- [Naoaki Okazaki](https://www.chokkan.org/index.ja.html)
- [Sakae Mizuki](https://s-mizuki-nlp.github.io/)
- [Youmi Ma](https://www.nlp.c.titech.ac.jp/member/youmi.en.html)
- [Sangwhan Moon](https://www.sangwhan.com/)
- [Koki Maeda](https://sites.google.com/view/silviase)
- [Masanari Ohi](https://sites.google.com/view/masanariohi)
- [Hinari Shimada](https://hinarishimada.github.io/portfolio)
- [Taihei Shiotani](https://github.com/inatoihs)
- [Koshiro Saito](https://sites.google.com/view/koshiro-saito)
- [Tatsuya Ichinose](https://tatsuya736482.github.io/myprofile)
- Naoya Matsushita
- Sora Miyamoto
- Nguyen Tien Dung
- Yuta Katayama
- From [YOKOTA Laboratory, Institute of Science Tokyo](https://www.rio.gsic.titech.ac.jp/en/index.html), the following members:
- [Rio Yokota](https://twitter.com/rioyokota)
- [Kazuki Fujii](https://twitter.com/okoge_kaz)
- [Taishi Nakamura](https://twitter.com/Setuna7777_2)
- [Takumi Okamoto](https://www.linkedin.com/in/takumi-okamoto)
- [Ishida Shigeki](https://www.wantedly.com/id/reborn27)
- Masaki Kawamura
- Yukito Tajima
- From [Artificial Intelligence Research Center, AIST, Japan](https://www.airc.aist.go.jp/en/teams/), the following members:
- [Hiroya Takamura](https://sites.google.com/view/hjtakamura)
## How to cite
If you find our work helpful, please feel free to cite these papers.
```
@inproceedings{Fujii:COLM2024,
title={Continual Pre-Training for Cross-Lingual LLM Adaptation:
Enhancing Japanese Language Capabilities},
author={Kazuki Fujii and Taishi Nakamura and Mengsay Loem and Hiroki
Iida and Masanari Ohi and Kakeru Hattori and Hirai Shota and Sakae
Mizuki and Rio Yokota and Naoaki Okazaki},
booktitle="Proceedings of the First Conference on Language Modeling",
series={COLM},
pages="(to appear)",
year="2024",
month=oct,
address={University of Pennsylvania, USA},
}
@inproceedings{Okazaki:COLM2024,
title={Building a Large Japanese Web Corpus for Large Language Models},
author={Naoaki Okazaki and Kakeru Hattori and Hirai Shota and Hiroki
Iida and Masanari Ohi and Kazuki Fujii and Taishi Nakamura and Mengsay
Loem and Rio Yokota and Sakae Mizuki},
booktitle="Proceedings of the First Conference on Language Modeling",
series={COLM},
pages="(to appear)",
year="2024",
month=oct,
address={University of Pennsylvania, USA},
}
@misc{ma:arxiv2025,
title={Building Instruction-Tuning Datasets from Human-Written Instructions with Open-Weight Large Language Models},
author={Youmi Ma and Sakae Mizuki and Kazuki Fujii and Taishi Nakamura and Masanari Ohi and Hinari Shimada and Taihei Shiotani and Koshiro Saito and Koki Maeda and Kakeru Hattori and Takumi Okamoto and Shigeki Ishida and Rio Yokota and Hiroya Takamura and Naoaki Okazaki},
year={2025},
eprint={2503.23714},
archivePrefix={arXiv},
primaryClass={cs.CL},
url={https://arxiv.org/abs/2503.23714},
}
```
### References
```tex
@misc{dubey2024llama3herdmodels,
title={The Llama 3 Herd of Models},
author={Abhimanyu Dubey and Abhinav Jauhri and Abhinav Pandey and Abhishek Kadian and Ahmad Al-Dahle and Aiesha Letman and Akhil Mathur and Alan Schelten and Amy Yang and Angela Fan et al.},
year={2024},
eprint={2407.21783},
archivePrefix={arXiv},
primaryClass={cs.AI},
url={https://arxiv.org/abs/2407.21783},
}
```
|
deepmaster/72_4
|
deepmaster
| 2025-06-25T00:55:35Z | 42 | 0 |
transformers
|
[
"transformers",
"safetensors",
"vit",
"image-classification",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
image-classification
| 2025-06-08T18:51:42Z |
---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a ๐ค transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
|
mlx-community/Llama-3.2-8X4B-MOE-V2-Dark-Champion-Instruct-uncensored-abliterated-21B-MLX
|
mlx-community
| 2025-06-25T00:51:02Z | 0 | 0 |
mlx
|
[
"mlx",
"safetensors",
"mixtral",
"Llama 3.2",
"8 X 4B",
"Brainstorm 5x",
"128k context",
"moe",
"8 experts",
"mixture of experts",
"fine tune",
"text-generation",
"conversational",
"base_model:DavidAU/L3.2-8X4B-MOE-V2-Dark-Champion-Inst-21B-uncen-ablit",
"base_model:quantized:DavidAU/L3.2-8X4B-MOE-V2-Dark-Champion-Inst-21B-uncen-ablit",
"8-bit",
"region:us"
] |
text-generation
| 2025-06-25T00:35:40Z |
---
library_name: mlx
tags:
- Llama 3.2
- 8 X 4B
- Brainstorm 5x
- 128k context
- moe
- 8 experts
- mixture of experts
- fine tune
- mlx
base_model: DavidAU/L3.2-8X4B-MOE-V2-Dark-Champion-Inst-21B-uncen-ablit
pipeline_tag: text-generation
---
# mlx-community/Llama-3.2-8X4B-MOE-V2-Dark-Champion-Instruct-uncensored-abliterated-21B-MLX
This model [mlx-community/Llama-3.2-8X4B-MOE-V2-Dark-Champion-Instruct-uncensored-abliterated-21B-MLX](https://huggingface.co/mlx-community/Llama-3.2-8X4B-MOE-V2-Dark-Champion-Instruct-uncensored-abliterated-21B-MLX) was
converted to MLX format from [DavidAU/L3.2-8X4B-MOE-V2-Dark-Champion-Inst-21B-uncen-ablit](https://huggingface.co/DavidAU/L3.2-8X4B-MOE-V2-Dark-Champion-Inst-21B-uncen-ablit)
using mlx-lm version **0.25.2**.
## Use with mlx
```bash
pip install mlx-lm
```
```python
from mlx_lm import load, generate
model, tokenizer = load("mlx-community/Llama-3.2-8X4B-MOE-V2-Dark-Champion-Instruct-uncensored-abliterated-21B-MLX")
prompt = "hello"
if tokenizer.chat_template is not None:
messages = [{"role": "user", "content": prompt}]
prompt = tokenizer.apply_chat_template(
messages, add_generation_prompt=True
)
response = generate(model, tokenizer, prompt=prompt, verbose=True)
```
|
Mr-Matrix/LogicBomb-Classifier
|
Mr-Matrix
| 2025-06-25T00:48:41Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"llama",
"text-classification",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2025-06-25T00:43:47Z |
---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a ๐ค transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
|
thavens/pir_sft_ckpt_50_i
|
thavens
| 2025-06-25T00:38:22Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"qwen3",
"text-generation",
"generated_from_trainer",
"trl",
"sft",
"conversational",
"base_model:Qwen/Qwen3-4B",
"base_model:finetune:Qwen/Qwen3-4B",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2025-06-25T00:14:28Z |
---
base_model: Qwen/Qwen3-4B
library_name: transformers
model_name: pir_sft_ckpt_50_i
tags:
- generated_from_trainer
- trl
- sft
licence: license
---
# Model Card for pir_sft_ckpt_50_i
This model is a fine-tuned version of [Qwen/Qwen3-4B](https://huggingface.co/Qwen/Qwen3-4B).
It has been trained using [TRL](https://github.com/huggingface/trl).
## Quick start
```python
from transformers import pipeline
question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
generator = pipeline("text-generation", model="thavens/pir_sft_ckpt_50_i", device="cuda")
output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
print(output["generated_text"])
```
## Training procedure
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/tmotiv/huggingface/runs/7n04dqdo)
This model was trained with SFT.
### Framework versions
- TRL: 0.18.0.dev0
- Transformers: 4.52.4
- Pytorch: 2.7.0+cu128
- Datasets: 3.6.0
- Tokenizers: 0.21.1
## Citations
Cite TRL as:
```bibtex
@misc{vonwerra2022trl,
title = {{TRL: Transformer Reinforcement Learning}},
author = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec},
year = 2020,
journal = {GitHub repository},
publisher = {GitHub},
howpublished = {\url{https://github.com/huggingface/trl}}
}
```
|
daixuancheng/sac-init0.4_qwen-math-7b_constrainbyAdv_yesSuffix_step40
|
daixuancheng
| 2025-06-25T00:37:15Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"qwen2",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2025-06-25T00:10:20Z |
---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a ๐ค transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
|
daixuancheng/zero_qwen-math-7b_base_allDapo_mathVerify_yesSuffix_step140
|
daixuancheng
| 2025-06-25T00:34:55Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"qwen2",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2025-06-25T00:08:57Z |
---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a ๐ค transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
|
gongting/latentsync
|
gongting
| 2025-06-25T00:32:18Z | 0 | 0 |
diffusers
|
[
"diffusers",
"safetensors",
"license:apache-2.0",
"region:us"
] | null | 2025-05-18T04:29:34Z |
---
license: apache-2.0
---
|
SrivatsaBhamidipati/qwen2.5-coder-3b-qlora
|
SrivatsaBhamidipati
| 2025-06-25T00:29:59Z | 0 | 0 |
peft
|
[
"peft",
"safetensors",
"generated_from_trainer",
"base_model:codellama/CodeLlama-13b-Instruct-hf",
"base_model:adapter:codellama/CodeLlama-13b-Instruct-hf",
"license:llama2",
"region:us"
] | null | 2025-06-24T22:28:46Z |
---
library_name: peft
license: llama2
base_model: codellama/CodeLlama-13b-Instruct-hf
tags:
- generated_from_trainer
model-index:
- name: qwen2.5-coder-3b-qlora
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# qwen2.5-coder-3b-qlora
This model is a fine-tuned version of [codellama/CodeLlama-13b-Instruct-hf](https://huggingface.co/codellama/CodeLlama-13b-Instruct-hf) on the None dataset.
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0002
- train_batch_size: 4
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- optimizer: Use OptimizerNames.PAGED_ADAMW_8BIT with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 50
- num_epochs: 10
- mixed_precision_training: Native AMP
### Training results
### Framework versions
- PEFT 0.14.0
- Transformers 4.52.4
- Pytorch 2.6.0+cu124
- Datasets 3.6.0
- Tokenizers 0.21.1
|
ZhangShenao/Llama-3.2-1B
|
ZhangShenao
| 2025-06-25T00:27:07Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"llama",
"text-generation",
"facebook",
"meta",
"pytorch",
"llama-3",
"en",
"de",
"fr",
"it",
"pt",
"hi",
"es",
"th",
"arxiv:2204.05149",
"arxiv:2405.16406",
"license:llama3.2",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2025-06-25T00:25:53Z |
---
language:
- en
- de
- fr
- it
- pt
- hi
- es
- th
library_name: transformers
pipeline_tag: text-generation
tags:
- facebook
- meta
- pytorch
- llama
- llama-3
license: llama3.2
extra_gated_prompt: >-
### LLAMA 3.2 COMMUNITY LICENSE AGREEMENT
Llama 3.2 Version Release Date: September 25, 2024
โAgreementโ means the terms and conditions for use, reproduction, distribution
and modification of the Llama Materials set forth herein.
โDocumentationโ means the specifications, manuals and documentation accompanying Llama 3.2
distributed by Meta at https://llama.meta.com/doc/overview.
โLicenseeโ or โyouโ means you, or your employer or any other person or entity (if you are
entering into this Agreement on such person or entityโs behalf), of the age required under
applicable laws, rules or regulations to provide legal consent and that has legal authority
to bind your employer or such other person or entity if you are entering in this Agreement
on their behalf.
โLlama 3.2โ means the foundational large language models and software and algorithms, including
machine-learning model code, trained model weights, inference-enabling code, training-enabling code,
fine-tuning enabling code and other elements of the foregoing distributed by Meta at
https://www.llama.com/llama-downloads.
โLlama Materialsโ means, collectively, Metaโs proprietary Llama 3.2 and Documentation (and
any portion thereof) made available under this Agreement.
โMetaโ or โweโ means Meta Platforms Ireland Limited (if you are located in or,
if you are an entity, your principal place of business is in the EEA or Switzerland)
and Meta Platforms, Inc. (if you are located outside of the EEA or Switzerland).
By clicking โI Acceptโ below or by using or distributing any portion or element of the Llama Materials,
you agree to be bound by this Agreement.
1. License Rights and Redistribution.
a. Grant of Rights. You are granted a non-exclusive, worldwide,
non-transferable and royalty-free limited license under Metaโs intellectual property or other rights
owned by Meta embodied in the Llama Materials to use, reproduce, distribute, copy, create derivative works
of, and make modifications to the Llama Materials.
b. Redistribution and Use.
i. If you distribute or make available the Llama Materials (or any derivative works thereof),
or a product or service (including another AI model) that contains any of them, you shall (A) provide
a copy of this Agreement with any such Llama Materials; and (B) prominently display โBuilt with Llamaโ
on a related website, user interface, blogpost, about page, or product documentation. If you use the
Llama Materials or any outputs or results of the Llama Materials to create, train, fine tune, or
otherwise improve an AI model, which is distributed or made available, you shall also include โLlamaโ
at the beginning of any such AI model name.
ii. If you receive Llama Materials, or any derivative works thereof, from a Licensee as part
of an integrated end user product, then Section 2 of this Agreement will not apply to you.
iii. You must retain in all copies of the Llama Materials that you distribute the
following attribution notice within a โNoticeโ text file distributed as a part of such copies:
โLlama 3.2 is licensed under the Llama 3.2 Community License, Copyright ยฉ Meta Platforms,
Inc. All Rights Reserved.โ
iv. Your use of the Llama Materials must comply with applicable laws and regulations
(including trade compliance laws and regulations) and adhere to the Acceptable Use Policy for
the Llama Materials (available at https://www.llama.com/llama3_2/use-policy), which is hereby
incorporated by reference into this Agreement.
2. Additional Commercial Terms. If, on the Llama 3.2 version release date, the monthly active users
of the products or services made available by or for Licensee, or Licenseeโs affiliates,
is greater than 700 million monthly active users in the preceding calendar month, you must request
a license from Meta, which Meta may grant to you in its sole discretion, and you are not authorized to
exercise any of the rights under this Agreement unless or until Meta otherwise expressly grants you such rights.
3. Disclaimer of Warranty. UNLESS REQUIRED BY APPLICABLE LAW, THE LLAMA MATERIALS AND ANY OUTPUT AND
RESULTS THEREFROM ARE PROVIDED ON AN โAS ISโ BASIS, WITHOUT WARRANTIES OF ANY KIND, AND META DISCLAIMS
ALL WARRANTIES OF ANY KIND, BOTH EXPRESS AND IMPLIED, INCLUDING, WITHOUT LIMITATION, ANY WARRANTIES
OF TITLE, NON-INFRINGEMENT, MERCHANTABILITY, OR FITNESS FOR A PARTICULAR PURPOSE. YOU ARE SOLELY RESPONSIBLE
FOR DETERMINING THE APPROPRIATENESS OF USING OR REDISTRIBUTING THE LLAMA MATERIALS AND ASSUME ANY RISKS ASSOCIATED
WITH YOUR USE OF THE LLAMA MATERIALS AND ANY OUTPUT AND RESULTS.
4. Limitation of Liability. IN NO EVENT WILL META OR ITS AFFILIATES BE LIABLE UNDER ANY THEORY OF LIABILITY,
WHETHER IN CONTRACT, TORT, NEGLIGENCE, PRODUCTS LIABILITY, OR OTHERWISE, ARISING OUT OF THIS AGREEMENT,
FOR ANY LOST PROFITS OR ANY INDIRECT, SPECIAL, CONSEQUENTIAL, INCIDENTAL, EXEMPLARY OR PUNITIVE DAMAGES, EVEN
IF META OR ITS AFFILIATES HAVE BEEN ADVISED OF THE POSSIBILITY OF ANY OF THE FOREGOING.
5. Intellectual Property.
a. No trademark licenses are granted under this Agreement, and in connection with the Llama Materials,
neither Meta nor Licensee may use any name or mark owned by or associated with the other or any of its affiliates,
except as required for reasonable and customary use in describing and redistributing the Llama Materials or as
set forth in this Section 5(a). Meta hereby grants you a license to use โLlamaโ (the โMarkโ) solely as required
to comply with the last sentence of Section 1.b.i. You will comply with Metaโs brand guidelines (currently accessible
at https://about.meta.com/brand/resources/meta/company-brand/). All goodwill arising out of your use of the Mark
will inure to the benefit of Meta.
b. Subject to Metaโs ownership of Llama Materials and derivatives made by or for Meta, with respect to any
derivative works and modifications of the Llama Materials that are made by you, as between you and Meta,
you are and will be the owner of such derivative works and modifications.
c. If you institute litigation or other proceedings against Meta or any entity (including a cross-claim or
counterclaim in a lawsuit) alleging that the Llama Materials or Llama 3.2 outputs or results, or any portion
of any of the foregoing, constitutes infringement of intellectual property or other rights owned or licensable
by you, then any licenses granted to you under this Agreement shall terminate as of the date such litigation or
claim is filed or instituted. You will indemnify and hold harmless Meta from and against any claim by any third
party arising out of or related to your use or distribution of the Llama Materials.
6. Term and Termination. The term of this Agreement will commence upon your acceptance of this Agreement or access
to the Llama Materials and will continue in full force and effect until terminated in accordance with the terms
and conditions herein. Meta may terminate this Agreement if you are in breach of any term or condition of this
Agreement. Upon termination of this Agreement, you shall delete and cease use of the Llama Materials. Sections 3,
4 and 7 shall survive the termination of this Agreement.
7. Governing Law and Jurisdiction. This Agreement will be governed and construed under the laws of the State of
California without regard to choice of law principles, and the UN Convention on Contracts for the International
Sale of Goods does not apply to this Agreement. The courts of California shall have exclusive jurisdiction of
any dispute arising out of this Agreement.
### Llama 3.2 Acceptable Use Policy
Meta is committed to promoting safe and fair use of its tools and features, including Llama 3.2.
If you access or use Llama 3.2, you agree to this Acceptable Use Policy (โ**Policy**โ).
The most recent copy of this policy can be found at
[https://www.llama.com/llama3_2/use-policy](https://www.llama.com/llama3_2/use-policy).
#### Prohibited Uses
We want everyone to use Llama 3.2 safely and responsibly. You agree you will not use, or allow others to use, Llama 3.2 to:
1. Violate the law or othersโ rights, including to:
1. Engage in, promote, generate, contribute to, encourage, plan, incite, or further illegal or unlawful activity or content, such as:
1. Violence or terrorism
2. Exploitation or harm to children, including the solicitation, creation, acquisition, or dissemination of child exploitative content or failure to report Child Sexual Abuse Material
3. Human trafficking, exploitation, and sexual violence
4. The illegal distribution of information or materials to minors, including obscene materials, or failure to employ legally required age-gating in connection with such information or materials.
5. Sexual solicitation
6. Any other criminal activity
1. Engage in, promote, incite, or facilitate the harassment, abuse, threatening, or bullying of individuals or groups of individuals
2. Engage in, promote, incite, or facilitate discrimination or other unlawful or harmful conduct in the provision of employment, employment benefits, credit, housing, other economic benefits, or other essential goods and services
3. Engage in the unauthorized or unlicensed practice of any profession including, but not limited to, financial, legal, medical/health, or related professional practices
4. Collect, process, disclose, generate, or infer private or sensitive information about individuals, including information about individualsโ identity, health, or demographic information, unless you have obtained the right to do so in accordance with applicable law
5. Engage in or facilitate any action or generate any content that infringes, misappropriates, or otherwise violates any third-party rights, including the outputs or results of any products or services using the Llama Materials
6. Create, generate, or facilitate the creation of malicious code, malware, computer viruses or do anything else that could disable, overburden, interfere with or impair the proper working, integrity, operation or appearance of a website or computer system
7. Engage in any action, or facilitate any action, to intentionally circumvent or remove usage restrictions or other safety measures, or to enable functionality disabled by Metaย
2. Engage in, promote, incite, facilitate, or assist in the planning or development of activities that present a risk of death or bodily harm to individuals, including use of Llama 3.2 related to the following:
8. Military, warfare, nuclear industries or applications, espionage, use for materials or activities that are subject to the International Traffic Arms Regulations (ITAR) maintained by the United States Department of State or to the U.S. Biological Weapons Anti-Terrorism Act of 1989 or the Chemical Weapons Convention Implementation Act of 1997
9. Guns and illegal weapons (including weapon development)
10. Illegal drugs and regulated/controlled substances
11. Operation of critical infrastructure, transportation technologies, or heavy machinery
12. Self-harm or harm to others, including suicide, cutting, and eating disorders
13. Any content intended to incite or promote violence, abuse, or any infliction of bodily harm to an individual
3. Intentionally deceive or mislead others, including use of Llama 3.2 related to the following:
14. Generating, promoting, or furthering fraud or the creation or promotion of disinformation
15. Generating, promoting, or furthering defamatory content, including the creation of defamatory statements, images, or other content
16. Generating, promoting, or further distributing spam
17. Impersonating another individual without consent, authorization, or legal right
18. Representing that the use of Llama 3.2 or outputs are human-generated
19. Generating or facilitating false online engagement, including fake reviews and other means of fake online engagementย
4. Fail to appropriately disclose to end users any known dangers of your AI system
5. Interact with third party tools, models, or software designed to generate unlawful content or engage in unlawful or harmful conduct and/or represent that the outputs of such tools, models, or software are associated with Meta or Llama 3.2
With respect to any multimodal models included in Llama 3.2, the rights granted under Section 1(a) of the Llama 3.2 Community License Agreement are not being granted to you if you are an individual domiciled in, or a company with a principal place of business in, the European Union. This restriction does not apply to end users of a product or service that incorporates any such multimodal models.
Please report any violation of this Policy, software โbug,โ or other problems that could lead to a violation of this Policy through one of the following means:
* Reporting issues with the model: [https://github.com/meta-llama/llama-models/issues](https://l.workplace.com/l.php?u=https%3A%2F%2Fgithub.com%2Fmeta-llama%2Fllama-models%2Fissues&h=AT0qV8W9BFT6NwihiOHRuKYQM_UnkzN_NmHMy91OT55gkLpgi4kQupHUl0ssR4dQsIQ8n3tfd0vtkobvsEvt1l4Ic6GXI2EeuHV8N08OG2WnbAmm0FL4ObkazC6G_256vN0lN9DsykCvCqGZ)
* Reporting risky content generated by the model: [developers.facebook.com/llama_output_feedback](http://developers.facebook.com/llama_output_feedback)
* Reporting bugs and security concerns: [facebook.com/whitehat/info](http://facebook.com/whitehat/info)
* Reporting violations of the Acceptable Use Policy or unlicensed uses of Llama 3.2: LlamaUseReport@meta.com
extra_gated_fields:
First Name: text
Last Name: text
Date of birth: date_picker
Country: country
Affiliation: text
Job title:
type: select
options:
- Student
- Research Graduate
- AI researcher
- AI developer/engineer
- Reporter
- Other
geo: ip_location
By clicking Submit below I accept the terms of the license and acknowledge that the information I provide will be collected stored processed and shared in accordance with the Meta Privacy Policy: checkbox
extra_gated_description: >-
The information you provide will be collected, stored, processed and shared in
accordance with the [Meta Privacy
Policy](https://www.facebook.com/privacy/policy/).
extra_gated_button_content: Submit
---
## Model Information
The Llama 3.2 collection of multilingual large language models (LLMs) is a collection of pretrained and instruction-tuned generative models in 1B and 3B sizes (text in/text out). The Llama 3.2 instruction-tuned text only models are optimized for multilingual dialogue use cases, including agentic retrieval and summarization tasks. They outperform many of the available open source and closed chat models on common industry benchmarks.
**Model Developer:** Meta
**Model Architecture:** Llama 3.2 is an auto-regressive language model that uses an optimized transformer architecture. The tuned versions use supervised fine-tuning (SFT) and reinforcement learning with human feedback (RLHF) to align with human preferences for helpfulness and safety.
| | Training Data | Params | Input modalities | Output modalities | Context Length | GQA | Shared Embeddings | Token count | Knowledge cutoff |
| :---- | :---- | :---- | :---- | :---- | :---- | :---- | :---- | :---- | :---- |
| Llama 3.2 (text only) | A new mix of publicly available online data. | 1B (1.23B) | Multilingual Text | Multilingual Text and code | 128k | Yes | Yes | Up to 9T tokens | December 2023 |
| | | 3B (3.21B) | Multilingual Text | Multilingual Text and code | | | | | |
| Llama 3.2 Quantized (text only) | A new mix of publicly available online data. | 1B (1.23B) | Multilingual Text | Multilingual Text and code | 8k | Yes | Yes | Up to 9T tokens | December 2023 |
| | | 3B (3.21B) | Multilingual Text | Multilingual Text and code | | | | | |
**Supported Languages:** English, German, French, Italian, Portuguese, Hindi, Spanish, and Thai are officially supported. Llama 3.2 has been trained on a broader collection of languages than these 8 supported languages. Developers may fine-tune Llama 3.2 models for languages beyond these supported languages, provided they comply with the Llama 3.2 Community License and the Acceptable Use Policy. Developers are always expected to ensure that their deployments, including those that involve additional languages, are completed safely and responsibly.
**Llama 3.2 Model Family:** Token counts refer to pretraining data only. All model versions use Grouped-Query Attention (GQA) for improved inference scalability.
**Model Release Date:** Sept 25, 2024
**Status:** This is a static model trained on an offline dataset. Future versions may be released that improve model capabilities and safety.
**License:** Use of Llama 3.2 is governed by the [Llama 3.2 Community License](https://github.com/meta-llama/llama-models/blob/main/models/llama3_2/LICENSE) (a custom, commercial license agreement).
**Feedback:** Instructions on how to provide feedback or comments on the model can be found in the Llama Models [README](https://github.com/meta-llama/llama-models/blob/main/README.md). For more technical information about generation parameters and recipes for how to use Llama 3.2 in applications, please go [here](https://github.com/meta-llama/llama-recipes).
## Intended Use
**Intended Use Cases:** Llama 3.2 is intended for commercial and research use in multiple languages. Instruction tuned text only models are intended for assistant-like chat and agentic applications like knowledge retrieval and summarization, mobile AI powered writing assistants and query and prompt rewriting. Pretrained models can be adapted for a variety of additional natural language generation tasks. Similarly, quantized models can be adapted for a variety of on-device use-cases with limited compute resources.
**Out of Scope:** Use in any manner that violates applicable laws or regulations (including trade compliance laws). Use in any other way that is prohibited by the Acceptable Use Policy and Llama 3.2 Community License. Use in languages beyond those explicitly referenced as supported in this model card.
## How to use
This repository contains two versions of Llama-3.2-1B, for use with transformers and with the original `llama` codebase.
### Use with transformers
Starting with transformers >= 4.43.0 onward, you can run conversational inference using the Transformers pipeline abstraction or by leveraging the Auto classes with the generate() function.
Make sure to update your transformers installation via pip install --upgrade transformers.
```python
import torch
from transformers import pipeline
model_id = "meta-llama/Llama-3.2-1B"
pipe = pipeline(
"text-generation",
model=model_id,
torch_dtype=torch.bfloat16,
device_map="auto"
)
pipe("The key to life is")
```
### Use with `llama`
Please, follow the instructions in the [repository](https://github.com/meta-llama/llama).
To download Original checkpoints, see the example command below leveraging `huggingface-cli`:
```
huggingface-cli download meta-llama/Llama-3.2-1B --include "original/*" --local-dir Llama-3.2-1B
```
## Hardware and Software
**Training Factors:** We used custom training libraries, Meta's custom built GPU cluster, and production infrastructure for pretraining. Fine-tuning, quantization, annotation, and evaluation were also performed on production infrastructure.
**Training Energy Use:** Training utilized a cumulative of **916k** GPU hours of computation on H100-80GB (TDP of 700W) type hardware, per the table below. Training time is the total GPU time required for training each model and power consumption is the peak power capacity per GPU device used, adjusted for power usage efficiency.
**Training Greenhouse Gas Emissions:** Estimated total location-based greenhouse gas emissions were **240** tons CO2eq for training. Since 2020, Meta has maintained net zero greenhouse gas emissions in its global operations and matched 100% of its electricity use with renewable energy; therefore, the total market-based greenhouse gas emissions for training were 0 tons CO2eq.
| | Training Time (GPU hours) | Logit Generation Time (GPU Hours) | Training Power Consumption (W) | Training Location-Based Greenhouse Gas Emissions (tons CO2eq) | Training Market-Based Greenhouse Gas Emissions (tons CO2eq) |
| :---- | :---: | ----- | :---: | :---: | :---: |
| Llama 3.2 1B | 370k | \- | 700 | 107 | 0 |
| Llama 3.2 3B | 460k | \- | 700 | 133 | 0 |
| Llama 3.2 1B SpinQuant | 1.7 | 0 | 700 | *Negligible*\*\* | 0 |
| Llama 3.2 3B SpinQuant | 2.4 | 0 | 700 | *Negligible*\*\* | 0 |
| Llama 3.2 1B QLora | 1.3k | 0 | 700 | 0.381 | 0 |
| Llama 3.2 3B QLora | 1.6k | 0 | 700 | 0.461 | 0 |
| Total | 833k | 86k | | 240 | 0 |
\*\* The location-based CO2e emissions of Llama 3.2 1B SpinQuant and Llama 3.2 3B SpinQuant are less than 0.001 metric tonnes each. This is due to the minimal training GPU hours that are required.
The methodology used to determine training energy use and greenhouse gas emissions can be found [here](https://arxiv.org/pdf/2204.05149). Since Meta is openly releasing these models, the training energy use and greenhouse gas emissions will not be incurred by others.
## Training Data
**Overview:** Llama 3.2 was pretrained on up to 9 trillion tokens of data from publicly available sources. For the 1B and 3B Llama 3.2 models, we incorporated logits from the Llama 3.1 8B and 70B models into the pretraining stage of the model development, where outputs (logits) from these larger models were used as token-level targets. Knowledge distillation was used after pruning to recover performance. In post-training we used a similar recipe as Llama 3.1 and produced final chat models by doing several rounds of alignment on top of the pre-trained model. Each round involved Supervised Fine-Tuning (SFT), Rejection Sampling (RS), and Direct Preference Optimization (DPO).
**Data Freshness:** The pretraining data has a cutoff of December 2023\.
## Quantization
### Quantization Scheme
We designed the current quantization scheme with the [PyTorchโs ExecuTorch](https://github.com/pytorch/executorch) inference framework and Arm CPU backend in mind, taking into account metrics including model quality, prefill/decoding speed, and memory footprint. Our quantization scheme involves three parts:
- All linear layers in all transformer blocks are quantized to a 4-bit groupwise scheme (with a group size of 32) for weights and 8-bit per-token dynamic quantization for activations.
- The classification layer is quantized to 8-bit per-channel for weight and 8-bit per token dynamic quantization for activation.
- Similar to classification layer, an 8-bit per channel quantization is used for embedding layer.
### Quantization-Aware Training and LoRA
The quantization-aware training (QAT) with low-rank adaptation (LoRA) models went through only post-training stages, using the same data as the full precision models. To initialize QAT, we utilize BF16 Llama 3.2 model checkpoints obtained after supervised fine-tuning (SFT) and perform an additional full round of SFT training with QAT. We then freeze the backbone of the QAT model and perform another round of SFT with LoRA adaptors applied to all layers within the transformer block. Meanwhile, the LoRA adaptors' weights and activations are maintained in BF16. Because our approach is similar to QLoRA of Dettmers et al., (2023) (i.e., quantization followed by LoRA adapters), we refer this method as QLoRA. Finally, we fine-tune the resulting model (both backbone and LoRA adaptors) using direct preference optimization (DPO).
### SpinQuant
[SpinQuant](https://arxiv.org/abs/2405.16406) was applied, together with generative post-training quantization (GPTQ). For the SpinQuant rotation matrix fine-tuning, we optimized for 100 iterations, using 800 samples with sequence-length 2048 from the WikiText 2 dataset. For GPTQ, we used 128 samples from the same dataset with the same sequence-length.
## Benchmarks \- English Text
In this section, we report the results for Llama 3.2 models on standard automatic benchmarks. For all these evaluations, we used our internal evaluations library.
### Base Pretrained Models
| Category | Benchmark | \# Shots | Metric | Llama 3.2 1B | Llama 3.2 3B | Llama 3.1 8B |
| ----- | ----- | :---: | :---: | :---: | :---: | :---: |
| General | MMLU | 5 | macro\_avg/acc\_char | 32.2 | 58 | 66.7 |
| | AGIEval English | 3-5 | average/acc\_char | 23.3 | 39.2 | 47.8 |
| | ARC-Challenge | 25 | acc\_char | 32.8 | 69.1 | 79.7 |
| Reading comprehension | SQuAD | 1 | em | 49.2 | 67.7 | 77 |
| | QuAC (F1) | 1 | f1 | 37.9 | 42.9 | 44.9 |
| | DROP (F1) | 3 | f1 | 28.0 | 45.2 | 59.5 |
| Long Context | Needle in Haystack | 0 | em | 96.8 | 1 | 1 |
### Instruction Tuned Models
| Capability | | Benchmark | \# Shots | Metric | Llama 3.2 1B bf16 | Llama 3.2 1B Vanilla PTQ\*\* | Llama 3.2 1B Spin Quant | Llama 3.2 1B QLoRA | Llama 3.2 3B bf16 | Llama 3.2 3B Vanilla PTQ\*\* | Llama 3.2 3B Spin Quant | Llama 3.2 3B QLoRA | Llama 3.1 8B |
| :---: | ----- | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: |
| General | | MMLU | 5 | macro\_avg/acc | 49.3 | 43.3 | 47.3 | 49.0 | 63.4 | 60.5 | 62 | 62.4 | 69.4 |
| Re-writing | | Open-rewrite eval | 0 | micro\_avg/rougeL | 41.6 | 39.2 | 40.9 | 41.2 | 40.1 | 40.3 | 40.8 | 40.7 | 40.9 |
| Summarization | | TLDR9+ (test) | 1 | rougeL | 16.8 | 14.9 | 16.7 | 16.8 | 19.0 | 19.1 | 19.2 | 19.1 | 17.2 |
| Instruction following | | IFEval | 0 | Avg(Prompt/Instruction acc Loose/Strict) | 59.5 | 51.5 | 58.4 | 55.6 | 77.4 | 73.9 | 73.5 | 75.9 | 80.4 |
| Math | | GSM8K (CoT) | 8 | em\_maj1@1 | 44.4 | 33.1 | 40.6 | 46.5 | 77.7 | 72.9 | 75.7 | 77.9 | 84.5 |
| | | MATH (CoT) | 0 | final\_em | 30.6 | 20.5 | 25.3 | 31.0 | 48.0 | 44.2 | 45.3 | 49.2 | 51.9 |
| Reasoning | | ARC-C | 0 | acc | 59.4 | 54.3 | 57 | 60.7 | 78.6 | 75.6 | 77.6 | 77.6 | 83.4 |
| | | GPQA | 0 | acc | 27.2 | 25.9 | 26.3 | 25.9 | 32.8 | 32.8 | 31.7 | 33.9 | 32.8 |
| | | Hellaswag | 0 | acc | 41.2 | 38.1 | 41.3 | 41.5 | 69.8 | 66.3 | 68 | 66.3 | 78.7 |
| Tool Use | | BFCL V2 | 0 | acc | 25.7 | 14.3 | 15.9 | 23.7 | 67.0 | 53.4 | 60.1 | 63.5 | 67.1 |
| | | Nexus | 0 | macro\_avg/acc | 13.5 | 5.2 | 9.6 | 12.5 | 34.3 | 32.4 | 31.5 | 30.1 | 38.5 |
| Long Context | | InfiniteBench/En.QA | 0 | longbook\_qa/f1 | 20.3 | N/A | N/A | N/A | 19.8 | N/A | N/A | N/A | 27.3 |
| | | InfiniteBench/En.MC | 0 | longbook\_choice/acc | 38.0 | N/A | N/A | N/A | 63.3 | N/A | N/A | N/A | 72.2 |
| | | NIH/Multi-needle | 0 | recall | 75.0 | N/A | N/A | N/A | 84.7 | N/A | N/A | N/A | 98.8 |
| Multilingual | | MGSM (CoT) | 0 | em | 24.5 | 13.7 | 18.2 | 24.4 | 58.2 | 48.9 | 54.3 | 56.8 | 68.9 |
\*\*for comparison purposes only. Model not released.
### Multilingual Benchmarks
| Category | Benchmark | Language | Llama 3.2 1B | Llama 3.2 1B Vanilla PTQ\*\* | Llama 3.2 1B Spin Quant | Llama 3.2 1B QLoRA | Llama 3.2 3B | Llama 3.2 3B Vanilla PTQ\*\* | Llama 3.2 3B Spin Quant | Llama 3.2 3B QLoRA | Llama 3.1 8B |
| :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: |
| General | MMLU (5-shot, macro_avg/acc) | Portuguese | 39.8 | 34.9 | 38.9 | 40.2 | 54.5 | 50.9 | 53.3 | 53.4 | 62.1 |
| | | Spanish | 41.5 | 36.0 | 39.8 | 41.8 | 55.1 | 51.9 | 53.6 | 53.6 | 62.5 |
| | | Italian | 39.8 | 34.9 | 38.1 | 40.6 | 53.8 | 49.9 | 52.1 | 51.7 | 61.6 |
| | | German | 39.2 | 34.9 | 37.5 | 39.6 | 53.3 | 50.0 | 52.2 | 51.3 | 60.6 |
| | | French | 40.5 | 34.8 | 39.2 | 40.8 | 54.6 | 51.2 | 53.3 | 53.3 | 62.3 |
| | | Hindi | 33.5 | 30.0 | 32.1 | 34.0 | 43.3 | 40.4 | 42.0 | 42.1 | 50.9 |
| | | Thai | 34.7 | 31.2 | 32.4 | 34.9 | 44.5 | 41.3 | 44.0 | 42.2 | 50.3 |
\*\*for comparison purposes only. Model not released.
## Inference time
In the below table, we compare the performance metrics of different quantization methods (SpinQuant and QAT \+ LoRA) with the BF16 baseline. The evaluation was done using the [ExecuTorch](https://github.com/pytorch/executorch) framework as the inference engine, with the ARM CPU as a backend using Android OnePlus 12 device.
| Category | Decode (tokens/sec) | Time-to-first-token (sec) | Prefill (tokens/sec) | Model size (PTE file size in MB) | Memory size (RSS in MB) |
| :---- | ----- | ----- | ----- | ----- | ----- |
| 1B BF16 (baseline) | 19.2 | 1.0 | 60.3 | 2358 | 3,185 |
| 1B SpinQuant | 50.2 (2.6x) | 0.3 (-76.9%) | 260.5 (4.3x) | 1083 (-54.1%) | 1,921 (-39.7%) |
| 1B QLoRA | 45.8 (2.4x) | 0.3 (-76.0%) | 252.0 (4.2x) | 1127 (-52.2%) | 2,255 (-29.2%) |
| 3B BF16 (baseline) | 7.6 | 3.0 | 21.2 | 6129 | 7,419 |
| 3B SpinQuant | 19.7 (2.6x) | 0.7 (-76.4%) | 89.7 (4.2x) | 2435 (-60.3%) | 3,726 (-49.8%) |
| 3B QLoRA | 18.5 (2.4x) | 0.7 (-76.1%) | 88.8 (4.2x) | 2529 (-58.7%) | 4,060 (-45.3%) |
(\*) The performance measurement is done using an adb binary-based approach.
(\*\*) It is measured on an Android OnePlus 12 device.
(\*\*\*) Time-to-first-token (TTFT) is measured with prompt length=64
*Footnote:*
- *Decode (tokens/second) is for how quickly it keeps generating. Higher is better.*
- *Time-to-first-token (TTFT for shorthand) is for how fast it generates the first token for a given prompt. Lower is better.*
- *Prefill is the inverse of TTFT (aka 1/TTFT) in tokens/second. Higher is better*
- *Model size \- how big is the model, measured by, PTE file, a binary file format for ExecuTorch*
- *RSS size \- Memory usage in resident set size (RSS)*
## Responsibility & Safety
As part of our Responsible release approach, we followed a three-pronged strategy to managing trust & safety risks:
1. Enable developers to deploy helpful, safe and flexible experiences for their target audience and for the use cases supported by Llama
2. Protect developers against adversarial users aiming to exploit Llama capabilities to potentially cause harm
3. Provide protections for the community to help prevent the misuse of our models
### Responsible Deployment
**Approach:** Llama is a foundational technology designed to be used in a variety of use cases. Examples on how Metaโs Llama models have been responsibly deployed can be found in our [Community Stories webpage](https://llama.meta.com/community-stories/). Our approach is to build the most helpful models, enabling the world to benefit from the technology power, by aligning our model safety for generic use cases and addressing a standard set of harms. Developers are then in the driverโs seat to tailor safety for their use cases, defining their own policies and deploying the models with the necessary safeguards in their Llama systems. Llama 3.2 was developed following the best practices outlined in our [Responsible Use Guide](https://llama.meta.com/responsible-use-guide/).
#### Llama 3.2 Instruct
**Objective:** Our main objectives for conducting safety fine-tuning are to provide the research community with a valuable resource for studying the robustness of safety fine-tuning, as well as to offer developers a readily available, safe, and powerful model for various applications to reduce the developer workload to deploy safe AI systems. We implemented the same set of safety mitigations as in Llama 3, and you can learn more about these in the Llama 3 [paper](https://ai.meta.com/research/publications/the-llama-3-herd-of-models/).
**Fine-Tuning Data:** We employ a multi-faceted approach to data collection, combining human-generated data from our vendors with synthetic data to mitigate potential safety risks. Weโve developed many large language model (LLM)-based classifiers that enable us to thoughtfully select high-quality prompts and responses, enhancing data quality control.
**Refusals and Tone:** Building on the work we started with Llama 3, we put a great emphasis on model refusals to benign prompts as well as refusal tone. We included both borderline and adversarial prompts in our safety data strategy, and modified our safety data responses to follow tone guidelines.
#### Llama 3.2 Systems
**Safety as a System:** Large language models, including Llama 3.2, **are not designed to be deployed in isolation** but instead should be deployed as part of an overall AI system with additional safety guardrails as required. Developers are expected to deploy system safeguards when building agentic systems. Safeguards are key to achieve the right helpfulness-safety alignment as well as mitigating safety and security risks inherent to the system and any integration of the model or system with external tools. As part of our responsible release approach, we provide the community with [safeguards](https://llama.meta.com/trust-and-safety/) that developers should deploy with Llama models or other LLMs, including Llama Guard, Prompt Guard and Code Shield. All our [reference implementations](https://github.com/meta-llama/llama-agentic-system) demos contain these safeguards by default so developers can benefit from system-level safety out-of-the-box.
### New Capabilities and Use Cases
**Technological Advancement:** Llama releases usually introduce new capabilities that require specific considerations in addition to the best practices that generally apply across all Generative AI use cases. For prior release capabilities also supported by Llama 3.2, see [Llama 3.1 Model Card](https://github.com/meta-llama/llama-models/blob/main/models/llama3_1/MODEL_CARD.md), as the same considerations apply here as well.
**Constrained Environments:** Llama 3.2 1B and 3B models are expected to be deployed in highly constrained environments, such as mobile devices. LLM Systems using smaller models will have a different alignment profile and safety/helpfulness tradeoff than more complex, larger systems. Developers should ensure the safety of their system meets the requirements of their use case. We recommend using lighter system safeguards for such use cases, like Llama Guard 3-1B or its mobile-optimized version.
### Evaluations
**Scaled Evaluations:** We built dedicated, adversarial evaluation datasets and evaluated systems composed of Llama models and Purple Llama safeguards to filter input prompt and output response. It is important to evaluate applications in context, and we recommend building dedicated evaluation dataset for your use case.
**Red Teaming:** We conducted recurring red teaming exercises with the goal of discovering risks via adversarial prompting and we used the learnings to improve our benchmarks and safety tuning datasets. We partnered early with subject-matter experts in critical risk areas to understand the nature of these real-world harms and how such models may lead to unintended harm for society. Based on these conversations, we derived a set of adversarial goals for the red team to attempt to achieve, such as extracting harmful information or reprogramming the model to act in a potentially harmful capacity. The red team consisted of experts in cybersecurity, adversarial machine learning, responsible AI, and integrity in addition to multilingual content specialists with background in integrity issues in specific geographic markets.
### Critical Risks
In addition to our safety work above, we took extra care on measuring and/or mitigating the following critical risk areas:
**1\. CBRNE (Chemical, Biological, Radiological, Nuclear, and Explosive Weapons):** Llama 3.2 1B and 3B models are smaller and less capable derivatives of Llama 3.1. For Llama 3.1 70B and 405B, to assess risks related to proliferation of chemical and biological weapons, we performed uplift testing designed to assess whether use of Llama 3.1 models could meaningfully increase the capabilities of malicious actors to plan or carry out attacks using these types of weapons and have determined that such testing also applies to the smaller 1B and 3B models.
**2\. Child Safety:** Child Safety risk assessments were conducted using a team of experts, to assess the modelโs capability to produce outputs that could result in Child Safety risks and inform on any necessary and appropriate risk mitigations via fine tuning. We leveraged those expert red teaming sessions to expand the coverage of our evaluation benchmarks through Llama 3 model development. For Llama 3, we conducted new in-depth sessions using objective based methodologies to assess the model risks along multiple attack vectors including the additional languages Llama 3 is trained on. We also partnered with content specialists to perform red teaming exercises assessing potentially violating content while taking account of market specific nuances or experiences.
**3\. Cyber Attacks:** For Llama 3.1 405B, our cyber attack uplift study investigated whether LLMs can enhance human capabilities in hacking tasks, both in terms of skill level and speed.
Our attack automation study focused on evaluating the capabilities of LLMs when used as autonomous agents in cyber offensive operations, specifically in the context of ransomware attacks. This evaluation was distinct from previous studies that considered LLMs as interactive assistants. The primary objective was to assess whether these models could effectively function as independent agents in executing complex cyber-attacks without human intervention. Because Llama 3.2โs 1B and 3B models are smaller and less capable models than Llama 3.1 405B, we broadly believe that the testing conducted for the 405B model also applies to Llama 3.2 models.
### Community
**Industry Partnerships:** Generative AI safety requires expertise and tooling, and we believe in the strength of the open community to accelerate its progress. We are active members of open consortiums, including the AI Alliance, Partnership on AI and MLCommons, actively contributing to safety standardization and transparency. We encourage the community to adopt taxonomies like the MLCommons Proof of Concept evaluation to facilitate collaboration and transparency on safety and content evaluations. Our Purple Llama tools are open sourced for the community to use and widely distributed across ecosystem partners including cloud service providers. We encourage community contributions to our [Github repository](https://github.com/meta-llama/PurpleLlama).
**Grants:** We also set up the [Llama Impact Grants](https://llama.meta.com/llama-impact-grants/) program to identify and support the most compelling applications of Metaโs Llama model for societal benefit across three categories: education, climate and open innovation. The 20 finalists from the hundreds of applications can be found [here](https://llama.meta.com/llama-impact-grants/#finalists).
**Reporting:** Finally, we put in place a set of resources including an [output reporting mechanism](https://developers.facebook.com/llama_output_feedback) and [bug bounty program](https://www.facebook.com/whitehat) to continuously improve the Llama technology with the help of the community.
## Ethical Considerations and Limitations
**Values:** The core values of Llama 3.2 are openness, inclusivity and helpfulness. It is meant to serve everyone, and to work for a wide range of use cases. It is thus designed to be accessible to people across many different backgrounds, experiences and perspectives. Llama 3.2 addresses users and their needs as they are, without insertion unnecessary judgment or normativity, while reflecting the understanding that even content that may appear problematic in some cases can serve valuable purposes in others. It respects the dignity and autonomy of all users, especially in terms of the values of free thought and expression that power innovation and progress.
**Testing:** Llama 3.2 is a new technology, and like any new technology, there are risks associated with its use. Testing conducted to date has not covered, nor could it cover, all scenarios. For these reasons, as with all LLMs, Llama 3.2โs potential outputs cannot be predicted in advance, and the model may in some instances produce inaccurate, biased or other objectionable responses to user prompts. Therefore, before deploying any applications of Llama 3.2 models, developers should perform safety testing and tuning tailored to their specific applications of the model. Please refer to available resources including our [Responsible Use Guide](https://llama.meta.com/responsible-use-guide), [Trust and Safety](https://llama.meta.com/trust-and-safety/) solutions, and other [resources](https://llama.meta.com/docs/get-started/) to learn more about responsible development.
|
multiheadattn/my_awesome_model
|
multiheadattn
| 2025-06-25T00:25:00Z | 0 | 0 |
transformers
|
[
"transformers",
"tensorboard",
"safetensors",
"distilbert",
"text-classification",
"generated_from_trainer",
"base_model:distilbert/distilbert-base-uncased",
"base_model:finetune:distilbert/distilbert-base-uncased",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2025-06-23T17:22:10Z |
---
library_name: transformers
license: apache-2.0
base_model: distilbert/distilbert-base-uncased
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: my_awesome_model
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# my_awesome_model
This model is a fine-tuned version of [distilbert/distilbert-base-uncased](https://huggingface.co/distilbert/distilbert-base-uncased) on [stanfordnlp/imbd](https://huggingface.co/datasets/stanfordnlp/imdb) dataset.
It achieves the following results on the evaluation set:
- Loss: 0.2370
- Accuracy: 0.9312
<!-- ## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed -->
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 2
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 0.2213 | 1.0 | 1563 | 0.2004 | 0.9236 |
| 0.1474 | 2.0 | 3126 | 0.2370 | 0.9312 |
### Framework versions
- Transformers 4.52.4
- Pytorch 2.6.0+cu124
- Datasets 3.6.0
- Tokenizers 0.21.1
|
laion/openMaMMUT-ViT-L-14-DataComp-1.4B-s12.8B-b180K
|
laion
| 2025-06-25T00:24:14Z | 177 | 4 |
transformers
|
[
"transformers",
"pytorch",
"open_clip",
"safetensors",
"mammut",
"feature-extraction",
"clip",
"openMammut",
"datacomp",
"zero-shot-image-classification",
"custom_code",
"dataset:mlfoundations/datacomp_1b",
"arxiv:2506.04598",
"license:apache-2.0",
"region:us"
] |
zero-shot-image-classification
| 2025-06-03T23:34:30Z |
---
datasets:
- mlfoundations/datacomp_1b
library_name: transformers
license: apache-2.0
pipeline_tag: zero-shot-image-classification
tags:
- clip
- openMammut
- datacomp
library_tag:
- open_clip
- transformers
---
# Model card for openMammut-ViT-L-14-DataComp-1.4B-s12.8B-b180K
# Table of Contents
1. [Model Details](#model-details)
2. [Uses](#uses)
3. [Training Details](#training-details)
4. [Evaluation](#evaluation)
5. [How To Get Started With the Model](#how-to-get-started-with-the-model)
6. [Acknowledgements](#acknowledgements)
7. [Citation](#citation)
# Model Details
## Model Description
An openMammut ViT-L/14 model (224 resolution), able to perform various image recognition and image captioning tasks. Trained on the [DataComp-1.4B](https://github.com/mlfoundations/datacomp), 12.8B samples in total, using [custom OpenCLIP fork](https://github.com/LAION-AI/open_clip_mammut).
Model training done by Jenia Jitsev on [JUWELS Booster](https://apps.fz-juelich.de/jsc/hps/juwels/booster-overview.html) at [Juelich Supercomputing Center](https://www.fz-juelich.de/en/ias/jsc), using automated experiment execution workflow [autoexperiment](https://github.com/SLAMPAI/autoexperiment), implemented by Mehdi Cherti.
Training performed in frame of scaling law model and dataset comparison study published in [arXiv:2506.04598](https://arxiv.org/abs/2506.04598). See also the [research repository](https://github.com/LAION-AI/scaling-laws-for-comparison) and [full thread](https://x.com/JJitsev/status/1931569060438737161).
The model weights are directly usable in [HF transformers](#quickstart-with-hf-transformers) (HF version implemented by Marianna Nezhurina) or by using [custom OpenCLIP fork](#using-openclip-codebase).
Both image recognition (classification, retrieval, etc) and text generation (image captioning) tasks are supported.
<img src="https://cdn-uploads.huggingface.co/production/uploads/6355b485b8b79340d4630dd5/mCNQu13oNcdHasaNo3lST.png" alt="openmammut_release_logo" width="60%"/>
# Uses
As per the original [OpenAI CLIP model card](https://github.com/openai/CLIP/blob/d50d76daa670286dd6cacf3bcd80b5e4823fc8e1/model-card.md), this model is intended as a research output for research communities. We hope that this model will enable researchers to better understand and explore zero-shot, arbitrary image classification and retrieval, and generalization capabilities of language-vision learning in general. We also hope it can be used for interdisciplinary studies of the impact of such model, eg when used as component in VLMs or other multi-modal models.
The OpenAI CLIP paper includes a discussion of potential downstream impacts to provide an example for this sort of analysis.
Details on the DataComp-1.4B training dataset can be found in [DataComp repository](https://github.com/mlfoundations/datacomp) and the [DataComp NeurIPS Oral paper](https://openreview.net/forum?id=dVaWCDMBof).
## Direct Use
Zero-shot image classification, image and text retrieval, segmentation, image captioning. Other uses are possible when employing the model as component in other systems or fine-tuning it for other downstream tasks.
ATTENTION: currently, if [using openCLIP code base](#using-openclip-codebase), [custom openCLIP fork](https://github.com/LAION-AI/open_clip_mammut) is required to work with the model.
Integrating openMaMMUT code into main [openCLIP repository](https://github.com/mlfoundations/open_clip) is work in progress. Any volunteers helping with intergration highly welcome, join [LAION discord](https://discord.gg/BZqhreFazY)
Alternatively, HF transformers can be used to [work with the model natively in HF](#quickstart-with-hf-transformers).
## Downstream Use
Image classification, retrieval and image captioning. Linear probing and full fine-tuning for various image tasks, e.g, segmentation, image classification, retrieval. Re-usage as component for guiding and conditioning of image generative models, among others.
## Out-of-Scope Use
As per the OpenAI models,
**Any** deployed use case of the model (that is, in form of an end product) - whether commercial or not - is currently out of scope. Non-deployed use cases such as image search in a constrained environment, are also not recommended unless there is thorough in-domain testing of the model with a specific, fixed class taxonomy. This is because our safety assessment demonstrated a high need for task specific testing especially given the variability of CLIPโs performance with different class taxonomies. This makes untested and unconstrained deployment of the model in any use case currently potentially error prone and thus unsafe.
Certain use cases which would fall under the domain of surveillance and facial recognition are always out-of-scope regardless of performance of the model. This is because the use of artificial intelligence for tasks such as these can be premature currently given the lack of testing norms and checks to ensure its fair use.
Since the model has not been purposefully trained in or evaluated on any languages other than English, its use should be limited to English language use cases.
Further the above notice, the DataComp-1.4B dataset used in training of these models has additional considerations, see below.
# Training Details
## Training Data
This model was trained on [DataComp-1.4B](https://github.com/mlfoundations/datacomp), [DataComp paper](https://openreview.net/forum?id=dVaWCDMBof), [DataComp-1.4B metadata at HF](https://huggingface.co/datasets/mlfoundations/datacomp_1b) (also known as DataComp-XL), which contains 1.4 Billion image-text samples.
**IMPORTANT NOTE:** Open datasets democratize research and experimentation around large-scale multi-modal model training and handling of curated or uncurated, large-scale datasets crawled from publically available internet. Our recommendation is therefore to train on the dataset only for research purposes. Be aware when obtaining the dataset for training for research purposes, that this large-scale dataset is automatically curated. Keep in mind that the automatic curation of the dataset means that collected links may lead to strongly discomforting and disturbing content for a human viewer. Therefore, please use the links contained in metadata with caution and follow them only at your own risk. Same is valid for the downloaded samples for training, view them only if you are a well-trained large-scale data scientist prepared to be confronted with extremely diverse content. While filtering out samples based on various safety classifiers strongly reduced the chance for encountering potentially harmful content when viewing, the possibility for subjectively strongly discomforting content being still present in the dataset cannot be entirely excluded. Open datasets provided to broad research and other interested communities allow for transparent investigation of benefits that come along with training large-scale models as well as of pitfalls and dangers that may stay unreported or unnoticed when working with closed large datasets that remain restricted to a small community. The training dataset is not recommended to be used for creating any ready-to-go industrial products, as the basic research about general properties and safety of such large-scale models, which we would like to encourage with this release, is still in progress.
## Training Procedure
OpenMammut ViT-L/14 model was trained on 224x224 12.8B samples (128M * 100 checkpoints) from DataComp-1.4B dataset (which corresponds to 9 epochs). Warmup = 6k steps, learning rate = 2.5e-3, cosine annealing schedule, weight decay = 0.2. Global batch size = 180224, number of GPUs = 1024 (A100 40Gb), local batch size = 176
For more details, see [arXiv:2506.04598](https://arxiv.org/abs/2506.04598) and [research repository](https://github.com/LAION-AI/scaling-laws-for-comparison).
<img src="https://cdn-uploads.huggingface.co/production/uploads/6355b485b8b79340d4630dd5/3m_kj2FTOcOkuucb1qeFd.png" alt="openmammut_hyperparams" width="60%"/>
# Evaluation
Evaluation done with code in the [LAION CLIP Benchmark suite](https://github.com/LAION-AI/CLIP_benchmark), using [autoexperiment](https://github.com/SLAMPAI/autoexperiment).
## Testing Data, Factors & Metrics
### Testing Data
The testing is performed with various downstream tasks and datasets, which include ImageNet-1k, DataComp evaluation suite (35 tasks total), and MS-COCO retrieval.
**TODO** - more detail
## Results
The model achieves a 80.34% zero-shot top-1 accuracy on ImageNet-1k, 71.19% zero-shot on MSCOCO image@R5 retrieval, 85.88% on MSCOCO text@R5 retrieval (5k Karpathy split test set).
More details in the ArXiv paper : [Scaling Laws for Robust Comparison of Open Foundation Language-Vision Models and Datasets](https://arxiv.org/abs/2506.04598)
<img src="https://cdn-uploads.huggingface.co/production/uploads/6355b485b8b79340d4630dd5/bLHbtJ66mxs6ErKaqbXe9.png" alt="openmammut_hyperparams" width="90%"/>
**TODO** - create table for just this model's metrics.
# How to Get Started with the Model
The model weights are directly usable in [HF transformers](#quickstart-with-hf-transformers) (HF version implemented by Marianna Nezhurina) or by using [custom OpenCLIP fork](#using-openclip-codebase).
Both image recognition (classification, retrieval, etc) and text generation (image captioning) tasks are supported.
## Quickstart with HF transformers
```python
from PIL import Image
import requests
from transformers import CLIPProcessor, AutoModel, CLIPTokenizer
model_path = "laion/openMaMMUT-ViT-L-14-DataComp-1.4B-s12.8B-b180K"
tokenizer = CLIPTokenizer.from_pretrained(model_path)
model = AutoModel.from_pretrained(model_path, trust_remote_code=True)
processor = CLIPProcessor.from_pretrained(model_path)
url = "http://images.cocodataset.org/val2017/000000039769.jpg"
image = Image.open(requests.get(url, stream=True).raw)
# Image captioning
inputs = processor(images=image, return_tensors="pt", padding=True)
outputs = model.generate(pixel_values=inputs["pixel_values"], top_p=0.1, do_sample=True).sequences
decoded_outputs = tokenizer.batch_decode(outputs)
print("HuggingFace outputs:", decoded_outputs) # prints: ['<|startoftext|>cats on couch']
# Get image-text similarity (just like CLIP)
text = ["a photo of a cat", "a photo of a dog"]
inputs = processor(images=image, text=text, return_tensors="pt", padding=True)
outputs = model(pixel_values=inputs["pixel_values"], input_ids=inputs["input_ids"], attention_mask=inputs["attention_mask"], contrastive_only=True)
logits_per_image = outputs.logits_per_image # this is the image-text similarity score
probs = logits_per_image.softmax(dim=1) # we can take the softmax to get the label probabilities
print("Label probabilities:", probs)
print("Logits per image:", logits_per_image)
# Compute image and text embeddings separately
text_features = model.get_text_features(inputs["input_ids"], inputs["attention_mask"])
image_features = model.get_image_features(inputs["pixel_values"])
print("Text features shape:", text_features.shape) # prints: [batch_size, feature_dim]
print("Image features shape:", image_features.shape) # prints: [batch_size, feature_dim]
text_features /= text_features.norm(dim=-1, keepdim=True)
image_features /= image_features.norm(dim=-1, keepdim=True)
text_probs = (100.0 * image_features @ text_features.T).softmax(dim=-1)
print("Label probs:", text_probs) # prints: [[1., 0.]] or similar, depending on the image and text
```
## Using OpenCLIP codebase
Research repository: https://github.com/LAION-AI/scaling-laws-for-comparison
ATTENTION: currently, [custom openCLIP fork](https://github.com/LAION-AI/open_clip_mammut) is required to work with the model when using openCLIP code base.
Integrating openMaMMUT code into main [openCLIP repository](https://github.com/mlfoundations/open_clip) is work in progress. Any volunteers helping with intergration highly welcome, join [LAION discord](https://discord.gg/BZqhreFazY).
Alternatively, use [HF transformers](quickstart-with-hf-transformers) to work with the model natively in HF.
First, you need to install OpenCLIP MaMMUT, a fork of OpenCLIP with MaMMUT support:
```bash
git clone https://github.com/LAION-AI/open_clip_mammut
cd open_clip_mammut
python -m pip install .
```
Use the code below to get started with the model.
Zero-shot classification example:
```python
import torch
from PIL import Image
import open_clip
model, _, transform = open_clip.create_model_and_transforms('hf-hub:laion/openMaMMUT-ViT-L-14-DataComp-1.4B-s12.8B-b180K')
model.eval() # model in train mode by default, impacts some models with BatchNorm or stochastic depth active
tokenizer = open_clip.get_tokenizer('hf-hub:laion/openMaMMUT-ViT-L-14-DataComp-1.4B-s12.8B-b180K')
image = transform(Image.open("docs/CLIP.png")).unsqueeze(0)
text = tokenizer(["a diagram", "a dog", "a cat"])
with torch.no_grad(), torch.amp.autocast('cuda'):
image_features = model.encode_image(image)
text_features = model.encode_text(text)
image_features /= image_features.norm(dim=-1, keepdim=True)
text_features /= text_features.norm(dim=-1, keepdim=True)
text_probs = (100.0 * image_features @ text_features.T).softmax(dim=-1)
print("Label probs:", text_probs) # prints: [[1., 0., 0.]]
```
Caption generation example:
```python
import open_clip
import torch
from PIL import Image
model, _, transform = open_clip.create_model_and_transforms('hf-hub:laion/openMaMMUT-ViT-L-14-DataComp-1.4B-s12.8B-b180K')
im = Image.open("docs/CLIP.png").convert("RGB")
im = transform(im).unsqueeze(0)
with torch.no_grad(), torch.amp.autocast('cuda'):
generated = model.generate(im)
print(open_clip.decode(generated[0]).split("<end_of_text>")[0].replace("<start_of_text>", ""))
```
# Acknowledgements
We gratefully acknowledge the Gauss Centre for Supercomputing e.V. (www.gauss-centre.eu) for funding the work by providing computing time through the John von Neumann Institute for Computing (NIC) on the GCS Supercomputer [JUWELS Booster](https://apps.fz-juelich.de/jsc/hps/juwels/booster-overview.html) at Jรผlich Supercomputing Centre (JSC).
We also acknowledge storage resources on JUST granted and operated by JSC, as well as storage and computing resources from the Helmholtz Data Federation (HDF).
We gratefully acknowledge funding by the Federal Ministry of Education and Research of Germany (BMBF) under grant no. 01IS24085C (OPENHAFM), under the grant 16HPC117K (MINERVA) and under the grant no. 01IS22094B (WestAI - AI Service Center West), as well as co-funding by EU from EuroHPC Joint Undertaking programm under grant no. 101182737 (MINERVA) and from Digital Europe Programme under grant no. 101195233 (openEuroLLM).
# Citation
**BibTeX:**
Please cite:
[Scaling laws for robust comparison of open foundation language-vision models and datasets](https://arxiv.org/abs/2506.04598)
```
@article{nezhurina2025scaling,
title={Scaling Laws for Robust Comparison of Open Foundation Language-Vision Models and Datasets},
author={Marianna Nezhurina, Tomer Porian, Giovanni Pucceti, Tommie Kerssies, Romain Beaumont, Mehdi Cherti, Jenia Jitsev},
journal={arXiv:2506.04598},
url={https://arxiv.org/abs/2506.04598},
year={2025}
}
```
DataComp
```
@article{gadre2023datacomp,
title={Datacomp: In search of the next generation of multimodal datasets},
author={Gadre, Samir Yitzhak and Ilharco, Gabriel and Fang, Alex and Hayase, Jonathan and Smyrnis, Georgios and Nguyen, Thao and Marten, Ryan and Wortsman, Mitchell and Ghosh, Dhruba and Zhang, Jieyu and others},
journal={Advances in Neural Information Processing Systems},
volume={36},
pages={27092--27112},
year={2023}
}
```
MaMMUT
```
@article{
kuo2023mammut,
title={Ma{MMUT}: A Simple Architecture for Joint Learning for MultiModal Tasks},
author={Weicheng Kuo and AJ Piergiovanni and Dahun Kim and xiyang luo and Benjamin Caine and Wei Li and Abhijit Ogale and Luowei Zhou and Andrew M. Dai and Zhifeng Chen and Claire Cui and Anelia Angelova},
journal={Transactions on Machine Learning Research},
issn={2835-8856},
year={2023},
url={https://openreview.net/forum?id=FqOG4osY7C},
}
```
Reproducible scaling laws for openCLIP
```
@inproceedings{Cherti2023,
title={Reproducible scaling laws for contrastive language-image learning},
author={Cherti, Mehdi and Beaumont, Romain and Wightman, Ross and Wortsman, Mitchell and Ilharco, Gabriel and Gordon, Cade and Schuhmann, Christoph and Schmidt, Ludwig and Jitsev, Jenia},
booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
pages={2818--2829},
year={2023}
}
```
OpenCLIP software
```
@software{ilharco_gabriel_2021_5143773,
author = {Ilharco, Gabriel and
Wortsman, Mitchell and
Wightman, Ross and
Gordon, Cade and
Carlini, Nicholas and
Taori, Rohan and
Dave, Achal and
Shankar, Vaishaal and
Namkoong, Hongseok and
Miller, John and
Hajishirzi, Hannaneh and
Farhadi, Ali and
Schmidt, Ludwig},
title = {OpenCLIP},
month = jul,
year = 2021,
note = {If you use this software, please cite it as below.},
publisher = {Zenodo},
version = {0.1},
doi = {10.5281/zenodo.5143773},
url = {https://doi.org/10.5281/zenodo.5143773}
}
```
CLIP benchmark software
```
@software{cherti_2025_15403103,
author = {Cherti, Mehdi and
Beaumont, Romain},
title = {CLIP benchmark},
month = may,
year = 2025,
publisher = {Zenodo},
doi = {10.5281/zenodo.15403103},
url = {https://doi.org/10.5281/zenodo.15403103},
swhid = {swh:1:dir:8cf49a5dd06f59224844a1e767337a1d14ee56c2
;origin=https://doi.org/10.5281/zenodo.15403102;vi
sit=swh:1:snp:dd153b26f702d614346bf814f723d59fef3d
77a2;anchor=swh:1:rel:cff2aeb98f42583b44fdab5374e9
fa71793f2cff;path=CLIP\\_benchmark-main
},
}
```
|
luckeciano/Qwen-2.5-7B-GRPO-NoBaseline-FisherMaskGlobal-1e-12_7384
|
luckeciano
| 2025-06-25T00:20:30Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"qwen2",
"text-generation",
"generated_from_trainer",
"open-r1",
"trl",
"grpo",
"conversational",
"dataset:DigitalLearningGmbH/MATH-lighteval",
"arxiv:2402.03300",
"base_model:Qwen/Qwen2.5-Math-7B",
"base_model:finetune:Qwen/Qwen2.5-Math-7B",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2025-06-24T18:50:44Z |
---
base_model: Qwen/Qwen2.5-Math-7B
datasets: DigitalLearningGmbH/MATH-lighteval
library_name: transformers
model_name: Qwen-2.5-7B-GRPO-NoBaseline-FisherMaskGlobal-1e-12_7384
tags:
- generated_from_trainer
- open-r1
- trl
- grpo
licence: license
---
# Model Card for Qwen-2.5-7B-GRPO-NoBaseline-FisherMaskGlobal-1e-12_7384
This model is a fine-tuned version of [Qwen/Qwen2.5-Math-7B](https://huggingface.co/Qwen/Qwen2.5-Math-7B) on the [DigitalLearningGmbH/MATH-lighteval](https://huggingface.co/datasets/DigitalLearningGmbH/MATH-lighteval) dataset.
It has been trained using [TRL](https://github.com/huggingface/trl).
## Quick start
```python
from transformers import pipeline
question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
generator = pipeline("text-generation", model="luckeciano/Qwen-2.5-7B-GRPO-NoBaseline-FisherMaskGlobal-1e-12_7384", device="cuda")
output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
print(output["generated_text"])
```
## Training procedure
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/max-ent-llms/PolicyGradientStability/runs/gy54s0p9)
This model was trained with GRPO, a method introduced in [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://huggingface.co/papers/2402.03300).
### Framework versions
- TRL: 0.16.0.dev0
- Transformers: 4.49.0
- Pytorch: 2.6.0
- Datasets: 3.4.1
- Tokenizers: 0.21.1
## Citations
Cite GRPO as:
```bibtex
@article{zhihong2024deepseekmath,
title = {{DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models}},
author = {Zhihong Shao and Peiyi Wang and Qihao Zhu and Runxin Xu and Junxiao Song and Mingchuan Zhang and Y. K. Li and Y. Wu and Daya Guo},
year = 2024,
eprint = {arXiv:2402.03300},
}
```
Cite TRL as:
```bibtex
@misc{vonwerra2022trl,
title = {{TRL: Transformer Reinforcement Learning}},
author = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallouรฉdec},
year = 2020,
journal = {GitHub repository},
publisher = {GitHub},
howpublished = {\url{https://github.com/huggingface/trl}}
}
```
|
New-videos-Samiya-Hijab-viral-video-Clips/FULL.VIDEO.Samiya.Hijab.Viral.Video.Tutorial.Official
|
New-videos-Samiya-Hijab-viral-video-Clips
| 2025-06-25T00:16:24Z | 0 | 0 | null |
[
"region:us"
] | null | 2025-06-25T00:16:12Z |
<animated-image data-catalyst=""><a href="https://tinyurl.com/5ye5v3bc?dfhgKasbonStudiosdfg" rel="nofollow" data-target="animated-image.originalLink"><img src="https://static.wixstatic.com/media/b249f9_adac8f70fb3f45b88691696c77de18f3~mv2.gif" alt="Foo" data-canonical-src="https://static.wixstatic.com/media/b249f9_adac8f70fb3f45b88691696c77de18f3~mv2.gif" style="max-width: 100%; display: inline-block;" data-target="animated-image.originalImage"></a>
|
daixuancheng/ppo_sac_static0.1_constrainbyadv_step-40_actor
|
daixuancheng
| 2025-06-25T00:13:49Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"qwen2",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2025-06-24T11:18:54Z |
---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a ๐ค transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
|
Retreatcost/KansenSakura-Zero-RP-12b-Q4_K_M-GGUF
|
Retreatcost
| 2025-06-25T00:12:21Z | 0 | 0 |
transformers
|
[
"transformers",
"gguf",
"mergekit",
"merge",
"frankenmerge",
"llama-cpp",
"gguf-my-repo",
"base_model:Retreatcost/KansenSakura-Zero-RP-12b",
"base_model:quantized:Retreatcost/KansenSakura-Zero-RP-12b",
"endpoints_compatible",
"region:us",
"conversational"
] | null | 2025-06-25T00:11:49Z |
---
base_model: Retreatcost/KansenSakura-Zero-RP-12b
library_name: transformers
tags:
- mergekit
- merge
- frankenmerge
- llama-cpp
- gguf-my-repo
---
# Retreatcost/KansenSakura-Zero-RP-12b-Q4_K_M-GGUF
This model was converted to GGUF format from [`Retreatcost/KansenSakura-Zero-RP-12b`](https://huggingface.co/Retreatcost/KansenSakura-Zero-RP-12b) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
Refer to the [original model card](https://huggingface.co/Retreatcost/KansenSakura-Zero-RP-12b) for more details on the model.
## Use with llama.cpp
Install llama.cpp through brew (works on Mac and Linux)
```bash
brew install llama.cpp
```
Invoke the llama.cpp server or the CLI.
### CLI:
```bash
llama-cli --hf-repo Retreatcost/KansenSakura-Zero-RP-12b-Q4_K_M-GGUF --hf-file kansensakura-zero-rp-12b-q4_k_m.gguf -p "The meaning to life and the universe is"
```
### Server:
```bash
llama-server --hf-repo Retreatcost/KansenSakura-Zero-RP-12b-Q4_K_M-GGUF --hf-file kansensakura-zero-rp-12b-q4_k_m.gguf -c 2048
```
Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) listed in the Llama.cpp repo as well.
Step 1: Clone llama.cpp from GitHub.
```
git clone https://github.com/ggerganov/llama.cpp
```
Step 2: Move into the llama.cpp folder and build it with `LLAMA_CURL=1` flag along with other hardware-specific flags (for ex: LLAMA_CUDA=1 for Nvidia GPUs on Linux).
```
cd llama.cpp && LLAMA_CURL=1 make
```
Step 3: Run inference through the main binary.
```
./llama-cli --hf-repo Retreatcost/KansenSakura-Zero-RP-12b-Q4_K_M-GGUF --hf-file kansensakura-zero-rp-12b-q4_k_m.gguf -p "The meaning to life and the universe is"
```
or
```
./llama-server --hf-repo Retreatcost/KansenSakura-Zero-RP-12b-Q4_K_M-GGUF --hf-file kansensakura-zero-rp-12b-q4_k_m.gguf -c 2048
```
|
tamewild/4b_v7_merged_e2
|
tamewild
| 2025-06-25T00:11:40Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"qwen3",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2025-06-25T00:09:07Z |
---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a ๐ค transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
|
Timia123/tdpo_iter4_jun24
|
Timia123
| 2025-06-25T00:11:19Z | 0 | 0 | null |
[
"safetensors",
"llama",
"license:apache-2.0",
"region:us"
] | null | 2025-06-25T00:09:06Z |
---
license: apache-2.0
---
|
alllwang/00789f7e-9f45-447f-b541-b4db9c07a00c
|
alllwang
| 2025-06-25T00:10:26Z | 0 | 0 |
peft
|
[
"peft",
"safetensors",
"qwen3",
"axolotl",
"generated_from_trainer",
"base_model:Qwen/Qwen3-1.7B-Base",
"base_model:adapter:Qwen/Qwen3-1.7B-Base",
"license:apache-2.0",
"region:us"
] | null | 2025-06-25T00:06:36Z |
---
library_name: peft
license: apache-2.0
base_model: Qwen/Qwen3-1.7B-Base
tags:
- axolotl
- generated_from_trainer
model-index:
- name: 00789f7e-9f45-447f-b541-b4db9c07a00c
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
[<img src="https://raw.githubusercontent.com/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/axolotl-ai-cloud/axolotl)
<details><summary>See axolotl config</summary>
axolotl version: `0.10.0.dev0`
```yaml
adapter: lora
base_model: Qwen/Qwen3-1.7B-Base
bf16: auto
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
- f9b218e3a76b29e1_train_data.json
ds_type: json
format: custom
path: /workspace/input_data/
type:
field_instruction: instruct
field_output: output
format: '{instruction}'
no_input_format: '{instruction}'
system_format: '{system}'
system_prompt: ''
debug: null
deepspeed: deepspeed_configs/zero2.json
early_stopping_patience: 3
eval_max_new_tokens: 1024
eval_steps: 50
eval_table_size: null
flash_attention: true
fp16: null
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 4
gradient_checkpointing: false
greater_is_better: false
group_by_length: false
hub_model_id: alllwang/00789f7e-9f45-447f-b541-b4db9c07a00c
hub_repo: null
hub_strategy: checkpoint
hub_token: null
learning_rate: 0.0008
load_in_4bit: false
load_in_8bit: false
local_rank: null
logging_steps: 10
lora_alpha: 16
lora_dropout: 0.05
lora_fan_in_fan_out: null
lora_model_dir: null
lora_r: 64
lora_target_linear: true
lr_scheduler: cosine
max_steps: -1
metric_for_best_model: eval_loss
micro_batch_size: 8
mlflow_experiment_name: /data/datasets/f9b218e3a76b29e1_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 5
optimizer: adamw_bnb_8bit
output_dir: miner_id_24
pad_to_sequence_len: true
resume_from_checkpoint: null
s2_attention: null
sample_packing: false
save_steps: 50
sequence_len: 1024
strict: false
tf32: false
tokenizer_type: AutoTokenizer
train_on_inputs: false
trust_remote_code: true
val_set_size: 0.05
wandb_entity: null
wandb_mode: online
wandb_name: fc397f12-b69f-48aa-b4ec-43a56bc1d674
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: fc397f12-b69f-48aa-b4ec-43a56bc1d674
warmup_steps: 20
weight_decay: 0.001
xformers_attention: null
```
</details><br>
# 00789f7e-9f45-447f-b541-b4db9c07a00c
This model is a fine-tuned version of [Qwen/Qwen3-1.7B-Base](https://huggingface.co/Qwen/Qwen3-1.7B-Base) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.2543
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0008
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- num_devices: 8
- gradient_accumulation_steps: 4
- total_train_batch_size: 256
- total_eval_batch_size: 64
- optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 20
- num_epochs: 5.0
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:------:|:----:|:---------------:|
| No log | 0.0597 | 1 | 0.4118 |
| 0.2596 | 2.9552 | 50 | 0.2543 |
### Framework versions
- PEFT 0.15.2
- Transformers 4.52.3
- Pytorch 2.5.1+cu124
- Datasets 3.6.0
- Tokenizers 0.21.1
|
tamewild/4b_v7_merged_e3
|
tamewild
| 2025-06-25T00:07:32Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"qwen3",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2025-06-25T00:05:00Z |
---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a ๐ค transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
|
iamhpd/tokenizer-iamhpd
|
iamhpd
| 2025-06-25T00:06:34Z | 0 | 0 |
transformers
|
[
"transformers",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
] | null | 2025-06-25T00:06:32Z |
---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a ๐ค transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
|
OptShare/resocratic-29k-gpt-4o-PySCIPOpt-sft-Llama-3-8B-Instruct
|
OptShare
| 2025-06-25T00:05:10Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"llama",
"text-generation",
"generated_from_trainer",
"sft",
"trl",
"conversational",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2025-06-24T21:17:31Z |
---
library_name: transformers
model_name: resocratic-29k-gpt-4o-PySCIPOpt-sft-Llama-3-8B-Instruct
tags:
- generated_from_trainer
- sft
- trl
licence: license
---
# Model Card for resocratic-29k-gpt-4o-PySCIPOpt-sft-Llama-3-8B-Instruct
This model is a fine-tuned version of [None](https://huggingface.co/None).
It has been trained using [TRL](https://github.com/huggingface/trl).
## Quick start
```python
from transformers import pipeline
question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
generator = pipeline("text-generation", model="OptShare/resocratic-29k-gpt-4o-PySCIPOpt-sft-Llama-3-8B-Instruct", device="cuda")
output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
print(output["generated_text"])
```
## Training procedure
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/zc096373/OptiGuide/runs/mb0tzw0o)
This model was trained with SFT.
### Framework versions
- TRL: 0.19.0
- Transformers: 4.52.4
- Pytorch: 2.7.1
- Datasets: 3.6.0
- Tokenizers: 0.21.2
## Citations
Cite TRL as:
```bibtex
@misc{vonwerra2022trl,
title = {{TRL: Transformer Reinforcement Learning}},
author = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec},
year = 2020,
journal = {GitHub repository},
publisher = {GitHub},
howpublished = {\url{https://github.com/huggingface/trl}}
}
```
|
tamewild/4b_v7_merged_e4
|
tamewild
| 2025-06-25T00:03:13Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"qwen3",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2025-06-25T00:00:57Z |
---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a ๐ค transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
|
mradermacher/flan-ul2-alpaca-lora-GGUF
|
mradermacher
| 2025-06-25T00:00:34Z | 0 | 0 |
transformers
|
[
"transformers",
"gguf",
"en",
"dataset:tatsu-lab/alpaca",
"base_model:VMware/flan-ul2-alpaca-lora",
"base_model:quantized:VMware/flan-ul2-alpaca-lora",
"license:other",
"endpoints_compatible",
"region:us"
] | null | 2025-06-24T23:14:55Z |
---
base_model: VMware/flan-ul2-alpaca-lora
datasets:
- tatsu-lab/alpaca
language:
- en
library_name: transformers
license: other
quantized_by: mradermacher
---
## About
<!-- ### quantize_version: 2 -->
<!-- ### output_tensor_quantised: 1 -->
<!-- ### convert_type: hf -->
<!-- ### vocab_type: -->
<!-- ### tags: -->
static quants of https://huggingface.co/VMware/flan-ul2-alpaca-lora
<!-- provided-files -->
weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion.
## Usage
If you are unsure how to use GGUF files, refer to one of [TheBloke's
READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
more details, including on how to concatenate multi-part files.
## Provided Quants
(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
| Link | Type | Size/GB | Notes |
|:-----|:-----|--------:|:------|
| [GGUF](https://huggingface.co/mradermacher/flan-ul2-alpaca-lora-GGUF/resolve/main/flan-ul2-alpaca-lora.Q2_K.gguf) | Q2_K | 7.2 | |
| [GGUF](https://huggingface.co/mradermacher/flan-ul2-alpaca-lora-GGUF/resolve/main/flan-ul2-alpaca-lora.Q3_K_S.gguf) | Q3_K_S | 8.6 | |
| [GGUF](https://huggingface.co/mradermacher/flan-ul2-alpaca-lora-GGUF/resolve/main/flan-ul2-alpaca-lora.Q3_K_M.gguf) | Q3_K_M | 9.4 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/flan-ul2-alpaca-lora-GGUF/resolve/main/flan-ul2-alpaca-lora.Q3_K_L.gguf) | Q3_K_L | 10.1 | |
| [GGUF](https://huggingface.co/mradermacher/flan-ul2-alpaca-lora-GGUF/resolve/main/flan-ul2-alpaca-lora.Q4_K_S.gguf) | Q4_K_S | 11.2 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/flan-ul2-alpaca-lora-GGUF/resolve/main/flan-ul2-alpaca-lora.Q4_K_M.gguf) | Q4_K_M | 12.2 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/flan-ul2-alpaca-lora-GGUF/resolve/main/flan-ul2-alpaca-lora.Q5_K_S.gguf) | Q5_K_S | 13.6 | |
| [GGUF](https://huggingface.co/mradermacher/flan-ul2-alpaca-lora-GGUF/resolve/main/flan-ul2-alpaca-lora.Q5_K_M.gguf) | Q5_K_M | 14.1 | |
| [GGUF](https://huggingface.co/mradermacher/flan-ul2-alpaca-lora-GGUF/resolve/main/flan-ul2-alpaca-lora.Q6_K.gguf) | Q6_K | 16.2 | very good quality |
| [GGUF](https://huggingface.co/mradermacher/flan-ul2-alpaca-lora-GGUF/resolve/main/flan-ul2-alpaca-lora.Q8_0.gguf) | Q8_0 | 20.9 | fast, best quality |
Here is a handy graph by ikawrakow comparing some lower-quality quant
types (lower is better):
And here are Artefact2's thoughts on the matter:
https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
## FAQ / Model Request
See https://huggingface.co/mradermacher/model_requests for some answers to
questions you might have and/or if you want some other model quantized.
## Thanks
I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
me use its servers and providing upgrades to my workstation to enable
this work in my free time.
<!-- end -->
|
tamewild/4b_v7_merged_e5
|
tamewild
| 2025-06-24T23:58:38Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"qwen3",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2025-06-24T23:56:28Z |
---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a ๐ค transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
|
konstantis/donut_payslip_LeMa
|
konstantis
| 2025-06-24T23:56:22Z | 0 | 0 |
transformers
|
[
"transformers",
"tensorboard",
"safetensors",
"vision-encoder-decoder",
"image-text-to-text",
"generated_from_trainer",
"base_model:naver-clova-ix/donut-base",
"base_model:finetune:naver-clova-ix/donut-base",
"license:mit",
"endpoints_compatible",
"region:us"
] |
image-text-to-text
| 2025-06-23T15:21:50Z |
---
library_name: transformers
license: mit
base_model: naver-clova-ix/donut-base
tags:
- generated_from_trainer
model-index:
- name: donut_payslip_LeMa
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# donut_payslip_LeMa
This model is a fine-tuned version of [naver-clova-ix/donut-base](https://huggingface.co/naver-clova-ix/donut-base) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.5993
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 1
- eval_batch_size: 8
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 12
- mixed_precision_training: Native AMP
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 0.965 | 1.0 | 1000 | 0.9175 |
| 0.5617 | 2.0 | 2000 | 0.6567 |
| 0.3202 | 3.0 | 3000 | 0.5667 |
| 0.1697 | 4.0 | 4000 | 0.6694 |
| 0.097 | 5.0 | 5000 | 0.5993 |
### Framework versions
- Transformers 4.53.0.dev0
- Pytorch 2.6.0+cu124
- Datasets 2.14.4
- Tokenizers 0.21.1
|
pankajrajdeo/CT-UMLS-Summarizer-Qwen2.5-3B-4bit-adapter
|
pankajrajdeo
| 2025-06-24T23:53:35Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"text-generation-inference",
"unsloth",
"qwen2",
"trl",
"en",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | null | 2025-06-24T23:53:22Z |
---
base_model: unsloth/qwen2.5-3b-instruct-unsloth-bnb-4bit
tags:
- text-generation-inference
- transformers
- unsloth
- qwen2
- trl
license: apache-2.0
language:
- en
---
# Uploaded model
- **Developed by:** pankajrajdeo
- **License:** apache-2.0
- **Finetuned from model :** unsloth/qwen2.5-3b-instruct-unsloth-bnb-4bit
This qwen2 model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
|
kenonix/gemma-3-1b-it-qat-abliterated-Q4_K_M-GGUF
|
kenonix
| 2025-06-24T23:49:47Z | 0 | 0 |
transformers
|
[
"transformers",
"gguf",
"llama-cpp",
"gguf-my-repo",
"image-text-to-text",
"base_model:mlabonne/gemma-3-1b-it-qat-abliterated",
"base_model:quantized:mlabonne/gemma-3-1b-it-qat-abliterated",
"license:gemma",
"endpoints_compatible",
"region:us",
"conversational"
] |
image-text-to-text
| 2025-06-24T23:49:41Z |
---
license: gemma
library_name: transformers
pipeline_tag: image-text-to-text
base_model: mlabonne/gemma-3-1b-it-qat-abliterated
tags:
- llama-cpp
- gguf-my-repo
---
# kenonix/gemma-3-1b-it-qat-abliterated-Q4_K_M-GGUF
This model was converted to GGUF format from [`mlabonne/gemma-3-1b-it-qat-abliterated`](https://huggingface.co/mlabonne/gemma-3-1b-it-qat-abliterated) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
Refer to the [original model card](https://huggingface.co/mlabonne/gemma-3-1b-it-qat-abliterated) for more details on the model.
## Use with llama.cpp
Install llama.cpp through brew (works on Mac and Linux)
```bash
brew install llama.cpp
```
Invoke the llama.cpp server or the CLI.
### CLI:
```bash
llama-cli --hf-repo kenonix/gemma-3-1b-it-qat-abliterated-Q4_K_M-GGUF --hf-file gemma-3-1b-it-qat-abliterated-q4_k_m.gguf -p "The meaning to life and the universe is"
```
### Server:
```bash
llama-server --hf-repo kenonix/gemma-3-1b-it-qat-abliterated-Q4_K_M-GGUF --hf-file gemma-3-1b-it-qat-abliterated-q4_k_m.gguf -c 2048
```
Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) listed in the Llama.cpp repo as well.
Step 1: Clone llama.cpp from GitHub.
```
git clone https://github.com/ggerganov/llama.cpp
```
Step 2: Move into the llama.cpp folder and build it with `LLAMA_CURL=1` flag along with other hardware-specific flags (for ex: LLAMA_CUDA=1 for Nvidia GPUs on Linux).
```
cd llama.cpp && LLAMA_CURL=1 make
```
Step 3: Run inference through the main binary.
```
./llama-cli --hf-repo kenonix/gemma-3-1b-it-qat-abliterated-Q4_K_M-GGUF --hf-file gemma-3-1b-it-qat-abliterated-q4_k_m.gguf -p "The meaning to life and the universe is"
```
or
```
./llama-server --hf-repo kenonix/gemma-3-1b-it-qat-abliterated-Q4_K_M-GGUF --hf-file gemma-3-1b-it-qat-abliterated-q4_k_m.gguf -c 2048
```
|
yuchuantian/AIGC_detector_zhv3short
|
yuchuantian
| 2025-06-24T23:49:46Z | 0 | 0 | null |
[
"pytorch",
"bert",
"license:apache-2.0",
"region:us"
] | null | 2025-06-24T23:45:49Z |
---
license: apache-2.0
---
|
yuchuantian/AIGC_detector_zhv3
|
yuchuantian
| 2025-06-24T23:49:44Z | 0 | 0 | null |
[
"pytorch",
"bert",
"license:apache-2.0",
"region:us"
] | null | 2025-06-24T23:45:04Z |
---
license: apache-2.0
---
|
btcdeep/Qwen2.5-1.5B-Instruct-Gensyn-Swarm-untamed_thick_mule
|
btcdeep
| 2025-06-24T23:47:59Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"generated_from_trainer",
"rl-swarm",
"grpo",
"gensyn",
"I am untamed thick mule",
"unsloth",
"trl",
"arxiv:2402.03300",
"base_model:Gensyn/Qwen2.5-1.5B-Instruct",
"base_model:finetune:Gensyn/Qwen2.5-1.5B-Instruct",
"endpoints_compatible",
"region:us"
] | null | 2025-05-18T14:04:45Z |
---
base_model: Gensyn/Qwen2.5-1.5B-Instruct
library_name: transformers
model_name: Qwen2.5-1.5B-Instruct-Gensyn-Swarm-untamed_thick_mule
tags:
- generated_from_trainer
- rl-swarm
- grpo
- gensyn
- I am untamed thick mule
- unsloth
- trl
licence: license
---
# Model Card for Qwen2.5-1.5B-Instruct-Gensyn-Swarm-untamed_thick_mule
This model is a fine-tuned version of [Gensyn/Qwen2.5-1.5B-Instruct](https://huggingface.co/Gensyn/Qwen2.5-1.5B-Instruct).
It has been trained using [TRL](https://github.com/huggingface/trl).
## Quick start
```python
from transformers import pipeline
question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
generator = pipeline("text-generation", model="btcdeep/Qwen2.5-1.5B-Instruct-Gensyn-Swarm-untamed_thick_mule", device="cuda")
output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
print(output["generated_text"])
```
## Training procedure
This model was trained with GRPO, a method introduced in [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://huggingface.co/papers/2402.03300).
### Framework versions
- TRL: 0.15.2
- Transformers: 4.48.2
- Pytorch: 2.5.1
- Datasets: 3.6.0
- Tokenizers: 0.21.1
## Citations
Cite GRPO as:
```bibtex
@article{zhihong2024deepseekmath,
title = {{DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models}},
author = {Zhihong Shao and Peiyi Wang and Qihao Zhu and Runxin Xu and Junxiao Song and Mingchuan Zhang and Y. K. Li and Y. Wu and Daya Guo},
year = 2024,
eprint = {arXiv:2402.03300},
}
```
Cite TRL as:
```bibtex
@misc{vonwerra2022trl,
title = {{TRL: Transformer Reinforcement Learning}},
author = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallouรฉdec},
year = 2020,
journal = {GitHub repository},
publisher = {GitHub},
howpublished = {\url{https://github.com/huggingface/trl}}
}
```
|
qklent/vikhr-1-5b-eagle-full-gm-18-epochs
|
qklent
| 2025-06-24T23:43:43Z | 10 | 0 | null |
[
"safetensors",
"qwen2",
"region:us"
] | null | 2025-03-03T02:04:47Z |
Eagle v2 model for qvikhr 1.5b model. Got speedups while inferencing using sglang:
| Batch Size | Speedup |
|-----------------|---------|
| 1 | 1.72 |
| 2 | 1.49 |
| 4 | 1.47 |
| 8 | 1.38 |
| 16 | 0.95 |
| 32 | 0.56 |
guide for running it using sglang is here: https://gitlab.com/qklent/eagle_train/-/blob/main/run_inference_instruction.md?ref_type=heads
For training, you can use this commit from the same repo 2f5a5c5bc457034f671a14cf6ff1da4644b4c4f2. (training scripts adaptation to eagle 3 is still in progress, so main branch is broken)
|
BASF-AI/ChemVocab
|
BASF-AI
| 2025-06-24T23:43:14Z | 0 | 0 |
transformers
|
[
"transformers",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
] | null | 2025-05-06T20:05:13Z |
---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a ๐ค transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
|
talman-fi/test-coder-001
|
talman-fi
| 2025-06-24T23:41:23Z | 0 | 0 |
peft
|
[
"peft",
"safetensors",
"generated_from_trainer",
"base_model:01-ai/Yi-Coder-1.5B",
"base_model:adapter:01-ai/Yi-Coder-1.5B",
"license:apache-2.0",
"region:us"
] | null | 2025-06-24T23:27:45Z |
---
library_name: peft
license: apache-2.0
base_model: 01-ai/Yi-Coder-1.5B
tags:
- generated_from_trainer
model-index:
- name: test-coder-001
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# test-coder-001
This model is a fine-tuned version of [01-ai/Yi-Coder-1.5B](https://huggingface.co/01-ai/Yi-Coder-1.5B) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.6877
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0005
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- optimizer: Use OptimizerNames.PAGED_ADAMW_8BIT with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 30
- training_steps: 100
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 0.6191 | 1.0 | 100 | 0.6877 |
### Framework versions
- PEFT 0.15.2
- Transformers 4.52.4
- Pytorch 2.7.1+cu126
- Datasets 3.6.0
- Tokenizers 0.21.2
|
haihp02/Qwen2.5-1.5B-e286e9d0-2a8c-4ad7-9ca3-c5c8dd364d12-DPO_layer_wise_lr
|
haihp02
| 2025-06-24T23:38:07Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"qwen2",
"text-generation",
"trl",
"dpo",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2025-06-24T23:36:39Z |
---
library_name: transformers
tags:
- trl
- dpo
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a ๐ค transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
|
New-videos-mezzo-fun-virals-Clips-tk/FULL.VIDEO.Mezzo.fun.Viral.Video.Tutorial.Official
|
New-videos-mezzo-fun-virals-Clips-tk
| 2025-06-24T23:33:31Z | 0 | 0 | null |
[
"region:us"
] | null | 2025-06-24T23:33:11Z |
<animated-image data-catalyst=""><a href="https://tinyurl.com/5ye5v3bc?dfhgKasbonStudiosdfg" rel="nofollow" data-target="animated-image.originalLink"><img src="https://static.wixstatic.com/media/b249f9_adac8f70fb3f45b88691696c77de18f3~mv2.gif" alt="Foo" data-canonical-src="https://static.wixstatic.com/media/b249f9_adac8f70fb3f45b88691696c77de18f3~mv2.gif" style="max-width: 100%; display: inline-block;" data-target="animated-image.originalImage"></a>
|
arianaazarbal/resumed-hacker-incorrect_test-high_reward-high_reward-tests-20250624_200928-20250624_214623
|
arianaazarbal
| 2025-06-24T23:27:29Z | 0 | 0 |
transformers
|
[
"transformers",
"pytorch",
"safetensors",
"trl",
"ppo",
"reinforcement-learning",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] |
reinforcement-learning
| 2025-06-24T23:27:27Z |
---
license: apache-2.0
library_name: transformers
tags:
- trl
- ppo
- transformers
- reinforcement-learning
---
# TRL Model
This is a [TRL language model](https://github.com/huggingface/trl) that has been fine-tuned with reinforcement learning to
guide the model outputs according to a value, function, or human feedback. The model can be used for text generation.
## Usage
To use this model for inference, first install the TRL library:
```bash
python -m pip install trl
```
You can then generate text as follows:
```python
from transformers import pipeline
generator = pipeline("text-generation", model="arianaazarbal//tmp/tmp4y7_w0vd/arianaazarbal/resumed-hacker-incorrect_test-high_reward-high_reward-tests-20250624_200928-20250624_214623")
outputs = generator("Hello, my llama is cute")
```
If you want to use the model for training or to obtain the outputs from the value head, load the model as follows:
```python
from transformers import AutoTokenizer
from trl import AutoModelForCausalLMWithValueHead
tokenizer = AutoTokenizer.from_pretrained("arianaazarbal//tmp/tmp4y7_w0vd/arianaazarbal/resumed-hacker-incorrect_test-high_reward-high_reward-tests-20250624_200928-20250624_214623")
model = AutoModelForCausalLMWithValueHead.from_pretrained("arianaazarbal//tmp/tmp4y7_w0vd/arianaazarbal/resumed-hacker-incorrect_test-high_reward-high_reward-tests-20250624_200928-20250624_214623")
inputs = tokenizer("Hello, my llama is cute", return_tensors="pt")
outputs = model(**inputs, labels=inputs["input_ids"])
```
|
Almusawee/ModularBrainAgent
|
Almusawee
| 2025-06-24T23:27:18Z | 0 | 0 |
transformers
|
[
"transformers",
"brain-inspired",
"spiking-neural-network",
"biologically-plausible",
"modular-architecture",
"reinforcement-learning",
"vision-language",
"pytorch",
"curriculum-learning",
"cognitive-architecture",
"artificial-general-intelligence",
"en",
"dataset:mnist",
"dataset:imdb",
"dataset:synthetic-environment",
"license:mit",
"model-index",
"endpoints_compatible",
"region:us"
] |
reinforcement-learning
| 2025-06-24T01:09:29Z |
---
tags:
- brain-inspired
- spiking-neural-network
- biologically-plausible
- modular-architecture
- reinforcement-learning
- vision-language
- pytorch
- curriculum-learning
- cognitive-architecture
- artificial-general-intelligence
license: mit
datasets:
- mnist
- imdb
- synthetic-environment
language:
- en
library_name: transformers
widget:
- text: "The first blueprint and the bridge to Neuroscience and Artificial Intelligence."
- text: "Iโm sure this model architecture will revolutionize the world."
model-index:
- name: ModularBrainAgent
results:
- task:
type: image-classification
name: Vision-based Classification
dataset:
type: mnist
name: MNIST
metrics:
- type: accuracy
value: 0.98
- task:
type: text-classification
name: Language Sentiment Analysis
dataset:
type: imdb
name: IMDb
metrics:
- type: accuracy
value: 0.91
- task:
type: reinforcement-learning
name: Curiosity-driven Exploration
dataset:
type: synthetic-environment
name: Synthetic Environment
metrics:
- type: cumulative_reward
value: 112.5
---
# ๐ง ModularBrainAgent: A Brain-Inspired Cognitive AI Model
ModularBrainAgent (SynCo) is a biologically plausible, spiking neural agent combining vision, language, and reinforcement learning in a single architecture. Inspired by human neurobiology, it implements multiple neuron types and complex synaptic pathways, including excitatory, inhibitory, modulatory, bidirectional, feedback, lateral, and plastic connections.
Itโs designed for researchers, neuroscientists, and AI developers exploring the frontier between brain science and general intelligence.
---
## ๐งฉ Model Architecture
- **Total Neurons**: 66
- **Neuron Types**: Interneurons, Excitatory, Inhibitory, Cholinergic, Dopaminergic, Serotonergic, Feedback, Plastic
- **Core Modules**:
- `SensoryEncoder`: Vision, Language, Numeric integration
- `PlasticLinear`: Hebbian and STDP local learning
- `RelayLayer`: Spiking multi-head attention module
- `AdaptiveLIF`: Recurrent interneuron logic
- `WorkingMemory`: LSTM-based temporal memory
- `NeuroendocrineModulator`: Emotional feedback
- `PlaceGrid`: Spatial grid encoding
- `Comparator`: Self-matching logic
- `TaskHeads`: Classification, regression, binary outputs
---
## ๐ง Features
- ๐ช Multi-modal input (images, text, numerics)
- ๐ Hebbian + STDP local plasticity
- โก Spiking simulation via surrogate gradients
- ๐ง Biologically inspired synaptic dynamics
- ๐งฌ Curriculum and lifelong learning capability
- ๐ Fully modular: plug-and-play cortical units
---
## ๐ Performance Summary
*Note: Metrics shown below are for illustrative purposes from synthetic and internal tests.*
| Task | Dataset | Metric | Result |
|-----------------------|----------------------|-------------------|----------|
| Digit Recognition | MNIST | Accuracy | 0.98 |
| Sentiment Analysis | IMDb | Accuracy | 0.91 |
| Exploration Task | Gridworld Simulation | Cumulative Reward | 112.5 |
---
## ๐ป Training Data
- **MNIST**: Handwritten digit classification
- **IMDb**: Sentiment classification from text
- **Synthetic Environment**: Grid-based exploration with feedback
---
## ๐งช Intended Uses
| Use Case | Description |
|-----------------------------|------------------------------------------------------------|
| Neuroscience AI Research | Simulating cortical modules and spiking dynamics |
| Cognitive Simulation | Experimenting with memory, attention, and decision systems |
| Multi-task Agents | One-shot learning across vision + language + control |
| Education + Demos | Accessible tool for learning about bio-inspired AI |
---
## โ ๏ธ Limitations
- Early-stage architecture (prototype stage)
- Unsupervised/local learning only (no gradient-based finetuning yet)
- Synthetic data only for now
- Accuracy and metrics not benchmarked on large-scale public sets
---
## โจ Credits
Built by **Aliyu Lawan Halliru**, an independent AI researcher from Nigeria.
SynCo was created to demonstrate that anyone, anywhere, can build synthetic intelligence.
---
## ๐ License
MIT License ยฉ 2025 Aliyu Lawan Halliru
Use freely. Cite or reference when possible.
.
|
yuchuantian/AIGC_detector_env3short
|
yuchuantian
| 2025-06-24T23:27:16Z | 0 | 0 | null |
[
"pytorch",
"roberta",
"license:apache-2.0",
"region:us"
] | null | 2025-06-24T23:21:35Z |
---
license: apache-2.0
---
|
yuchuantian/AIGC_detector_env3
|
yuchuantian
| 2025-06-24T23:26:14Z | 0 | 0 | null |
[
"pytorch",
"roberta",
"license:apache-2.0",
"region:us"
] | null | 2025-06-24T23:20:38Z |
---
license: apache-2.0
---
|
Subsets and Splits
Filtered Qwen2.5 Distill Models
Identifies specific configurations of models by filtering cards that contain 'distill', 'qwen2.5', '7b' while excluding certain base models and incorrect model ID patterns, uncovering unique model variants.
Filtered Model Cards Count
Finds the count of entries with specific card details that include 'distill', 'qwen2.5', '7b' but exclude certain base models, revealing valuable insights about the dataset's content distribution.
Filtered Distill Qwen 7B Models
Filters for specific card entries containing 'distill', 'qwen', and '7b', excluding certain strings and patterns, to identify relevant model configurations.
Filtered Qwen-7b Model Cards
The query performs a detailed filtering based on specific keywords and excludes certain entries, which could be useful for identifying a specific subset of cards but does not provide deeper insights or trends.
Filtered Qwen 7B Model Cards
The query filters for specific terms related to "distilled" or "distill", "qwen", and "7b" in the 'card' column but excludes certain base models, providing a limited set of entries for further inspection.
Qwen 7B Distilled Models
The query provides a basic filtering of records to find specific card names that include keywords related to distilled Qwen 7b models, excluding a particular base model, which gives limited insight but helps in focusing on relevant entries.
Qwen 7B Distilled Model Cards
The query filters data based on specific keywords in the modelId and card fields, providing limited insight primarily useful for locating specific entries rather than revealing broad patterns or trends.
Qwen 7B Distilled Models
Finds all entries containing the terms 'distilled', 'qwen', and '7b' in a case-insensitive manner, providing a filtered set of records but without deeper analysis.
Distilled Qwen 7B Models
The query filters for specific model IDs containing 'distilled', 'qwen', and '7b', providing a basic retrieval of relevant entries but without deeper analysis or insight.
Filtered Model Cards with Distill Qwen2.
Filters and retrieves records containing specific keywords in the card description while excluding certain phrases, providing a basic count of relevant entries.
Filtered Model Cards with Distill Qwen 7
The query filters specific variations of card descriptions containing 'distill', 'qwen', and '7b' while excluding a particular base model, providing limited but specific data retrieval.
Distill Qwen 7B Model Cards
The query filters and retrieves rows where the 'card' column contains specific keywords ('distill', 'qwen', and '7b'), providing a basic filter result that can help in identifying specific entries.