modelId
stringlengths 5
139
| author
stringlengths 2
42
| last_modified
timestamp[us, tz=UTC]date 2020-02-15 11:33:14
2025-08-30 18:26:50
| downloads
int64 0
223M
| likes
int64 0
11.7k
| library_name
stringclasses 530
values | tags
listlengths 1
4.05k
| pipeline_tag
stringclasses 55
values | createdAt
timestamp[us, tz=UTC]date 2022-03-02 23:29:04
2025-08-30 18:26:48
| card
stringlengths 11
1.01M
|
|---|---|---|---|---|---|---|---|---|---|
kuuroo/models
|
kuuroo
| 2025-06-19T18:34:16Z | 639 | 0 | null |
[
"gguf",
"license:apache-2.0",
"region:us"
] | null | 2025-03-06T15:10:02Z |
---
license: apache-2.0
---
|
full-video-shah-sapna-viral-video/FULL.VIDEO.sapna.shah.Viral.Video.Tutorial.Official
|
full-video-shah-sapna-viral-video
| 2025-06-19T18:31:44Z | 0 | 0 | null |
[
"region:us"
] | null | 2025-06-19T18:31:07Z |
<animated-image data-catalyst=""><a href="https://tinyurl.com/56hn7ue8/?news-viral-video" 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>
|
salv47/erdm
|
salv47
| 2025-06-19T18:29:36Z | 0 | 0 | null |
[
"license:apache-2.0",
"region:us"
] | null | 2025-06-19T17:25:28Z |
---
license: apache-2.0
---
|
ZOAIW/ZIV5
|
ZOAIW
| 2025-06-19T18:28:23Z | 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
| 2025-06-19T17:51:06Z |
---
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: ziv5
---
# Ziv5
<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 `ziv5` to trigger the image generation.
## Run this LoRA with an API using Replicate
```py
import replicate
input = {
"prompt": "ziv5",
"lora_weights": "https://huggingface.co/ZOAIW/ZIV5/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('ZOAIW/ZIV5', weight_name='lora.safetensors')
image = pipeline('ziv5').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: 2000
- Learning rate: 0.0004
- LoRA rank: 16
## Contribute your own examples
You can use the [community tab](https://huggingface.co/ZOAIW/ZIV5/discussions) to add images that show off what youโve made with this LoRA.
|
TOTORONG/nemo_49b_lora
|
TOTORONG
| 2025-06-19T18:28:00Z | 0 | 0 |
peft
|
[
"peft",
"safetensors",
"arxiv:1910.09700",
"base_model:unsloth/Llama-3_3-Nemotron-Super-49B-v1",
"base_model:adapter:unsloth/Llama-3_3-Nemotron-Super-49B-v1",
"region:us"
] | null | 2025-06-19T18:26:57Z |
---
base_model: unsloth/Llama-3_3-Nemotron-Super-49B-v1
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
|
makataomu/ppo-PyramidsMasony
|
makataomu
| 2025-06-19T18:27:26Z | 0 | 0 |
ml-agents
|
[
"ml-agents",
"tensorboard",
"onnx",
"Pyramids",
"deep-reinforcement-learning",
"reinforcement-learning",
"ML-Agents-Pyramids",
"region:us"
] |
reinforcement-learning
| 2025-06-19T18:27:23Z |
---
library_name: ml-agents
tags:
- Pyramids
- deep-reinforcement-learning
- reinforcement-learning
- ML-Agents-Pyramids
---
# **ppo** Agent playing **Pyramids**
This is a trained model of a **ppo** agent playing **Pyramids**
using the [Unity ML-Agents Library](https://github.com/Unity-Technologies/ml-agents).
## Usage (with ML-Agents)
The Documentation: https://unity-technologies.github.io/ml-agents/ML-Agents-Toolkit-Documentation/
We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub:
- A *short tutorial* where you teach Huggy the Dog ๐ถ to fetch the stick and then play with him directly in your
browser: https://huggingface.co/learn/deep-rl-course/unitbonus1/introduction
- A *longer tutorial* to understand how works ML-Agents:
https://huggingface.co/learn/deep-rl-course/unit5/introduction
### Resume the training
```bash
mlagents-learn <your_configuration_file_path.yaml> --run-id=<run_id> --resume
```
### Watch your Agent play
You can watch your agent **playing directly in your browser**
1. If the environment is part of ML-Agents official environments, go to https://huggingface.co/unity
2. Step 1: Find your model_id: makataomu/ppo-PyramidsMasony
3. Step 2: Select your *.nn /*.onnx file
4. Click on Watch the agent play ๐
|
LinguaSpanApp/lora-yoruba-model
|
LinguaSpanApp
| 2025-06-19T18:27:17Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
] | null | 2025-06-19T18:27:08Z |
---
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]
|
amalsp/mistral-7b-ai-tools-finetuned
|
amalsp
| 2025-06-19T18:24:07Z | 0 | 0 |
peft
|
[
"peft",
"safetensors",
"text-generation",
"ai-tools",
"lora",
"mistral",
"fine-tuned",
"base_model:mistralai/Mistral-7B-v0.1",
"base_model:adapter:mistralai/Mistral-7B-v0.1",
"license:apache-2.0",
"region:us"
] |
text-generation
| 2025-06-19T18:17:48Z |
---
license: apache-2.0
base_model: mistralai/Mistral-7B-v0.1
tags:
- text-generation
- ai-tools
- lora
- peft
- mistral
- fine-tuned
pipeline_tag: text-generation
library_name: peft
---
# ๐ ๏ธ Mistral-7B AI Tools Explainer (LoRA Fine-tuned)
This model is a fine-tuned version of **[Mistral-7B](https://huggingface.co/mistralai/Mistral-7B-v0.1)** using **LoRA (Low-Rank Adaptation)**. It is trained specifically to explain the use, purpose, and functionality of AI tools when given their name, task, and description.
---
## ๐ Model Details
- **Developed by**: [`amalsp`](https://huggingface.co/amalsp)
- **Model type**: Causal Language Model (Decoder-only Transformer)
- **Base model**: `mistralai/Mistral-7B-v0.1`
- **Fine-tuning technique**: PEFT with LoRA
- **Language(s)**: English
- **License**: Apache 2.0
- **Trained on**: 2000 entries about AI tools
- **GPU Used**: T4 (Colab Pro)
- **Training Time**: ~2.7 hours
- **Loss**: 1.83
- **Sequence Length**: 256 tokens
---
## ๐ Intended Use
### โ
Direct Use
- Generate accurate and informative descriptions of AI tools
- Help end-users, students, or professionals understand what a given AI tool does
### ๐ซ Out-of-Scope Use
- Not intended for general Q&A about geography, politics, history, or unrelated domains
- Will reply with: `"I am not trained for this."` to unrelated prompts
---
## ๐ก Usage
```python
from transformers import AutoTokenizer, AutoModelForCausalLM
from peft import PeftModel
import torch
# Load model
base = AutoModelForCausalLM.from_pretrained("mistralai/Mistral-7B-v0.1", torch_dtype=torch.float16, device_map="auto")
model = PeftModel.from_pretrained(base, "amalsp/mistral-7b-ai-tools-finetuned")
tokenizer = AutoTokenizer.from_pretrained("amalsp/mistral-7b-ai-tools-finetuned")
# Generate
prompt = """Tool: ChatGPT
Task: Conversational AI
Short Description: AI chatbot for natural conversations
Explain the tool:"""
inputs = tokenizer(prompt, return_tensors="pt").to("cuda")
outputs = model.generate(**inputs, max_length=300)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
|
New-Clip-Arovi-Nusrat-Ridhi-18-viral-Vide/FULL.VIDEO.Arovi.Nusrat.Ridhi.Viral.Video.Tutorial.Official
|
New-Clip-Arovi-Nusrat-Ridhi-18-viral-Vide
| 2025-06-19T18:21:47Z | 0 | 0 | null |
[
"region:us"
] | null | 2025-06-19T18:21:42Z |
<a href="https://watch-blogg777xx.blogspot.com/2025/06/maallu.html"><img src="http://4.bp.blogspot.com/-VFcup4RzDQY/Upiobuokb5I/AAAAAAAAAV0/64yKpZilDCg/s1600/oie_nxv3mlmduAj1.gif" alt="fsd" /></a>
<a href="https://watch-blogg777xx.blogspot.com/2025/06/maallu.html" rel="nofollow">๐ด โคโบ๐๐ฅ๐ข๐ค ๐๐๐ซ๐ ๐ญ๐จ๐๐ (๐๐๐ญ๐๐ก ๐
๐ฎ๐ฅ๐ฅ ๐ฏ๐ข๐๐๐จ)</a>
<a href="https://watch-blogg777xx.blogspot.com/2025/06/maallu.html" rel="nofollow">๐ด โคโบ๐๐ฅ๐ข๐ค ๐๐๐ซ๐ ๐ญ๐จ๐๐ (๐
๐ฎ๐ฅ๐ฅ ๐ฏ๐ข๐๐๐จ ๐๐ข๐ง๐ค)</a>
|
New-tutorial-prajakta-mali-19-Viral-Videos/FULL.VIDEO.Prajakta.Mali.Viral.Video.Tutorial.Official
|
New-tutorial-prajakta-mali-19-Viral-Videos
| 2025-06-19T18:20:50Z | 0 | 0 | null |
[
"region:us"
] | null | 2025-06-19T18:20:33Z |
<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>
<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>
|
makataomu/Reinforce-FlappyBird-v1
|
makataomu
| 2025-06-19T18:19:35Z | 0 | 0 | null |
[
"Pixelcopter-PLE-v0",
"reinforce",
"reinforcement-learning",
"custom-implementation",
"deep-rl-class",
"model-index",
"region:us"
] |
reinforcement-learning
| 2025-06-19T14:50:54Z |
---
tags:
- Pixelcopter-PLE-v0
- reinforce
- reinforcement-learning
- custom-implementation
- deep-rl-class
model-index:
- name: Reinforce-FlappyBird-v1
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: Pixelcopter-PLE-v0
type: Pixelcopter-PLE-v0
metrics:
- type: mean_reward
value: 26.20 +/- 25.60
name: mean_reward
verified: false
---
# **Reinforce** Agent playing **Pixelcopter-PLE-v0**
This is a trained model of a **Reinforce** agent playing **Pixelcopter-PLE-v0** .
To learn to use this model and train yours check Unit 4 of the Deep Reinforcement Learning Course: https://huggingface.co/deep-rl-course/unit4/introduction
|
robb-0/miami-beach-hologram
|
robb-0
| 2025-06-19T18:14:20Z | 6 | 1 |
diffusers
|
[
"diffusers",
"text-to-image",
"lora",
"template:diffusion-lora",
"โจ๐๐",
"๐ปโจ",
"en",
"dataset:robb-0/miami-hologram-dataset",
"dataset:robb-0/amazing_miami_holograms_dataset",
"base_model:stabilityai/sdxl-turbo",
"base_model:adapter:stabilityai/sdxl-turbo",
"license:cc-by-4.0",
"region:us"
] |
text-to-image
| 2025-05-05T12:23:45Z |
---
tags:
- text-to-image
- lora
- diffusers
- template:diffusion-lora
- โจ๐๐
- ๐ปโจ
widget:
- text: >-
miami beach hologram, majestic geometric statue of Cristo Redentor, slices
of moon, surreal geometric cyan forest, star lit sky
parameters:
negative_prompt: ugly, lowres, lowqualty, blurry, jpeg articats, worst quality, bad,
output:
url: images/859741383999677716.png
- text: >-
desert with geometric Pyramids in Egypt, bathed in a warm glow. The iconic
boardwalk is transformed into a canvas of geometric wonder as holographic
Egyptian pyramids rise from the sand. Neon lights dance across their
facades, casting a kaleidoscope of colors onto the pavement. Above, the
star-studded sky twinkles like diamonds scattered by the vaporwave moon,
which hangs low in the horizon, its soft light reflected off the pyramids'
perfect geometry. Wide-angle shot captures the vibrant scene as neon hues
blend with the beach's golden glow.
output:
url: images/859741142407742069.png
- text: >-
synthwave, miami beach hologram, featuring geometric NEON Statue of liberty,
star lit sky, neon, perfect geometry, 3d, cg, colorful, reflection,
wide-angle, vaporwave moon
output:
url: images/859740214694801286.png
- text: >-
miami beach hologram, synthwave sun, geometric waters, vaporwave, 3d, cg,
wide-angle, neon, colorful, reflections, concecpt art
output:
url: >-
images/workspace_trainsamples_859727997526151536_3d0ea384-a5b5-473a-be73-daec9db026cf.png
base_model: stabilityai/sdxl-turbo
instance_prompt: miami beach hologram
license: cc-by-4.0
language:
- en
pipeline_tag: text-to-image
datasets:
- robb-0/miami-hologram-dataset
- robb-0/amazing_miami_holograms_dataset
new_version: robb-0/miami_beach_hologram_2_sdxl
---
# Miami Beach Hologram (it's amazing! Check it out new dataset and image below)
<Gallery />
### Theme
๐๐๏ธ๐๐ฉ๏ธ๐๐๐ธ "Miami Beach Hologram" ๐บ๐ต๐บ๐
<audio controls src="https://cdn-uploads.huggingface.co/production/uploads/6740a691ddc2c8e208a41102/ODhrLG1MH4iU766WnWzIQ.mpga"></audio>
## Model description
## Model Card: Miami Beach Hologram โจ๐๐ ๐ปโจ
```
focused on a CRT screen old tv displaying miami beach hologram, neon text "MIAMI"
```
```
aquarium with radioactive glowing fish in the house in the night, refractions on the wall behind,
mutated geometric glowing plants, 3d, miami beach hologram,
liquid cg, high-definition, majestic, sci-wave, depth of field,
glass reflection, very detailed, selective focus, long aperture, professional photo
```
```
videogame arcade place, all screens display neon light miami beach hologram action game, 1980s,
detailed arcade venue, night time, soda_vending_machine in the corner, sci-fi posters made of leds,
black rubber floor, black walls with small fluorescent stars stickers, high-definition, creative,
high-octane, 3d
```
```
old computer desktop was left turned on and its crt monitor screen is alive and emitting magical rays,
cute gaming room, posters, toys, glassy desk, tidy, old telephone with disk, alarm clock,
videogame console with joystick, pens, pencils, sheet of paper, detailed, high resolution,
perfect lighting, depth of field, colourful, 3d,miami beach hologram
```
### Overview
The Miami Beach Hologram model is a custom Image LoRA (Low-Rank Adaptation) designed to generate vibrant, neon-lit, and geometrically precise artworks inspired by the iconic aesthetics of Miami Beach. This model specializes in creating futuristic, holographic-style images with a strong emphasis on neon lighting, reflective surfaces, and retro-futuristic elements. Whether youโre an artist, designer, or creator, this model offers a powerful tool for generating stunning, synthwave-inspired visuals.
---
### Key Features
- Neon Holographic Style: Produces images with glowing neon lights, reflective surfaces, and a dreamy, futuristic atmosphere.
- Geometric Precision: Emphasizes clean lines, sharp shapes, and low-poly aesthetics, perfect for creating sci-fi and retro-futuristic scenes.
- Versatile Applications: Ideal for AI art, video game assets, album covers, digital installations, and conceptual designs.
- Inspired by Miami Beach: Captures the vibrant, neon-lit essence of Miami Beach, blending it with a holographic, cyberpunk-inspired aesthetic.
---
### Training Details
#### Dataset
- Dataset Size: 15 images
- Source: Custom-curated dataset shared on Civitai, featuring high-quality images with text file captions.
- Content: The dataset includes examples of neon-lit scenes, geometric shapes, reflective surfaces, and iconic landmarks rendered in a holographic style.
#### Training Parameters
- Model Base: SDXL 1.0
- VAE: SDXL-VAE-16-Fix
- Scheduler: Euler
- Steps: 30
- Clip Skip: 1
- Total Training Steps: 380
- Epochs: 10
- Batch Size: 4
- Optimizer: AdamW
- Learning Rate Schedule: Cosine with Restarts
#### Training Environment
- Stable Diffusion Version: SDXL 1.0
- Training Framework: Custom LoRA training pipeline
- Device: GPU (Recommended for efficient inference)
---
####. Optional Parameters:
- Adjust num_inference_steps for higher quality (default: 30).
- Modify the guidance_scale for more or less creativity.
- Experiment with different seeds for varied outputs.
---
### Sample Outputs
Below are some sample images generated using this model. These examples demonstrate the modelโs ability to create vibrant, neon-lit, and geometrically precise scenes:
1. Miami Beach Hologram:
Prompt: Miami Beach Hologram, neon, geometric, wide angle
2. Desert Pyramids:
Prompt: Desert with geometric Pyramids in Egypt, bathed in a warm glow
3. Statue of Liberty:
Prompt: Synthwave, Miami Beach Hologram, featuring geometric NEON Statue of Liberty, star-lit sky, neon, perfect geometry, 3D, CG, colorful, reflection, wide-angle, vaporwave moon
4. Christ the Redeemer:
Prompt: Miami Beach Hologram, majestic geometric statue of Cristo Redentor, slices of moon, surreal geometric cyan forest, star-lit sky
---
### License
The Miami Beach Hologram model is licensed under the Creative Commons Attribution 4.0 International (CC BY 4.0) license.
- Attribution: When using this model, please credit the author and include the following information:
```
Miami Beach Hologram ยฉ 2025 by Robb-0
Licensed under CC BY 4.0
```
### Disclaimer
This model is provided as-is. While efforts have been made to ensure its quality, the author is not responsible for any issues arising from its use. Use at your own discretion.
---
๐โจ
## Trigger words
You should use `miami beach hologram` to trigger the image generation.
## Download model
Weights for this model are available in Safetensors format.
[Download](/robb-0/miami-beach-hologram/tree/main) them in the Files & versions tab.
|
Akashiurahara/testingDataset
|
Akashiurahara
| 2025-06-19T18:12:50Z | 66 | 0 | null |
[
"gguf",
"llama",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | null | 2025-06-06T18:05:44Z |
---
license: apache-2.0
---
|
robb-0/miami_beach_hologram_2
|
robb-0
| 2025-06-19T18:12:24Z | 40 | 1 |
diffusers
|
[
"diffusers",
"text-to-image",
"lora",
"template:diffusion-lora",
"sdxl",
"en",
"dataset:robb-0/miami_beach_hologram2_dataset",
"dataset:robb-0/amazing_miami_holograms_dataset",
"base_model:stabilityai/sdxl-turbo",
"base_model:adapter:stabilityai/sdxl-turbo",
"license:cc-by-4.0",
"region:us"
] |
text-to-image
| 2025-06-04T04:18:00Z |
---
tags:
- text-to-image
- lora
- diffusers
- template:diffusion-lora
- sdxl
widget:
- text: >-
clear clean visible glowing aquarium at wall displaying (amazing image of
the car at the beach, photorealistic, neon style, asphalt, reflective ocean,
gradient colored sky, synthwave sun, geometric palm trees, depth of field
,vibrant, high-definition, high-octane), wide-angle, indoors, text "Miami",
parameters:
negative_prompt: >-
worst quality, low quality, lowres,flattened image, dull, illustration,
amateurish illustration, beginner, ugly
output:
url: images/bc61a66e-323d-4d8c-8932-2fa4153d19c2.jpeg
- text: >-
(macro:1.3), (night time) , macro photo of a cute cat on the grass in the
yard,the cat wears a necklace with a bing which reads "miami", city lights
in the blurry bokeh background,nighttime, miami beach hologram, DPM++ 2S a
Karras, CFG 6, Steps 25, Clip 2, Seed: 150062445,
<lora:miami_beach_hologram_2:1.0>
parameters:
negative_prompt: >-
worst quality, low quality, lowres,flattened image, dull, illustration,
amateurish illustration, beginner, ugly,
output:
url: images/cat.png
- text: >-
(macro:1.3), (night time) , macro photo of a cute puppy on the grass in the
yard,the puppy wears a necklace with a bing which reads "miami", city lights
in the blurry bokeh background,nighttime, DPM++ 2S a Karras, CFG 6, Steps
24, Clip 2, Seed: 149393699, <lora:miami_beach_hologram_2:1.0>
parameters:
negative_prompt: >-
worst quality, low quality, lowres,flattened image, dull, illustration,
amateurish illustration, beginner, ugly,
output:
url: images/dog.png
- text: >-
small tourism hologram of a paradise beach on a desk, realistic,miami beach
hologram, uhd, high definition, high octane Euler A, CFG 5.9, Steps 20,
Seed: 14385437570 - Clipskip 2, <lora:miami_beach_hologram_2:0.8>
parameters:
negative_prompt: lowres, ugly, low quality, blurry, (jpeg artifacts)
output:
url: images/hologram.png
base_model: stabilityai/sdxl-turbo
instance_prompt: null
license: cc-by-4.0
language:
- en
datasets:
- robb-0/miami_beach_hologram2_dataset
- robb-0/amazing_miami_holograms_dataset
---
# Miami Beach Hologram 2
<Gallery />
## Model description
<img src="https://cdn-uploads.huggingface.co/production/uploads/6740a691ddc2c8e208a41102/TwsqGxQIyPLQjMX45JN1F.png" alt="871203627362987285.png" width="500px">
```
small tourism hologram of a paradise beach on a desk,
realistic,miami beach hologram, uhd, high definition,
high octane,
seed: 1438543757
Euler A, CFG 5.9 Steps 20, Clip Skip 2
Miami_Beach_Hologram_2: 0.80
```
๐๐
๐๏ธ `Endless Summer` ๐๐๐น
<audio controls src="https://cdn-uploads.huggingface.co/production/uploads/6740a691ddc2c8e208a41102/R2m-0UknK5tFUtPuHmUej.mpga"></audio>
This is a second version of Miami Beach Hologram, which is able to generate the hologram mentioned and the text for "Miami" is improved, hehe not only for Miami but
for many single words on stickers, covers, brands and neon signs.
First version here
https://huggingface.co/robb-0/miami-beach-hologram
It produces less jpeg artifacts, it now truly helps rendering props and scenes as seen on the dataset (shared on the hub.)
Set the weight around 0.8 and change it according to desired results.
Trigger word: "**miami beach hologram**", or "**miami hologram**"
---
Disclaimer:
This model is provided โas isโ without any warranty. The creator is not responsible for any misuse or unintended consequences of using this model.
---
For extra info (image samples) and free online generation, it's available on Civitai
https://civitai.com/models/1546236/miami-beach-hologram?modelVersionId=1861856
## Download model
Weights for this model are available in Safetensors format.
[Download](/robb-0/miami_beach_hologram_2_sdxl/tree/main) them in the Files & versions tab.
---
```
Trained on Civitai
60 images x 5 repeats
10 Epochs - 4 Batches
760 Steps
Adafactor + Cosine with restarts
LR 0.0005
TE 0.00005
UNET 0.0005
DIM/Alpha 32/16
Noise Offset
0.1
Pyramid Noise Iterations
6
Discount
0.3
SNR 5
```
|
angela-white-viral-Video/Angela.White.Viral.Video.Official
|
angela-white-viral-Video
| 2025-06-19T18:11:51Z | 0 | 0 | null |
[
"region:us"
] | null | 2025-06-19T18:11:43Z |
18 seconds ago
<a href="https://viralinfo.xyz/video/?v=Katrina+lim+kiffy" rel="nofollow">โบโบโ
๐พ๐๐๐พ๐ ๐๐๐๐ ==โบโบ ๐๐ช๐ก๐ก ๐๐๐๐๐ค๏ธโ</a></p>
<a href="https://viralinfo.xyz/video/?v=Katrina+lim+kiffy" rel="nofollow">๐ดโบ๐๐๐๐๐ ๐๐๐๐ ๐==โบโบ ๐๐จ๐ฐ๐ง๐ฅ๐จ๐๐ ๐๐จ๐ฐโฌ๏ธโฌ๏ธโ</a></p>
<p><a rel="nofollow" title="WATCH NOW" href="https://viralinfo.xyz/video/?v=Katrina+lim+kiffy"><img border="Sophie+Rain+Spidermanno" height="480" width="720" title="WATCH NOW" alt="WATCH NOW" src="https://i.ibb.co.com/xMMVF88/686577567.gif"></a></p>
|
New-Clip-Prajakta-Mali-18-Viral-videos/FULL.VIDEO.Prajakta.Mali.Viral.Video.Tutorial.Official
|
New-Clip-Prajakta-Mali-18-Viral-videos
| 2025-06-19T18:11:45Z | 0 | 0 | null |
[
"region:us"
] | null | 2025-06-19T18:11:26Z |
<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>
<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>
|
Redeem-Craze-Official-Viral-Video/FULL.VIDEO.Redeem.Craze.Viral.Video.Tutorial.Official
|
Redeem-Craze-Official-Viral-Video
| 2025-06-19T18:11:23Z | 0 | 0 | null |
[
"region:us"
] | null | 2025-06-19T18:11:12Z |
<a href="https://watch-blogg777xx.blogspot.com/2025/06/maallu.html"><img src="http://4.bp.blogspot.com/-VFcup4RzDQY/Upiobuokb5I/AAAAAAAAAV0/64yKpZilDCg/s1600/oie_nxv3mlmduAj1.gif" alt="fsd" /></a>
<a href="https://watch-blogg777xx.blogspot.com/2025/06/maallu.html" rel="nofollow">๐ด โคโบ๐๐ฅ๐ข๐ค ๐๐๐ซ๐ ๐ญ๐จ๐๐ (๐๐๐ญ๐๐ก ๐
๐ฎ๐ฅ๐ฅ ๐ฏ๐ข๐๐๐จ)</a>
<a href="https://watch-blogg777xx.blogspot.com/2025/06/maallu.html" rel="nofollow">๐ด โคโบ๐๐ฅ๐ข๐ค ๐๐๐ซ๐ ๐ญ๐จ๐๐ (๐
๐ฎ๐ฅ๐ฅ ๐ฏ๐ข๐๐๐จ ๐๐ข๐ง๐ค)</a>
|
phospho-app/joshvista-ACT_BBOX-PickAndPlace-bx23w
|
phospho-app
| 2025-06-19T18:08:14Z | 0 | 0 | null |
[
"phosphobot",
"act",
"region:us"
] | null | 2025-06-19T18:08:01Z |
---
tags:
- phosphobot
- act
task_categories:
- robotics
---
# act Model - phospho Training Pipeline
## Error Traceback
We faced an issue while training your model.
```
Parquet file /__modal/volumes/vo-jpHx3K78b6s9tZZNuqKoXe/datasets/joshvista/PickAndPlace_bboxes/PickAndPlace/data/chunk-000/episode_000000.parquet does not contain 'observation.environment_state' key. This is unexpected after computing bounding boxes.
```
## Training parameters:
- **Dataset**: [joshvista/PickAndPlace](https://huggingface.co/datasets/joshvista/PickAndPlace)
- **Wandb run URL**: None
- **Epochs**: None
- **Batch size**: 100
- **Training steps**: 10000
๐ **Get Started**: [docs.phospho.ai](https://docs.phospho.ai?utm_source=huggingface_readme)
๐ค **Get your robot**: [robots.phospho.ai](https://robots.phospho.ai?utm_source=huggingface_readme)
|
Eskender/products-ranker-preprod-bge
|
Eskender
| 2025-06-19T18:06:20Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"roberta",
"text-classification",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2025-06-19T18:05:19Z |
---
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]
|
phospho-app/joshvista-ACT_BBOX-PickAndPlace-bn3yl
|
phospho-app
| 2025-06-19T18:06:00Z | 0 | 0 | null |
[
"phosphobot",
"act",
"region:us"
] | null | 2025-06-19T18:05:51Z |
---
tags:
- phosphobot
- act
task_categories:
- robotics
---
# act Model - phospho Training Pipeline
## Error Traceback
We faced an issue while training your model.
```
The object 'dark ring' was detected in 2 episodes in main camera (should be: 10 episodes min). This is not enough to train a model. Check your dataset: https://lerobot-visualize-dataset.hf.space/joshvista/PickAndPlace/ and rephrase the instruction.
```
## Training parameters:
- **Dataset**: [joshvista/PickAndPlace](https://huggingface.co/datasets/joshvista/PickAndPlace)
- **Wandb run URL**: None
- **Epochs**: None
- **Batch size**: 100
- **Training steps**: 10000
๐ **Get Started**: [docs.phospho.ai](https://docs.phospho.ai?utm_source=huggingface_readme)
๐ค **Get your robot**: [robots.phospho.ai](https://robots.phospho.ai?utm_source=huggingface_readme)
|
phospho-app/joshvista-ACT_BBOX-PickAndPlace-66i8k
|
phospho-app
| 2025-06-19T18:04:47Z | 0 | 0 | null |
[
"phosphobot",
"act",
"region:us"
] | null | 2025-06-19T18:03:37Z |
---
tags:
- phosphobot
- act
task_categories:
- robotics
---
# act Model - phospho Training Pipeline
## Error Traceback
We faced an issue while training your model.
```
The object 'e.g.: black and yellow roll of tape' was detected in 0 episodes in main camera (should be: 10 episodes min). This is not enough to train a model. Check your dataset: https://lerobot-visualize-dataset.hf.space/joshvista/PickAndPlace/ and rephrase the instruction.
```
## Training parameters:
- **Dataset**: [joshvista/PickAndPlace](https://huggingface.co/datasets/joshvista/PickAndPlace)
- **Wandb run URL**: None
- **Epochs**: None
- **Batch size**: 100
- **Training steps**: 10000
๐ **Get Started**: [docs.phospho.ai](https://docs.phospho.ai?utm_source=huggingface_readme)
๐ค **Get your robot**: [robots.phospho.ai](https://robots.phospho.ai?utm_source=huggingface_readme)
|
LaaP-ai/donut-base-invoice-v1.24
|
LaaP-ai
| 2025-06-19T18:03:45Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"vision-encoder-decoder",
"image-text-to-text",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
] |
image-text-to-text
| 2025-06-19T18:03:33Z |
---
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]
|
New-tutorial-Camilla-Araujo-18-Viral-Video/FULL.VIDEO.Camilla.Araujo.Viral.Video.Tutorial.Official
|
New-tutorial-Camilla-Araujo-18-Viral-Video
| 2025-06-19T18:01:45Z | 0 | 0 | null |
[
"region:us"
] | null | 2025-06-19T18:01:40Z |
<a href="https://watch-blogg777xx.blogspot.com/2025/06/maallu.html"><img src="http://4.bp.blogspot.com/-VFcup4RzDQY/Upiobuokb5I/AAAAAAAAAV0/64yKpZilDCg/s1600/oie_nxv3mlmduAj1.gif" alt="fsd" /></a>
<a href="https://watch-blogg777xx.blogspot.com/2025/06/maallu.html" rel="nofollow">๐ด โคโบ๐๐ฅ๐ข๐ค ๐๐๐ซ๐ ๐ญ๐จ๐๐ (๐๐๐ญ๐๐ก ๐
๐ฎ๐ฅ๐ฅ ๐ฏ๐ข๐๐๐จ)</a>
<a href="https://watch-blogg777xx.blogspot.com/2025/06/maallu.html" rel="nofollow">๐ด โคโบ๐๐ฅ๐ข๐ค ๐๐๐ซ๐ ๐ญ๐จ๐๐ (๐
๐ฎ๐ฅ๐ฅ ๐ฏ๐ข๐๐๐จ ๐๐ข๐ง๐ค)</a>
|
phospho-app/joshvista-ACT_BBOX-PickAndPlace-bqa8q
|
phospho-app
| 2025-06-19T18:01:13Z | 0 | 0 | null |
[
"phosphobot",
"act",
"region:us"
] | null | 2025-06-19T18:01:01Z |
---
tags:
- phosphobot
- act
task_categories:
- robotics
---
# act Model - phospho Training Pipeline
## Error Traceback
We faced an issue while training your model.
```
The object 'black and yellow circle' was detected in 9 episodes in main camera (should be: 10 episodes min). This is not enough to train a model. Check your dataset: https://lerobot-visualize-dataset.hf.space/joshvista/PickAndPlace/ and rephrase the instruction.
```
## Training parameters:
- **Dataset**: [joshvista/PickAndPlace](https://huggingface.co/datasets/joshvista/PickAndPlace)
- **Wandb run URL**: None
- **Epochs**: None
- **Batch size**: 100
- **Training steps**: 10000
๐ **Get Started**: [docs.phospho.ai](https://docs.phospho.ai?utm_source=huggingface_readme)
๐ค **Get your robot**: [robots.phospho.ai](https://robots.phospho.ai?utm_source=huggingface_readme)
|
phospho-app/joshvista-ACT_BBOX-PickAndPlace-8sa4e
|
phospho-app
| 2025-06-19T18:00:19Z | 0 | 0 | null |
[
"phosphobot",
"act",
"region:us"
] | null | 2025-06-19T17:59:20Z |
---
tags:
- phosphobot
- act
task_categories:
- robotics
---
# act Model - phospho Training Pipeline
## Error Traceback
We faced an issue while training your model.
```
The object 'circle' was detected in 0 episodes in main camera (should be: 10 episodes min). This is not enough to train a model. Check your dataset: https://lerobot-visualize-dataset.hf.space/joshvista/PickAndPlace/ and rephrase the instruction.
```
## Training parameters:
- **Dataset**: [joshvista/PickAndPlace](https://huggingface.co/datasets/joshvista/PickAndPlace)
- **Wandb run URL**: None
- **Epochs**: None
- **Batch size**: 100
- **Training steps**: 10000
๐ **Get Started**: [docs.phospho.ai](https://docs.phospho.ai?utm_source=huggingface_readme)
๐ค **Get your robot**: [robots.phospho.ai](https://robots.phospho.ai?utm_source=huggingface_readme)
|
katrina-lim-kify-18-new-Video-tutorial/katrina.lim.viral.kiffy.Viral.Video.Official
|
katrina-lim-kify-18-new-Video-tutorial
| 2025-06-19T17:55:37Z | 0 | 0 | null |
[
"region:us"
] | null | 2025-06-19T17:55:11Z |
18 seconds ago
<a href="https://viralinfo.xyz/video/?v=Katrina+lim+kiffy" rel="nofollow">โบโบโ
๐พ๐๐๐พ๐ ๐๐๐๐ ==โบโบ ๐๐ช๐ก๐ก ๐๐๐๐๐ค๏ธโ</a></p>
<a href="https://viralinfo.xyz/video/?v=Katrina+lim+kiffy" rel="nofollow">๐ดโบ๐๐๐๐๐ ๐๐๐๐ ๐==โบโบ ๐๐จ๐ฐ๐ง๐ฅ๐จ๐๐ ๐๐จ๐ฐโฌ๏ธโฌ๏ธโ</a></p>
<p><a rel="nofollow" title="WATCH NOW" href="https://viralinfo.xyz/video/?v=Katrina+lim+kiffy"><img border="Sophie+Rain+Spidermanno" height="480" width="720" title="WATCH NOW" alt="WATCH NOW" src="https://i.ibb.co.com/xMMVF88/686577567.gif"></a></p>
|
erdfg43/VIDEO.18.Official-mezzo-fun-18-Viral-videos.FULL.VIDEO.Mezzo.fun.Viral.Video.Tutorial.Official
|
erdfg43
| 2025-06-19T17:53:27Z | 0 | 0 | null |
[
"region:us"
] | null | 2025-06-19T17:52:44Z |
<a href="https://allyoutubers.com/Official-mezzo-fun-18-Viral-videos"> ๐ VIDEO.18.Official-mezzo-fun-18-Viral-videos.FULL.VIDEO.Mezzo.fun.Viral.Video.Tutorial.Official
๐ด โคโบDOWNLOAD๐๐๐ข โค <a href="https://allyoutubers.com/Official-mezzo-fun-18-Viral-videos"> ๐ VIDEO.18.Official-mezzo-fun-18-Viral-videos.FULL.VIDEO.Mezzo.fun.Viral.Video.Tutorial.Official
<a href="https://allyoutubers.com/Official-mezzo-fun-18-Viral-videos"> ๐ VIDEO.18.Official-mezzo-fun-18-Viral-videos.FULL.VIDEO.Mezzo.fun.Viral.Video.Tutorial.Official
๐ด โคโบDOWNLOAD๐๐๐ข โค <a href="https://allyoutubers.com/Official-mezzo-fun-18-Viral-videos"> ๐ VIDEO.18.Official-mezzo-fun-18-Viral-videos.FULL.VIDEO.Mezzo.fun.Viral.Video.Tutorial.Official
|
rodrigomt/veiled-japanse-Q8_0-GGUF
|
rodrigomt
| 2025-06-19T17:53:04Z | 0 | 0 | null |
[
"gguf",
"merge",
"mergekit",
"lazymergekit",
"Aratako/gemma-3-4b-it-RP-v0.1",
"soob3123/Veiled-Calla-4B",
"llama-cpp",
"gguf-my-repo",
"base_model:rodrigomt/veiled-japanse",
"base_model:quantized:rodrigomt/veiled-japanse",
"endpoints_compatible",
"region:us"
] | null | 2025-06-19T17:52:42Z |
---
base_model: rodrigomt/veiled-japanse
tags:
- merge
- mergekit
- lazymergekit
- Aratako/gemma-3-4b-it-RP-v0.1
- soob3123/Veiled-Calla-4B
- llama-cpp
- gguf-my-repo
---
# rodrigomt/veiled-japanse-Q8_0-GGUF
This model was converted to GGUF format from [`rodrigomt/veiled-japanse`](https://huggingface.co/rodrigomt/veiled-japanse) 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/rodrigomt/veiled-japanse) 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 rodrigomt/veiled-japanse-Q8_0-GGUF --hf-file veiled-japanse-q8_0.gguf -p "The meaning to life and the universe is"
```
### Server:
```bash
llama-server --hf-repo rodrigomt/veiled-japanse-Q8_0-GGUF --hf-file veiled-japanse-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 rodrigomt/veiled-japanse-Q8_0-GGUF --hf-file veiled-japanse-q8_0.gguf -p "The meaning to life and the universe is"
```
or
```
./llama-server --hf-repo rodrigomt/veiled-japanse-Q8_0-GGUF --hf-file veiled-japanse-q8_0.gguf -c 2048
```
|
Florisst/model_phi_4_Justid
|
Florisst
| 2025-06-19T17:52:17Z | 0 | 0 |
transformers
|
[
"transformers",
"gguf",
"llama",
"text-generation-inference",
"unsloth",
"en",
"base_model:unsloth/phi-4-unsloth-bnb-4bit",
"base_model:quantized:unsloth/phi-4-unsloth-bnb-4bit",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | null | 2025-06-19T17:48:47Z |
---
base_model: unsloth/phi-4-unsloth-bnb-4bit
tags:
- text-generation-inference
- transformers
- unsloth
- llama
- gguf
license: apache-2.0
language:
- en
---
# Uploaded model
- **Developed by:** Florisst
- **License:** apache-2.0
- **Finetuned from model :** unsloth/phi-4-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)
|
phospho-app/joshvista-ACT_BBOX-PickAndPlace-u4xqd
|
phospho-app
| 2025-06-19T17:50:46Z | 0 | 0 | null |
[
"phosphobot",
"act",
"region:us"
] | null | 2025-06-19T17:49:08Z |
---
tags:
- phosphobot
- act
task_categories:
- robotics
---
# act Model - phospho Training Pipeline
## Error Traceback
We faced an issue while training your model.
```
The object 'black roll of tape' was detected in 2 episodes in main camera (should be: 10 episodes min). This is not enough to train a model. Check your dataset: https://lerobot-visualize-dataset.hf.space/joshvista/PickAndPlace/ and rephrase the instruction.
```
## Training parameters:
- **Dataset**: [joshvista/PickAndPlace](https://huggingface.co/datasets/joshvista/PickAndPlace)
- **Wandb run URL**: None
- **Epochs**: None
- **Batch size**: 100
- **Training steps**: 10000
๐ **Get Started**: [docs.phospho.ai](https://docs.phospho.ai?utm_source=huggingface_readme)
๐ค **Get your robot**: [robots.phospho.ai](https://robots.phospho.ai?utm_source=huggingface_readme)
|
LaaP-ai/donut-base-invoice-v1.23
|
LaaP-ai
| 2025-06-19T17:50:27Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"vision-encoder-decoder",
"image-text-to-text",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
] |
image-text-to-text
| 2025-06-19T17:50:15Z |
---
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]
|
bawsala/phi4-ft-ar-chem-quiz
|
bawsala
| 2025-06-19T17:47:59Z | 68 | 0 |
transformers
|
[
"transformers",
"safetensors",
"phi3",
"text-generation",
"conversational",
"custom_code",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2025-06-17T10:56:21Z |
---
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]
|
segopecelus/5322cced-9613-4e9f-8c37-169117aeba42
|
segopecelus
| 2025-06-19T17:47:39Z | 0 | 0 |
transformers
|
[
"transformers",
"tensorboard",
"safetensors",
"qwen2",
"text-generation",
"generated_from_trainer",
"axolotl",
"trl",
"grpo",
"unsloth",
"conversational",
"arxiv:2402.03300",
"base_model:unsloth/Qwen2-7B",
"base_model:quantized:unsloth/Qwen2-7B",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"4-bit",
"bitsandbytes",
"region:us"
] |
text-generation
| 2025-06-19T17:14:17Z |
---
base_model: unsloth/Qwen2-7B
library_name: transformers
model_name: 5322cced-9613-4e9f-8c37-169117aeba42
tags:
- generated_from_trainer
- axolotl
- trl
- grpo
- unsloth
licence: license
---
# Model Card for 5322cced-9613-4e9f-8c37-169117aeba42
This model is a fine-tuned version of [unsloth/Qwen2-7B](https://huggingface.co/unsloth/Qwen2-7B).
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="segopecelus/5322cced-9613-4e9f-8c37-169117aeba42", 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/apriasmoro-abcstudio/Gradients-On-Demand/runs/09y1gd20)
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: 0.17.0
- Transformers: 4.51.3
- Pytorch: 2.5.1+cu124
- Datasets: 3.5.1
- 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 Gallou{\'e}dec},
year = 2020,
journal = {GitHub repository},
publisher = {GitHub},
howpublished = {\url{https://github.com/huggingface/trl}}
}
```
|
haider-cheema28/llama3-conspiracy-lora
|
haider-cheema28
| 2025-06-19T17:47:22Z | 0 | 0 |
peft
|
[
"peft",
"safetensors",
"arxiv:1910.09700",
"region:us"
] | null | 2025-06-19T17:34:53Z |
---
base_model: unsloth/llama-3.1-8b-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
|
nanotechnologie/G-Medicale-R1
|
nanotechnologie
| 2025-06-19T17:47:21Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"t5",
"text2text-generation",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text2text-generation
| 2025-06-19T17:24:50Z |
---
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]
|
AlSamCur123/NemoTunerR1ContinuedFine
|
AlSamCur123
| 2025-06-19T17:45:16Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"mistral",
"text-generation",
"text-generation-inference",
"unsloth",
"conversational",
"en",
"base_model:AlSamCur123/NemoTuneContinuedFine",
"base_model:finetune:AlSamCur123/NemoTuneContinuedFine",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2025-06-19T17:31:56Z |
---
base_model: AlSamCur123/NemoTuneContinuedFine
tags:
- text-generation-inference
- transformers
- unsloth
- mistral
license: apache-2.0
language:
- en
---
# Uploaded finetuned model
- **Developed by:** AlSamCur123
- **License:** apache-2.0
- **Finetuned from model :** AlSamCur123/NemoTuneContinuedFine
This mistral 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)
|
zalewskij/ppo-Huggy
|
zalewskij
| 2025-06-19T17:45:07Z | 0 | 0 |
ml-agents
|
[
"ml-agents",
"tensorboard",
"onnx",
"Huggy",
"deep-reinforcement-learning",
"reinforcement-learning",
"ML-Agents-Huggy",
"region:us"
] |
reinforcement-learning
| 2025-06-19T17:45:00Z |
---
library_name: ml-agents
tags:
- Huggy
- deep-reinforcement-learning
- reinforcement-learning
- ML-Agents-Huggy
---
# **ppo** Agent playing **Huggy**
This is a trained model of a **ppo** agent playing **Huggy**
using the [Unity ML-Agents Library](https://github.com/Unity-Technologies/ml-agents).
## Usage (with ML-Agents)
The Documentation: https://unity-technologies.github.io/ml-agents/ML-Agents-Toolkit-Documentation/
We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub:
- A *short tutorial* where you teach Huggy the Dog ๐ถ to fetch the stick and then play with him directly in your
browser: https://huggingface.co/learn/deep-rl-course/unitbonus1/introduction
- A *longer tutorial* to understand how works ML-Agents:
https://huggingface.co/learn/deep-rl-course/unit5/introduction
### Resume the training
```bash
mlagents-learn <your_configuration_file_path.yaml> --run-id=<run_id> --resume
```
### Watch your Agent play
You can watch your agent **playing directly in your browser**
1. If the environment is part of ML-Agents official environments, go to https://huggingface.co/unity
2. Step 1: Find your model_id: zalewskij/ppo-Huggy
3. Step 2: Select your *.nn /*.onnx file
4. Click on Watch the agent play ๐
|
morturr/Llama-2-7b-hf-PAIR_headlines_one_liners-COMB-headlines-comb-2-seed-7-2025-06-19
|
morturr
| 2025-06-19T17:41:00Z | 0 | 0 |
peft
|
[
"peft",
"safetensors",
"trl",
"sft",
"generated_from_trainer",
"base_model:meta-llama/Llama-2-7b-hf",
"base_model:adapter:meta-llama/Llama-2-7b-hf",
"license:llama2",
"region:us"
] | null | 2025-06-19T17:40:44Z |
---
library_name: peft
license: llama2
base_model: meta-llama/Llama-2-7b-hf
tags:
- trl
- sft
- generated_from_trainer
model-index:
- name: Llama-2-7b-hf-PAIR_headlines_one_liners-COMB-headlines-comb-2-seed-7-2025-06-19
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. -->
# Llama-2-7b-hf-PAIR_headlines_one_liners-COMB-headlines-comb-2-seed-7-2025-06-19
This model is a fine-tuned version of [meta-llama/Llama-2-7b-hf](https://huggingface.co/meta-llama/Llama-2-7b-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: 5e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 7
- gradient_accumulation_steps: 4
- total_train_batch_size: 32
- 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
### Framework versions
- PEFT 0.13.2
- Transformers 4.46.1
- Pytorch 2.5.1+cu124
- Datasets 3.0.2
- Tokenizers 0.20.1
|
lakhera2023/deepseek-children-stories
|
lakhera2023
| 2025-06-19T17:40:07Z | 0 | 0 | null |
[
"pytorch",
"deepseek",
"children-stories",
"story-generation",
"gpt",
"mixture-of-experts",
"en",
"license:mit",
"region:us"
] | null | 2025-06-19T17:35:34Z |
---
language: en
tags:
- deepseek
- children-stories
- story-generation
- pytorch
- gpt
- mixture-of-experts
license: mit
---
# DeepSeek Children's Stories Model
A lightweight (15-18M parameters) story generation model specifically designed for children's content, featuring advanced architecture components like Mixture of Experts (MoE) and Multihead Latent Attention (MLA).
## Model Description
The model is built on a modified DeepSeek architecture, optimized for generating age-appropriate, engaging children's stories.
### Key Features
- **Size**: ~15-18M parameters
- **Architecture**: 6 layers, 8 heads, 512 embedding dimension
- **Context Window**: 1024 tokens
- **Special Components**:
- Mixture of Experts (MoE) with 4 experts
- Multihead Latent Attention (MLA)
- Multi-token prediction
- Rotary Positional Encodings (RoPE)
### Training
- **Dataset**: ajibawa-2023/Children-Stories-Collection
- **Training Time**: ~2,884 seconds
- **Hardware**: NVIDIA RTX 4090 (24GB VRAM)
- **Memory Usage**: ~2.24GB GPU memory
## Training Metrics
The training metrics show:
- Rapid initial convergence (loss drops from 10.89 to 3.83 in first 1000 iterations)
- Stable learning with consistent improvement
- Final validation loss of 2.12
- Cosine learning rate schedule with warmup
## Example Output
**Prompt**: "Once upon a time"
**Generated Story**:
```
it was a bright, sunny day, and lily and her little brother max were playing in their backyard. they found a piece of paper with two sentence written on it. "let's make sense of some of these sentences," said max, pointing to the first sentence. "these people are playing on the grass," "but i don't know," replied lily. she thought for a moment. "maybe they only talk with the others or not, right?" she asked. max nodded. "yeah, and what about 'he', 'he', 'an', 'man', and 'man'?" lily explained, "it means they're playing with their dogs. but they don't say anything about someone talking." max asked, "but what about the others? we don't talk to each other!" lily thought for a moment before answering, "that's right! sometimes, people try to talk to each other. when we talk about something, we need to tell others"
```
## Usage
```python
from transformers import AutoTokenizer, AutoModelForCausalLM
# Load model and tokenizer
model = AutoModelForCausalLM.from_pretrained("your-username/deepseek-children-stories")
tokenizer = AutoTokenizer.from_pretrained("your-username/deepseek-children-stories")
# Generate text
prompt = "Once upon a time"
inputs = tokenizer(prompt, return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=200, temperature=0.8)
story = tokenizer.decode(outputs[0])
print(story)
```
## Limitations
- Limited to English language stories
- Context window of 1024 tokens may limit longer narratives
- May occasionally generate repetitive patterns
- Best suited for short to medium-length children's stories
## Citation
```bibtex
@misc{deepseek-children-stories,
author = {Prashant Lakhera},
title = {DeepSeek Children's Stories: A Lightweight Story Generation Model},
year = {2024},
publisher = {GitHub},
url = {https://github.com/ideaweaver-ai/DeepSeek-Children-Stories-15M-model}
}
```
## License
This project is licensed under the MIT License. See the LICENSE file for details.
|
yalhessi/lemexp-task1-v2-lemma_object_small_nodefs-Llama-3.2-1B-ddp-8lr-v2
|
yalhessi
| 2025-06-19T17:39:25Z | 0 | 0 |
peft
|
[
"peft",
"safetensors",
"generated_from_trainer",
"base_model:meta-llama/Llama-3.2-1B",
"base_model:adapter:meta-llama/Llama-3.2-1B",
"license:llama3.2",
"region:us"
] | null | 2025-06-19T17:38:47Z |
---
library_name: peft
license: llama3.2
base_model: meta-llama/Llama-3.2-1B
tags:
- generated_from_trainer
model-index:
- name: lemexp-task1-v2-lemma_object_small_nodefs-Llama-3.2-1B-ddp-8lr-v2
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. -->
# lemexp-task1-v2-lemma_object_small_nodefs-Llama-3.2-1B-ddp-8lr-v2
This model is a fine-tuned version of [meta-llama/Llama-3.2-1B](https://huggingface.co/meta-llama/Llama-3.2-1B) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.3233
## 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: 2
- eval_batch_size: 2
- seed: 42
- distributed_type: multi-GPU
- num_devices: 8
- total_train_batch_size: 16
- total_eval_batch_size: 16
- 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 |
|:-------------:|:-------:|:-----:|:---------------:|
| 0.8717 | 0.2001 | 720 | 0.7491 |
| 0.7206 | 0.4001 | 1440 | 0.6902 |
| 0.6392 | 0.6002 | 2160 | 0.6415 |
| 0.6135 | 0.8002 | 2880 | 0.6129 |
| 0.588 | 1.0003 | 3600 | 0.6039 |
| 0.5555 | 1.2003 | 4320 | 0.5792 |
| 0.5439 | 1.4004 | 5040 | 0.5666 |
| 0.5387 | 1.6004 | 5760 | 0.5562 |
| 0.5267 | 1.8005 | 6480 | 0.5579 |
| 0.5236 | 2.0006 | 7200 | 0.5447 |
| 0.5018 | 2.2006 | 7920 | 0.5271 |
| 0.4967 | 2.4007 | 8640 | 0.5159 |
| 0.4775 | 2.6007 | 9360 | 0.5015 |
| 0.4818 | 2.8008 | 10080 | 0.5015 |
| 0.4799 | 3.0008 | 10800 | 0.5015 |
| 0.4538 | 3.2009 | 11520 | 0.4905 |
| 0.4558 | 3.4009 | 12240 | 0.4862 |
| 0.4482 | 3.6010 | 12960 | 0.4776 |
| 0.4467 | 3.8011 | 13680 | 0.4782 |
| 0.4453 | 4.0011 | 14400 | 0.4660 |
| 0.4176 | 4.2012 | 15120 | 0.4661 |
| 0.4243 | 4.4012 | 15840 | 0.4635 |
| 0.4148 | 4.6013 | 16560 | 0.4606 |
| 0.4207 | 4.8013 | 17280 | 0.4470 |
| 0.4042 | 5.0014 | 18000 | 0.4488 |
| 0.3896 | 5.2014 | 18720 | 0.4345 |
| 0.3885 | 5.4015 | 19440 | 0.4352 |
| 0.3857 | 5.6016 | 20160 | 0.4383 |
| 0.3879 | 5.8016 | 20880 | 0.4250 |
| 0.3774 | 6.0017 | 21600 | 0.4223 |
| 0.3618 | 6.2017 | 22320 | 0.4183 |
| 0.3642 | 6.4018 | 23040 | 0.4084 |
| 0.3591 | 6.6018 | 23760 | 0.4098 |
| 0.3558 | 6.8019 | 24480 | 0.4043 |
| 0.3522 | 7.0019 | 25200 | 0.3931 |
| 0.3319 | 7.2020 | 25920 | 0.3963 |
| 0.3319 | 7.4021 | 26640 | 0.3862 |
| 0.3303 | 7.6021 | 27360 | 0.3937 |
| 0.3243 | 7.8022 | 28080 | 0.3886 |
| 0.3341 | 8.0022 | 28800 | 0.3781 |
| 0.307 | 8.2023 | 29520 | 0.3769 |
| 0.3003 | 8.4023 | 30240 | 0.3793 |
| 0.3028 | 8.6024 | 30960 | 0.3693 |
| 0.2977 | 8.8024 | 31680 | 0.3640 |
| 0.2971 | 9.0025 | 32400 | 0.3586 |
| 0.2751 | 9.2026 | 33120 | 0.3573 |
| 0.2712 | 9.4026 | 33840 | 0.3525 |
| 0.277 | 9.6027 | 34560 | 0.3480 |
| 0.2737 | 9.8027 | 35280 | 0.3417 |
| 0.2647 | 10.0028 | 36000 | 0.3428 |
| 0.2469 | 10.2028 | 36720 | 0.3414 |
| 0.2442 | 10.4029 | 37440 | 0.3341 |
| 0.2431 | 10.6029 | 38160 | 0.3312 |
| 0.2448 | 10.8030 | 38880 | 0.3312 |
| 0.2455 | 11.0031 | 39600 | 0.3252 |
| 0.2252 | 11.2031 | 40320 | 0.3282 |
| 0.2209 | 11.4032 | 41040 | 0.3222 |
| 0.2174 | 11.6032 | 41760 | 0.3230 |
| 0.2173 | 11.8033 | 42480 | 0.3233 |
### Framework versions
- PEFT 0.14.0
- Transformers 4.47.0
- Pytorch 2.5.1+cu124
- Datasets 3.2.0
- Tokenizers 0.21.0
|
mradermacher/KwaiCoder-AutoThink-preview-GGUF
|
mradermacher
| 2025-06-19T17:37:25Z | 0 | 0 |
transformers
|
[
"transformers",
"gguf",
"multilingual",
"base_model:Kwaipilot/KwaiCoder-AutoThink-preview",
"base_model:quantized:Kwaipilot/KwaiCoder-AutoThink-preview",
"license:other",
"endpoints_compatible",
"region:us",
"conversational"
] | null | 2025-06-19T10:35:08Z |
---
base_model: Kwaipilot/KwaiCoder-AutoThink-preview
language:
- multilingual
library_name: transformers
license: other
license_link: LICENSE
license_name: kwaipilot-license
quantized_by: mradermacher
---
## About
<!-- ### quantize_version: 2 -->
<!-- ### output_tensor_quantised: 1 -->
<!-- ### convert_type: hf -->
<!-- ### vocab_type: -->
<!-- ### tags: -->
static quants of https://huggingface.co/Kwaipilot/KwaiCoder-AutoThink-preview
<!-- provided-files -->
weighted/imatrix quants are available at https://huggingface.co/mradermacher/KwaiCoder-AutoThink-preview-i1-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/KwaiCoder-AutoThink-preview-GGUF/resolve/main/KwaiCoder-AutoThink-preview.Q2_K.gguf) | Q2_K | 15.3 | |
| [GGUF](https://huggingface.co/mradermacher/KwaiCoder-AutoThink-preview-GGUF/resolve/main/KwaiCoder-AutoThink-preview.Q3_K_S.gguf) | Q3_K_S | 18.0 | |
| [GGUF](https://huggingface.co/mradermacher/KwaiCoder-AutoThink-preview-GGUF/resolve/main/KwaiCoder-AutoThink-preview.Q3_K_M.gguf) | Q3_K_M | 19.8 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/KwaiCoder-AutoThink-preview-GGUF/resolve/main/KwaiCoder-AutoThink-preview.Q3_K_L.gguf) | Q3_K_L | 21.4 | |
| [GGUF](https://huggingface.co/mradermacher/KwaiCoder-AutoThink-preview-GGUF/resolve/main/KwaiCoder-AutoThink-preview.IQ4_XS.gguf) | IQ4_XS | 22.2 | |
| [GGUF](https://huggingface.co/mradermacher/KwaiCoder-AutoThink-preview-GGUF/resolve/main/KwaiCoder-AutoThink-preview.Q4_K_S.gguf) | Q4_K_S | 23.4 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/KwaiCoder-AutoThink-preview-GGUF/resolve/main/KwaiCoder-AutoThink-preview.Q4_K_M.gguf) | Q4_K_M | 24.7 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/KwaiCoder-AutoThink-preview-GGUF/resolve/main/KwaiCoder-AutoThink-preview.Q5_K_S.gguf) | Q5_K_S | 28.1 | |
| [GGUF](https://huggingface.co/mradermacher/KwaiCoder-AutoThink-preview-GGUF/resolve/main/KwaiCoder-AutoThink-preview.Q5_K_M.gguf) | Q5_K_M | 28.9 | |
| [GGUF](https://huggingface.co/mradermacher/KwaiCoder-AutoThink-preview-GGUF/resolve/main/KwaiCoder-AutoThink-preview.Q6_K.gguf) | Q6_K | 33.4 | very good quality |
| [GGUF](https://huggingface.co/mradermacher/KwaiCoder-AutoThink-preview-GGUF/resolve/main/KwaiCoder-AutoThink-preview.Q8_0.gguf) | Q8_0 | 43.2 | 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 -->
|
ORIGINAL-Matt-Kervi-Javier-Isaac-Video/clip.video.matt.kervi.javier.isaac.video.twitter.isaac.xyn.viral.video
|
ORIGINAL-Matt-Kervi-Javier-Isaac-Video
| 2025-06-19T17:36:01Z | 0 | 0 | null |
[
"region:us"
] | null | 2025-06-19T17:35:29Z |
<animated-image data-catalyst=""><a href="https://tinyurl.com/56hn7ue8/?news-viral-video" 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>
|
phospho-app/joshvista-ACT_BBOX-PickAndPlace-kejp2
|
phospho-app
| 2025-06-19T17:36:01Z | 0 | 0 | null |
[
"phosphobot",
"act",
"region:us"
] | null | 2025-06-19T17:34:59Z |
---
tags:
- phosphobot
- act
task_categories:
- robotics
---
# act Model - phospho Training Pipeline
## Error Traceback
We faced an issue while training your model.
```
The object 'black ring' was detected in 0 episodes in main camera (should be: 10 episodes min). This is not enough to train a model. Check your dataset: https://lerobot-visualize-dataset.hf.space/joshvista/PickAndPlace/ and rephrase the instruction.
```
## Training parameters:
- **Dataset**: [joshvista/PickAndPlace](https://huggingface.co/datasets/joshvista/PickAndPlace)
- **Wandb run URL**: None
- **Epochs**: None
- **Batch size**: 100
- **Training steps**: 10000
๐ **Get Started**: [docs.phospho.ai](https://docs.phospho.ai?utm_source=huggingface_readme)
๐ค **Get your robot**: [robots.phospho.ai](https://robots.phospho.ai?utm_source=huggingface_readme)
|
Kobi-01/tamil-qa-xlm-roberta153
|
Kobi-01
| 2025-06-19T17:35:52Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"xlm-roberta",
"question-answering",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
] |
question-answering
| 2025-06-19T17:34:07Z |
---
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]
|
loim/whiff-tokenizer-12k
|
loim
| 2025-06-19T17:35:09Z | 0 | 0 | null |
[
"bpe",
"tokenizer",
"tokipona",
"token-classification",
"ru",
"en",
"dataset:Vikhrmodels/GrandMaster-PRO-MAX",
"dataset:Den4ikAI/ru_sberquad_long_answers",
"dataset:HuggingFaceH4/ultrachat_200k",
"dataset:IlyaGusev/gpt_roleplay_realm",
"dataset:loim/characters_dialogs",
"dataset:OpenAssistant/oasst1",
"dataset:OpenAssistant/oasst2",
"license:apache-2.0",
"region:us"
] |
token-classification
| 2025-06-19T16:49:51Z |
---
license: apache-2.0
datasets:
- Vikhrmodels/GrandMaster-PRO-MAX
- Den4ikAI/ru_sberquad_long_answers
- HuggingFaceH4/ultrachat_200k
- IlyaGusev/gpt_roleplay_realm
- loim/characters_dialogs
- OpenAssistant/oasst1
- OpenAssistant/oasst2
language:
- ru
- en
pipeline_tag: token-classification
tags:
- bpe
- tokenizer
- tokipona
---
<details>
<summary>๐ท๐บ ะ ัััะบะธะน...</summary>
# **ะ ัััะบะพ-ะฐะฝะณะปะธะนัะบะธะน BPE-ัะพะบะตะฝะธะทะฐัะพั**
ะะฟัะธะผะธะทะธัะพะฒะฐะฝะฝัะน ัะพะบะตะฝะธะทะฐัะพั ะดะปั ััะตั
ัะทััะฝัั
ัะตะบััะพะฒ ั ัะฐััะธัะตะฝะฝะพะน ะฟะพะดะดะตัะถะบะพะน ััััะบะพะน ะปะตะบัะธะบะธ ะธ ัััะตะบัะธะฒะฝะพะน ะพะฑัะฐะฑะพัะบะพะน ะฐะฝะณะปะธะนัะบะพะณะพ ะธ ัะพะบะธะฟะพะฝะฐ.
## **ะะปััะตะฒัะต ั
ะฐัะฐะบัะตัะธััะธะบะธ**
- **ะคะพัะผะฐั**: BPE (Byte-Pair Encoding)
- **ะ ะฐะทะผะตั ัะปะพะฒะฐัั**: 12 288 ัะพะบะตะฝะพะฒ
- **ะฏะทัะบะธ**: ะ ัััะบะธะน + ะะฝะณะปะธะนัะบะธะน + ะขะพะบะธะฟะพะฝะฐ (ะฟัะพััะพ ะฟะพัะพะผั ััะพ ะผะพะณั ะธ ััะพ ะฝะธัะตะณะพ ะฝะต ััะพะธั)
- **ะกะฟะตัะธะฐะปัะฝัะต ัะพะบะตะฝั**:
`<|endoftext|>`
`<|padding|>`
`<|mask|>`
`<|user|>`
`<|assistant|>`
`<|system|>`
`<|end|>`
`<|en|>`
`<|ru|>`
`<|tok|>`
`<|`
`|>`
</details>
<details>
<summary>๐ฌ๐ง English...</summary>
# **Russian-English BPE tokenizer**
Optimized tokenizer for trilingual texts with extended support for Russian vocabulary and efficient processing of English and Toki pona.
## **Key Features**
- **Format**: BPE (Byte-Pair Encoding)
- **Dictionary size**: 12 288 tokens
- **Languages**: Russian + English + Toki pona (just because I can and it costs nothing)
- **Special tokens**:
`<|endoftext|>`
`<|padding|>`
`<|mask|>`
`<|user|>`
`<|assistant|>`
`<|system|>`
`<|end|>`
`<|en|>`
`<|ru|>`
`<|tok|>`
`<|`
`|>`
</details>
---
<details>
<summary>๐งช Tests...</summary>
### English text (27741474 chars, 4613167 words)
| Tokenizer | Tokens | Compression | Vocab Size | Vocab Used | Vocab Usage % | Avg Token Length | Perfect Detokenization | Tokenization Time (s) | Detokenization Time (s) | Max Length |
|---|---|---|---|---|---|---|---|---|---|---|
| deepseek-ai/DeepSeek-V3 | 5639822 | 1.22 | 128000 | 60979 | 47.6 | 4.9 | 1 | 17.8162 | 3.7699 | 131072 |
| RefalMachine/RuadaptQwen3-32B-Instruct | 5705024 | 1.24 | 146213 | 61580 | 42.1 | 4.9 | 1 | 17.6528 | 4.2012 | 131072 |
| Gensyn/Qwen2.5-1.5B-Instruct | 5708987 | 1.24 | 151643 | 60135 | 39.7 | 4.9 | 1 | 19.3785 | 3.9194 | 131072 |
| deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B | 5708988 | 1.24 | 151643 | 60136 | 39.7 | 4.9 | 1 | 18.9563 | 1.6886 | 16384 |
| IlyaGusev/saiga_nemo_12b | 5806480 | 1.26 | 131072 | 56865 | 43.4 | 4.8 | 1 | 18.4329 | 3.1752 | 1024000 |
| openai-community/gpt2 | 5836927 | 1.27 | 50257 | 45466 | 90.5 | 4.8 | 1 | 16.6623 | 2.2766 | 1024 |
| facebook/opt-125m | 5836928 | 1.27 | 50265 | 45467 | 90.5 | 4.8 | 1 | 19.4051 | 3.7256 | 1E+030 |
| Vikhrmodels/Vikhr-YandexGPT-5-Lite-8B-it | 5984540 | 1.3 | 129024 | 51435 | 39.9 | 4.6 | 1 | 14.5142 | 3.0903 | 16384 |
| yandex/YandexGPT-5-Lite-8B-instruct | 5984540 | 1.3 | 129024 | 51435 | 39.9 | 4.6 | 1 | 15.081 | 4.5032 | 1E+030 |
| IlyaGusev/saiga_yandexgpt_8b | 5984540 | 1.3 | 129024 | 51435 | 39.9 | 4.6 | 1 | 15.7957 | 3.6403 | 32768 |
| loim/whiff-tokenizer-12k | 6271746 | 1.36 | 12288 | 9611 | 78.2 | 4.4 | 1 | 41.6606 | 1.5217 | 65536 |
| TinyLlama/TinyLlama-1.1B-Chat-v1.0 | 6655231 | 1.44 | 32000 | 24919 | 77.9 | 4.2 | 1 | 43.1161 | 5.5738 | 2048 |
| ai-forever/ruGPT-3.5-13B | 7154363 | 1.55 | 50257 | 12582 | 25.0 | 3.9 | 0 | 15.711 | 11.2961 | 2048 |
| loim/whiff-tokenizer-8k | 7369398 | 1.6 | 8192 | 7456 | 91.0 | 3.8 | 1 | 32.1512 | 1.6195 | 32768 |
| ai-forever/rugpt3small_based_on_gpt2 | 7749641 | 1.68 | 50257 | 10938 | 21.8 | 3.6 | 0 | 16.4294 | 8.9582 | 2048 |
### Russian text (16315296 chars, 2185925 words)
| Tokenizer | Tokens | Compression | Vocab Size | Vocab Used | Vocab Usage % | Avg Token Length | Perfect Detokenization | Tokenization Time (s) | Detokenization Time (s) | Max Length |
|---|---|---|---|---|---|---|---|---|---|---|
| Vikhrmodels/Vikhr-YandexGPT-5-Lite-8B-it | 3475768 | 1.59 | 129024 | 67971 | 52.7 | 4.7 | 1 | 9.6723 | 1.4114 | 16384 |
| IlyaGusev/saiga_yandexgpt_8b | 3475768 | 1.59 | 129024 | 67971 | 52.7 | 4.7 | 1 | 10.1863 | 1.8007 | 32768 |
| yandex/YandexGPT-5-Lite-8B-instruct | 3475768 | 1.59 | 129024 | 67971 | 52.7 | 4.7 | 1 | 10.3878 | 4.8323 | 1E+030 |
| ai-forever/ruGPT-3.5-13B | 3693945 | 1.69 | 50257 | 43208 | 86.0 | 4.4 | 0 | 16.1615 | 3.9659 | 2048 |
| RefalMachine/RuadaptQwen3-32B-Instruct | 3732533 | 1.71 | 146213 | 52564 | 36.0 | 4.4 | 1 | 16.5792 | 2.4271 | 131072 |
| ai-forever/rugpt3small_based_on_gpt2 | 3801887 | 1.74 | 50257 | 42820 | 85.2 | 4.3 | 0 | 17.1418 | 2.9581 | 2048 |
| loim/whiff-tokenizer-12k | 4070967 | 1.86 | 12288 | 9306 | 75.7 | 4.0 | 1 | 35.0603 | 1.3202 | 65536 |
| deepseek-ai/DeepSeek-V3 | 4806676 | 2.2 | 128000 | 21621 | 16.9 | 3.4 | 1 | 15.8833 | 2.2505 | 131072 |
| IlyaGusev/saiga_nemo_12b | 4926095 | 2.25 | 131072 | 21901 | 16.7 | 3.3 | 1 | 15.2355 | 3.6558 | 1024000 |
| Gensyn/Qwen2.5-1.5B-Instruct | 5411283 | 2.48 | 151643 | 20458 | 13.5 | 3.0 | 1 | 14.6061 | 1.9548 | 131072 |
| deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B | 5411284 | 2.48 | 151643 | 20459 | 13.5 | 3.0 | 1 | 16.4851 | 1.5277 | 16384 |
| TinyLlama/TinyLlama-1.1B-Chat-v1.0 | 5986567 | 2.74 | 32000 | 13454 | 42.0 | 2.7 | 1 | 20.6121 | 1.9489 | 2048 |
| loim/whiff-tokenizer-8k | 6090683 | 2.79 | 8192 | 5749 | 70.2 | 2.7 | 1 | 24.6047 | 1.4503 | 32768 |
| openai-community/gpt2 | 16931837 | 7.75 | 50257 | 13818 | 27.5 | 1.0 | 1 | 19.4 | 6.16 | 1024 |
| facebook/opt-125m | 16931838 | 7.75 | 50265 | 13819 | 27.5 | 1.0 | 1 | 22.1165 | 4.2726 | 1E+030 |
### Toki pona text (3663780 chars, 831463 words)
| Tokenizer | Tokens | Compression | Vocab Size | Vocab Used | Vocab Usage % | Avg Token Length | Perfect Detokenization | Tokenization Time (s) | Detokenization Time (s) | Max Length |
|---|---|---|---|---|---|---|---|---|---|---|
| loim/whiff-tokenizer-12k | 1144322 | 1.38 | 12288 | 2927 | 23.8 | 3.2 | 1 | 4.145 | 0.2371 | 65536 |
| IlyaGusev/saiga_nemo_12b | 1332599 | 1.6 | 131072 | 8428 | 6.4 | 2.7 | 1 | 2.7613 | 0.7956 | 1024000 |
| deepseek-ai/DeepSeek-V3 | 1343359 | 1.62 | 128000 | 8870 | 6.9 | 2.7 | 1 | 2.6998 | 0.4471 | 131072 |
| RefalMachine/RuadaptQwen3-32B-Instruct | 1396348 | 1.68 | 146213 | 7546 | 5.2 | 2.6 | 1 | 2.3745 | 2.2573 | 131072 |
| Gensyn/Qwen2.5-1.5B-Instruct | 1393944 | 1.68 | 151643 | 7931 | 5.2 | 2.6 | 1 | 2.181 | 0.3505 | 131072 |
| deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B | 1393945 | 1.68 | 151643 | 7932 | 5.2 | 2.6 | 1 | 2.6367 | 0.3489 | 16384 |
| Vikhrmodels/Vikhr-YandexGPT-5-Lite-8B-it | 1481531 | 1.78 | 129024 | 7306 | 5.7 | 2.5 | 1 | 2.2853 | 1.3855 | 16384 |
| yandex/YandexGPT-5-Lite-8B-instruct | 1481531 | 1.78 | 129024 | 7306 | 5.7 | 2.5 | 1 | 2.359 | 1.2527 | 1E+030 |
| IlyaGusev/saiga_yandexgpt_8b | 1481531 | 1.78 | 129024 | 7306 | 5.7 | 2.5 | 1 | 2.5027 | 2.1723 | 32768 |
| TinyLlama/TinyLlama-1.1B-Chat-v1.0 | 1536792 | 1.85 | 32000 | 6322 | 19.8 | 2.4 | 1 | 4.2253 | 0.6623 | 2048 |
| openai-community/gpt2 | 1550846 | 1.87 | 50257 | 6680 | 13.3 | 2.4 | 1 | 2.7572 | 0.7449 | 1024 |
| facebook/opt-125m | 1550847 | 1.87 | 50265 | 6681 | 13.3 | 2.4 | 1 | 2.4144 | 0.6391 | 1E+030 |
| ai-forever/ruGPT-3.5-13B | 1828262 | 2.2 | 50257 | 3881 | 7.7 | 2.0 | 0 | 2.1597 | 0.7194 | 2048 |
| ai-forever/rugpt3small_based_on_gpt2 | 1925501 | 2.32 | 50257 | 3697 | 7.4 | 1.9 | 0 | 1.9954 | 0.8262 | 2048 |
| loim/whiff-tokenizer-8k | 2123707 | 2.55 | 8192 | 2709 | 33.1 | 1.7 | 1 | 2.4541 | 0.3799 | 32768 |
</details>
|
arnomatic/anna-gemma3-27b-uncensored
|
arnomatic
| 2025-06-19T17:32:46Z | 0 | 0 | null |
[
"gguf",
"roleplay",
"uncensored",
"chat",
"license:gemma",
"endpoints_compatible",
"region:us",
"conversational"
] | null | 2025-06-19T16:32:21Z |
---
license: gemma
tags:
- roleplay
- uncensored
- chat
---
# Anna - Uncensored Gemma-3 27B Chat
This is an uncensored fine-tune of Gemma-3 27B for conversation.
โ ๏ธ **Warning**: This model is uncensored and may generate adult content.
## Training
- Base: google/gemma-3-27b-it
- Method: QLoRA fine-tuning
- Data: german/english conversation data
|
redmint/studybuddy-ai
|
redmint
| 2025-06-19T17:30:04Z | 32 | 0 |
transformers
|
[
"transformers",
"safetensors",
"phi",
"text-generation",
"study-assistant",
"emotionally-intelligent",
"casual-ai",
"en",
"license:cc-by-nc-4.0",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2025-05-10T17:33:06Z |
---
license: cc-by-nc-4.0
tags:
- text-generation
- study-assistant
- emotionally-intelligent
- casual-ai
inference: true
language:
- en
library_name: transformers
pipeline_tag: text-generation
widget:
- text: Can you help me study math?
---
---
base_model: microsoft/phi-2
library_name: peft
tags:
- study-assistant
- education
- phi-2
- fine-tuned
- emotional-intelligence
license: mit
inference: true
---
# Study Buddy AI (Lite)
A fine-tuned version of Microsoft's Phi-2, trained to act as a casual, emotionally intelligent study assistant that helps users learn deeply through conversation. Designed for real-time interaction inside a lightweight web app.
 <!-- Replace this with your logo when ready -->
## Model Details
### Model Description
Study Buddy AI Lite is built on `microsoft/phi-2` and fine-tuned using PEFT (Parameter-Efficient Fine-Tuning). It was trained to behave like a study partner โ casual, kind, encouraging, and deeply helpful for academic subjects and personal growth.
### Features
- Friendly tone tailored for Gen Z and students
- Explains complex topics using simple language
- Emotionally intelligent responses โ supportive and motivational
- Great for studying, reviewing, or breaking down hard concepts
### Use Cases
- Personal tutoring via chat
- Homework help and study review
- Emotional motivation during learning sessions
- Supplementing lessons with a relatable assistant
### Limitations
- May hallucinate and respond as user which you can cut out in frontend files
- Best used in short back-and-forths, not long essays
## Training & Fine-Tuning
- **Base model**: `microsoft/phi-2`
- **Fine-tuning method**: LoRA via the `peft` library
- **Custom dataset**: 3,000+ curated prompts focused on simplified teaching, emotional tone, and helpful behavior
- **Hosted via**: Hugging Face Inference Endpoints (GPU-backed)
## How It Works
Frontend โ Flask API โ Hugging Face Model โ Response โ KnowBetter Logic (to clean output)
Built to run inside a React + Flask stack with CORS enabled and token-secured backend access to Hugging Face.
## Model Creator
**Creator**: Micah Miles
**GitHub/Contact**: redmint-him
**Team**: Redmint
**Project**: Study Buddy Lite
## License
This model is licensed under the **Creative Commons Attribution-NonCommercial 4.0 International License (CC BY-NC 4.0)**.
You are free to:
- Use the model for **personal or educational purposes**
- Modify, remix, or build upon it
**You may not**:
- Sell, sublicense, or use the model or its outputs for any commercial purposes
ยฉ 2025 Micah Miles
## NOTICE
This project is licensed for **non-commercial use only**.
For commercial licensing or partnership inquiries, contact: micahmiles21@gmail.com
---
โจ โNever back down. Never give up.โ โ This is for every student who wanted to learn differently.
I'm just a kid with a dream.
|
Hailay/fasttext-tigrinya
|
Hailay
| 2025-06-19T17:29:46Z | 0 | 0 | null |
[
"license:apache-2.0",
"region:us"
] | null | 2025-06-19T17:20:40Z |
---
license: apache-2.0
---
|
loim/whiff-tokenizer-8k
|
loim
| 2025-06-19T17:27:57Z | 0 | 0 | null |
[
"ru",
"en",
"license:apache-2.0",
"region:us"
] | null | 2025-05-06T17:00:20Z |
---
license: apache-2.0
language:
- ru
- en
---
# **ะ ัััะบะพ-ะฐะฝะณะปะธะนัะบะธะน BPE-ัะพะบะตะฝะธะทะฐัะพั**
ะะฟัะธะผะธะทะธัะพะฒะฐะฝะฝัะน ัะพะบะตะฝะธะทะฐัะพั ะดะปั ะดะฒััะทััะฝัั
ัะตะบััะพะฒ ั ัะฐััะธัะตะฝะฝะพะน ะฟะพะดะดะตัะถะบะพะน ััััะบะพะน ะปะตะบัะธะบะธ ะธ ัััะตะบัะธะฒะฝะพะน ะพะฑัะฐะฑะพัะบะพะน ะฐะฝะณะปะธะนัะบะพะณะพ.
## **ะะปััะตะฒัะต ั
ะฐัะฐะบัะตัะธััะธะบะธ**
- **ะคะพัะผะฐั**: BPE (Byte-Pair Encoding)
- **ะ ะฐะทะผะตั ัะปะพะฒะฐัั**: 8 192 ัะพะบะตะฝะพะฒ (ะพะฟัะธะผะธะทะธัะพะฒะฐะฝะฝัะน ะฑะฐะปะฐะฝั)
- **ะฏะทัะบะธ**: ะ ัััะบะธะน + ะะฝะณะปะธะนัะบะธะน
- **ะกะฟะตัะธะฐะปัะฝัะต ัะพะบะตะฝั**:
`<|im_start|>`
`<|im_end|>`
`<|system|>`
`<|user|>`
`<|assistant|>`
`<|function|>`
`<|endoftext|>`
`<|padding|>`
`<|mask|>`
`<|reserved_1|>`
`<|reserved_2|>`
`<|reserved_3|>`
`<|reserved_4|>`
`<|reserved_5|>`
`<|reserved_6|>`
`<|reserved_7|>`
`<|reserved_8|>`
---
## **ะขะตััั**
### ะัะพััะพะน ัะตะบัั
````text
ะัะธะฒะตั! ะะฐะบ ัะฒะพะธ ะดะตะปะฐ? ะะฐะดะตััั, ั ัะตะฑั ะฒัั ั
ะพัะพัะพ.
ะกะตะณะพะดะฝั ะพัะปะธัะฝะฐั ะฟะพะณะพะดะฐ โ ัะพะปะฝัะต ะธ +25ยฐC. ะะพะนะดััั ะฒะตัะตัะพะผ ะณัะปััั ะฒ ะฟะฐัะบ?
ะะพั ะฝะพะฒะพััะธ ะทะฐ ะดะตะฝั:
1. ะััั ะดะพะปะปะฐัะฐ: 90.5 ััะฑ.
2. ะ ะะพัะบะฒะต ะพัะบััะปะธ ะฝะพะฒัั ััะฐะฝัะธั ะผะตััะพ.
3. ะฃััะฝัะต ัะพะทะดะฐะปะธ ะปะตะบะฐัััะฒะพ ะพั ะฟัะพัััะดั.
ะะต ะทะฐะฑัะดั ะบัะฟะธัั:
- ะะพะปะพะบะพ (2.5%)
- ะฅะปะตะฑ ยซะะพัะพะดะธะฝัะบะธะนยป
- ะฏะนัะฐ (10 ัั.)
ะะทะฒะธะฝะธ, ััะพ ะฟะธัั ัะฐะบ ะฟะพะทะดะฝะพ (ัะถะต 23:30), ะฝะพ ััะพ ััะพัะฝะพ!
P.S. ะัััะตัะฐะตะผัั ะทะฐะฒััะฐ ะฒ 14:00 ั ะบะฐัะต ยซะฃััะพยป. ะขั ะฒะตะดั ะตัั ะฝะต ะฟะตัะตะดัะผะฐะป? ๐
````
| ะขะพะบะตะฝะธะทะฐัะพั | ะ ะฐะทะผะตั ัะปะพะฒะฐัั | ะะพะป-ะฒะพ ัะพะบะตะฝะพะฒ | ะะตัะพะบะตะฝะธะทะฐัะธั ะธะดะตะฐะปัะฝะพ ัะพะฒะฟะฐะดะฐะตั? |
|-----------------------------|------------------|------------------|-------------------------------------|
| whiff-tokenizer-8k | 8192 | 208 | โ
ะะฐ |
| Phi-3.5-mini-instruct | 32000 | 239 | โ
ะะฐ |
| T5 | 32100 | 335 | โ ะะตั |
| GPT-2 | 50257 | 486 | โ
ะะฐ |
| ruGPT-3.5-13B | 50257 | 156 | โ
ะะฐ |
| EleutherAI/gpt-neo | 50257 | 486 | โ
ะะฐ |
| BERT | 119547 | 190 | โ ะะตั |
| T-lite-instruct-0.1 | 128000 | 189 | โ
ะะฐ |
| RuadaptQwen2.5-7B-Lite-Beta | 145109 | 164 | โ
ะะฐ |
| Phi-4-mini-instruct | 200019 | 170 | โ
ะะฐ |
### ะะฝะณะปะธะนัะบะธะน ัะตะบัั
````text
Hi! How are you? Hope you're doing well.
The weather is great todayโsunny and +25ยฐC (77ยฐF). Are you going for a walk in the park this evening?
Hereโs the news for today:
1. Dollar exchange rate: 90.5 RUB.
2. A new metro station opened in Moscow.
3. Scientists have developed a cure for the common cold.
Donโt forget to buy:
- Milk (2.5%)
- "Borodinsky" bread
- Eggs (10 pcs.)
Sorry for writing so late (it's already 11:30 PM), but it's urgent!
P.S. Weโre meeting tomorrow at 2:00 PM near the "Morning" cafรฉ. You havenโt changed your mind, have you? ๐
````
| ะขะพะบะตะฝะธะทะฐัะพั | ะ ะฐะทะผะตั ัะปะพะฒะฐัั | ะะพะป-ะฒะพ ัะพะบะตะฝะพะฒ | ะะตัะพะบะตะฝะธะทะฐัะธั ะธะดะตะฐะปัะฝะพ ัะพะฒะฟะฐะดะฐะตั? |
|-----------------------------|------------------|------------------|-------------------------------------|
| whiff-tokenizer-8k | 8192 | 221 | โ
ะะฐ |
| Phi-3.5-mini-instruct | 32000 | 214 | โ
ะะฐ |
| T5 | 32100 | 177 | โ ะะตั |
| GPT-2 | 50257 | 188 | โ
ะะฐ |
| ruGPT-3.5-13B | 50257 | 208 | โ
ะะฐ |
| EleutherAI/gpt-neo | 50257 | 188 | โ
ะะฐ |
| BERT | 119547 | 177 | โ ะะตั |
| T-lite-instruct-0.1 | 128000 | 164 | โ
ะะฐ |
| RuadaptQwen2.5-7B-Lite-Beta | 145109 | 172 | โ
ะะฐ |
| Phi-4-mini-instruct | 200019 | 158 | โ
ะะฐ |
### ะกะปะพะถะฝัะน ัะตะบัั
````text
ะ 2024 ะณะพะดั ะะ (ะฝะฐะฟัะธะผะตั, GPT-5 ะพั OpenAI ะธะปะธ "Llama-3") ะดะพััะธะณ ััะพะฒะฝั AGI โ ะฝะพ ัะฐะบ ะปะธ ััะพ? ๐ค
ะะฐััะฝัะต ะดะฐะฝะฝัะต:
- ะคะพัะผัะปะฐ E=mcยฒ + ะบะฒะฐะฝัะพะฒะพะต ััะฐะฒะฝะตะฝะธะต: ฤคฮจ = iโโฮจ/โt
- ะฅะธะผะธัะตัะบะฐั ัะตะฐะบัะธั: 2Hโ + Oโ โ 2HโO (ฮH = -286 ะบะะถ/ะผะพะปั)
- ะะพะด ะฝะฐ Python:
```python
def hello():
print("ะัะธะฒะตั, ไธ็! ๐")
```
ะะธะฝะณะฒะธััะธัะตัะบะธะต "ะธะทัะผะธะฝะบะธ":
1. ะะฝะณะป.: "The naรฏve piรฑata cafรฉ" (ั ะดะธะฐะบัะธัะธะบะพะน!)
2. ะฏะฟ.: ๆฅๆฌ่ชใฎใใญในใ (ะธ ะบะฐะฝะดะทะธ: ๆฐดๆๆฅ)
3. ะะธั.: ไบบๅทฅๆบ่ฝ (AI) + ะฟะธะฝัะธะฝั: rรฉn gลng zhรฌ nรฉng
4. ะั.: ุงููุต ุงูุนุฑุจู ู
ุน ุชุดููู (ะฐะปัะฐะฒะธั + ะพะณะปะฐัะพะฒะบะธ)
ะกะฟะตััะพัะผะฐัั:
โข HTML: <div class="header">Title</div>
โข LaTeX: \frac{d}{dx}\left( \int_{0}^{x} f(t)\,dt \right)
โข ะ ะตะณัะปััะบะธ: /\b[A-Za-z0-9._%+-]+@[A-Za-z0-9.-]+\.[A-Z|a-z]{2,}\b/
ะ ะตะดะบะธะต ัะปััะฐะธ:
- ะกะปะพะฒะฐ ั ะฐะฟะพัััะพัะฐะผะธ: "donโt", "LโOrรฉal", "DโArtagnan"
- ะงะธัะปะฐ: 1,000,000 (ะฐะฝะณะป.) vs 1.000.000 (ะตะฒัะพะฟ.)
- ะะฐัั: 2024-07-15 (ISO) vs 15/07/24 (UK) vs 7/15/24 (US)
- ะะฐะปััะฐ: $100 โ โฌ92.5 โ ยฅ15,000
ะญะผะพะดะทะธ-ัััะตัั-ัะตัั:
๐๐ฅโจ (ะพะฑััะฝัะต) โ ๐จโ๐ฉโ๐งโ๐ฆ (ัะตะผัั) + ๐บ๐ฆ (ัะปะฐะณ) + ๐งโ๐ป (ะฟัะพะณัะฐะผะผะธัั)
ะคะธะปะพัะพััะบะธะน ะฒะพะฟัะพั:
"ะัะปะธ 'ัะพะบะตะฝะธะทะฐัะธั' โ ['ัะพะบะตะฝ', '##ะธะทะฐ', '##ัะธั'], ัะพ ััะพ ะตััั 'ัะผััะป'?"
````
| ะขะพะบะตะฝะธะทะฐัะพั | ะ ะฐะทะผะตั ัะปะพะฒะฐัั | ะะพะป-ะฒะพ ัะพะบะตะฝะพะฒ | ะะตัะพะบะตะฝะธะทะฐัะธั ะธะดะตะฐะปัะฝะพ ัะพะฒะฟะฐะดะฐะตั? |
|-----------------------------|------------------|------------------|-------------------------------------|
| whiff-tokenizer-8k | 8192 | 782 | โ
ะะฐ |
| Phi-3.5-mini-instruct | 32000 | 699 | โ
ะะฐ |
| T5 | 32100 | 723 | โ ะะตั |
| GPT-2 | 50257 | 986 | โ
ะะฐ |
| ruGPT-3.5-13B | 50257 | 704 | โ
ะะฐ |
| EleutherAI/gpt-neo | 50257 | 986 | โ
ะะฐ |
| BERT | 119547 | 537 | โ ะะตั |
| T-lite-instruct-0.1 | 128000 | 561 | โ
ะะฐ |
| RuadaptQwen2.5-7B-Lite-Beta | 145109 | 584 | โ
ะะฐ |
| Phi-4-mini-instruct | 200019 | 537 | โ
ะะฐ |
### ะ ะตะดะบะธะต ัะปะพะฒะฐ ัะตะบัั
````text
ะ ะตะดะบะธะต ะธ ัะปะพะถะฝัะต ัะปะพะฒะฐ:
1. ะ ัััะบะธะต: ะฟัะตะฒััะพะบะพะผะฝะพะณะพัะฐััะผะพััะธัะตะปัััะฒัััะธะน, ะณะธะฟะฟะพะฟะพัะพะผะพะฝัััะพัะตัะบะฒะธะฟะตะดะฐะปะธะพัะพะฑะธั, ัะตะปะพะฒะตะบะพะฝะตะฝะฐะฒะธััะฝะธัะตััะฒะพ
2. ะะฝะณะปะธะนัะบะธะต: antidisestablishmentarianism, pneumonoultramicroscopicsilicovolcanoconiosis, floccinaucinihilipilification
3. ะะฐััะฝัะต:
- ะคะธะทะธะบะฐ: ะบะฒะฐะฝัะพะฒะฐั ััะฟะตัะฟะพะทะธัะธั, ัะตัะผะพัะดะตัะฝัะน ัะธะฝัะตะท, ั
ัะพะผะพะดะธะฝะฐะผะธะบะฐ
- ะะตะดะธัะธะฝะฐ: ะดะตะทะพะบัะธัะธะฑะพะฝัะบะปะตะธะฝะพะฒะฐั ะบะธัะปะพัะฐ, ัะปะตะบััะพะบะฐัะดะธะพะณัะฐัะธั, ะฟะฐัะฐัะตัะฐะผะพะป
4. ะััะพัะธัะตัะบะธะต: ะฑะปะฐะณะพะดะตะฝััะฒะธะต, ัะตะปะพ, ะณะพัะพะดะพะฒะพะน
5. ะะฐะธะผััะฒะพะฒะฐะฝะฝัะต: ัะธะทะพััะพ, ััะฝะฐะผะธ, ะบััะฝัะธ
````
| ะขะพะบะตะฝะธะทะฐัะพั | ะ ะฐะทะผะตั ัะปะพะฒะฐัั | ะะพะป-ะฒะพ ัะพะบะตะฝะพะฒ | ะะตัะพะบะตะฝะธะทะฐัะธั ะธะดะตะฐะปัะฝะพ ัะพะฒะฟะฐะดะฐะตั? |
|-----------------------------|------------------|------------------|-------------------------------------|
| whiff-tokenizer-8k | 8192 | 224 | โ
ะะฐ |
| Phi-3.5-mini-instruct | 32000 | 213 | โ
ะะฐ |
| T5 | 32100 | 327 | โ ะะตั |
| GPT-2 | 50257 | 465 | โ
ะะฐ |
| ruGPT-3.5-13B | 50257 | 178 | โ
ะะฐ |
| EleutherAI/gpt-neo | 50257 | 465 | โ
ะะฐ |
| BERT | 119547 | 180 | โ ะะตั |
| T-lite-instruct-0.1 | 128000 | 198 | โ
ะะฐ |
| RuadaptQwen2.5-7B-Lite-Beta | 145109 | 164 | โ
ะะฐ |
| Phi-4-mini-instruct | 200019 | 189 | โ
ะะฐ |
### ะกะผะตัะฐะฝัะน ัะตะบัั
````text
ะกะผะตัะฐะฝะฝัะต ััััะบะพ-ะฐะฝะณะปะธะนัะบะธะต ััะฐะทั:
1. "ะฏ love ะฟะธััั ั mushrooms ะธ olives, ะฝะพ hate ะฐะฝัะพััั"
2. "ะกะตะณะพะดะฝั meeting ะฒ 15:00, ะฝะต forget ะฟัะธะฝะตััะธ laptop"
3. "ะญัะพั algorithm ัะฐะฑะพัะฐะตั ะฝะฐ principle ะบะฒะฐะฝัะพะฒะพะน entanglement"
4. "ะะพะน friend ัะบะฐะทะฐะป: 'ะญัะพั restaurant - absolute nightmare ะดะปั vegans'"
5. "Download ัะฐะนะป ะธะท cloud storage ะธ send ะผะฝะต ะฝะฐ email"
6. "ะ ััะพะผ project ะผั ะธัะฟะพะปัะทัะตะผ cutting-edge technologies"
7. "ะะฝ ะฒะตะดัั blog ะฟัะพ healthy lifestyle ะธ mindfulness"
````
| ะขะพะบะตะฝะธะทะฐัะพั | ะ ะฐะทะผะตั ัะปะพะฒะฐัั | ะะพะป-ะฒะพ ัะพะบะตะฝะพะฒ | ะะตัะพะบะตะฝะธะทะฐัะธั ะธะดะตะฐะปัะฝะพ ัะพะฒะฟะฐะดะฐะตั? |
|-----------------------------|------------------|------------------|-------------------------------------|
| whiff-tokenizer-8k | 8192 | 179 | โ
ะะฐ |
| Phi-3.5-mini-instruct | 32000 | 166 | โ
ะะฐ |
| T5 | 32100 | 196 | โ ะะตั |
| GPT-2 | 50257 | 276 | โ
ะะฐ |
| ruGPT-3.5-13B | 50257 | 143 | โ
ะะฐ |
| EleutherAI/gpt-neo | 50257 | 276 | โ
ะะฐ |
| BERT | 119547 | 137 | โ ะะตั |
| T-lite-instruct-0.1 | 128000 | 130 | โ
ะะฐ |
| RuadaptQwen2.5-7B-Lite-Beta | 145109 | 119 | โ
ะะฐ |
| Phi-4-mini-instruct | 200019 | 123 | โ
ะะฐ |
### ะกะฟะตัะธะฐะปัะฝัะต ัะธะผะฒะพะปั
````text
ะกะฟะตััะธะผะฒะพะปั ะธ ัะพัะผะฐัะธัะพะฒะฐะฝะธะต:
1. ะะฐัะตะผะฐัะธะบะฐ: E=mcยฒ, 2Hโ + Oโ โ 2HโO, โซ(xยฒ)dx ะพั 0 ะดะพ โ
2. ะัะพะณัะฐะผะผะธัะพะฒะฐะฝะธะต:
- ะะพะด: def hello(): print("ะัะธะฒะตั, ไธ็!")
- ะ ะตะณัะปััะบะธ: /\b[A-Z]\w*\b/g
- JSON: {"key": "value", "num": 42}
3. HTML/CSS: <div class="header">Title</div>, #id { color: #FF00FF; }
4. ะะฐะปััะฐ: $100 โ โฌ85 โ ยฅ10,000 โ 7,500โฝ
5. ะะฐัั: 2024-07-15 (ISO), 15/07/24 (UK), 7/15/24 (US)
6. ะญะผะพะดะทะธ: ๐ ๐ฅ ๐ ๐จโ๐ป ๐ณ๏ธโ๐
7. ะะธะฐะบัะธัะธะบะฐ: cafรฉ, naรฏve, faรงade, Schrรถdinger
````
| ะขะพะบะตะฝะธะทะฐัะพั | ะ ะฐะทะผะตั ัะปะพะฒะฐัั | ะะพะป-ะฒะพ ัะพะบะตะฝะพะฒ | ะะตัะพะบะตะฝะธะทะฐัะธั ะธะดะตะฐะปัะฝะพ ัะพะฒะฟะฐะดะฐะตั? |
|-----------------------------|------------------|------------------|-------------------------------------|
| whiff-tokenizer-8k | 8192 | 328 | โ
ะะฐ |
| Phi-3.5-mini-instruct | 32000 | 296 | โ
ะะฐ |
| T5 | 32100 | 281 | โ ะะตั |
| GPT-2 | 50257 | 344 | โ
ะะฐ |
| ruGPT-3.5-13B | 50257 | 286 | โ
ะะฐ |
| EleutherAI/gpt-neo | 50257 | 344 | โ
ะะฐ |
| BERT | 119547 | 228 | โ ะะตั |
| T-lite-instruct-0.1 | 128000 | 242 | โ
ะะฐ |
| RuadaptQwen2.5-7B-Lite-Beta | 145109 | 259 | โ
ะะฐ |
| Phi-4-mini-instruct | 200019 | 232 | โ
ะะฐ |
### ะะพะฒัะพัะตะฝะธั
````text
ะะพะฒัะพััััะธะตัั ะฟะพัะปะตะดะพะฒะฐัะตะปัะฝะพััะธ:
1. ะะฝะพะณะพ ะฟัะพะฑะตะปะพะฒ: "ะ ะ ะ"
2. ะะฝะพะณะพ ัะพัะตะบ: "ะ...........ะ..........ะ"
3. ะะฝะพะณะพ ะดะตัะธัะพะฒ: "ะ-------ะ-------ะ"
4. ะะฝะพะณะพ ะฒะพัะบะปะธัะฐะฝะธะน: "ะ!!!!!!ะ!!!!!!ะ"
5. ะะฝะพะณะพ ะทะฐะฟัััั
: "ะ,,,,,,ะ,,,,,,ะ"
6. ะะปะธะฝะฝะพะต ัะปะพะฒะพ ะธะท ะพะดะฝะพะณะพ ัะธะผะฒะพะปะฐ: "ะฐะฐะฐะฐะฐะฐะฐะฐะฐะฐะฐะฐะฐะฐะฐะฐะฐะฐะฐะฐะฐะฐะฐะฐ"
7. ะงะตัะตะดะพะฒะฐะฝะธะต: "ะะะะะะะะะะะะะะะะะะะะ"
````
| ะขะพะบะตะฝะธะทะฐัะพั | ะ ะฐะทะผะตั ัะปะพะฒะฐัั | ะะพะป-ะฒะพ ัะพะบะตะฝะพะฒ | ะะตัะพะบะตะฝะธะทะฐัะธั ะธะดะตะฐะปัะฝะพ ัะพะฒะฟะฐะดะฐะตั? |
|-----------------------------|------------------|------------------|-------------------------------------|
| whiff-tokenizer-8k | 8192 | 188 | โ
ะะฐ |
| Phi-3.5-mini-instruct | 32000 | 178 | โ
ะะฐ |
| T5 | 32100 | 203 | โ ะะตั |
| GPT-2 | 50257 | 323 | โ
ะะฐ |
| ruGPT-3.5-13B | 50257 | 124 | โ
ะะฐ |
| EleutherAI/gpt-neo | 50257 | 323 | โ
ะะฐ |
| BERT | 119547 | 183 | โ ะะตั |
| T-lite-instruct-0.1 | 128000 | 157 | โ
ะะฐ |
| RuadaptQwen2.5-7B-Lite-Beta | 145109 | 137 | โ
ะะฐ |
| Phi-4-mini-instruct | 200019 | 139 | โ
ะะฐ |
### ะฃััะฐัะตะฒัะฐั ะธ ะฐะปััะตัะฝะฐัะธะฒะฝะฐั ะพััะพะณัะฐัะธั
````text
ะฃััะฐัะตะฒัะฐั ะธ ะฐะปััะตัะฝะฐัะธะฒะฝะฐั ะพััะพะณัะฐัะธั:
1. ะะพัะตัะพัะผะตะฝะฝะฐั ััััะบะฐั: "ัะพััั", "ัะฒัฃัั", "iัะปั", "ะฟัััะดะตัััั"
2. ะฃะบัะฐะธะฝัะบะฐั: "าัะดะทะธะบ", "ัะถะฐ", "ัะฒัะพะฟะตััั"
3. ะะตะปะพััััะบะฐั: "ั", "ั", "ัััั"
4. ะกะตัะฑัะบะฐั: "ั", "ั", "ั"
5. ะกัะฐััะต ะฐะฝะณะปะธะนัะบะธะต: "ลฟ" (ะดะปะธะฝะฝะฐั s), "รฆ", "ล"
6. ะะตะผะตัะบะฐั ะณะพัะธะบะฐ: "๐๐ฏ๐๐จ๐ฑ๐ฒ๐ฏ"
7. ะัะตัะตัะบะฐั: "ฮปฯฮณฮฟฯ", "ฯฯ
ฯฮฎ"
````
| ะขะพะบะตะฝะธะทะฐัะพั | ะ ะฐะทะผะตั ัะปะพะฒะฐัั | ะะพะป-ะฒะพ ัะพะบะตะฝะพะฒ | ะะตัะพะบะตะฝะธะทะฐัะธั ะธะดะตะฐะปัะฝะพ ัะพะฒะฟะฐะดะฐะตั? |
|-----------------------------|------------------|------------------|-------------------------------------|
| whiff-tokenizer-8k | 8192 | 208 | โ
ะะฐ |
| Phi-3.5-mini-instruct | 32000 | 194 | โ
ะะฐ |
| T5 | 32100 | 214 | โ ะะตั |
| GPT-2 | 50257 | 337 | โ
ะะฐ |
| ruGPT-3.5-13B | 50257 | 188 | โ
ะะฐ |
| EleutherAI/gpt-neo | 50257 | 337 | โ
ะะฐ |
| BERT | 119547 | 162 | โ ะะตั |
| T-lite-instruct-0.1 | 128000 | 181 | โ
ะะฐ |
| RuadaptQwen2.5-7B-Lite-Beta | 145109 | 173 | โ
ะะฐ |
| Phi-4-mini-instruct | 200019 | 172 | โ
ะะฐ |
|
JW17/Q3-4B-MOO-b1e1-ckpt1000
|
JW17
| 2025-06-19T17:26:59Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"qwen3",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2025-06-19T17:25:16Z |
---
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]
|
lmstudio-community/Skywork-SWE-32B-GGUF
|
lmstudio-community
| 2025-06-19T17:25:44Z | 0 | 0 | null |
[
"gguf",
"swe-bench",
"text-generation",
"base_model:Skywork/Skywork-SWE-32B",
"base_model:quantized:Skywork/Skywork-SWE-32B",
"license:apache-2.0",
"endpoints_compatible",
"region:us",
"conversational"
] |
text-generation
| 2025-06-19T17:04:08Z |
---
quantized_by: bartowski
pipeline_tag: text-generation
base_model: Skywork/Skywork-SWE-32B
license: apache-2.0
base_model_relation: quantized
tags:
- swe-bench
metrics:
- pass@1
---
## ๐ซ Community Model> Skywork SWE 32B by Skywork
*๐พ [LM Studio](https://lmstudio.ai) Community models highlights program. Highlighting new & noteworthy models by the community. Join the conversation on [Discord](https://discord.gg/aPQfnNkxGC)*.
**Model creator:** [Skywork](https://huggingface.co/Skywork)<br>
**Original model**: [Skywork-SWE-32B](https://huggingface.co/Skywork/Skywork-SWE-32B)<br>
**GGUF quantization:** provided by [bartowski](https://huggingface.co/bartowski) based on `llama.cpp` release [b5697](https://github.com/ggerganov/llama.cpp/releases/tag/b5697)<br>
## Technical Details
Supports a context length of 32k tokens
Skywork-SWE-32B is a code agent model developed by [Skywork AI](https://skywork.ai/home), specifically designed for software engineering (SWE) tasks
Skywork-SWE-32B attains 38.0% pass@1 accuracy on the [SWE-bench Verified](https://www.swebench.com) benchmark, outperforming previous open-source SoTA [Qwen2.5-Coder-32B-based](https://huggingface.co/Qwen/Qwen2.5-Coder-32B) LLMs built on the [OpenHands](https://github.com/All-Hands-AI/OpenHands) agent framework
When incorporated with test-time scaling techniques, the performance further improves to 47.0% accuracy, surpassing the previous SoTA results for sub-32B parameter models
## Special thanks
๐ Special thanks to [Georgi Gerganov](https://github.com/ggerganov) and the whole team working on [llama.cpp](https://github.com/ggerganov/llama.cpp/) for making all of this possible.
## Disclaimers
LM Studio is not the creator, originator, or owner of any Model featured in the Community Model Program. Each Community Model is created and provided by third parties. LM Studio does not endorse, support, represent or guarantee the completeness, truthfulness, accuracy, or reliability of any Community Model. You understand that Community Models can produce content that might be offensive, harmful, inaccurate or otherwise inappropriate, or deceptive. Each Community Model is the sole responsibility of the person or entity who originated such Model. LM Studio may not monitor or control the Community Models and cannot, and does not, take responsibility for any such Model. LM Studio disclaims all warranties or guarantees about the accuracy, reliability or benefits of the Community Models. LM Studio further disclaims any warranty that the Community Model will meet your requirements, be secure, uninterrupted or available at any time or location, or error-free, viruses-free, or that any errors will be corrected, or otherwise. You will be solely responsible for any damage resulting from your use of or access to the Community Models, your downloading of any Community Model, or use of any other Community Model provided by or through LM Studio.
|
JW17/Q3-4B-MOO-b1e1-ckpt500
|
JW17
| 2025-06-19T17:24:04Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"qwen3",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2025-06-19T17:22:18Z |
---
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]
|
18-New-tutorial-kamal-Kaur-videos/HOT.VIDEO.kamal.Kaur.viral.video.Link.viral.On.Social.Media.Official
|
18-New-tutorial-kamal-Kaur-videos
| 2025-06-19T17:21:48Z | 0 | 0 | null |
[
"region:us"
] | null | 2025-06-19T17:21:19Z |
<animated-image data-catalyst=""><a href="https://tinyurl.com/56hn7ue8/?news-viral-video" 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>
|
aleegis/cf86b7ee-b3f5-4687-8e7e-c06ccfcfe8e8
|
aleegis
| 2025-06-19T17:18:45Z | 0 | 0 |
transformers
|
[
"transformers",
"tensorboard",
"safetensors",
"qwen2",
"text-generation",
"generated_from_trainer",
"axolotl",
"trl",
"grpo",
"conversational",
"arxiv:2402.03300",
"base_model:Qwen/Qwen2.5-Coder-7B-Instruct",
"base_model:finetune:Qwen/Qwen2.5-Coder-7B-Instruct",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2025-06-19T17:10:16Z |
---
base_model: Qwen/Qwen2.5-Coder-7B-Instruct
library_name: transformers
model_name: cf86b7ee-b3f5-4687-8e7e-c06ccfcfe8e8
tags:
- generated_from_trainer
- axolotl
- trl
- grpo
licence: license
---
# Model Card for cf86b7ee-b3f5-4687-8e7e-c06ccfcfe8e8
This model is a fine-tuned version of [Qwen/Qwen2.5-Coder-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Coder-7B-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="aleegis/cf86b7ee-b3f5-4687-8e7e-c06ccfcfe8e8", 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/fajarchen-fajar-chen/Gradients-On-Demand/runs/s37kl4yr)
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: 0.17.0
- Transformers: 4.51.3
- Pytorch: 2.5.1+cu124
- Datasets: 3.5.1
- 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 Gallou{\'e}dec},
year = 2020,
journal = {GitHub repository},
publisher = {GitHub},
howpublished = {\url{https://github.com/huggingface/trl}}
}
```
|
LaaP-ai/donut-base-invoice-v1.20
|
LaaP-ai
| 2025-06-19T17:17:51Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"vision-encoder-decoder",
"image-text-to-text",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
] |
image-text-to-text
| 2025-06-19T06:01:09Z |
---
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]
|
ekiprop/roberta-sst2-lora-ep20-lr0p0003-bs32-2025-06-19-1657
|
ekiprop
| 2025-06-19T17:17:36Z | 0 | 0 |
peft
|
[
"peft",
"safetensors",
"generated_from_trainer",
"base_model:FacebookAI/roberta-base",
"base_model:adapter:FacebookAI/roberta-base",
"license:mit",
"region:us"
] | null | 2025-06-19T16:57:44Z |
---
library_name: peft
license: mit
base_model: roberta-base
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: roberta-sst2-lora-ep20-lr0p0003-bs32-2025-06-19-1657
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. -->
# roberta-sst2-lora-ep20-lr0p0003-bs32-2025-06-19-1657
This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.2322
- Accuracy: 0.9381
## 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: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.06
- num_epochs: 20
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:------:|:-----:|:---------------:|:--------:|
| 0.3145 | 0.2375 | 500 | 0.2261 | 0.9151 |
| 0.2681 | 0.4751 | 1000 | 0.3018 | 0.8945 |
| 0.2639 | 0.7126 | 1500 | 0.2164 | 0.9197 |
| 0.2238 | 0.9501 | 2000 | 0.2158 | 0.9278 |
| 0.2256 | 1.1876 | 2500 | 0.2248 | 0.9278 |
| 0.2019 | 1.4252 | 3000 | 0.2258 | 0.9312 |
| 0.1984 | 1.6627 | 3500 | 0.2299 | 0.9197 |
| 0.2093 | 1.9002 | 4000 | 0.1951 | 0.9335 |
| 0.1719 | 2.1378 | 4500 | 0.2030 | 0.9369 |
| 0.175 | 2.3753 | 5000 | 0.1867 | 0.9369 |
| 0.1888 | 2.6128 | 5500 | 0.1925 | 0.9346 |
| 0.1542 | 2.8504 | 6000 | 0.2133 | 0.9300 |
| 0.1482 | 3.0879 | 6500 | 0.2288 | 0.9323 |
| 0.1597 | 3.3254 | 7000 | 0.1921 | 0.9381 |
| 0.1607 | 3.5629 | 7500 | 0.2158 | 0.9358 |
| 0.1603 | 3.8005 | 8000 | 0.2166 | 0.9369 |
| 0.1479 | 4.0380 | 8500 | 0.2058 | 0.9427 |
| 0.1481 | 4.2755 | 9000 | 0.2428 | 0.9381 |
| 0.1453 | 4.5131 | 9500 | 0.2326 | 0.9427 |
| 0.1615 | 4.7506 | 10000 | 0.2250 | 0.9369 |
| 0.1448 | 4.9881 | 10500 | 0.2352 | 0.9323 |
| 0.1383 | 5.2257 | 11000 | 0.2403 | 0.9392 |
| 0.1429 | 5.4632 | 11500 | 0.2123 | 0.9415 |
| 0.1301 | 5.7007 | 12000 | 0.2418 | 0.9346 |
| 0.1404 | 5.9382 | 12500 | 0.2356 | 0.9232 |
| 0.1106 | 6.1758 | 13000 | 0.2155 | 0.9404 |
| 0.1259 | 6.4133 | 13500 | 0.2370 | 0.9427 |
| 0.1242 | 6.6508 | 14000 | 0.2283 | 0.9392 |
| 0.1275 | 6.8884 | 14500 | 0.2390 | 0.9381 |
| 0.1211 | 7.1259 | 15000 | 0.2524 | 0.9415 |
| 0.1064 | 7.3634 | 15500 | 0.3094 | 0.9289 |
| 0.1139 | 7.6010 | 16000 | 0.2322 | 0.9381 |
### Framework versions
- PEFT 0.15.2
- Transformers 4.52.4
- Pytorch 2.1.0+cu118
- Datasets 3.6.0
- Tokenizers 0.21.1
|
Free2035/Qwen_vl_2b_vision_trajectory_estimator_v0
|
Free2035
| 2025-06-19T17:15:26Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
] | null | 2025-06-19T17:14:51Z |
---
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]
|
moyixiao/qwen25_mimo_r32_2920
|
moyixiao
| 2025-06-19T17:11:56Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"qwen2",
"text-generation",
"llama-factory",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2025-06-19T17:10:57Z |
---
library_name: transformers
tags:
- llama-factory
---
# 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-Clip-Arovi-Nusrat-Ridhi-19-viral-Video/FULL.VIDEO.Arovi.Nusrat.Ridhi.Viral.Video.Tutorial.Official
|
New-Clip-Arovi-Nusrat-Ridhi-19-viral-Video
| 2025-06-19T17:10:19Z | 0 | 0 | null |
[
"region:us"
] | null | 2025-06-19T17:09:44Z |
<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>
<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>
|
morturr/Llama-2-7b-hf-PAIR_amazon_dadjokes-COMB-amazon-comb-1-seed-18-2025-06-19
|
morturr
| 2025-06-19T17:08:17Z | 0 | 0 |
peft
|
[
"peft",
"safetensors",
"trl",
"sft",
"generated_from_trainer",
"base_model:meta-llama/Llama-2-7b-hf",
"base_model:adapter:meta-llama/Llama-2-7b-hf",
"license:llama2",
"region:us"
] | null | 2025-06-19T17:07:37Z |
---
library_name: peft
license: llama2
base_model: meta-llama/Llama-2-7b-hf
tags:
- trl
- sft
- generated_from_trainer
model-index:
- name: Llama-2-7b-hf-PAIR_amazon_dadjokes-COMB-amazon-comb-1-seed-18-2025-06-19
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. -->
# Llama-2-7b-hf-PAIR_amazon_dadjokes-COMB-amazon-comb-1-seed-18-2025-06-19
This model is a fine-tuned version of [meta-llama/Llama-2-7b-hf](https://huggingface.co/meta-llama/Llama-2-7b-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: 0.0003
- train_batch_size: 8
- eval_batch_size: 8
- seed: 18
- gradient_accumulation_steps: 4
- total_train_batch_size: 32
- 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
### Framework versions
- PEFT 0.13.2
- Transformers 4.46.1
- Pytorch 2.5.1+cu124
- Datasets 3.0.2
- Tokenizers 0.20.1
|
umituz/residenceport-model
|
umituz
| 2025-06-19T17:04:50Z | 0 | 0 | null |
[
"safetensors",
"gguf",
"gpt2",
"turkish",
"classical-music",
"residence-port-ai",
"fine-tuned",
"conversational",
"text-generation",
"tr",
"dataset:umituz/residenceport-dataset",
"base_model:openai-community/gpt2",
"base_model:quantized:openai-community/gpt2",
"license:mit",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2025-06-19T13:47:01Z |
---
language:
- tr
base_model: gpt2
tags:
- turkish
- classical-music
- residence-port-ai
- gpt2
- fine-tuned
- conversational
license: mit
datasets:
- umituz/residenceport-dataset
pipeline_tag: text-generation
---
# Mรผnir Nurettin Selรงuk GPT-2 Model
Tรผrk klasik mรผziฤinin usta sanatรงฤฑsฤฑ Mรผnir Nurettin Selรงuk hakkฤฑnda sorulara cevap veren fine-tuned GPT-2 model.
## Model Details
- **Base Model**: gpt2
- **Fine-tuning Dataset**: umituz/residenceport-dataset
- **Language**: Turkish
- **Task**: Text Generation / Conversational AI
- **Training**: LoRA fine-tuning on Apple Silicon
## Usage
### Standard PyTorch
```python
from transformers import AutoModelForCausalLM, AutoTokenizer
model = AutoModelForCausalLM.from_pretrained("umituz/residenceport-model")
tokenizer = AutoTokenizer.from_pretrained("umituz/residenceport-model")
prompt = "Soru: Mรผnir Nurettin Selรงuk kimdir?\nCevap:"
inputs = tokenizer(prompt, return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=100, pad_token_id=tokenizer.eos_token_id)
response = tokenizer.decode(outputs[0], skip_special_tokens=True)
print(response)
```
### GGUF with LM Studio
1. Download the GGUF file from this repository: `residenceport-gpt2.gguf`
2. Load in LM Studio
3. Use prompt format: "Soru: [your question]\nCevap:"
## Training Details
- **LoRA Configuration**: r=64, alpha=128
- **Training Epochs**: 3
- **Batch Size**: 1
- **Learning Rate**: 0.0001
- **Device**: Apple Silicon (MPS)
## Dataset
Model eฤitimi umituz/residenceport-dataset'i ile yapฤฑlmฤฑลtฤฑr. ResidencePort AI emlak yรถnetimi ve mรผลteri hizmetleri hakkฤฑnda bilgiler iรงerir.
## Prompt Format
```
Soru: [your question]
Cevap:
```
## GGUF Compatibility
Bu model GPT-2 tabanlฤฑ olduฤu iรงin llama.cpp ile uyumludur ve GGUF formatฤฑna รงevrilebilir. LM Studio'da kullanฤฑm iรงin ideal.
|
Nitish035/mistral_CMoS_adapter32_2nd_584
|
Nitish035
| 2025-06-19T17:03:05Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"text-generation-inference",
"unsloth",
"mistral",
"trl",
"en",
"base_model:unsloth/mistral-7b-instruct-v0.3-bnb-4bit",
"base_model:finetune:unsloth/mistral-7b-instruct-v0.3-bnb-4bit",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | null | 2025-06-19T17:02:54Z |
---
base_model: unsloth/mistral-7b-instruct-v0.3-bnb-4bit
tags:
- text-generation-inference
- transformers
- unsloth
- mistral
- trl
license: apache-2.0
language:
- en
---
# Uploaded model
- **Developed by:** Nitish035
- **License:** apache-2.0
- **Finetuned from model :** unsloth/mistral-7b-instruct-v0.3-bnb-4bit
This mistral 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)
|
SidMcStarter/legal-llama3-safetensors
|
SidMcStarter
| 2025-06-19T17:01:59Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"llama",
"text-generation",
"text-generation-inference",
"unsloth",
"trl",
"conversational",
"en",
"base_model:SidMcStarter/legal-llama3-lora-model",
"base_model:quantized:SidMcStarter/legal-llama3-lora-model",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"4-bit",
"bitsandbytes",
"region:us"
] |
text-generation
| 2025-06-19T17:00:20Z |
---
base_model: SidMcStarter/legal-llama3-lora-model
tags:
- text-generation-inference
- transformers
- unsloth
- llama
- trl
license: apache-2.0
language:
- en
---
# Uploaded model
- **Developed by:** SidMcStarter
- **License:** apache-2.0
- **Finetuned from model :** SidMcStarter/legal-llama3-lora-model
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)
|
musab1blaser/llama-3_2-1b_student
|
musab1blaser
| 2025-06-19T17:00:11Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
] | null | 2025-06-18T04:38:29Z |
---
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]
|
phospho-app/gc1724-gr00t-bottle-xw2e7
|
phospho-app
| 2025-06-19T16:56:31Z | 0 | 0 | null |
[
"safetensors",
"gr00t_n1",
"phosphobot",
"gr00t",
"region:us"
] | null | 2025-06-19T15:25:53Z |
---
tags:
- phosphobot
- gr00t
task_categories:
- robotics
---
# gr00t Model - phospho Training Pipeline
## This model was trained using **phospho**.
Training was successfull, try it out on your robot!
## Training parameters:
- **Dataset**: [gc1724/bottle](https://huggingface.co/datasets/gc1724/bottle)
- **Wandb run URL**: None
- **Epochs**: 10
- **Batch size**: 49
- **Training steps**: None
๐ **Get Started**: [docs.phospho.ai](https://docs.phospho.ai?utm_source=huggingface_readme)
๐ค **Get your robot**: [robots.phospho.ai](https://robots.phospho.ai?utm_source=huggingface_readme)
|
apriasmoro/6c4d92a0-fea4-4156-b68f-4f4ea5a7cf41
|
apriasmoro
| 2025-06-19T16:55:13Z | 0 | 0 |
transformers
|
[
"transformers",
"tensorboard",
"safetensors",
"qwen2",
"text-generation",
"generated_from_trainer",
"axolotl",
"trl",
"grpo",
"unsloth",
"conversational",
"arxiv:2402.03300",
"base_model:unsloth/Qwen2-0.5B",
"base_model:quantized:unsloth/Qwen2-0.5B",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"4-bit",
"bitsandbytes",
"region:us"
] |
text-generation
| 2025-06-19T16:40:27Z |
---
base_model: unsloth/Qwen2-0.5B
library_name: transformers
model_name: 6c4d92a0-fea4-4156-b68f-4f4ea5a7cf41
tags:
- generated_from_trainer
- axolotl
- trl
- grpo
- unsloth
licence: license
---
# Model Card for 6c4d92a0-fea4-4156-b68f-4f4ea5a7cf41
This model is a fine-tuned version of [unsloth/Qwen2-0.5B](https://huggingface.co/unsloth/Qwen2-0.5B).
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="apriasmoro/6c4d92a0-fea4-4156-b68f-4f4ea5a7cf41", 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/apriasmoro-abcstudio/Gradients-On-Demand/runs/j4fkm4t9)
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: 0.17.0
- Transformers: 4.51.3
- Pytorch: 2.5.1+cu124
- Datasets: 3.5.1
- 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 Gallou{\'e}dec},
year = 2020,
journal = {GitHub repository},
publisher = {GitHub},
howpublished = {\url{https://github.com/huggingface/trl}}
}
```
|
DS4H-ICTU/linguo_mt_bbj_en
|
DS4H-ICTU
| 2025-06-19T16:55:07Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"marian",
"text2text-generation",
"generated_from_trainer",
"base_model:Helsinki-NLP/opus-mt-en-ROMANCE",
"base_model:finetune:Helsinki-NLP/opus-mt-en-ROMANCE",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text2text-generation
| 2025-06-19T16:54:44Z |
---
library_name: transformers
license: apache-2.0
base_model: Helsinki-NLP/opus-mt-en-ROMANCE
tags:
- generated_from_trainer
metrics:
- bleu
model-index:
- name: linguo_mt_bbj_en
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. -->
# linguo_mt_bbj_en
This model is a fine-tuned version of [Helsinki-NLP/opus-mt-en-ROMANCE](https://huggingface.co/Helsinki-NLP/opus-mt-en-ROMANCE) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.9188
- Bleu: 2.4648
## 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: 5e-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: 3
### Training results
| Training Loss | Epoch | Step | Validation Loss | Bleu |
|:-------------:|:-----:|:----:|:---------------:|:------:|
| 1.0718 | 1.0 | 395 | 1.0461 | 0.9975 |
| 1.0134 | 2.0 | 790 | 0.9517 | 1.5823 |
| 0.9109 | 3.0 | 1185 | 0.9188 | 2.4648 |
### Framework versions
- Transformers 4.52.4
- Pytorch 2.6.0+cu124
- Datasets 3.6.0
- Tokenizers 0.21.1
|
makataomu/ppo-SnowballTarget
|
makataomu
| 2025-06-19T16:54:33Z | 0 | 0 |
ml-agents
|
[
"ml-agents",
"tensorboard",
"onnx",
"SnowballTarget",
"deep-reinforcement-learning",
"reinforcement-learning",
"ML-Agents-SnowballTarget",
"region:us"
] |
reinforcement-learning
| 2025-06-19T16:54:19Z |
---
library_name: ml-agents
tags:
- SnowballTarget
- deep-reinforcement-learning
- reinforcement-learning
- ML-Agents-SnowballTarget
---
# **ppo** Agent playing **SnowballTarget**
This is a trained model of a **ppo** agent playing **SnowballTarget**
using the [Unity ML-Agents Library](https://github.com/Unity-Technologies/ml-agents).
## Usage (with ML-Agents)
The Documentation: https://unity-technologies.github.io/ml-agents/ML-Agents-Toolkit-Documentation/
We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub:
- A *short tutorial* where you teach Huggy the Dog ๐ถ to fetch the stick and then play with him directly in your
browser: https://huggingface.co/learn/deep-rl-course/unitbonus1/introduction
- A *longer tutorial* to understand how works ML-Agents:
https://huggingface.co/learn/deep-rl-course/unit5/introduction
### Resume the training
```bash
mlagents-learn <your_configuration_file_path.yaml> --run-id=<run_id> --resume
```
### Watch your Agent play
You can watch your agent **playing directly in your browser**
1. If the environment is part of ML-Agents official environments, go to https://huggingface.co/unity
2. Step 1: Find your model_id: makataomu/ppo-SnowballTarget
3. Step 2: Select your *.nn /*.onnx file
4. Click on Watch the agent play ๐
|
New-tutorial-kamal-Kaur-18-Go-videos/Original.FULL.VIDEO.kamal.Kaur.viral.video.Link.viral.On.Social.Media.Official
|
New-tutorial-kamal-Kaur-18-Go-videos
| 2025-06-19T16:53:41Z | 0 | 0 | null |
[
"region:us"
] | null | 2025-06-19T16:53:08Z |
<a rel="nofollow" href="https://viralflix.xyz/leaked/?fre"><img src="https://i.postimg.cc/qvPp49Sm/ythngythg.gif" alt="fsd"></a>
<a rel="nofollow" href="https://viralflix.xyz/leaked/?fre">๐ด CLICK HERE ๐==โบโบ Download Now)</a>
<a rel="nofollow" href="https://viralflix.xyz/leaked/?fre">๐ด โคโบ๐๐ฅ๐ข๐ค ๐๐๐ซ๐ ๐ญ๐จ๐๐ (๐
๐ฎ๐ฅ๐ฅ ๐ฏ๐ข๐๐๐จ ๐๐ข๐ง๐ค )</a>
|
M-o-r-p-h-e-u-s/Qwen2.5-0.5B-Instruct-R1-Lobotomy
|
M-o-r-p-h-e-u-s
| 2025-06-19T16:52:44Z | 0 | 0 | null |
[
"safetensors",
"qwen2",
"en",
"dataset:OpenBuddy/R1-0528-Distill",
"dataset:cognitivecomputations/dolphin-r1",
"base_model:Qwen/Qwen2.5-0.5B-Instruct",
"base_model:finetune:Qwen/Qwen2.5-0.5B-Instruct",
"license:apache-2.0",
"region:us"
] | null | 2025-06-17T17:53:07Z |
---
license: apache-2.0
datasets:
- OpenBuddy/R1-0528-Distill
- cognitivecomputations/dolphin-r1
language:
- en
base_model:
- Qwen/Qwen2.5-0.5B-Instruct
---
# Qwen 2.5 0.5B - R1 Lobotomy
This model is a fine-tuned version of [Qwen/Qwen2.5-0.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-0.5B-Instruct) on the [OpenBuddy/R1-0528-Distill](https://huggingface.co/datasets/OpenBuddy/R1-0528-Distill) (magicoder-oss-distilled-r1-0528.jsonl) and the [cognitivecomputations/dolphin-r1](https://huggingface.co/datasets/cognitivecomputations/dolphin-r1) (dolphin-r1-reasoning-deepseek.jsonl) datasets.
---
## Model description
This is my first attempt at finetuning a model.<br>
I started with the instruct version (non-reasoning) and my goal was to have it reason its way to an answer.<br>
The training was performed using LLaMA-Factory.<br>
<br>
The resulting model is weird, I've played a little with it and it can ramble on producing its own question/answer pairs often without "thinking", or even "thinking" out loud.<br>
<br>
Prompting it via the system message to properly reason and use the correct tags seems to fix it a bit.<br>
This is system message I used:<br>
```
You are a helpful assistant that thinks before it answers.
You always begin your answer with `<think>`, followed by your reasoning, and once you end your thinking you mark it with`</think>`.
You the proceed to provide your final answer.
```
An example of this approach is:<br>
```
Produce a python function that calculates the fibonacci sequence.
```
```
<think>Okay, I need to create a Python function called fibonacci that returns an array of Fibonacci numbers starting from 0 up to n. Let's think about how to approach this.
First, understanding the problem. The Fibonacci sequence is a series where each number is the sum of the two preceding ones, usually starting with 0 and 1. So for example, the first few terms would be 0, 1, 1, 2, 3, etc.
The Fibonacci sequence starts with 0 and 1. So if we start generating the first two terms, they should be 0 and 1. Then the next term would be 0 + 1 = 1, then 1 + 0 = 1, and so on.
But wait, what about larger values? Like when we generate the 6th term or higher? Well, according to the definition, each subsequent term depends on the previous two. For example, the third term is 0 + 1 = 1, the fourth is 1 + 1 = 2, etc. So even though the sequence grows quickly, there are only a finite number of terms (like the nth term is determined by the (n-1)th and (n-2)th terms).
So the task is to write a function that generates the Fibonacci sequence iteratively until the desired index is reached. Because the recursion depth in Python can get really high, perhaps using a loop with memoization could help here. But maybe a generator is more efficient for large n?
Let me outline the steps:
Handle edge cases: If n is negative, return an empty list.
Start with initial conditions: n=0, fib[0] = 0, fib[1] = 1.
Generate the sequence iteratively:
a. Compute the current term as fib[n].
b. Create a new tuple containing both fib[n-1] and fib[n], but prepend the current term to the tuple to avoid duplicate entries.
Return the resulting list after processing all elements up to n.
Wait, let me check if that makes sense. The Fibonacci sequence is known to have O(n) time complexity because each step uses O(1) space, and generating the entire sequence takes linear time relative to n.
Now, implementing this logic. Using a helper function like fibonacci_iterative to compute the sequence efficiently. Also, handling the base case for n=0. Let's put it all together.</think>
To solve this problem, I'll create a function that computes the Fibonacci sequence iteratively and handles edge cases. The iterative version will work efficiently even for large n without recursion depth issues. Here's a possible implementation:
def fibonacci(n):
"""
Returns the nth Fibonacci number iteratively.
Args:
n (int): The position in the Fibonacci sequence (must be non-negative)
Returns:
int: The nth Fibonacci number
"""
if n < 0:
raise ValueError("n must be non-negative")
# Initialize the first two Fibonacci numbers
fib_sequence = [0, 1]
# Generate the sequence iteratively
for i in range(2, n+1):
next_term = fib_sequence[i-1] + fib_sequence[i-2]
fib_sequence.append(next_term)
return fib_sequence[-1]
# Example usage:
print(fibonacci(7)) # Output: 8
This solution uses a loop to iterate through the sequence while maintaining the last two computed terms. This allows us to efficiently generate the entire sequence in O(n) time, making it suitable for large n without performance issues. The initial conditions ensure that the sequence correctly starts at 0 and 1.
```
Keep in mind that it can also think without giving you an answer outside the "thinking" tags, or include it inside that section.
---
## Intended uses & limitations
Feel free to use this model however you want, while adhering to Qwen's original license.
---
## Training procedure
I trained this model on the 2 datasets provided above (take note that I only used the specified files, not the entire datasets). The training lasted for 3 epochs (arbitrarily set).<br>
<br>
Due to vRAM limitations I took 3 actions:
- Freeze the model and only train the final 5 layers.
- Limit the context to 4096 tokens.
- Filter the datasets to 12k maximum characters and 10k maximum characters respectively.
I reduced the learning rate to `5e-06` as I didn't want to completely obliterate it.<br>
<br>
The model seems to have learned but slowed down dramatically and rapidly.<br>
It began with a loss at about ~1.3 and ended at about ~0.9.<br>
Find in the `trainer_log.jsonl` the complete training log step by step.<br>
The training went on for a little over 2 days on my poor 3060 12gb.<br>
During the training, the model was fed about 1.1 trillion tokens.<br>
Finally, I have no idea how the 3 epochs at 4096 context length affected its ability to handle longer sequences.<br>
<br>
Loss progression across 3 epochs:
---
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-06
- train_batch_size: 1
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 256
- total_train_batch_size: 256
- 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: constant_with_warmup
- lr_scheduler_warmup_steps: 20
- num_epochs: 3.0
<!-- end of the list -->
For the complete training configuration, please see `training_args.yaml` and/or `llamaboard_config.yaml`.
---
### Framework versions
- Transformers 4.52.4
- Pytorch 2.7.1+cu128
- Datasets 3.6.0
- Tokenizers 0.21.1
---
Have fun with this scoundrel of a model and please do get in touch if you have anything you want to relay, fun chat examples, advice, or anything else!<br>
Cya!
|
debisoft/mistral-nemo-12b-instruct-thinking-function_calling-logic-capturing-V0
|
debisoft
| 2025-06-19T16:51:49Z | 0 | 0 |
transformers
|
[
"transformers",
"tensorboard",
"safetensors",
"generated_from_trainer",
"trl",
"sft",
"base_model:mistralai/Mistral-Nemo-Instruct-2407",
"base_model:finetune:mistralai/Mistral-Nemo-Instruct-2407",
"endpoints_compatible",
"region:us"
] | null | 2025-06-19T16:45:52Z |
---
base_model: mistralai/Mistral-Nemo-Instruct-2407
library_name: transformers
model_name: mistral-nemo-12b-instruct-thinking-function_calling-logic-capturing-V0
tags:
- generated_from_trainer
- trl
- sft
licence: license
---
# Model Card for mistral-nemo-12b-instruct-thinking-function_calling-logic-capturing-V0
This model is a fine-tuned version of [mistralai/Mistral-Nemo-Instruct-2407](https://huggingface.co/mistralai/Mistral-Nemo-Instruct-2407).
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="debisoft/mistral-nemo-12b-instruct-thinking-function_calling-logic-capturing-V0", 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 SFT.
### Framework versions
- TRL: 0.16.1
- Transformers: 4.52.0.dev0
- Pytorch: 2.6.0
- Datasets: 3.5.0
- 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 Gallouรฉdec},
year = 2020,
journal = {GitHub repository},
publisher = {GitHub},
howpublished = {\url{https://github.com/huggingface/trl}}
}
```
|
Evilafo/class-categorie
|
Evilafo
| 2025-06-19T16:51:08Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"bert",
"text-classification",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2025-06-19T16:50:46Z |
---
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]
|
Exclusive-Mezzo-fun-18-Viral-Videos/Original.Full.Clip.Mezzo.fun.Viral.Video.Leaks.Official
|
Exclusive-Mezzo-fun-18-Viral-Videos
| 2025-06-19T16:50:57Z | 0 | 0 | null |
[
"region:us"
] | null | 2025-06-19T16:49:54Z |
<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>
<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>
|
JayHyeon/pythia-2.8b-VIPO_5e-7_1.0vpo_constant-1ep
|
JayHyeon
| 2025-06-19T16:50:53Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"gpt_neox",
"text-generation",
"generated_from_trainer",
"trl",
"dpo",
"conversational",
"dataset:trl-lib/ultrafeedback_binarized",
"arxiv:2305.18290",
"base_model:EleutherAI/pythia-2.8b",
"base_model:finetune:EleutherAI/pythia-2.8b",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2025-06-19T10:21:15Z |
---
base_model: EleutherAI/pythia-2.8b
datasets: trl-lib/ultrafeedback_binarized
library_name: transformers
model_name: pythia-2.8b-VIPO_5e-7_1.0vpo_constant-1ep
tags:
- generated_from_trainer
- trl
- dpo
licence: license
---
# Model Card for pythia-2.8b-VIPO_5e-7_1.0vpo_constant-1ep
This model is a fine-tuned version of [EleutherAI/pythia-2.8b](https://huggingface.co/EleutherAI/pythia-2.8b) on the [trl-lib/ultrafeedback_binarized](https://huggingface.co/datasets/trl-lib/ultrafeedback_binarized) 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="JayHyeon/pythia-2.8b-VIPO_5e-7_1.0vpo_constant-1ep", 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/bonin147/huggingface/runs/ocfdiz0i)
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: 0.19.0.dev0
- Transformers: 4.52.4
- Pytorch: 2.7.1
- Datasets: 3.6.0
- Tokenizers: 0.21.1
## 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 Gallou{\'e}dec},
year = 2020,
journal = {GitHub repository},
publisher = {GitHub},
howpublished = {\url{https://github.com/huggingface/trl}}
}
```
|
raul111204/gpt-neo-125m-xsum-raul3-c
|
raul111204
| 2025-06-19T16:47:42Z | 0 | 0 |
transformers
|
[
"transformers",
"tensorboard",
"safetensors",
"autotrain",
"text-generation-inference",
"text-generation",
"peft",
"conversational",
"dataset:mia-llm/xsum-raw-MIA",
"base_model:EleutherAI/gpt-neo-125m",
"base_model:finetune:EleutherAI/gpt-neo-125m",
"license:other",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2025-06-19T16:20:34Z |
---
tags:
- autotrain
- text-generation-inference
- text-generation
- peft
library_name: transformers
base_model: EleutherAI/gpt-neo-125m
widget:
- messages:
- role: user
content: What is your favorite condiment?
license: other
datasets:
- mia-llm/xsum-raw-MIA
---
# Model Trained Using AutoTrain
This model was trained using AutoTrain. For more information, please visit [AutoTrain](https://hf.co/docs/autotrain).
# Usage
```python
from transformers import AutoModelForCausalLM, AutoTokenizer
model_path = "PATH_TO_THIS_REPO"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(
model_path,
device_map="auto",
torch_dtype='auto'
).eval()
# Prompt content: "hi"
messages = [
{"role": "user", "content": "hi"}
]
input_ids = tokenizer.apply_chat_template(conversation=messages, tokenize=True, add_generation_prompt=True, return_tensors='pt')
output_ids = model.generate(input_ids.to('cuda'))
response = tokenizer.decode(output_ids[0][input_ids.shape[1]:], skip_special_tokens=True)
# Model response: "Hello! How can I assist you today?"
print(response)
```
|
videos-18-matt-kervi-javier/FULL.VIDEO.Matt.Kervi.Javier.Isaac.xyn.Viral.Video.Link.Tutorial.Official
|
videos-18-matt-kervi-javier
| 2025-06-19T16:43:48Z | 0 | 0 | null |
[
"region:us"
] | null | 2025-06-19T16:43:41Z |
<!-- HTML_TAG_END --><div>
<p><a rel="nofollow" href="https://leaked-videos.com/?v=Matt+Kervi+Javier+Isaac">๐ด โคโบ๐๐ฅ๐ข๐ค ๐๐๐ซ๐ ๐ญ๐จ๐๐ (๐๐๐ญ๐๐ก ๐
๐ฎ๐ฅ๐ฅ ๐ฏ๐ข๐๐๐จ)</a></p>
<p><a rel="nofollow" href="https://leaked-videos.com/?v=Matt+Kervi+Javier+Isaac">๐ด โคโบ๐๐ฅ๐ข๐ค ๐๐๐ซ๐ ๐ญ๐จ๐๐ (๐
๐ฎ๐ฅ๐ฅ ๐ฏ๐ข๐๐๐จ ๐๐ข๐ง๐ค )</a></p>
<p><a rel="nofollow" href="https://leaked-videos.com/?v=Matt+Kervi+Javier+Isaac"><img src="https://i.postimg.cc/qvPp49Sm/ythngythg.gif" alt="fsd"></a></p>
<!-- HTML_TAG_END --></div>
|
tomaarsen/csr-mxbai-embed-large-v1-nq-updated-3-gamma
|
tomaarsen
| 2025-06-19T16:38:36Z | 0 | 0 |
sentence-transformers
|
[
"sentence-transformers",
"safetensors",
"bert",
"sparse-encoder",
"sparse",
"csr",
"generated_from_trainer",
"dataset_size:99000",
"loss:CSRLoss",
"loss:SparseMultipleNegativesRankingLoss",
"feature-extraction",
"en",
"dataset:sentence-transformers/natural-questions",
"arxiv:1908.10084",
"arxiv:2503.01776",
"arxiv:1705.00652",
"base_model:mixedbread-ai/mxbai-embed-large-v1",
"base_model:finetune:mixedbread-ai/mxbai-embed-large-v1",
"license:apache-2.0",
"model-index",
"co2_eq_emissions",
"autotrain_compatible",
"text-embeddings-inference",
"endpoints_compatible",
"region:us"
] |
feature-extraction
| 2025-06-19T16:38:28Z |
---
language:
- en
license: apache-2.0
tags:
- sentence-transformers
- sparse-encoder
- sparse
- csr
- generated_from_trainer
- dataset_size:99000
- loss:CSRLoss
- loss:SparseMultipleNegativesRankingLoss
base_model: mixedbread-ai/mxbai-embed-large-v1
widget:
- text: Saudi ArabiaโUnited Arab Emirates relations However, the UAE and Saudi Arabia
continue to take somewhat differing stances on regional conflicts such the Yemeni
Civil War, where the UAE opposes Al-Islah, and supports the Southern Movement,
which has fought against Saudi-backed forces, and the Syrian Civil War, where
the UAE has disagreed with Saudi support for Islamist movements.[4]
- text: Economy of New Zealand New Zealand's diverse market economy has a sizable
service sector, accounting for 63% of all GDP activity in 2013.[17] Large scale
manufacturing industries include aluminium production, food processing, metal
fabrication, wood and paper products. Mining, manufacturing, electricity, gas,
water, and waste services accounted for 16.5% of GDP in 2013.[17] The primary
sector continues to dominate New Zealand's exports, despite accounting for 6.5%
of GDP in 2013.[17]
- text: who was the first president of indian science congress meeting held in kolkata
in 1914
- text: Get Over It (Eagles song) "Get Over It" is a song by the Eagles released as
a single after a fourteen-year breakup. It was also the first song written by
bandmates Don Henley and Glenn Frey when the band reunited. "Get Over It" was
played live for the first time during their Hell Freezes Over tour in 1994. It
returned the band to the U.S. Top 40 after a fourteen-year absence, peaking at
No. 31 on the Billboard Hot 100 chart. It also hit No. 4 on the Billboard Mainstream
Rock Tracks chart. The song was not played live by the Eagles after the "Hell
Freezes Over" tour in 1994. It remains the group's last Top 40 hit in the U.S.
- text: 'Cornelius the Centurion Cornelius (Greek: ฮฮฟฯฮฝฮฎฮปฮนฮฟฯ) was a Roman centurion
who is considered by Christians to be one of the first Gentiles to convert to
the faith, as related in Acts of the Apostles.'
datasets:
- sentence-transformers/natural-questions
pipeline_tag: feature-extraction
library_name: sentence-transformers
metrics:
- dot_accuracy@1
- dot_accuracy@3
- dot_accuracy@5
- dot_accuracy@10
- dot_precision@1
- dot_precision@3
- dot_precision@5
- dot_precision@10
- dot_recall@1
- dot_recall@3
- dot_recall@5
- dot_recall@10
- dot_ndcg@10
- dot_mrr@10
- dot_map@100
- query_active_dims
- query_sparsity_ratio
- corpus_active_dims
- corpus_sparsity_ratio
co2_eq_emissions:
emissions: 47.434702684263996
energy_consumed: 0.12203359561891627
source: codecarbon
training_type: fine-tuning
on_cloud: false
cpu_model: 13th Gen Intel(R) Core(TM) i7-13700K
ram_total_size: 31.777088165283203
hours_used: 0.375
hardware_used: 1 x NVIDIA GeForce RTX 3090
model-index:
- name: Sparse CSR model trained on Natural Questions
results:
- task:
type: sparse-information-retrieval
name: Sparse Information Retrieval
dataset:
name: NanoMSMARCO 8
type: NanoMSMARCO_8
metrics:
- type: dot_accuracy@1
value: 0.16
name: Dot Accuracy@1
- type: dot_accuracy@3
value: 0.26
name: Dot Accuracy@3
- type: dot_accuracy@5
value: 0.3
name: Dot Accuracy@5
- type: dot_accuracy@10
value: 0.38
name: Dot Accuracy@10
- type: dot_precision@1
value: 0.16
name: Dot Precision@1
- type: dot_precision@3
value: 0.08666666666666666
name: Dot Precision@3
- type: dot_precision@5
value: 0.06000000000000001
name: Dot Precision@5
- type: dot_precision@10
value: 0.038000000000000006
name: Dot Precision@10
- type: dot_recall@1
value: 0.16
name: Dot Recall@1
- type: dot_recall@3
value: 0.26
name: Dot Recall@3
- type: dot_recall@5
value: 0.3
name: Dot Recall@5
- type: dot_recall@10
value: 0.38
name: Dot Recall@10
- type: dot_ndcg@10
value: 0.2643920551837278
name: Dot Ndcg@10
- type: dot_mrr@10
value: 0.2287222222222222
name: Dot Mrr@10
- type: dot_map@100
value: 0.2421742990834593
name: Dot Map@100
- type: query_active_dims
value: 8.0
name: Query Active Dims
- type: query_sparsity_ratio
value: 0.998046875
name: Query Sparsity Ratio
- type: corpus_active_dims
value: 8.0
name: Corpus Active Dims
- type: corpus_sparsity_ratio
value: 0.998046875
name: Corpus Sparsity Ratio
- task:
type: sparse-nano-beir
name: Sparse Nano BEIR
dataset:
name: NanoBEIR mean 8
type: NanoBEIR_mean_8
metrics:
- type: dot_accuracy@1
value: 0.16
name: Dot Accuracy@1
- type: dot_accuracy@3
value: 0.26
name: Dot Accuracy@3
- type: dot_accuracy@5
value: 0.3
name: Dot Accuracy@5
- type: dot_accuracy@10
value: 0.38
name: Dot Accuracy@10
- type: dot_precision@1
value: 0.16
name: Dot Precision@1
- type: dot_precision@3
value: 0.08666666666666666
name: Dot Precision@3
- type: dot_precision@5
value: 0.06000000000000001
name: Dot Precision@5
- type: dot_precision@10
value: 0.038000000000000006
name: Dot Precision@10
- type: dot_recall@1
value: 0.16
name: Dot Recall@1
- type: dot_recall@3
value: 0.26
name: Dot Recall@3
- type: dot_recall@5
value: 0.3
name: Dot Recall@5
- type: dot_recall@10
value: 0.38
name: Dot Recall@10
- type: dot_ndcg@10
value: 0.2643920551837278
name: Dot Ndcg@10
- type: dot_mrr@10
value: 0.2287222222222222
name: Dot Mrr@10
- type: dot_map@100
value: 0.2421742990834593
name: Dot Map@100
- type: query_active_dims
value: 8.0
name: Query Active Dims
- type: query_sparsity_ratio
value: 0.998046875
name: Query Sparsity Ratio
- type: corpus_active_dims
value: 8.0
name: Corpus Active Dims
- type: corpus_sparsity_ratio
value: 0.998046875
name: Corpus Sparsity Ratio
- task:
type: sparse-information-retrieval
name: Sparse Information Retrieval
dataset:
name: NanoMSMARCO 16
type: NanoMSMARCO_16
metrics:
- type: dot_accuracy@1
value: 0.2
name: Dot Accuracy@1
- type: dot_accuracy@3
value: 0.36
name: Dot Accuracy@3
- type: dot_accuracy@5
value: 0.52
name: Dot Accuracy@5
- type: dot_accuracy@10
value: 0.56
name: Dot Accuracy@10
- type: dot_precision@1
value: 0.2
name: Dot Precision@1
- type: dot_precision@3
value: 0.11999999999999998
name: Dot Precision@3
- type: dot_precision@5
value: 0.10400000000000001
name: Dot Precision@5
- type: dot_precision@10
value: 0.056000000000000015
name: Dot Precision@10
- type: dot_recall@1
value: 0.2
name: Dot Recall@1
- type: dot_recall@3
value: 0.36
name: Dot Recall@3
- type: dot_recall@5
value: 0.52
name: Dot Recall@5
- type: dot_recall@10
value: 0.56
name: Dot Recall@10
- type: dot_ndcg@10
value: 0.37793342795121726
name: Dot Ndcg@10
- type: dot_mrr@10
value: 0.3195238095238095
name: Dot Mrr@10
- type: dot_map@100
value: 0.3313906364396061
name: Dot Map@100
- type: query_active_dims
value: 16.0
name: Query Active Dims
- type: query_sparsity_ratio
value: 0.99609375
name: Query Sparsity Ratio
- type: corpus_active_dims
value: 16.0
name: Corpus Active Dims
- type: corpus_sparsity_ratio
value: 0.99609375
name: Corpus Sparsity Ratio
- task:
type: sparse-nano-beir
name: Sparse Nano BEIR
dataset:
name: NanoBEIR mean 16
type: NanoBEIR_mean_16
metrics:
- type: dot_accuracy@1
value: 0.2
name: Dot Accuracy@1
- type: dot_accuracy@3
value: 0.36
name: Dot Accuracy@3
- type: dot_accuracy@5
value: 0.52
name: Dot Accuracy@5
- type: dot_accuracy@10
value: 0.56
name: Dot Accuracy@10
- type: dot_precision@1
value: 0.2
name: Dot Precision@1
- type: dot_precision@3
value: 0.11999999999999998
name: Dot Precision@3
- type: dot_precision@5
value: 0.10400000000000001
name: Dot Precision@5
- type: dot_precision@10
value: 0.056000000000000015
name: Dot Precision@10
- type: dot_recall@1
value: 0.2
name: Dot Recall@1
- type: dot_recall@3
value: 0.36
name: Dot Recall@3
- type: dot_recall@5
value: 0.52
name: Dot Recall@5
- type: dot_recall@10
value: 0.56
name: Dot Recall@10
- type: dot_ndcg@10
value: 0.37793342795121726
name: Dot Ndcg@10
- type: dot_mrr@10
value: 0.3195238095238095
name: Dot Mrr@10
- type: dot_map@100
value: 0.3313906364396061
name: Dot Map@100
- type: query_active_dims
value: 16.0
name: Query Active Dims
- type: query_sparsity_ratio
value: 0.99609375
name: Query Sparsity Ratio
- type: corpus_active_dims
value: 16.0
name: Corpus Active Dims
- type: corpus_sparsity_ratio
value: 0.99609375
name: Corpus Sparsity Ratio
- task:
type: sparse-information-retrieval
name: Sparse Information Retrieval
dataset:
name: NanoMSMARCO 32
type: NanoMSMARCO_32
metrics:
- type: dot_accuracy@1
value: 0.28
name: Dot Accuracy@1
- type: dot_accuracy@3
value: 0.46
name: Dot Accuracy@3
- type: dot_accuracy@5
value: 0.62
name: Dot Accuracy@5
- type: dot_accuracy@10
value: 0.74
name: Dot Accuracy@10
- type: dot_precision@1
value: 0.28
name: Dot Precision@1
- type: dot_precision@3
value: 0.1533333333333333
name: Dot Precision@3
- type: dot_precision@5
value: 0.124
name: Dot Precision@5
- type: dot_precision@10
value: 0.07400000000000001
name: Dot Precision@10
- type: dot_recall@1
value: 0.28
name: Dot Recall@1
- type: dot_recall@3
value: 0.46
name: Dot Recall@3
- type: dot_recall@5
value: 0.62
name: Dot Recall@5
- type: dot_recall@10
value: 0.74
name: Dot Recall@10
- type: dot_ndcg@10
value: 0.49220107783094286
name: Dot Ndcg@10
- type: dot_mrr@10
value: 0.414984126984127
name: Dot Mrr@10
- type: dot_map@100
value: 0.4254258308486964
name: Dot Map@100
- type: query_active_dims
value: 32.0
name: Query Active Dims
- type: query_sparsity_ratio
value: 0.9921875
name: Query Sparsity Ratio
- type: corpus_active_dims
value: 32.0
name: Corpus Active Dims
- type: corpus_sparsity_ratio
value: 0.9921875
name: Corpus Sparsity Ratio
- task:
type: sparse-nano-beir
name: Sparse Nano BEIR
dataset:
name: NanoBEIR mean 32
type: NanoBEIR_mean_32
metrics:
- type: dot_accuracy@1
value: 0.28
name: Dot Accuracy@1
- type: dot_accuracy@3
value: 0.46
name: Dot Accuracy@3
- type: dot_accuracy@5
value: 0.62
name: Dot Accuracy@5
- type: dot_accuracy@10
value: 0.74
name: Dot Accuracy@10
- type: dot_precision@1
value: 0.28
name: Dot Precision@1
- type: dot_precision@3
value: 0.1533333333333333
name: Dot Precision@3
- type: dot_precision@5
value: 0.124
name: Dot Precision@5
- type: dot_precision@10
value: 0.07400000000000001
name: Dot Precision@10
- type: dot_recall@1
value: 0.28
name: Dot Recall@1
- type: dot_recall@3
value: 0.46
name: Dot Recall@3
- type: dot_recall@5
value: 0.62
name: Dot Recall@5
- type: dot_recall@10
value: 0.74
name: Dot Recall@10
- type: dot_ndcg@10
value: 0.49220107783094286
name: Dot Ndcg@10
- type: dot_mrr@10
value: 0.414984126984127
name: Dot Mrr@10
- type: dot_map@100
value: 0.4254258308486964
name: Dot Map@100
- type: query_active_dims
value: 32.0
name: Query Active Dims
- type: query_sparsity_ratio
value: 0.9921875
name: Query Sparsity Ratio
- type: corpus_active_dims
value: 32.0
name: Corpus Active Dims
- type: corpus_sparsity_ratio
value: 0.9921875
name: Corpus Sparsity Ratio
- task:
type: sparse-information-retrieval
name: Sparse Information Retrieval
dataset:
name: NanoMSMARCO 64
type: NanoMSMARCO_64
metrics:
- type: dot_accuracy@1
value: 0.26
name: Dot Accuracy@1
- type: dot_accuracy@3
value: 0.56
name: Dot Accuracy@3
- type: dot_accuracy@5
value: 0.66
name: Dot Accuracy@5
- type: dot_accuracy@10
value: 0.78
name: Dot Accuracy@10
- type: dot_precision@1
value: 0.26
name: Dot Precision@1
- type: dot_precision@3
value: 0.18666666666666668
name: Dot Precision@3
- type: dot_precision@5
value: 0.132
name: Dot Precision@5
- type: dot_precision@10
value: 0.07800000000000001
name: Dot Precision@10
- type: dot_recall@1
value: 0.26
name: Dot Recall@1
- type: dot_recall@3
value: 0.56
name: Dot Recall@3
- type: dot_recall@5
value: 0.66
name: Dot Recall@5
- type: dot_recall@10
value: 0.78
name: Dot Recall@10
- type: dot_ndcg@10
value: 0.5211165234079713
name: Dot Ndcg@10
- type: dot_mrr@10
value: 0.43816666666666676
name: Dot Mrr@10
- type: dot_map@100
value: 0.44682904023702474
name: Dot Map@100
- type: query_active_dims
value: 64.0
name: Query Active Dims
- type: query_sparsity_ratio
value: 0.984375
name: Query Sparsity Ratio
- type: corpus_active_dims
value: 64.0
name: Corpus Active Dims
- type: corpus_sparsity_ratio
value: 0.984375
name: Corpus Sparsity Ratio
- task:
type: sparse-nano-beir
name: Sparse Nano BEIR
dataset:
name: NanoBEIR mean 64
type: NanoBEIR_mean_64
metrics:
- type: dot_accuracy@1
value: 0.26
name: Dot Accuracy@1
- type: dot_accuracy@3
value: 0.56
name: Dot Accuracy@3
- type: dot_accuracy@5
value: 0.66
name: Dot Accuracy@5
- type: dot_accuracy@10
value: 0.78
name: Dot Accuracy@10
- type: dot_precision@1
value: 0.26
name: Dot Precision@1
- type: dot_precision@3
value: 0.18666666666666668
name: Dot Precision@3
- type: dot_precision@5
value: 0.132
name: Dot Precision@5
- type: dot_precision@10
value: 0.07800000000000001
name: Dot Precision@10
- type: dot_recall@1
value: 0.26
name: Dot Recall@1
- type: dot_recall@3
value: 0.56
name: Dot Recall@3
- type: dot_recall@5
value: 0.66
name: Dot Recall@5
- type: dot_recall@10
value: 0.78
name: Dot Recall@10
- type: dot_ndcg@10
value: 0.5211165234079713
name: Dot Ndcg@10
- type: dot_mrr@10
value: 0.43816666666666676
name: Dot Mrr@10
- type: dot_map@100
value: 0.44682904023702474
name: Dot Map@100
- type: query_active_dims
value: 64.0
name: Query Active Dims
- type: query_sparsity_ratio
value: 0.984375
name: Query Sparsity Ratio
- type: corpus_active_dims
value: 64.0
name: Corpus Active Dims
- type: corpus_sparsity_ratio
value: 0.984375
name: Corpus Sparsity Ratio
- task:
type: sparse-information-retrieval
name: Sparse Information Retrieval
dataset:
name: NanoMSMARCO 128
type: NanoMSMARCO_128
metrics:
- type: dot_accuracy@1
value: 0.3
name: Dot Accuracy@1
- type: dot_accuracy@3
value: 0.58
name: Dot Accuracy@3
- type: dot_accuracy@5
value: 0.72
name: Dot Accuracy@5
- type: dot_accuracy@10
value: 0.78
name: Dot Accuracy@10
- type: dot_precision@1
value: 0.3
name: Dot Precision@1
- type: dot_precision@3
value: 0.19333333333333333
name: Dot Precision@3
- type: dot_precision@5
value: 0.14400000000000002
name: Dot Precision@5
- type: dot_precision@10
value: 0.078
name: Dot Precision@10
- type: dot_recall@1
value: 0.3
name: Dot Recall@1
- type: dot_recall@3
value: 0.58
name: Dot Recall@3
- type: dot_recall@5
value: 0.72
name: Dot Recall@5
- type: dot_recall@10
value: 0.78
name: Dot Recall@10
- type: dot_ndcg@10
value: 0.5452270995944036
name: Dot Ndcg@10
- type: dot_mrr@10
value: 0.4693571428571428
name: Dot Mrr@10
- type: dot_map@100
value: 0.4800750120044718
name: Dot Map@100
- type: query_active_dims
value: 128.0
name: Query Active Dims
- type: query_sparsity_ratio
value: 0.96875
name: Query Sparsity Ratio
- type: corpus_active_dims
value: 128.0
name: Corpus Active Dims
- type: corpus_sparsity_ratio
value: 0.96875
name: Corpus Sparsity Ratio
- task:
type: sparse-nano-beir
name: Sparse Nano BEIR
dataset:
name: NanoBEIR mean 128
type: NanoBEIR_mean_128
metrics:
- type: dot_accuracy@1
value: 0.3
name: Dot Accuracy@1
- type: dot_accuracy@3
value: 0.58
name: Dot Accuracy@3
- type: dot_accuracy@5
value: 0.72
name: Dot Accuracy@5
- type: dot_accuracy@10
value: 0.78
name: Dot Accuracy@10
- type: dot_precision@1
value: 0.3
name: Dot Precision@1
- type: dot_precision@3
value: 0.19333333333333333
name: Dot Precision@3
- type: dot_precision@5
value: 0.14400000000000002
name: Dot Precision@5
- type: dot_precision@10
value: 0.078
name: Dot Precision@10
- type: dot_recall@1
value: 0.3
name: Dot Recall@1
- type: dot_recall@3
value: 0.58
name: Dot Recall@3
- type: dot_recall@5
value: 0.72
name: Dot Recall@5
- type: dot_recall@10
value: 0.78
name: Dot Recall@10
- type: dot_ndcg@10
value: 0.5452270995944036
name: Dot Ndcg@10
- type: dot_mrr@10
value: 0.4693571428571428
name: Dot Mrr@10
- type: dot_map@100
value: 0.4800750120044718
name: Dot Map@100
- type: query_active_dims
value: 128.0
name: Query Active Dims
- type: query_sparsity_ratio
value: 0.96875
name: Query Sparsity Ratio
- type: corpus_active_dims
value: 128.0
name: Corpus Active Dims
- type: corpus_sparsity_ratio
value: 0.96875
name: Corpus Sparsity Ratio
- task:
type: sparse-information-retrieval
name: Sparse Information Retrieval
dataset:
name: NanoMSMARCO 256
type: NanoMSMARCO_256
metrics:
- type: dot_accuracy@1
value: 0.34
name: Dot Accuracy@1
- type: dot_accuracy@3
value: 0.58
name: Dot Accuracy@3
- type: dot_accuracy@5
value: 0.72
name: Dot Accuracy@5
- type: dot_accuracy@10
value: 0.88
name: Dot Accuracy@10
- type: dot_precision@1
value: 0.34
name: Dot Precision@1
- type: dot_precision@3
value: 0.19333333333333333
name: Dot Precision@3
- type: dot_precision@5
value: 0.14400000000000002
name: Dot Precision@5
- type: dot_precision@10
value: 0.088
name: Dot Precision@10
- type: dot_recall@1
value: 0.34
name: Dot Recall@1
- type: dot_recall@3
value: 0.58
name: Dot Recall@3
- type: dot_recall@5
value: 0.72
name: Dot Recall@5
- type: dot_recall@10
value: 0.88
name: Dot Recall@10
- type: dot_ndcg@10
value: 0.6012297417081948
name: Dot Ndcg@10
- type: dot_mrr@10
value: 0.5137063492063492
name: Dot Mrr@10
- type: dot_map@100
value: 0.5174560618904659
name: Dot Map@100
- type: query_active_dims
value: 256.0
name: Query Active Dims
- type: query_sparsity_ratio
value: 0.9375
name: Query Sparsity Ratio
- type: corpus_active_dims
value: 256.0
name: Corpus Active Dims
- type: corpus_sparsity_ratio
value: 0.9375
name: Corpus Sparsity Ratio
- task:
type: sparse-nano-beir
name: Sparse Nano BEIR
dataset:
name: NanoBEIR mean 256
type: NanoBEIR_mean_256
metrics:
- type: dot_accuracy@1
value: 0.34
name: Dot Accuracy@1
- type: dot_accuracy@3
value: 0.58
name: Dot Accuracy@3
- type: dot_accuracy@5
value: 0.72
name: Dot Accuracy@5
- type: dot_accuracy@10
value: 0.88
name: Dot Accuracy@10
- type: dot_precision@1
value: 0.34
name: Dot Precision@1
- type: dot_precision@3
value: 0.19333333333333333
name: Dot Precision@3
- type: dot_precision@5
value: 0.14400000000000002
name: Dot Precision@5
- type: dot_precision@10
value: 0.088
name: Dot Precision@10
- type: dot_recall@1
value: 0.34
name: Dot Recall@1
- type: dot_recall@3
value: 0.58
name: Dot Recall@3
- type: dot_recall@5
value: 0.72
name: Dot Recall@5
- type: dot_recall@10
value: 0.88
name: Dot Recall@10
- type: dot_ndcg@10
value: 0.6012297417081948
name: Dot Ndcg@10
- type: dot_mrr@10
value: 0.5137063492063492
name: Dot Mrr@10
- type: dot_map@100
value: 0.5174560618904659
name: Dot Map@100
- type: query_active_dims
value: 256.0
name: Query Active Dims
- type: query_sparsity_ratio
value: 0.9375
name: Query Sparsity Ratio
- type: corpus_active_dims
value: 256.0
name: Corpus Active Dims
- type: corpus_sparsity_ratio
value: 0.9375
name: Corpus Sparsity Ratio
- task:
type: sparse-information-retrieval
name: Sparse Information Retrieval
dataset:
name: NanoClimateFEVER
type: NanoClimateFEVER
metrics:
- type: dot_accuracy@1
value: 0.26
name: Dot Accuracy@1
- type: dot_accuracy@3
value: 0.54
name: Dot Accuracy@3
- type: dot_accuracy@5
value: 0.68
name: Dot Accuracy@5
- type: dot_accuracy@10
value: 0.8
name: Dot Accuracy@10
- type: dot_precision@1
value: 0.26
name: Dot Precision@1
- type: dot_precision@3
value: 0.2
name: Dot Precision@3
- type: dot_precision@5
value: 0.16
name: Dot Precision@5
- type: dot_precision@10
value: 0.11599999999999999
name: Dot Precision@10
- type: dot_recall@1
value: 0.125
name: Dot Recall@1
- type: dot_recall@3
value: 0.264
name: Dot Recall@3
- type: dot_recall@5
value: 0.3413333333333334
name: Dot Recall@5
- type: dot_recall@10
value: 0.45966666666666667
name: Dot Recall@10
- type: dot_ndcg@10
value: 0.35170577305757716
name: Dot Ndcg@10
- type: dot_mrr@10
value: 0.43010317460317443
name: Dot Mrr@10
- type: dot_map@100
value: 0.2687894311785997
name: Dot Map@100
- type: query_active_dims
value: 256.0
name: Query Active Dims
- type: query_sparsity_ratio
value: 0.9375
name: Query Sparsity Ratio
- type: corpus_active_dims
value: 256.0
name: Corpus Active Dims
- type: corpus_sparsity_ratio
value: 0.9375
name: Corpus Sparsity Ratio
- task:
type: sparse-information-retrieval
name: Sparse Information Retrieval
dataset:
name: NanoDBPedia
type: NanoDBPedia
metrics:
- type: dot_accuracy@1
value: 0.84
name: Dot Accuracy@1
- type: dot_accuracy@3
value: 0.86
name: Dot Accuracy@3
- type: dot_accuracy@5
value: 0.94
name: Dot Accuracy@5
- type: dot_accuracy@10
value: 0.98
name: Dot Accuracy@10
- type: dot_precision@1
value: 0.84
name: Dot Precision@1
- type: dot_precision@3
value: 0.64
name: Dot Precision@3
- type: dot_precision@5
value: 0.5840000000000001
name: Dot Precision@5
- type: dot_precision@10
value: 0.496
name: Dot Precision@10
- type: dot_recall@1
value: 0.10173542236179474
name: Dot Recall@1
- type: dot_recall@3
value: 0.17058256895318635
name: Dot Recall@3
- type: dot_recall@5
value: 0.2583095364918772
name: Dot Recall@5
- type: dot_recall@10
value: 0.3630014394355859
name: Dot Recall@10
- type: dot_ndcg@10
value: 0.6336927949275843
name: Dot Ndcg@10
- type: dot_mrr@10
value: 0.8761904761904762
name: Dot Mrr@10
- type: dot_map@100
value: 0.4758024592559406
name: Dot Map@100
- type: query_active_dims
value: 256.0
name: Query Active Dims
- type: query_sparsity_ratio
value: 0.9375
name: Query Sparsity Ratio
- type: corpus_active_dims
value: 256.0
name: Corpus Active Dims
- type: corpus_sparsity_ratio
value: 0.9375
name: Corpus Sparsity Ratio
- task:
type: sparse-information-retrieval
name: Sparse Information Retrieval
dataset:
name: NanoFEVER
type: NanoFEVER
metrics:
- type: dot_accuracy@1
value: 0.86
name: Dot Accuracy@1
- type: dot_accuracy@3
value: 0.92
name: Dot Accuracy@3
- type: dot_accuracy@5
value: 0.94
name: Dot Accuracy@5
- type: dot_accuracy@10
value: 0.94
name: Dot Accuracy@10
- type: dot_precision@1
value: 0.86
name: Dot Precision@1
- type: dot_precision@3
value: 0.3133333333333333
name: Dot Precision@3
- type: dot_precision@5
value: 0.19599999999999995
name: Dot Precision@5
- type: dot_precision@10
value: 0.09799999999999998
name: Dot Precision@10
- type: dot_recall@1
value: 0.8066666666666665
name: Dot Recall@1
- type: dot_recall@3
value: 0.8766666666666667
name: Dot Recall@3
- type: dot_recall@5
value: 0.9066666666666667
name: Dot Recall@5
- type: dot_recall@10
value: 0.9066666666666667
name: Dot Recall@10
- type: dot_ndcg@10
value: 0.8718114197539545
name: Dot Ndcg@10
- type: dot_mrr@10
value: 0.8873333333333332
name: Dot Mrr@10
- type: dot_map@100
value: 0.8545556012614837
name: Dot Map@100
- type: query_active_dims
value: 256.0
name: Query Active Dims
- type: query_sparsity_ratio
value: 0.9375
name: Query Sparsity Ratio
- type: corpus_active_dims
value: 256.0
name: Corpus Active Dims
- type: corpus_sparsity_ratio
value: 0.9375
name: Corpus Sparsity Ratio
- task:
type: sparse-information-retrieval
name: Sparse Information Retrieval
dataset:
name: NanoFiQA2018
type: NanoFiQA2018
metrics:
- type: dot_accuracy@1
value: 0.52
name: Dot Accuracy@1
- type: dot_accuracy@3
value: 0.68
name: Dot Accuracy@3
- type: dot_accuracy@5
value: 0.74
name: Dot Accuracy@5
- type: dot_accuracy@10
value: 0.78
name: Dot Accuracy@10
- type: dot_precision@1
value: 0.52
name: Dot Precision@1
- type: dot_precision@3
value: 0.32666666666666666
name: Dot Precision@3
- type: dot_precision@5
value: 0.244
name: Dot Precision@5
- type: dot_precision@10
value: 0.136
name: Dot Precision@10
- type: dot_recall@1
value: 0.27924603174603174
name: Dot Recall@1
- type: dot_recall@3
value: 0.46423809523809517
name: Dot Recall@3
- type: dot_recall@5
value: 0.5373730158730158
name: Dot Recall@5
- type: dot_recall@10
value: 0.5967063492063491
name: Dot Recall@10
- type: dot_ndcg@10
value: 0.524168679753325
name: Dot Ndcg@10
- type: dot_mrr@10
value: 0.6079999999999999
name: Dot Mrr@10
- type: dot_map@100
value: 0.4629550043583209
name: Dot Map@100
- type: query_active_dims
value: 256.0
name: Query Active Dims
- type: query_sparsity_ratio
value: 0.9375
name: Query Sparsity Ratio
- type: corpus_active_dims
value: 256.0
name: Corpus Active Dims
- type: corpus_sparsity_ratio
value: 0.9375
name: Corpus Sparsity Ratio
- task:
type: sparse-information-retrieval
name: Sparse Information Retrieval
dataset:
name: NanoHotpotQA
type: NanoHotpotQA
metrics:
- type: dot_accuracy@1
value: 0.78
name: Dot Accuracy@1
- type: dot_accuracy@3
value: 0.96
name: Dot Accuracy@3
- type: dot_accuracy@5
value: 0.96
name: Dot Accuracy@5
- type: dot_accuracy@10
value: 0.96
name: Dot Accuracy@10
- type: dot_precision@1
value: 0.78
name: Dot Precision@1
- type: dot_precision@3
value: 0.5266666666666666
name: Dot Precision@3
- type: dot_precision@5
value: 0.33599999999999997
name: Dot Precision@5
- type: dot_precision@10
value: 0.17199999999999996
name: Dot Precision@10
- type: dot_recall@1
value: 0.39
name: Dot Recall@1
- type: dot_recall@3
value: 0.79
name: Dot Recall@3
- type: dot_recall@5
value: 0.84
name: Dot Recall@5
- type: dot_recall@10
value: 0.86
name: Dot Recall@10
- type: dot_ndcg@10
value: 0.8057192735678995
name: Dot Ndcg@10
- type: dot_mrr@10
value: 0.86
name: Dot Mrr@10
- type: dot_map@100
value: 0.7534450002577441
name: Dot Map@100
- type: query_active_dims
value: 256.0
name: Query Active Dims
- type: query_sparsity_ratio
value: 0.9375
name: Query Sparsity Ratio
- type: corpus_active_dims
value: 256.0
name: Corpus Active Dims
- type: corpus_sparsity_ratio
value: 0.9375
name: Corpus Sparsity Ratio
- task:
type: sparse-information-retrieval
name: Sparse Information Retrieval
dataset:
name: NanoMSMARCO
type: NanoMSMARCO
metrics:
- type: dot_accuracy@1
value: 0.34
name: Dot Accuracy@1
- type: dot_accuracy@3
value: 0.58
name: Dot Accuracy@3
- type: dot_accuracy@5
value: 0.72
name: Dot Accuracy@5
- type: dot_accuracy@10
value: 0.88
name: Dot Accuracy@10
- type: dot_precision@1
value: 0.34
name: Dot Precision@1
- type: dot_precision@3
value: 0.19333333333333333
name: Dot Precision@3
- type: dot_precision@5
value: 0.14400000000000002
name: Dot Precision@5
- type: dot_precision@10
value: 0.088
name: Dot Precision@10
- type: dot_recall@1
value: 0.34
name: Dot Recall@1
- type: dot_recall@3
value: 0.58
name: Dot Recall@3
- type: dot_recall@5
value: 0.72
name: Dot Recall@5
- type: dot_recall@10
value: 0.88
name: Dot Recall@10
- type: dot_ndcg@10
value: 0.6004025758045302
name: Dot Ndcg@10
- type: dot_mrr@10
value: 0.5123253968253968
name: Dot Mrr@10
- type: dot_map@100
value: 0.516161874779488
name: Dot Map@100
- type: query_active_dims
value: 256.0
name: Query Active Dims
- type: query_sparsity_ratio
value: 0.9375
name: Query Sparsity Ratio
- type: corpus_active_dims
value: 256.0
name: Corpus Active Dims
- type: corpus_sparsity_ratio
value: 0.9375
name: Corpus Sparsity Ratio
- task:
type: sparse-information-retrieval
name: Sparse Information Retrieval
dataset:
name: NanoNFCorpus
type: NanoNFCorpus
metrics:
- type: dot_accuracy@1
value: 0.36
name: Dot Accuracy@1
- type: dot_accuracy@3
value: 0.54
name: Dot Accuracy@3
- type: dot_accuracy@5
value: 0.58
name: Dot Accuracy@5
- type: dot_accuracy@10
value: 0.78
name: Dot Accuracy@10
- type: dot_precision@1
value: 0.36
name: Dot Precision@1
- type: dot_precision@3
value: 0.3399999999999999
name: Dot Precision@3
- type: dot_precision@5
value: 0.324
name: Dot Precision@5
- type: dot_precision@10
value: 0.29600000000000004
name: Dot Precision@10
- type: dot_recall@1
value: 0.02204584498659392
name: Dot Recall@1
- type: dot_recall@3
value: 0.07879591204712627
name: Dot Recall@3
- type: dot_recall@5
value: 0.10547939299642282
name: Dot Recall@5
- type: dot_recall@10
value: 0.14785915311216402
name: Dot Recall@10
- type: dot_ndcg@10
value: 0.33938410167518285
name: Dot Ndcg@10
- type: dot_mrr@10
value: 0.4792698412698413
name: Dot Mrr@10
- type: dot_map@100
value: 0.15285384570175153
name: Dot Map@100
- type: query_active_dims
value: 256.0
name: Query Active Dims
- type: query_sparsity_ratio
value: 0.9375
name: Query Sparsity Ratio
- type: corpus_active_dims
value: 256.0
name: Corpus Active Dims
- type: corpus_sparsity_ratio
value: 0.9375
name: Corpus Sparsity Ratio
- task:
type: sparse-information-retrieval
name: Sparse Information Retrieval
dataset:
name: NanoNQ
type: NanoNQ
metrics:
- type: dot_accuracy@1
value: 0.48
name: Dot Accuracy@1
- type: dot_accuracy@3
value: 0.7
name: Dot Accuracy@3
- type: dot_accuracy@5
value: 0.78
name: Dot Accuracy@5
- type: dot_accuracy@10
value: 0.84
name: Dot Accuracy@10
- type: dot_precision@1
value: 0.48
name: Dot Precision@1
- type: dot_precision@3
value: 0.23333333333333336
name: Dot Precision@3
- type: dot_precision@5
value: 0.16
name: Dot Precision@5
- type: dot_precision@10
value: 0.092
name: Dot Precision@10
- type: dot_recall@1
value: 0.45
name: Dot Recall@1
- type: dot_recall@3
value: 0.65
name: Dot Recall@3
- type: dot_recall@5
value: 0.72
name: Dot Recall@5
- type: dot_recall@10
value: 0.81
name: Dot Recall@10
- type: dot_ndcg@10
value: 0.6405630856499873
name: Dot Ndcg@10
- type: dot_mrr@10
value: 0.6049444444444443
name: Dot Mrr@10
- type: dot_map@100
value: 0.5830795845663244
name: Dot Map@100
- type: query_active_dims
value: 256.0
name: Query Active Dims
- type: query_sparsity_ratio
value: 0.9375
name: Query Sparsity Ratio
- type: corpus_active_dims
value: 256.0
name: Corpus Active Dims
- type: corpus_sparsity_ratio
value: 0.9375
name: Corpus Sparsity Ratio
- task:
type: sparse-information-retrieval
name: Sparse Information Retrieval
dataset:
name: NanoQuoraRetrieval
type: NanoQuoraRetrieval
metrics:
- type: dot_accuracy@1
value: 0.9
name: Dot Accuracy@1
- type: dot_accuracy@3
value: 0.98
name: Dot Accuracy@3
- type: dot_accuracy@5
value: 1.0
name: Dot Accuracy@5
- type: dot_accuracy@10
value: 1.0
name: Dot Accuracy@10
- type: dot_precision@1
value: 0.9
name: Dot Precision@1
- type: dot_precision@3
value: 0.40666666666666657
name: Dot Precision@3
- type: dot_precision@5
value: 0.264
name: Dot Precision@5
- type: dot_precision@10
value: 0.13599999999999998
name: Dot Precision@10
- type: dot_recall@1
value: 0.7773333333333332
name: Dot Recall@1
- type: dot_recall@3
value: 0.9420000000000001
name: Dot Recall@3
- type: dot_recall@5
value: 0.986
name: Dot Recall@5
- type: dot_recall@10
value: 0.9933333333333334
name: Dot Recall@10
- type: dot_ndcg@10
value: 0.9416151444086611
name: Dot Ndcg@10
- type: dot_mrr@10
value: 0.9406666666666667
name: Dot Mrr@10
- type: dot_map@100
value: 0.9166897546897548
name: Dot Map@100
- type: query_active_dims
value: 256.0
name: Query Active Dims
- type: query_sparsity_ratio
value: 0.9375
name: Query Sparsity Ratio
- type: corpus_active_dims
value: 256.0
name: Corpus Active Dims
- type: corpus_sparsity_ratio
value: 0.9375
name: Corpus Sparsity Ratio
- task:
type: sparse-information-retrieval
name: Sparse Information Retrieval
dataset:
name: NanoSCIDOCS
type: NanoSCIDOCS
metrics:
- type: dot_accuracy@1
value: 0.54
name: Dot Accuracy@1
- type: dot_accuracy@3
value: 0.72
name: Dot Accuracy@3
- type: dot_accuracy@5
value: 0.8
name: Dot Accuracy@5
- type: dot_accuracy@10
value: 0.96
name: Dot Accuracy@10
- type: dot_precision@1
value: 0.54
name: Dot Precision@1
- type: dot_precision@3
value: 0.3533333333333333
name: Dot Precision@3
- type: dot_precision@5
value: 0.30000000000000004
name: Dot Precision@5
- type: dot_precision@10
value: 0.22
name: Dot Precision@10
- type: dot_recall@1
value: 0.11466666666666668
name: Dot Recall@1
- type: dot_recall@3
value: 0.22066666666666662
name: Dot Recall@3
- type: dot_recall@5
value: 0.3106666666666667
name: Dot Recall@5
- type: dot_recall@10
value: 0.45166666666666655
name: Dot Recall@10
- type: dot_ndcg@10
value: 0.43056509196331577
name: Dot Ndcg@10
- type: dot_mrr@10
value: 0.6608888888888889
name: Dot Mrr@10
- type: dot_map@100
value: 0.33416401376998806
name: Dot Map@100
- type: query_active_dims
value: 256.0
name: Query Active Dims
- type: query_sparsity_ratio
value: 0.9375
name: Query Sparsity Ratio
- type: corpus_active_dims
value: 256.0
name: Corpus Active Dims
- type: corpus_sparsity_ratio
value: 0.9375
name: Corpus Sparsity Ratio
- task:
type: sparse-information-retrieval
name: Sparse Information Retrieval
dataset:
name: NanoArguAna
type: NanoArguAna
metrics:
- type: dot_accuracy@1
value: 0.28
name: Dot Accuracy@1
- type: dot_accuracy@3
value: 0.68
name: Dot Accuracy@3
- type: dot_accuracy@5
value: 0.84
name: Dot Accuracy@5
- type: dot_accuracy@10
value: 0.96
name: Dot Accuracy@10
- type: dot_precision@1
value: 0.28
name: Dot Precision@1
- type: dot_precision@3
value: 0.22666666666666668
name: Dot Precision@3
- type: dot_precision@5
value: 0.16799999999999998
name: Dot Precision@5
- type: dot_precision@10
value: 0.09599999999999997
name: Dot Precision@10
- type: dot_recall@1
value: 0.28
name: Dot Recall@1
- type: dot_recall@3
value: 0.68
name: Dot Recall@3
- type: dot_recall@5
value: 0.84
name: Dot Recall@5
- type: dot_recall@10
value: 0.96
name: Dot Recall@10
- type: dot_ndcg@10
value: 0.6189399449298651
name: Dot Ndcg@10
- type: dot_mrr@10
value: 0.5095
name: Dot Mrr@10
- type: dot_map@100
value: 0.5115
name: Dot Map@100
- type: query_active_dims
value: 256.0
name: Query Active Dims
- type: query_sparsity_ratio
value: 0.9375
name: Query Sparsity Ratio
- type: corpus_active_dims
value: 256.0
name: Corpus Active Dims
- type: corpus_sparsity_ratio
value: 0.9375
name: Corpus Sparsity Ratio
- task:
type: sparse-information-retrieval
name: Sparse Information Retrieval
dataset:
name: NanoSciFact
type: NanoSciFact
metrics:
- type: dot_accuracy@1
value: 0.62
name: Dot Accuracy@1
- type: dot_accuracy@3
value: 0.72
name: Dot Accuracy@3
- type: dot_accuracy@5
value: 0.78
name: Dot Accuracy@5
- type: dot_accuracy@10
value: 0.86
name: Dot Accuracy@10
- type: dot_precision@1
value: 0.62
name: Dot Precision@1
- type: dot_precision@3
value: 0.25999999999999995
name: Dot Precision@3
- type: dot_precision@5
value: 0.17199999999999996
name: Dot Precision@5
- type: dot_precision@10
value: 0.09799999999999999
name: Dot Precision@10
- type: dot_recall@1
value: 0.595
name: Dot Recall@1
- type: dot_recall@3
value: 0.71
name: Dot Recall@3
- type: dot_recall@5
value: 0.765
name: Dot Recall@5
- type: dot_recall@10
value: 0.86
name: Dot Recall@10
- type: dot_ndcg@10
value: 0.7339772270342122
name: Dot Ndcg@10
- type: dot_mrr@10
value: 0.6960238095238094
name: Dot Mrr@10
- type: dot_map@100
value: 0.692771989570098
name: Dot Map@100
- type: query_active_dims
value: 256.0
name: Query Active Dims
- type: query_sparsity_ratio
value: 0.9375
name: Query Sparsity Ratio
- type: corpus_active_dims
value: 256.0
name: Corpus Active Dims
- type: corpus_sparsity_ratio
value: 0.9375
name: Corpus Sparsity Ratio
- task:
type: sparse-information-retrieval
name: Sparse Information Retrieval
dataset:
name: NanoTouche2020
type: NanoTouche2020
metrics:
- type: dot_accuracy@1
value: 0.5918367346938775
name: Dot Accuracy@1
- type: dot_accuracy@3
value: 0.8367346938775511
name: Dot Accuracy@3
- type: dot_accuracy@5
value: 0.9183673469387755
name: Dot Accuracy@5
- type: dot_accuracy@10
value: 0.9591836734693877
name: Dot Accuracy@10
- type: dot_precision@1
value: 0.5918367346938775
name: Dot Precision@1
- type: dot_precision@3
value: 0.5510204081632653
name: Dot Precision@3
- type: dot_precision@5
value: 0.5224489795918367
name: Dot Precision@5
- type: dot_precision@10
value: 0.436734693877551
name: Dot Precision@10
- type: dot_recall@1
value: 0.04213824203491695
name: Dot Recall@1
- type: dot_recall@3
value: 0.11466092557078722
name: Dot Recall@3
- type: dot_recall@5
value: 0.17849505170580585
name: Dot Recall@5
- type: dot_recall@10
value: 0.28879003826995
name: Dot Recall@10
- type: dot_ndcg@10
value: 0.48796783228419977
name: Dot Ndcg@10
- type: dot_mrr@10
value: 0.7384839650145772
name: Dot Mrr@10
- type: dot_map@100
value: 0.3666982120682313
name: Dot Map@100
- type: query_active_dims
value: 256.0
name: Query Active Dims
- type: query_sparsity_ratio
value: 0.9375
name: Query Sparsity Ratio
- type: corpus_active_dims
value: 256.0
name: Corpus Active Dims
- type: corpus_sparsity_ratio
value: 0.9375
name: Corpus Sparsity Ratio
- task:
type: sparse-nano-beir
name: Sparse Nano BEIR
dataset:
name: NanoBEIR mean
type: NanoBEIR_mean
metrics:
- type: dot_accuracy@1
value: 0.5670643642072213
name: Dot Accuracy@1
- type: dot_accuracy@3
value: 0.7474411302982732
name: Dot Accuracy@3
- type: dot_accuracy@5
value: 0.8214128728414443
name: Dot Accuracy@5
- type: dot_accuracy@10
value: 0.8999372056514913
name: Dot Accuracy@10
- type: dot_precision@1
value: 0.5670643642072213
name: Dot Precision@1
- type: dot_precision@3
value: 0.3516169544740973
name: Dot Precision@3
- type: dot_precision@5
value: 0.2749576138147567
name: Dot Precision@5
- type: dot_precision@10
value: 0.19082574568288851
name: Dot Precision@10
- type: dot_recall@1
value: 0.3326024775227695
name: Dot Recall@1
- type: dot_recall@3
value: 0.5032008334725021
name: Dot Recall@3
- type: dot_recall@5
value: 0.5776402818256761
name: Dot Recall@5
- type: dot_recall@10
value: 0.6598223317967217
name: Dot Recall@10
- type: dot_ndcg@10
value: 0.6138856111392534
name: Dot Ndcg@10
- type: dot_mrr@10
value: 0.6772099997508161
name: Dot Mrr@10
- type: dot_map@100
value: 0.529958982419825
name: Dot Map@100
- type: query_active_dims
value: 256.0
name: Query Active Dims
- type: query_sparsity_ratio
value: 0.9375
name: Query Sparsity Ratio
- type: corpus_active_dims
value: 256.0
name: Corpus Active Dims
- type: corpus_sparsity_ratio
value: 0.9375
name: Corpus Sparsity Ratio
---
# Sparse CSR model trained on Natural Questions
This is a [CSR Sparse Encoder](https://www.sbert.net/docs/sparse_encoder/usage/usage.html) model finetuned from [mixedbread-ai/mxbai-embed-large-v1](https://huggingface.co/mixedbread-ai/mxbai-embed-large-v1) on the [natural-questions](https://huggingface.co/datasets/sentence-transformers/natural-questions) dataset using the [sentence-transformers](https://www.SBERT.net) library. It maps sentences & paragraphs to a 4096-dimensional sparse vector space with 256 maximum active dimensions and can be used for semantic search and sparse retrieval.
## Model Details
### Model Description
- **Model Type:** CSR Sparse Encoder
- **Base model:** [mixedbread-ai/mxbai-embed-large-v1](https://huggingface.co/mixedbread-ai/mxbai-embed-large-v1) <!-- at revision db9d1fe0f31addb4978201b2bf3e577f3f8900d2 -->
- **Maximum Sequence Length:** 512 tokens
- **Output Dimensionality:** 4096 dimensions (trained with 256 maximum active dimensions)
- **Similarity Function:** Dot Product
- **Training Dataset:**
- [natural-questions](https://huggingface.co/datasets/sentence-transformers/natural-questions)
- **Language:** en
- **License:** apache-2.0
### Model Sources
- **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
- **Documentation:** [Sparse Encoder Documentation](https://www.sbert.net/docs/sparse_encoder/usage/usage.html)
- **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
- **Hugging Face:** [Sparse Encoders on Hugging Face](https://huggingface.co/models?library=sentence-transformers&other=sparse-encoder)
### Full Model Architecture
```
SparseEncoder(
(0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: BertModel
(1): Pooling({'word_embedding_dimension': 1024, 'pooling_mode_cls_token': True, 'pooling_mode_mean_tokens': False, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
(2): CSRSparsity({'input_dim': 1024, 'hidden_dim': 4096, 'k': 256, 'k_aux': 512, 'normalize': False, 'dead_threshold': 30})
)
```
## Usage
### Direct Usage (Sentence Transformers)
First install the Sentence Transformers library:
```bash
pip install -U sentence-transformers
```
Then you can load this model and run inference.
```python
from sentence_transformers import SparseEncoder
# Download from the ๐ค Hub
model = SparseEncoder("tomaarsen/csr-mxbai-embed-large-v1-nq-updated-3-gamma")
# Run inference
queries = [
"who is cornelius in the book of acts",
]
documents = [
'Cornelius the Centurion Cornelius (Greek: ฮฮฟฯฮฝฮฎฮปฮนฮฟฯ) was a Roman centurion who is considered by Christians to be one of the first Gentiles to convert to the faith, as related in Acts of the Apostles.',
"Joe Ranft Ranft reunited with Lasseter when he was hired by Pixar in 1991 as their head of story.[1] There he worked on all of their films produced up to 2006; this included Toy Story (for which he received an Academy Award nomination) and A Bug's Life, as the co-story writer and others as story supervisor. His final film was Cars. He also voiced characters in many of the films, including Heimlich the caterpillar in A Bug's Life, Wheezy the penguin in Toy Story 2, and Jacques the shrimp in Finding Nemo.[1]",
'Wonderful Tonight "Wonderful Tonight" is a ballad written by Eric Clapton. It was included on Clapton\'s 1977 album Slowhand. Clapton wrote the song about Pattie Boyd.[1] The female vocal harmonies on the song are provided by Marcella Detroit (then Marcy Levy) and Yvonne Elliman.',
]
query_embeddings = model.encode_query(queries)
document_embeddings = model.encode_document(documents)
print(query_embeddings.shape, document_embeddings.shape)
# [1, 4096] [3, 4096]
# Get the similarity scores for the embeddings
similarities = model.similarity(query_embeddings, document_embeddings)
print(similarities)
# tensor([[109.6969, 27.9723, 19.3123]])
```
<!--
### Direct Usage (Transformers)
<details><summary>Click to see the direct usage in Transformers</summary>
</details>
-->
<!--
### Downstream Usage (Sentence Transformers)
You can finetune this model on your own dataset.
<details><summary>Click to expand</summary>
</details>
-->
<!--
### Out-of-Scope Use
*List how the model may foreseeably be misused and address what users ought not to do with the model.*
-->
## Evaluation
### Metrics
#### Sparse Information Retrieval
* Dataset: `NanoMSMARCO_8`
* Evaluated with [<code>SparseInformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sparse_encoder/evaluation.html#sentence_transformers.sparse_encoder.evaluation.SparseInformationRetrievalEvaluator) with these parameters:
```json
{
"max_active_dims": 8
}
```
| Metric | Value |
|:----------------------|:-----------|
| dot_accuracy@1 | 0.16 |
| dot_accuracy@3 | 0.26 |
| dot_accuracy@5 | 0.3 |
| dot_accuracy@10 | 0.38 |
| dot_precision@1 | 0.16 |
| dot_precision@3 | 0.0867 |
| dot_precision@5 | 0.06 |
| dot_precision@10 | 0.038 |
| dot_recall@1 | 0.16 |
| dot_recall@3 | 0.26 |
| dot_recall@5 | 0.3 |
| dot_recall@10 | 0.38 |
| **dot_ndcg@10** | **0.2644** |
| dot_mrr@10 | 0.2287 |
| dot_map@100 | 0.2422 |
| query_active_dims | 8.0 |
| query_sparsity_ratio | 0.998 |
| corpus_active_dims | 8.0 |
| corpus_sparsity_ratio | 0.998 |
#### Sparse Nano BEIR
* Dataset: `NanoBEIR_mean_8`
* Evaluated with [<code>SparseNanoBEIREvaluator</code>](https://sbert.net/docs/package_reference/sparse_encoder/evaluation.html#sentence_transformers.sparse_encoder.evaluation.SparseNanoBEIREvaluator) with these parameters:
```json
{
"dataset_names": [
"msmarco"
],
"max_active_dims": 8
}
```
| Metric | Value |
|:----------------------|:-----------|
| dot_accuracy@1 | 0.16 |
| dot_accuracy@3 | 0.26 |
| dot_accuracy@5 | 0.3 |
| dot_accuracy@10 | 0.38 |
| dot_precision@1 | 0.16 |
| dot_precision@3 | 0.0867 |
| dot_precision@5 | 0.06 |
| dot_precision@10 | 0.038 |
| dot_recall@1 | 0.16 |
| dot_recall@3 | 0.26 |
| dot_recall@5 | 0.3 |
| dot_recall@10 | 0.38 |
| **dot_ndcg@10** | **0.2644** |
| dot_mrr@10 | 0.2287 |
| dot_map@100 | 0.2422 |
| query_active_dims | 8.0 |
| query_sparsity_ratio | 0.998 |
| corpus_active_dims | 8.0 |
| corpus_sparsity_ratio | 0.998 |
#### Sparse Information Retrieval
* Dataset: `NanoMSMARCO_16`
* Evaluated with [<code>SparseInformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sparse_encoder/evaluation.html#sentence_transformers.sparse_encoder.evaluation.SparseInformationRetrievalEvaluator) with these parameters:
```json
{
"max_active_dims": 16
}
```
| Metric | Value |
|:----------------------|:-----------|
| dot_accuracy@1 | 0.2 |
| dot_accuracy@3 | 0.36 |
| dot_accuracy@5 | 0.52 |
| dot_accuracy@10 | 0.56 |
| dot_precision@1 | 0.2 |
| dot_precision@3 | 0.12 |
| dot_precision@5 | 0.104 |
| dot_precision@10 | 0.056 |
| dot_recall@1 | 0.2 |
| dot_recall@3 | 0.36 |
| dot_recall@5 | 0.52 |
| dot_recall@10 | 0.56 |
| **dot_ndcg@10** | **0.3779** |
| dot_mrr@10 | 0.3195 |
| dot_map@100 | 0.3314 |
| query_active_dims | 16.0 |
| query_sparsity_ratio | 0.9961 |
| corpus_active_dims | 16.0 |
| corpus_sparsity_ratio | 0.9961 |
#### Sparse Nano BEIR
* Dataset: `NanoBEIR_mean_16`
* Evaluated with [<code>SparseNanoBEIREvaluator</code>](https://sbert.net/docs/package_reference/sparse_encoder/evaluation.html#sentence_transformers.sparse_encoder.evaluation.SparseNanoBEIREvaluator) with these parameters:
```json
{
"dataset_names": [
"msmarco"
],
"max_active_dims": 16
}
```
| Metric | Value |
|:----------------------|:-----------|
| dot_accuracy@1 | 0.2 |
| dot_accuracy@3 | 0.36 |
| dot_accuracy@5 | 0.52 |
| dot_accuracy@10 | 0.56 |
| dot_precision@1 | 0.2 |
| dot_precision@3 | 0.12 |
| dot_precision@5 | 0.104 |
| dot_precision@10 | 0.056 |
| dot_recall@1 | 0.2 |
| dot_recall@3 | 0.36 |
| dot_recall@5 | 0.52 |
| dot_recall@10 | 0.56 |
| **dot_ndcg@10** | **0.3779** |
| dot_mrr@10 | 0.3195 |
| dot_map@100 | 0.3314 |
| query_active_dims | 16.0 |
| query_sparsity_ratio | 0.9961 |
| corpus_active_dims | 16.0 |
| corpus_sparsity_ratio | 0.9961 |
#### Sparse Information Retrieval
* Dataset: `NanoMSMARCO_32`
* Evaluated with [<code>SparseInformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sparse_encoder/evaluation.html#sentence_transformers.sparse_encoder.evaluation.SparseInformationRetrievalEvaluator) with these parameters:
```json
{
"max_active_dims": 32
}
```
| Metric | Value |
|:----------------------|:-----------|
| dot_accuracy@1 | 0.28 |
| dot_accuracy@3 | 0.46 |
| dot_accuracy@5 | 0.62 |
| dot_accuracy@10 | 0.74 |
| dot_precision@1 | 0.28 |
| dot_precision@3 | 0.1533 |
| dot_precision@5 | 0.124 |
| dot_precision@10 | 0.074 |
| dot_recall@1 | 0.28 |
| dot_recall@3 | 0.46 |
| dot_recall@5 | 0.62 |
| dot_recall@10 | 0.74 |
| **dot_ndcg@10** | **0.4922** |
| dot_mrr@10 | 0.415 |
| dot_map@100 | 0.4254 |
| query_active_dims | 32.0 |
| query_sparsity_ratio | 0.9922 |
| corpus_active_dims | 32.0 |
| corpus_sparsity_ratio | 0.9922 |
#### Sparse Nano BEIR
* Dataset: `NanoBEIR_mean_32`
* Evaluated with [<code>SparseNanoBEIREvaluator</code>](https://sbert.net/docs/package_reference/sparse_encoder/evaluation.html#sentence_transformers.sparse_encoder.evaluation.SparseNanoBEIREvaluator) with these parameters:
```json
{
"dataset_names": [
"msmarco"
],
"max_active_dims": 32
}
```
| Metric | Value |
|:----------------------|:-----------|
| dot_accuracy@1 | 0.28 |
| dot_accuracy@3 | 0.46 |
| dot_accuracy@5 | 0.62 |
| dot_accuracy@10 | 0.74 |
| dot_precision@1 | 0.28 |
| dot_precision@3 | 0.1533 |
| dot_precision@5 | 0.124 |
| dot_precision@10 | 0.074 |
| dot_recall@1 | 0.28 |
| dot_recall@3 | 0.46 |
| dot_recall@5 | 0.62 |
| dot_recall@10 | 0.74 |
| **dot_ndcg@10** | **0.4922** |
| dot_mrr@10 | 0.415 |
| dot_map@100 | 0.4254 |
| query_active_dims | 32.0 |
| query_sparsity_ratio | 0.9922 |
| corpus_active_dims | 32.0 |
| corpus_sparsity_ratio | 0.9922 |
#### Sparse Information Retrieval
* Dataset: `NanoMSMARCO_64`
* Evaluated with [<code>SparseInformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sparse_encoder/evaluation.html#sentence_transformers.sparse_encoder.evaluation.SparseInformationRetrievalEvaluator) with these parameters:
```json
{
"max_active_dims": 64
}
```
| Metric | Value |
|:----------------------|:-----------|
| dot_accuracy@1 | 0.26 |
| dot_accuracy@3 | 0.56 |
| dot_accuracy@5 | 0.66 |
| dot_accuracy@10 | 0.78 |
| dot_precision@1 | 0.26 |
| dot_precision@3 | 0.1867 |
| dot_precision@5 | 0.132 |
| dot_precision@10 | 0.078 |
| dot_recall@1 | 0.26 |
| dot_recall@3 | 0.56 |
| dot_recall@5 | 0.66 |
| dot_recall@10 | 0.78 |
| **dot_ndcg@10** | **0.5211** |
| dot_mrr@10 | 0.4382 |
| dot_map@100 | 0.4468 |
| query_active_dims | 64.0 |
| query_sparsity_ratio | 0.9844 |
| corpus_active_dims | 64.0 |
| corpus_sparsity_ratio | 0.9844 |
#### Sparse Nano BEIR
* Dataset: `NanoBEIR_mean_64`
* Evaluated with [<code>SparseNanoBEIREvaluator</code>](https://sbert.net/docs/package_reference/sparse_encoder/evaluation.html#sentence_transformers.sparse_encoder.evaluation.SparseNanoBEIREvaluator) with these parameters:
```json
{
"dataset_names": [
"msmarco"
],
"max_active_dims": 64
}
```
| Metric | Value |
|:----------------------|:-----------|
| dot_accuracy@1 | 0.26 |
| dot_accuracy@3 | 0.56 |
| dot_accuracy@5 | 0.66 |
| dot_accuracy@10 | 0.78 |
| dot_precision@1 | 0.26 |
| dot_precision@3 | 0.1867 |
| dot_precision@5 | 0.132 |
| dot_precision@10 | 0.078 |
| dot_recall@1 | 0.26 |
| dot_recall@3 | 0.56 |
| dot_recall@5 | 0.66 |
| dot_recall@10 | 0.78 |
| **dot_ndcg@10** | **0.5211** |
| dot_mrr@10 | 0.4382 |
| dot_map@100 | 0.4468 |
| query_active_dims | 64.0 |
| query_sparsity_ratio | 0.9844 |
| corpus_active_dims | 64.0 |
| corpus_sparsity_ratio | 0.9844 |
#### Sparse Information Retrieval
* Dataset: `NanoMSMARCO_128`
* Evaluated with [<code>SparseInformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sparse_encoder/evaluation.html#sentence_transformers.sparse_encoder.evaluation.SparseInformationRetrievalEvaluator) with these parameters:
```json
{
"max_active_dims": 128
}
```
| Metric | Value |
|:----------------------|:-----------|
| dot_accuracy@1 | 0.3 |
| dot_accuracy@3 | 0.58 |
| dot_accuracy@5 | 0.72 |
| dot_accuracy@10 | 0.78 |
| dot_precision@1 | 0.3 |
| dot_precision@3 | 0.1933 |
| dot_precision@5 | 0.144 |
| dot_precision@10 | 0.078 |
| dot_recall@1 | 0.3 |
| dot_recall@3 | 0.58 |
| dot_recall@5 | 0.72 |
| dot_recall@10 | 0.78 |
| **dot_ndcg@10** | **0.5452** |
| dot_mrr@10 | 0.4694 |
| dot_map@100 | 0.4801 |
| query_active_dims | 128.0 |
| query_sparsity_ratio | 0.9688 |
| corpus_active_dims | 128.0 |
| corpus_sparsity_ratio | 0.9688 |
#### Sparse Nano BEIR
* Dataset: `NanoBEIR_mean_128`
* Evaluated with [<code>SparseNanoBEIREvaluator</code>](https://sbert.net/docs/package_reference/sparse_encoder/evaluation.html#sentence_transformers.sparse_encoder.evaluation.SparseNanoBEIREvaluator) with these parameters:
```json
{
"dataset_names": [
"msmarco"
],
"max_active_dims": 128
}
```
| Metric | Value |
|:----------------------|:-----------|
| dot_accuracy@1 | 0.3 |
| dot_accuracy@3 | 0.58 |
| dot_accuracy@5 | 0.72 |
| dot_accuracy@10 | 0.78 |
| dot_precision@1 | 0.3 |
| dot_precision@3 | 0.1933 |
| dot_precision@5 | 0.144 |
| dot_precision@10 | 0.078 |
| dot_recall@1 | 0.3 |
| dot_recall@3 | 0.58 |
| dot_recall@5 | 0.72 |
| dot_recall@10 | 0.78 |
| **dot_ndcg@10** | **0.5452** |
| dot_mrr@10 | 0.4694 |
| dot_map@100 | 0.4801 |
| query_active_dims | 128.0 |
| query_sparsity_ratio | 0.9688 |
| corpus_active_dims | 128.0 |
| corpus_sparsity_ratio | 0.9688 |
#### Sparse Information Retrieval
* Dataset: `NanoMSMARCO_256`
* Evaluated with [<code>SparseInformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sparse_encoder/evaluation.html#sentence_transformers.sparse_encoder.evaluation.SparseInformationRetrievalEvaluator) with these parameters:
```json
{
"max_active_dims": 256
}
```
| Metric | Value |
|:----------------------|:-----------|
| dot_accuracy@1 | 0.34 |
| dot_accuracy@3 | 0.58 |
| dot_accuracy@5 | 0.72 |
| dot_accuracy@10 | 0.88 |
| dot_precision@1 | 0.34 |
| dot_precision@3 | 0.1933 |
| dot_precision@5 | 0.144 |
| dot_precision@10 | 0.088 |
| dot_recall@1 | 0.34 |
| dot_recall@3 | 0.58 |
| dot_recall@5 | 0.72 |
| dot_recall@10 | 0.88 |
| **dot_ndcg@10** | **0.6012** |
| dot_mrr@10 | 0.5137 |
| dot_map@100 | 0.5175 |
| query_active_dims | 256.0 |
| query_sparsity_ratio | 0.9375 |
| corpus_active_dims | 256.0 |
| corpus_sparsity_ratio | 0.9375 |
#### Sparse Nano BEIR
* Dataset: `NanoBEIR_mean_256`
* Evaluated with [<code>SparseNanoBEIREvaluator</code>](https://sbert.net/docs/package_reference/sparse_encoder/evaluation.html#sentence_transformers.sparse_encoder.evaluation.SparseNanoBEIREvaluator) with these parameters:
```json
{
"dataset_names": [
"msmarco"
],
"max_active_dims": 256
}
```
| Metric | Value |
|:----------------------|:-----------|
| dot_accuracy@1 | 0.34 |
| dot_accuracy@3 | 0.58 |
| dot_accuracy@5 | 0.72 |
| dot_accuracy@10 | 0.88 |
| dot_precision@1 | 0.34 |
| dot_precision@3 | 0.1933 |
| dot_precision@5 | 0.144 |
| dot_precision@10 | 0.088 |
| dot_recall@1 | 0.34 |
| dot_recall@3 | 0.58 |
| dot_recall@5 | 0.72 |
| dot_recall@10 | 0.88 |
| **dot_ndcg@10** | **0.6012** |
| dot_mrr@10 | 0.5137 |
| dot_map@100 | 0.5175 |
| query_active_dims | 256.0 |
| query_sparsity_ratio | 0.9375 |
| corpus_active_dims | 256.0 |
| corpus_sparsity_ratio | 0.9375 |
#### Sparse Information Retrieval
* Datasets: `NanoClimateFEVER`, `NanoDBPedia`, `NanoFEVER`, `NanoFiQA2018`, `NanoHotpotQA`, `NanoMSMARCO`, `NanoNFCorpus`, `NanoNQ`, `NanoQuoraRetrieval`, `NanoSCIDOCS`, `NanoArguAna`, `NanoSciFact` and `NanoTouche2020`
* Evaluated with [<code>SparseInformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sparse_encoder/evaluation.html#sentence_transformers.sparse_encoder.evaluation.SparseInformationRetrievalEvaluator)
| Metric | NanoClimateFEVER | NanoDBPedia | NanoFEVER | NanoFiQA2018 | NanoHotpotQA | NanoMSMARCO | NanoNFCorpus | NanoNQ | NanoQuoraRetrieval | NanoSCIDOCS | NanoArguAna | NanoSciFact | NanoTouche2020 |
|:----------------------|:-----------------|:------------|:-----------|:-------------|:-------------|:------------|:-------------|:-----------|:-------------------|:------------|:------------|:------------|:---------------|
| dot_accuracy@1 | 0.26 | 0.84 | 0.86 | 0.52 | 0.78 | 0.34 | 0.36 | 0.48 | 0.9 | 0.54 | 0.28 | 0.62 | 0.5918 |
| dot_accuracy@3 | 0.54 | 0.86 | 0.92 | 0.68 | 0.96 | 0.58 | 0.54 | 0.7 | 0.98 | 0.72 | 0.68 | 0.72 | 0.8367 |
| dot_accuracy@5 | 0.68 | 0.94 | 0.94 | 0.74 | 0.96 | 0.72 | 0.58 | 0.78 | 1.0 | 0.8 | 0.84 | 0.78 | 0.9184 |
| dot_accuracy@10 | 0.8 | 0.98 | 0.94 | 0.78 | 0.96 | 0.88 | 0.78 | 0.84 | 1.0 | 0.96 | 0.96 | 0.86 | 0.9592 |
| dot_precision@1 | 0.26 | 0.84 | 0.86 | 0.52 | 0.78 | 0.34 | 0.36 | 0.48 | 0.9 | 0.54 | 0.28 | 0.62 | 0.5918 |
| dot_precision@3 | 0.2 | 0.64 | 0.3133 | 0.3267 | 0.5267 | 0.1933 | 0.34 | 0.2333 | 0.4067 | 0.3533 | 0.2267 | 0.26 | 0.551 |
| dot_precision@5 | 0.16 | 0.584 | 0.196 | 0.244 | 0.336 | 0.144 | 0.324 | 0.16 | 0.264 | 0.3 | 0.168 | 0.172 | 0.5224 |
| dot_precision@10 | 0.116 | 0.496 | 0.098 | 0.136 | 0.172 | 0.088 | 0.296 | 0.092 | 0.136 | 0.22 | 0.096 | 0.098 | 0.4367 |
| dot_recall@1 | 0.125 | 0.1017 | 0.8067 | 0.2792 | 0.39 | 0.34 | 0.022 | 0.45 | 0.7773 | 0.1147 | 0.28 | 0.595 | 0.0421 |
| dot_recall@3 | 0.264 | 0.1706 | 0.8767 | 0.4642 | 0.79 | 0.58 | 0.0788 | 0.65 | 0.942 | 0.2207 | 0.68 | 0.71 | 0.1147 |
| dot_recall@5 | 0.3413 | 0.2583 | 0.9067 | 0.5374 | 0.84 | 0.72 | 0.1055 | 0.72 | 0.986 | 0.3107 | 0.84 | 0.765 | 0.1785 |
| dot_recall@10 | 0.4597 | 0.363 | 0.9067 | 0.5967 | 0.86 | 0.88 | 0.1479 | 0.81 | 0.9933 | 0.4517 | 0.96 | 0.86 | 0.2888 |
| **dot_ndcg@10** | **0.3517** | **0.6337** | **0.8718** | **0.5242** | **0.8057** | **0.6004** | **0.3394** | **0.6406** | **0.9416** | **0.4306** | **0.6189** | **0.734** | **0.488** |
| dot_mrr@10 | 0.4301 | 0.8762 | 0.8873 | 0.608 | 0.86 | 0.5123 | 0.4793 | 0.6049 | 0.9407 | 0.6609 | 0.5095 | 0.696 | 0.7385 |
| dot_map@100 | 0.2688 | 0.4758 | 0.8546 | 0.463 | 0.7534 | 0.5162 | 0.1529 | 0.5831 | 0.9167 | 0.3342 | 0.5115 | 0.6928 | 0.3667 |
| query_active_dims | 256.0 | 256.0 | 256.0 | 256.0 | 256.0 | 256.0 | 256.0 | 256.0 | 256.0 | 256.0 | 256.0 | 256.0 | 256.0 |
| query_sparsity_ratio | 0.9375 | 0.9375 | 0.9375 | 0.9375 | 0.9375 | 0.9375 | 0.9375 | 0.9375 | 0.9375 | 0.9375 | 0.9375 | 0.9375 | 0.9375 |
| corpus_active_dims | 256.0 | 256.0 | 256.0 | 256.0 | 256.0 | 256.0 | 256.0 | 256.0 | 256.0 | 256.0 | 256.0 | 256.0 | 256.0 |
| corpus_sparsity_ratio | 0.9375 | 0.9375 | 0.9375 | 0.9375 | 0.9375 | 0.9375 | 0.9375 | 0.9375 | 0.9375 | 0.9375 | 0.9375 | 0.9375 | 0.9375 |
#### Sparse Nano BEIR
* Dataset: `NanoBEIR_mean`
* Evaluated with [<code>SparseNanoBEIREvaluator</code>](https://sbert.net/docs/package_reference/sparse_encoder/evaluation.html#sentence_transformers.sparse_encoder.evaluation.SparseNanoBEIREvaluator) with these parameters:
```json
{
"dataset_names": [
"climatefever",
"dbpedia",
"fever",
"fiqa2018",
"hotpotqa",
"msmarco",
"nfcorpus",
"nq",
"quoraretrieval",
"scidocs",
"arguana",
"scifact",
"touche2020"
]
}
```
| Metric | Value |
|:----------------------|:-----------|
| dot_accuracy@1 | 0.5671 |
| dot_accuracy@3 | 0.7474 |
| dot_accuracy@5 | 0.8214 |
| dot_accuracy@10 | 0.8999 |
| dot_precision@1 | 0.5671 |
| dot_precision@3 | 0.3516 |
| dot_precision@5 | 0.275 |
| dot_precision@10 | 0.1908 |
| dot_recall@1 | 0.3326 |
| dot_recall@3 | 0.5032 |
| dot_recall@5 | 0.5776 |
| dot_recall@10 | 0.6598 |
| **dot_ndcg@10** | **0.6139** |
| dot_mrr@10 | 0.6772 |
| dot_map@100 | 0.53 |
| query_active_dims | 256.0 |
| query_sparsity_ratio | 0.9375 |
| corpus_active_dims | 256.0 |
| corpus_sparsity_ratio | 0.9375 |
<!--
## Bias, Risks and Limitations
*What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
-->
<!--
### Recommendations
*What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
-->
## Training Details
### Training Dataset
#### natural-questions
* Dataset: [natural-questions](https://huggingface.co/datasets/sentence-transformers/natural-questions) at [f9e894e](https://huggingface.co/datasets/sentence-transformers/natural-questions/tree/f9e894e1081e206e577b4eaa9ee6de2b06ae6f17)
* Size: 99,000 training samples
* Columns: <code>query</code> and <code>answer</code>
* Approximate statistics based on the first 1000 samples:
| | query | answer |
|:--------|:-----------------------------------------------------------------------------------|:------------------------------------------------------------------------------------|
| type | string | string |
| details | <ul><li>min: 10 tokens</li><li>mean: 11.71 tokens</li><li>max: 26 tokens</li></ul> | <ul><li>min: 4 tokens</li><li>mean: 131.81 tokens</li><li>max: 450 tokens</li></ul> |
* Samples:
| query | answer |
|:--------------------------------------------------------------|:----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| <code>who played the father in papa don't preach</code> | <code>Alex McArthur Alex McArthur (born March 6, 1957) is an American actor.</code> |
| <code>where was the location of the battle of hastings</code> | <code>Battle of Hastings The Battle of Hastings[a] was fought on 14 October 1066 between the Norman-French army of William, the Duke of Normandy, and an English army under the Anglo-Saxon King Harold Godwinson, beginning the Norman conquest of England. It took place approximately 7 miles (11 kilometres) northwest of Hastings, close to the present-day town of Battle, East Sussex, and was a decisive Norman victory.</code> |
| <code>how many puppies can a dog give birth to</code> | <code>Canine reproduction The largest litter size to date was set by a Neapolitan Mastiff in Manea, Cambridgeshire, UK on November 29, 2004; the litter was 24 puppies.[22]</code> |
* Loss: [<code>CSRLoss</code>](https://sbert.net/docs/package_reference/sparse_encoder/losses.html#csrloss) with these parameters:
```json
{
"beta": 0.1,
"gamma": 3.0,
"loss": "SparseMultipleNegativesRankingLoss(scale=1.0, similarity_fct='dot_score')"
}
```
### Evaluation Dataset
#### natural-questions
* Dataset: [natural-questions](https://huggingface.co/datasets/sentence-transformers/natural-questions) at [f9e894e](https://huggingface.co/datasets/sentence-transformers/natural-questions/tree/f9e894e1081e206e577b4eaa9ee6de2b06ae6f17)
* Size: 1,000 evaluation samples
* Columns: <code>query</code> and <code>answer</code>
* Approximate statistics based on the first 1000 samples:
| | query | answer |
|:--------|:-----------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------|
| type | string | string |
| details | <ul><li>min: 10 tokens</li><li>mean: 11.69 tokens</li><li>max: 23 tokens</li></ul> | <ul><li>min: 15 tokens</li><li>mean: 134.01 tokens</li><li>max: 512 tokens</li></ul> |
* Samples:
| query | answer |
|:-------------------------------------------------------|:-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| <code>where is the tiber river located in italy</code> | <code>Tiber The Tiber (/หtaษชbษr/, Latin: Tiberis,[1] Italian: Tevere [หteหvere])[2] is the third-longest river in Italy, rising in the Apennine Mountains in Emilia-Romagna and flowing 406 kilometres (252ย mi) through Tuscany, Umbria and Lazio, where it is joined by the river Aniene, to the Tyrrhenian Sea, between Ostia and Fiumicino.[3] It drains a basin estimated at 17,375 square kilometres (6,709ย sqย mi). The river has achieved lasting fame as the main watercourse of the city of Rome, founded on its eastern banks.</code> |
| <code>what kind of car does jay gatsby drive</code> | <code>Jay Gatsby At the Buchanan home, Jordan Baker, Nick, Jay, and the Buchanans decide to visit New York City. Tom borrows Gatsby's yellow Rolls Royce to drive up to the city. On the way to New York City, Tom makes a detour at a gas station in "the Valley of Ashes", a run-down part of Long Island. The owner, George Wilson, shares his concern that his wife, Myrtle, may be having an affair. This unnerves Tom, who has been having an affair with Myrtle, and he leaves in a hurry.</code> |
| <code>who sings if i can dream about you</code> | <code>I Can Dream About You "I Can Dream About You" is a song performed by American singer Dan Hartman on the soundtrack album of the film Streets of Fire. Released in 1984 as a single from the soundtrack, and included on Hartman's album I Can Dream About You, it reached number 6 on the Billboard Hot 100.[1]</code> |
* Loss: [<code>CSRLoss</code>](https://sbert.net/docs/package_reference/sparse_encoder/losses.html#csrloss) with these parameters:
```json
{
"beta": 0.1,
"gamma": 3.0,
"loss": "SparseMultipleNegativesRankingLoss(scale=1.0, similarity_fct='dot_score')"
}
```
### Training Hyperparameters
#### Non-Default Hyperparameters
- `eval_strategy`: steps
- `per_device_train_batch_size`: 64
- `per_device_eval_batch_size`: 64
- `learning_rate`: 4e-05
- `num_train_epochs`: 1
- `bf16`: True
- `load_best_model_at_end`: True
- `batch_sampler`: no_duplicates
#### All Hyperparameters
<details><summary>Click to expand</summary>
- `overwrite_output_dir`: False
- `do_predict`: False
- `eval_strategy`: steps
- `prediction_loss_only`: True
- `per_device_train_batch_size`: 64
- `per_device_eval_batch_size`: 64
- `per_gpu_train_batch_size`: None
- `per_gpu_eval_batch_size`: None
- `gradient_accumulation_steps`: 1
- `eval_accumulation_steps`: None
- `torch_empty_cache_steps`: None
- `learning_rate`: 4e-05
- `weight_decay`: 0.0
- `adam_beta1`: 0.9
- `adam_beta2`: 0.999
- `adam_epsilon`: 1e-08
- `max_grad_norm`: 1.0
- `num_train_epochs`: 1
- `max_steps`: -1
- `lr_scheduler_type`: linear
- `lr_scheduler_kwargs`: {}
- `warmup_ratio`: 0.0
- `warmup_steps`: 0
- `log_level`: passive
- `log_level_replica`: warning
- `log_on_each_node`: True
- `logging_nan_inf_filter`: True
- `save_safetensors`: True
- `save_on_each_node`: False
- `save_only_model`: False
- `restore_callback_states_from_checkpoint`: False
- `no_cuda`: False
- `use_cpu`: False
- `use_mps_device`: False
- `seed`: 42
- `data_seed`: None
- `jit_mode_eval`: False
- `use_ipex`: False
- `bf16`: True
- `fp16`: False
- `fp16_opt_level`: O1
- `half_precision_backend`: auto
- `bf16_full_eval`: False
- `fp16_full_eval`: False
- `tf32`: None
- `local_rank`: 0
- `ddp_backend`: None
- `tpu_num_cores`: None
- `tpu_metrics_debug`: False
- `debug`: []
- `dataloader_drop_last`: False
- `dataloader_num_workers`: 0
- `dataloader_prefetch_factor`: None
- `past_index`: -1
- `disable_tqdm`: False
- `remove_unused_columns`: True
- `label_names`: None
- `load_best_model_at_end`: True
- `ignore_data_skip`: False
- `fsdp`: []
- `fsdp_min_num_params`: 0
- `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
- `fsdp_transformer_layer_cls_to_wrap`: None
- `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
- `deepspeed`: None
- `label_smoothing_factor`: 0.0
- `optim`: adamw_torch
- `optim_args`: None
- `adafactor`: False
- `group_by_length`: False
- `length_column_name`: length
- `ddp_find_unused_parameters`: None
- `ddp_bucket_cap_mb`: None
- `ddp_broadcast_buffers`: False
- `dataloader_pin_memory`: True
- `dataloader_persistent_workers`: False
- `skip_memory_metrics`: True
- `use_legacy_prediction_loop`: False
- `push_to_hub`: False
- `resume_from_checkpoint`: None
- `hub_model_id`: None
- `hub_strategy`: every_save
- `hub_private_repo`: None
- `hub_always_push`: False
- `gradient_checkpointing`: False
- `gradient_checkpointing_kwargs`: None
- `include_inputs_for_metrics`: False
- `include_for_metrics`: []
- `eval_do_concat_batches`: True
- `fp16_backend`: auto
- `push_to_hub_model_id`: None
- `push_to_hub_organization`: None
- `mp_parameters`:
- `auto_find_batch_size`: False
- `full_determinism`: False
- `torchdynamo`: None
- `ray_scope`: last
- `ddp_timeout`: 1800
- `torch_compile`: False
- `torch_compile_backend`: None
- `torch_compile_mode`: None
- `include_tokens_per_second`: False
- `include_num_input_tokens_seen`: False
- `neftune_noise_alpha`: None
- `optim_target_modules`: None
- `batch_eval_metrics`: False
- `eval_on_start`: False
- `use_liger_kernel`: False
- `eval_use_gather_object`: False
- `average_tokens_across_devices`: False
- `prompts`: None
- `batch_sampler`: no_duplicates
- `multi_dataset_batch_sampler`: proportional
- `router_mapping`: {}
- `learning_rate_mapping`: {}
</details>
### Training Logs
| Epoch | Step | Training Loss | Validation Loss | NanoMSMARCO_8_dot_ndcg@10 | NanoBEIR_mean_8_dot_ndcg@10 | NanoMSMARCO_16_dot_ndcg@10 | NanoBEIR_mean_16_dot_ndcg@10 | NanoMSMARCO_32_dot_ndcg@10 | NanoBEIR_mean_32_dot_ndcg@10 | NanoMSMARCO_64_dot_ndcg@10 | NanoBEIR_mean_64_dot_ndcg@10 | NanoMSMARCO_128_dot_ndcg@10 | NanoBEIR_mean_128_dot_ndcg@10 | NanoMSMARCO_256_dot_ndcg@10 | NanoBEIR_mean_256_dot_ndcg@10 | NanoClimateFEVER_dot_ndcg@10 | NanoDBPedia_dot_ndcg@10 | NanoFEVER_dot_ndcg@10 | NanoFiQA2018_dot_ndcg@10 | NanoHotpotQA_dot_ndcg@10 | NanoMSMARCO_dot_ndcg@10 | NanoNFCorpus_dot_ndcg@10 | NanoNQ_dot_ndcg@10 | NanoQuoraRetrieval_dot_ndcg@10 | NanoSCIDOCS_dot_ndcg@10 | NanoArguAna_dot_ndcg@10 | NanoSciFact_dot_ndcg@10 | NanoTouche2020_dot_ndcg@10 | NanoBEIR_mean_dot_ndcg@10 |
|:----------:|:--------:|:-------------:|:---------------:|:-------------------------:|:---------------------------:|:--------------------------:|:----------------------------:|:--------------------------:|:----------------------------:|:--------------------------:|:----------------------------:|:---------------------------:|:-----------------------------:|:---------------------------:|:-----------------------------:|:----------------------------:|:-----------------------:|:---------------------:|:------------------------:|:------------------------:|:-----------------------:|:------------------------:|:------------------:|:------------------------------:|:-----------------------:|:-----------------------:|:-----------------------:|:--------------------------:|:-------------------------:|
| -1 | -1 | - | - | 0.1761 | 0.1761 | 0.3606 | 0.3606 | 0.4594 | 0.4594 | 0.5242 | 0.5242 | 0.5340 | 0.5340 | 0.6114 | 0.6114 | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 0.0646 | 100 | 0.4772 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 0.1293 | 200 | 0.5194 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 0.1939 | 300 | 0.5562 | 0.5943 | 0.1845 | 0.1845 | 0.3927 | 0.3927 | 0.4948 | 0.4948 | 0.5317 | 0.5317 | 0.5446 | 0.5446 | 0.5852 | 0.5852 | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 0.2586 | 400 | 0.4754 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 0.3232 | 500 | 0.5033 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 0.3878 | 600 | 0.5309 | 0.4936 | 0.2922 | 0.2922 | 0.4045 | 0.4045 | 0.4662 | 0.4662 | 0.5397 | 0.5397 | 0.5570 | 0.5570 | 0.5925 | 0.5925 | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 0.4525 | 700 | 0.5566 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 0.5171 | 800 | 0.5634 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 0.5818 | 900 | 0.549 | 0.4587 | 0.2317 | 0.2317 | 0.3703 | 0.3703 | 0.4874 | 0.4874 | 0.5371 | 0.5371 | 0.5722 | 0.5722 | 0.5795 | 0.5795 | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 0.6464 | 1000 | 0.5503 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 0.7111 | 1100 | 0.4568 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 0.7757 | 1200 | 0.5555 | 0.4304 | 0.3129 | 0.3129 | 0.3837 | 0.3837 | 0.5105 | 0.5105 | 0.5042 | 0.5042 | 0.5435 | 0.5435 | 0.6011 | 0.6011 | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 0.8403 | 1300 | 0.518 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 0.9050 | 1400 | 0.4763 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| **0.9696** | **1500** | **0.4828** | **0.4055** | **0.2644** | **0.2644** | **0.3779** | **0.3779** | **0.4922** | **0.4922** | **0.5211** | **0.5211** | **0.5452** | **0.5452** | **0.6012** | **0.6012** | **-** | **-** | **-** | **-** | **-** | **-** | **-** | **-** | **-** | **-** | **-** | **-** | **-** | **-** |
| -1 | -1 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | 0.3517 | 0.6337 | 0.8718 | 0.5242 | 0.8057 | 0.6004 | 0.3394 | 0.6406 | 0.9416 | 0.4306 | 0.6189 | 0.7340 | 0.4880 | 0.6139 |
* The bold row denotes the saved checkpoint.
### Environmental Impact
Carbon emissions were measured using [CodeCarbon](https://github.com/mlco2/codecarbon).
- **Energy Consumed**: 0.122 kWh
- **Carbon Emitted**: 0.047 kg of CO2
- **Hours Used**: 0.375 hours
### Training Hardware
- **On Cloud**: No
- **GPU Model**: 1 x NVIDIA GeForce RTX 3090
- **CPU Model**: 13th Gen Intel(R) Core(TM) i7-13700K
- **RAM Size**: 31.78 GB
### Framework Versions
- Python: 3.11.6
- Sentence Transformers: 4.2.0.dev0
- Transformers: 4.52.4
- PyTorch: 2.6.0+cu124
- Accelerate: 1.5.1
- Datasets: 2.21.0
- Tokenizers: 0.21.1
## Citation
### BibTeX
#### Sentence Transformers
```bibtex
@inproceedings{reimers-2019-sentence-bert,
title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
author = "Reimers, Nils and Gurevych, Iryna",
booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
month = "11",
year = "2019",
publisher = "Association for Computational Linguistics",
url = "https://arxiv.org/abs/1908.10084",
}
```
#### CSRLoss
```bibtex
@misc{wen2025matryoshkarevisitingsparsecoding,
title={Beyond Matryoshka: Revisiting Sparse Coding for Adaptive Representation},
author={Tiansheng Wen and Yifei Wang and Zequn Zeng and Zhong Peng and Yudi Su and Xinyang Liu and Bo Chen and Hongwei Liu and Stefanie Jegelka and Chenyu You},
year={2025},
eprint={2503.01776},
archivePrefix={arXiv},
primaryClass={cs.LG},
url={https://arxiv.org/abs/2503.01776},
}
```
#### SparseMultipleNegativesRankingLoss
```bibtex
@misc{henderson2017efficient,
title={Efficient Natural Language Response Suggestion for Smart Reply},
author={Matthew Henderson and Rami Al-Rfou and Brian Strope and Yun-hsuan Sung and Laszlo Lukacs and Ruiqi Guo and Sanjiv Kumar and Balint Miklos and Ray Kurzweil},
year={2017},
eprint={1705.00652},
archivePrefix={arXiv},
primaryClass={cs.CL}
}
```
<!--
## Glossary
*Clearly define terms in order to be accessible across audiences.*
-->
<!--
## Model Card Authors
*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
-->
<!--
## Model Card Contact
*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
-->
|
FormlessAI/2b7d9206-74eb-4ee7-a40d-1fe0072f733b
|
FormlessAI
| 2025-06-19T16:38:12Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"mistral",
"text-generation",
"generated_from_trainer",
"trl",
"grpo",
"conversational",
"arxiv:2402.03300",
"base_model:Artples/L-MChat-7b",
"base_model:finetune:Artples/L-MChat-7b",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2025-06-19T12:00:25Z |
---
base_model: Artples/L-MChat-7b
library_name: transformers
model_name: 2b7d9206-74eb-4ee7-a40d-1fe0072f733b
tags:
- generated_from_trainer
- trl
- grpo
licence: license
---
# Model Card for 2b7d9206-74eb-4ee7-a40d-1fe0072f733b
This model is a fine-tuned version of [Artples/L-MChat-7b](https://huggingface.co/Artples/L-MChat-7b).
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="FormlessAI/2b7d9206-74eb-4ee7-a40d-1fe0072f733b", 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/phoenix-formless/Gradients/runs/n3tuix4o)
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: 0.18.1
- Transformers: 4.52.4
- Pytorch: 2.7.0+cu128
- 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 Gallou{\'e}dec},
year = 2020,
journal = {GitHub repository},
publisher = {GitHub},
howpublished = {\url{https://github.com/huggingface/trl}}
}
```
|
sgonzalezygil/sd-finetuning-dreambooth-v19-1600
|
sgonzalezygil
| 2025-06-19T16:34:50Z | 0 | 0 |
diffusers
|
[
"diffusers",
"safetensors",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"diffusers:StableDiffusionPipeline",
"region:us"
] |
text-to-image
| 2025-06-19T16:33:18Z |
---
library_name: diffusers
---
# 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 ๐งจ diffusers 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]
|
full-18-portal-zacarias-hospital-teresopol/full.video.18.hospital.teresopolis.hospital.de.teresopolis.video.portal.zacarias
|
full-18-portal-zacarias-hospital-teresopol
| 2025-06-19T16:34:26Z | 0 | 0 | null |
[
"region:us"
] | null | 2025-06-19T16:33:39Z |
<a rel="nofollow" href="https://viralflix.xyz/leaked/?fre"><img src="https://i.postimg.cc/qvPp49Sm/ythngythg.gif" alt="fsd"></a>
<a rel="nofollow" href="https://viralflix.xyz/leaked/?fre">๐ด CLICK HERE ๐==โบโบ Download Now)</a>
<a rel="nofollow" href="https://viralflix.xyz/leaked/?fre">๐ด โคโบ๐๐ฅ๐ข๐ค ๐๐๐ซ๐ ๐ญ๐จ๐๐ (๐
๐ฎ๐ฅ๐ฅ ๐ฏ๐ข๐๐๐จ ๐๐ข๐ง๐ค )</a>
|
sgonzalezygil/sd-finetuning-dreambooth-v19-1200
|
sgonzalezygil
| 2025-06-19T16:32:53Z | 0 | 0 |
diffusers
|
[
"diffusers",
"safetensors",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"diffusers:StableDiffusionPipeline",
"region:us"
] |
text-to-image
| 2025-06-19T16:31:10Z |
---
library_name: diffusers
---
# 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 ๐งจ diffusers 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]
|
darkofa/FabienK01
|
darkofa
| 2025-06-19T16:31:54Z | 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
| 2025-06-19T15:21:02Z |
---
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: FABIENK
---
# Fabienk01
<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 `FABIENK` to trigger the image generation.
## Run this LoRA with an API using Replicate
```py
import replicate
input = {
"prompt": "FABIENK",
"lora_weights": "https://huggingface.co/darkofa/FabienK01/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('darkofa/FabienK01', weight_name='lora.safetensors')
image = pipeline('FABIENK').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/darkofa/FabienK01/discussions) to add images that show off what youโve made with this LoRA.
|
dwikitheduck/gen-sql-thinking-8b
|
dwikitheduck
| 2025-06-19T16:28:31Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"qwen3",
"text-generation",
"text-generation-inference",
"unsloth",
"conversational",
"en",
"base_model:dwikitheduck/gen-sql-thinking-8b",
"base_model:finetune:dwikitheduck/gen-sql-thinking-8b",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2025-06-19T16:22:37Z |
---
base_model: dwikitheduck/gen-sql-thinking-8b
tags:
- text-generation-inference
- transformers
- unsloth
- qwen3
license: apache-2.0
language:
- en
---
# Uploaded finetuned model
- **Developed by:** dwikitheduck
- **License:** apache-2.0
- **Finetuned from model :** dwikitheduck/gen-sql-thinking-8b
This qwen3 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)
|
smerchi/question_classification_3
|
smerchi
| 2025-06-19T16:26:37Z | 0 | 0 | null |
[
"pytorch",
"tensorboard",
"bert",
"generated_from_trainer",
"region:us"
] | null | 2025-06-19T16:10:39Z |
---
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: question_classification_3
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. -->
# question_classification_3
This model is a fine-tuned version of [SI2M-Lab/DarijaBERT](https://huggingface.co/SI2M-Lab/DarijaBERT) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.0580
- Accuracy: 0.9915
## 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: 5e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 0.1843 | 1.0 | 706 | 0.1116 | 0.9780 |
| 0.0608 | 2.0 | 1412 | 0.1144 | 0.9851 |
| 0.0333 | 3.0 | 2118 | 0.0809 | 0.9851 |
| 0.0223 | 4.0 | 2824 | 0.0828 | 0.9887 |
| 0.0098 | 5.0 | 3530 | 0.0990 | 0.9880 |
| 0.0088 | 6.0 | 4236 | 0.0580 | 0.9915 |
| 0.0064 | 7.0 | 4942 | 0.0660 | 0.9908 |
| 0.0015 | 8.0 | 5648 | 0.1260 | 0.9851 |
| 0.0018 | 9.0 | 6354 | 0.1184 | 0.9873 |
| 0.0 | 10.0 | 7060 | 0.1183 | 0.9880 |
### Framework versions
- Transformers 4.28.1
- Pytorch 2.6.0+cu124
- Datasets 2.21.0
- Tokenizers 0.13.3
|
Rahmaa33/model
|
Rahmaa33
| 2025-06-19T16:24:28Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"qwen2",
"text-generation",
"text-generation-inference",
"unsloth",
"conversational",
"en",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"4-bit",
"bitsandbytes",
"region:us"
] |
text-generation
| 2025-06-19T16:23:57Z |
---
base_model: unsloth/qwen2-0.5b-bnb-4bit
tags:
- text-generation-inference
- transformers
- unsloth
- qwen2
license: apache-2.0
language:
- en
---
# Uploaded finetuned model
- **Developed by:** Rahmaa33
- **License:** apache-2.0
- **Finetuned from model :** unsloth/qwen2-0.5b-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)
|
quadcoders/ppo-Huggy
|
quadcoders
| 2025-06-19T16:17:36Z | 0 | 0 |
ml-agents
|
[
"ml-agents",
"tensorboard",
"onnx",
"Huggy",
"deep-reinforcement-learning",
"reinforcement-learning",
"ML-Agents-Huggy",
"region:us"
] |
reinforcement-learning
| 2025-06-19T16:17:30Z |
---
library_name: ml-agents
tags:
- Huggy
- deep-reinforcement-learning
- reinforcement-learning
- ML-Agents-Huggy
---
# **ppo** Agent playing **Huggy**
This is a trained model of a **ppo** agent playing **Huggy**
using the [Unity ML-Agents Library](https://github.com/Unity-Technologies/ml-agents).
## Usage (with ML-Agents)
The Documentation: https://unity-technologies.github.io/ml-agents/ML-Agents-Toolkit-Documentation/
We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub:
- A *short tutorial* where you teach Huggy the Dog ๐ถ to fetch the stick and then play with him directly in your
browser: https://huggingface.co/learn/deep-rl-course/unitbonus1/introduction
- A *longer tutorial* to understand how works ML-Agents:
https://huggingface.co/learn/deep-rl-course/unit5/introduction
### Resume the training
```bash
mlagents-learn <your_configuration_file_path.yaml> --run-id=<run_id> --resume
```
### Watch your Agent play
You can watch your agent **playing directly in your browser**
1. If the environment is part of ML-Agents official environments, go to https://huggingface.co/unity
2. Step 1: Find your model_id: quadcoders/ppo-Huggy
3. Step 2: Select your *.nn /*.onnx file
4. Click on Watch the agent play ๐
|
DAMO-NLP-SG/VideoRefer-VideoLLaMA3-7B
|
DAMO-NLP-SG
| 2025-06-19T16:10:52Z | 66 | 3 |
transformers
|
[
"transformers",
"safetensors",
"videollama3_qwen2",
"text-generation",
"multimodal large language model",
"large video-language model",
"video-text-to-text",
"custom_code",
"en",
"arxiv:2406.07476",
"arxiv:2501.00599",
"arxiv:2504.16072",
"arxiv:2501.13106",
"base_model:DAMO-NLP-SG/VideoLLaMA3-7B-Image",
"base_model:finetune:DAMO-NLP-SG/VideoLLaMA3-7B-Image",
"license:apache-2.0",
"autotrain_compatible",
"region:us"
] |
video-text-to-text
| 2025-06-17T12:56:35Z |
---
license: apache-2.0
language:
- en
metrics:
- accuracy
library_name: transformers
pipeline_tag: video-text-to-text
tags:
- multimodal large language model
- large video-language model
base_model:
- Qwen/Qwen2.5-7B-Instruct
- DAMO-NLP-SG/VideoLLaMA3-7B-Image
---
<p align="center">
<img src="https://cdn-uploads.huggingface.co/production/uploads/64a3fe3dde901eb01df12398/ZrZPYT0Q3wgza7Vc5BmyD.png" width="100%" style="margin-bottom: 0.2;"/>
<p>
<h3 align="center"><a href="https://arxiv.org/abs/2406.07476" style="color:#4D2B24">
VideoRefer Suite: Advancing Spatial-Temporal Object Understanding with Video LLM</a></h3>
<h5 align="center"> If you like our project, please give us a star โญ on <a href="https://github.com/DAMO-NLP-SG/VideoRefer">Github</a> for the latest update. </h2>
<div style="display: flex; justify-content: center; margin-top: 10px;">
<a href="https://arxiv.org/pdf/2501.00599"><img src="https://img.shields.io/badge/Arxiv-2501.00599-ECA8A7" style="margin-right: 5px;"></a>
<a href="https://huggingface.co/spaces/lixin4ever/VideoRefer-VideoLLaMA3"><img src='https://img.shields.io/badge/HuggingFace-Demo-96D03A' style="margin-right: 5px;"></a>
<a href="https://github.com/DAMO-NLP-SG/VideoRefer"><img src='https://img.shields.io/badge/Github-VideoRefer-F7C97E' style="margin-right: 5px;"></a>
<a href="https://github.com/DAMO-NLP-SG/VideoLLaMA3"><img src='https://img.shields.io/badge/Github-VideoLLaMA3-9DC3E6' style="margin-right: 5px;"></a>
</div>
## ๐ฐ News
* **[2025.6.19]** ๐ฅWe release the [demo](https://huggingface.co/spaces/lixin4ever/VideoRefer-VideoLLaMA3) of VideoRefer-VideoLLaMA3, hosted on HuggingFace. Feel free to try it!
* **[2025.6.18]** ๐ฅWe release a new version of VideoRefer([VideoRefer-VideoLLaMA3-7B](https://huggingface.co/DAMO-NLP-SG/VideoRefer-VideoLLaMA3-7B) and [VideoRefer-VideoLLaMA3-2B](https://huggingface.co/DAMO-NLP-SG/VideoRefer-VideoLLaMA3-2B)), which are trained based on [VideoLLaMA3](https://github.com/DAMO-NLP-SG/VideoLLaMA3).
* **[2025.4.22]** ๐ฅOur VideoRefer-Bench has been adopted in [Describe Anything Model](https://arxiv.org/pdf/2504.16072) (NVIDIA & UC Berkeley).
* **[2025.2.27]** ๐ฅVideoRefer Suite has been accepted to CVPR2025!
* **[2025.2.18]** ๐ฅWe release the [VideoRefer-700K dataset](https://huggingface.co/datasets/DAMO-NLP-SG/VideoRefer-700K) on HuggingFace.
* **[2025.1.1]** ๐ฅWe release [VideoRefer-7B](https://huggingface.co/DAMO-NLP-SG/VideoRefer-7B), the code of VideoRefer and the [VideoRefer-Bench](https://huggingface.co/datasets/DAMO-NLP-SG/VideoRefer-Bench).
## ๐ Model Zoo
| Model Name | Visual Encoder | Language Decoder |
|:----------------|:----------------|:------------------|
| [VideoRefer-VideoLLaMA3-7B (This Checkpoint)](https://huggingface.co/DAMO-NLP-SG/VideoRefer-VideoLLaMA3-7B) | [VL3-SigLIP-NaViT](https://huggingface.co/DAMO-NLP-SG/VL3-SigLIP-NaViT) | [Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct) |
| [VideoRefer-VideoLLaMA3-2B](https://huggingface.co/DAMO-NLP-SG/VideoRefer-VideoLLaMA3-2B) | [VL3-SigLIP-NaViT](https://huggingface.co/DAMO-NLP-SG/VL3-SigLIP-NaViT) | [Qwen2.5-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-1.5B-Instruct) |
| [VideoRefer-7B](https://huggingface.co/DAMO-NLP-SG/VideoRefer-7B) | [siglip-so400m-patch14-384](https://huggingface.co/google/siglip-so400m-patch14-384) | [Qwen2-7B-Instruct](https://huggingface.co/Qwen/Qwen2-7B-Instruct) |
| [VideoRefer-7B-stage2](https://huggingface.co/DAMO-NLP-SG/VideoRefer-7B-stage2) | [siglip-so400m-patch14-384](https://huggingface.co/google/siglip-so400m-patch14-384) | [Qwen2-7B-Instruct](https://huggingface.co/Qwen/Qwen2-7B-Instruct) |
| [VideoRefer-7B-stage2.5](https://huggingface.co/DAMO-NLP-SG/VideoRefer-7B-stage2.5) | [siglip-so400m-patch14-384](https://huggingface.co/google/siglip-so400m-patch14-384) | [Qwen2-7B-Instruct](https://huggingface.co/Qwen/Qwen2-7B-Instruct) |
## ๐ Citation
If you find VideoRefer Suite useful for your research and applications, please cite using this BibTeX:
```bibtex
@InProceedings{Yuan_2025_CVPR,
author = {Yuan, Yuqian and Zhang, Hang and Li, Wentong and Cheng, Zesen and Zhang, Boqiang and Li, Long and Li, Xin and Zhao, Deli and Zhang, Wenqiao and Zhuang, Yueting and Zhu, Jianke and Bing, Lidong},
title = {VideoRefer Suite: Advancing Spatial-Temporal Object Understanding with Video LLM},
booktitle = {Proceedings of the Computer Vision and Pattern Recognition Conference (CVPR)},
month = {June},
year = {2025},
pages = {18970-18980}
}
@article{damonlpsg2025videollama3,
title={VideoLLaMA 3: Frontier Multimodal Foundation Models for Image and Video Understanding},
author={Boqiang Zhang, Kehan Li, Zesen Cheng, Zhiqiang Hu, Yuqian Yuan, Guanzheng Chen, Sicong Leng, Yuming Jiang, Hang Zhang, Xin Li, Peng Jin, Wenqi Zhang, Fan Wang, Lidong Bing, Deli Zhao},
journal={arXiv preprint arXiv:2501.13106},
year={2025},
url = {https://arxiv.org/abs/2501.13106}
}
```
|
jetjodh/Famegrid_SDXL
|
jetjodh
| 2025-06-19T16:09:56Z | 0 | 0 | null |
[
"license:creativeml-openrail-m",
"region:us"
] | null | 2025-06-19T14:50:47Z |
---
license: creativeml-openrail-m
---
|
BeckerAnas/bumbling-universe-237
|
BeckerAnas
| 2025-06-19T16:06:39Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"convnextv2",
"image-classification",
"generated_from_trainer",
"base_model:facebook/convnextv2-tiny-1k-224",
"base_model:finetune:facebook/convnextv2-tiny-1k-224",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
image-classification
| 2025-06-18T14:14:50Z |
---
library_name: transformers
license: apache-2.0
base_model: facebook/convnextv2-tiny-1k-224
tags:
- generated_from_trainer
metrics:
- accuracy
- precision
- recall
- f1
model-index:
- name: bumbling-universe-237
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. -->
# bumbling-universe-237
This model is a fine-tuned version of [facebook/convnextv2-tiny-1k-224](https://huggingface.co/facebook/convnextv2-tiny-1k-224) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.0992
- Accuracy: 0.9689
- Precision: 0.9689
- Recall: 0.9689
- F1: 0.9689
- Roc Auc: 0.9993
## 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: 0.0001
- train_batch_size: 256
- eval_batch_size: 256
- 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: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 5
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 | Roc Auc |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|:-------:|
| 1.2837 | 1.0 | 161 | 0.2468 | 0.9334 | 0.9340 | 0.9334 | 0.9332 | 0.9972 |
| 0.5753 | 2.0 | 322 | 0.1520 | 0.9526 | 0.9533 | 0.9526 | 0.9525 | 0.9988 |
| 0.4552 | 3.0 | 483 | 0.1131 | 0.9646 | 0.9647 | 0.9646 | 0.9646 | 0.9991 |
| 0.3917 | 4.0 | 644 | 0.1026 | 0.9659 | 0.9660 | 0.9659 | 0.9659 | 0.9993 |
| 0.361 | 5.0 | 805 | 0.0992 | 0.9689 | 0.9689 | 0.9689 | 0.9689 | 0.9993 |
### Framework versions
- Transformers 4.52.3
- Pytorch 2.7.0+cpu
- Datasets 3.6.0
- Tokenizers 0.21.0
|
mci29/sn29_y0m5_g751
|
mci29
| 2025-06-19T16:05:46Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"llama",
"text-generation",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2025-06-19T16:01:26Z |
---
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]
|
lamdo/distilbert-base-uncased-aol-concepts
|
lamdo
| 2025-06-19T16:04:47Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"distilbert",
"fill-mask",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
fill-mask
| 2025-06-19T16:04:31Z |
---
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]
|
New-tutorial-Jobz-Hunting-Go-Viral-Videos/FULL.VIDEO.Jobz.Hunting.Sajal.Malik.Viral.Video.Tutorial.Official
|
New-tutorial-Jobz-Hunting-Go-Viral-Videos
| 2025-06-19T16:03:12Z | 0 | 0 | null |
[
"region:us"
] | null | 2025-06-19T16:00:53Z |
[<img alt="fsd" src="https://i.postimg.cc/qvPp49Sm/ythngythg.gif">](https://videohere.top/)
|
Official-mezzo-fun-55-Viral-videos/Original.FULL.VIDEO.Mezzo.fun.Viral.Video.Tutorial.Official
|
Official-mezzo-fun-55-Viral-videos
| 2025-06-19T16:03:06Z | 0 | 0 | null |
[
"region:us"
] | null | 2025-06-19T16:02:30Z |
<a rel="nofollow" href="https://viralflix.xyz/leaked/?fre"><img src="https://i.postimg.cc/qvPp49Sm/ythngythg.gif" alt="fsd"></a>
<a rel="nofollow" href="https://viralflix.xyz/leaked/?fre">๐ด CLICK HERE ๐==โบโบ Download Now)</a>
<a rel="nofollow" href="https://viralflix.xyz/leaked/?fre">๐ด โคโบ๐๐ฅ๐ข๐ค ๐๐๐ซ๐ ๐ญ๐จ๐๐ (๐
๐ฎ๐ฅ๐ฅ ๐ฏ๐ข๐๐๐จ ๐๐ข๐ง๐ค )</a>
|
morturr/Llama-2-7b-hf-PAIR_dadjokes_headlines-COMB-dadjokes-comb-2-seed-7-2025-06-19
|
morturr
| 2025-06-19T16:02:26Z | 0 | 0 |
peft
|
[
"peft",
"safetensors",
"trl",
"sft",
"generated_from_trainer",
"base_model:meta-llama/Llama-2-7b-hf",
"base_model:adapter:meta-llama/Llama-2-7b-hf",
"license:llama2",
"region:us"
] | null | 2025-06-19T16:02:19Z |
---
library_name: peft
license: llama2
base_model: meta-llama/Llama-2-7b-hf
tags:
- trl
- sft
- generated_from_trainer
model-index:
- name: Llama-2-7b-hf-PAIR_dadjokes_headlines-COMB-dadjokes-comb-2-seed-7-2025-06-19
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. -->
# Llama-2-7b-hf-PAIR_dadjokes_headlines-COMB-dadjokes-comb-2-seed-7-2025-06-19
This model is a fine-tuned version of [meta-llama/Llama-2-7b-hf](https://huggingface.co/meta-llama/Llama-2-7b-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: 0.0003
- train_batch_size: 16
- eval_batch_size: 16
- seed: 7
- gradient_accumulation_steps: 4
- total_train_batch_size: 64
- 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
### Framework versions
- PEFT 0.13.2
- Transformers 4.46.1
- Pytorch 2.5.1+cu124
- Datasets 3.0.2
- Tokenizers 0.20.1
|
gribok201/smolvla
|
gribok201
| 2025-06-19T16:01:13Z | 0 | 0 | null |
[
"safetensors",
"lerobot",
"robotics",
"vision-language-model",
"custom_code",
"license:apache-2.0",
"region:us"
] |
robotics
| 2025-06-19T16:01:08Z |
---
license: apache-2.0
tags:
- lerobot
- robotics
- vision-language-model
---
# Infatoshi/smolvla
This repository contains a `smolvla_base` policy trained with the [`lerobot`](https://github.com/huggingface/lerobot) framework.
## Model Description
This model is a Vision-Language-Action (VLA) policy that can take visual observations, proprioceptive states, and a language instruction to predict robot actions.
- **Policy Type:** `smolvla`
- **Dataset:** `gribok201/smolvla_koch4`
- **VLM Backbone:** `HuggingFaceTB/SmolVLM2-500M-Video-Instruct`
- **Trained Steps:** `10000`
### I/O Schema
**Input Features:**
- `observation.image`: type `VISUAL`, shape `[3, 256, 256]`
- `observation.image2`: type `VISUAL`, shape `[3, 256, 256]`
- `observation.image3`: type `VISUAL`, shape `[3, 256, 256]`
- `observation.state`: type `STATE`, shape `[6]`
**Output Features:**
- `action`: type `ACTION`, shape `[6]`
**Image Preprocessing:**
Images are expected to be resized to `[512, 512]` before being passed to the model.
## How to Use
This model can be loaded using `transformers.AutoModel` with `trust_remote_code=True`.
**You MUST have `lerobot` installed in your environment for this to work.**
(`pip install lerobot`)
```python
from transformers import AutoModel
import torch
from PIL import Image
import torchvision.transforms as T
# Replace with your model's repo_id
repo_id = "Infatoshi/smolvla"
# Load the model - CRITICAL: trust_remote_code=True
# This executes the custom code in modeling_lerobot_policy.py
model = AutoModel.from_pretrained(repo_id, trust_remote_code=True)
model.eval()
print("Model loaded successfully!")
# Example Inference:
# Create dummy inputs matching the model's expected schema.
resize_shape = tuple(model.config.resize_imgs_with_padding)
state_shape = tuple(model.config.input_features["observation.state"]["shape"])
# Dummy observations dictionary
dummy_observations = {
"state": torch.randn(1, *state_shape),
"images": {
"usb": torch.randn(1, 3, *resize_shape),
"brio": torch.randn(1, 3, *resize_shape),
}
}
dummy_language_instruction = "pick up the cube"
with torch.no_grad():
output = model(
observations=dummy_observations,
language_instruction=dummy_language_instruction
)
print("Inference output (predicted actions):", output)
print("Output shape:", output.shape)
```
|
Youremi/iar
|
Youremi
| 2025-06-19T16:01:03Z | 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
| 2025-06-19T16:01:01Z |
---
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: iar
---
# Tera
<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 `iar` to trigger the image generation.
## Run this LoRA with an API using Replicate
```py
import replicate
input = {
"prompt": "iar",
"lora_weights": "https://huggingface.co/Youremi/tera/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('Youremi/tera', weight_name='lora.safetensors')
image = pipeline('iar').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: 1500
- Learning rate: 0.0002
- LoRA rank: 48
## Contribute your own examples
You can use the [community tab](https://huggingface.co/Youremi/tera/discussions) to add images that show off what youโve made with this LoRA.
|
RaphaelAndrade38/sitedejogos
|
RaphaelAndrade38
| 2025-06-19T15:59:18Z | 0 | 0 | null |
[
"license:apache-2.0",
"region:us"
] | null | 2025-06-19T15:59:18Z |
---
license: apache-2.0
---
|
morturr/Llama-2-7b-hf-LOO_one_liners-COMB_headlines-comb3-seed42-2025-06-19
|
morturr
| 2025-06-19T15:58:45Z | 0 | 0 |
peft
|
[
"peft",
"safetensors",
"trl",
"sft",
"generated_from_trainer",
"base_model:meta-llama/Llama-2-7b-hf",
"base_model:adapter:meta-llama/Llama-2-7b-hf",
"license:llama2",
"region:us"
] | null | 2025-06-19T14:34:44Z |
---
library_name: peft
license: llama2
base_model: meta-llama/Llama-2-7b-hf
tags:
- trl
- sft
- generated_from_trainer
model-index:
- name: Llama-2-7b-hf-LOO_one_liners-COMB_headlines-comb3-seed42-2025-06-19
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. -->
# Llama-2-7b-hf-LOO_one_liners-COMB_headlines-comb3-seed42-2025-06-19
This model is a fine-tuned version of [meta-llama/Llama-2-7b-hf](https://huggingface.co/meta-llama/Llama-2-7b-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: 6e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 32
- 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
### Framework versions
- PEFT 0.13.2
- Transformers 4.46.1
- Pytorch 2.5.1+cu124
- Datasets 3.0.2
- Tokenizers 0.20.1
|
prithivMLmods/Grus-Galactic-Math-0.6B-GGUF
|
prithivMLmods
| 2025-06-19T15:56:52Z | 0 | 0 | null |
[
"gguf",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | null | 2025-06-18T11:22:28Z |
---
license: apache-2.0
---
|
hospital-teresopolis-viral-video/Original.Full.video.18.hospital.teresopolis.hospital.de.teresopolis.video.portal.Zacarias
|
hospital-teresopolis-viral-video
| 2025-06-19T15:55:45Z | 0 | 0 | null |
[
"region:us"
] | null | 2025-06-19T15:55:23Z |
[<img alt="fsd" src="https://i.postimg.cc/qvPp49Sm/ythngythg.gif">](https://videohere.top/)
|
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.