modelId
string | author
string | last_modified
timestamp[us, tz=UTC] | downloads
int64 | likes
int64 | library_name
string | tags
list | pipeline_tag
string | createdAt
timestamp[us, tz=UTC] | card
string |
|---|---|---|---|---|---|---|---|---|---|
Sanyam0605/Reinforce-PixelCop2
|
Sanyam0605
| 2023-09-22T21:41:34Z | 0 | 0 | null |
[
"Pixelcopter-PLE-v0",
"reinforce",
"reinforcement-learning",
"custom-implementation",
"deep-rl-class",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-09-22T21:39:51Z |
---
tags:
- Pixelcopter-PLE-v0
- reinforce
- reinforcement-learning
- custom-implementation
- deep-rl-class
model-index:
- name: Reinforce-PixelCop2
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: Pixelcopter-PLE-v0
type: Pixelcopter-PLE-v0
metrics:
- type: mean_reward
value: 19.70 +/- 14.31
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
|
CyberHarem/anzai_miyako_idolmastercinderellagirls
|
CyberHarem
| 2023-09-22T21:36:03Z | 0 | 0 | null |
[
"art",
"text-to-image",
"dataset:CyberHarem/anzai_miyako_idolmastercinderellagirls",
"license:mit",
"region:us"
] |
text-to-image
| 2023-09-22T21:26:39Z |
---
license: mit
datasets:
- CyberHarem/anzai_miyako_idolmastercinderellagirls
pipeline_tag: text-to-image
tags:
- art
---
# Lora of anzai_miyako_idolmastercinderellagirls
This model is trained with [HCP-Diffusion](https://github.com/7eu7d7/HCP-Diffusion). And the auto-training framework is maintained by [DeepGHS Team](https://huggingface.co/deepghs).
The base model used during training is [NAI](https://huggingface.co/deepghs/animefull-latest), and the base model used for generating preview images is [Meina/MeinaMix_V11](https://huggingface.co/Meina/MeinaMix_V11).
After downloading the pt and safetensors files for the specified step, you need to use them simultaneously. The pt file will be used as an embedding, while the safetensors file will be loaded for Lora.
For example, if you want to use the model from step 5100, you need to download `5100/anzai_miyako_idolmastercinderellagirls.pt` as the embedding and `5100/anzai_miyako_idolmastercinderellagirls.safetensors` for loading Lora. By using both files together, you can generate images for the desired characters.
**The best step we recommend is 5100**, with the score of 0.824. The trigger words are:
1. `anzai_miyako_idolmastercinderellagirls`
2. `short_hair, red_hair, blue_eyes, smile, open_mouth, blush`
For the following groups, it is not recommended to use this model and we express regret:
1. Individuals who cannot tolerate any deviations from the original character design, even in the slightest detail.
2. Individuals who are facing the application scenarios with high demands for accuracy in recreating character outfits.
3. Individuals who cannot accept the potential randomness in AI-generated images based on the Stable Diffusion algorithm.
4. Individuals who are not comfortable with the fully automated process of training character models using LoRA, or those who believe that training character models must be done purely through manual operations to avoid disrespecting the characters.
5. Individuals who finds the generated image content offensive to their values.
These are available steps:
| Steps | Score | Download | pattern_1 | pattern_2 | pattern_3 | pattern_4 | bikini | bondage | free | maid | miko | nude | nude2 | suit | yukata |
|:---------|:----------|:----------------------------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:----------------------------------------------------|:-----------------------------------------------|:-------------------------------------------------|:--------------------------------------------------|:-------------------------------------|:-------------------------------------|:-------------------------------------|:-----------------------------------------------|:------------------------------------------------|:-------------------------------------|:-----------------------------------------|
| **5100** | **0.824** | [**Download**](5100/anzai_miyako_idolmastercinderellagirls.zip) |  |  | [<NSFW, click to see>](5100/previews/pattern_3.png) |  | [<NSFW, click to see>](5100/previews/bikini.png) | [<NSFW, click to see>](5100/previews/bondage.png) |  |  |  | [<NSFW, click to see>](5100/previews/nude.png) | [<NSFW, click to see>](5100/previews/nude2.png) |  |  |
| 4760 | 0.805 | [Download](4760/anzai_miyako_idolmastercinderellagirls.zip) |  |  | [<NSFW, click to see>](4760/previews/pattern_3.png) |  | [<NSFW, click to see>](4760/previews/bikini.png) | [<NSFW, click to see>](4760/previews/bondage.png) |  |  |  | [<NSFW, click to see>](4760/previews/nude.png) | [<NSFW, click to see>](4760/previews/nude2.png) |  |  |
| 4420 | 0.724 | [Download](4420/anzai_miyako_idolmastercinderellagirls.zip) |  |  | [<NSFW, click to see>](4420/previews/pattern_3.png) |  | [<NSFW, click to see>](4420/previews/bikini.png) | [<NSFW, click to see>](4420/previews/bondage.png) |  |  |  | [<NSFW, click to see>](4420/previews/nude.png) | [<NSFW, click to see>](4420/previews/nude2.png) |  |  |
| 4080 | 0.765 | [Download](4080/anzai_miyako_idolmastercinderellagirls.zip) |  |  | [<NSFW, click to see>](4080/previews/pattern_3.png) |  | [<NSFW, click to see>](4080/previews/bikini.png) | [<NSFW, click to see>](4080/previews/bondage.png) |  |  |  | [<NSFW, click to see>](4080/previews/nude.png) | [<NSFW, click to see>](4080/previews/nude2.png) |  |  |
| 3740 | 0.813 | [Download](3740/anzai_miyako_idolmastercinderellagirls.zip) |  |  | [<NSFW, click to see>](3740/previews/pattern_3.png) |  | [<NSFW, click to see>](3740/previews/bikini.png) | [<NSFW, click to see>](3740/previews/bondage.png) |  |  |  | [<NSFW, click to see>](3740/previews/nude.png) | [<NSFW, click to see>](3740/previews/nude2.png) |  |  |
| 3400 | 0.774 | [Download](3400/anzai_miyako_idolmastercinderellagirls.zip) |  |  | [<NSFW, click to see>](3400/previews/pattern_3.png) |  | [<NSFW, click to see>](3400/previews/bikini.png) | [<NSFW, click to see>](3400/previews/bondage.png) |  |  |  | [<NSFW, click to see>](3400/previews/nude.png) | [<NSFW, click to see>](3400/previews/nude2.png) |  |  |
| 3060 | 0.718 | [Download](3060/anzai_miyako_idolmastercinderellagirls.zip) |  |  | [<NSFW, click to see>](3060/previews/pattern_3.png) |  | [<NSFW, click to see>](3060/previews/bikini.png) | [<NSFW, click to see>](3060/previews/bondage.png) |  |  |  | [<NSFW, click to see>](3060/previews/nude.png) | [<NSFW, click to see>](3060/previews/nude2.png) |  |  |
| 2720 | 0.797 | [Download](2720/anzai_miyako_idolmastercinderellagirls.zip) |  |  | [<NSFW, click to see>](2720/previews/pattern_3.png) |  | [<NSFW, click to see>](2720/previews/bikini.png) | [<NSFW, click to see>](2720/previews/bondage.png) |  |  |  | [<NSFW, click to see>](2720/previews/nude.png) | [<NSFW, click to see>](2720/previews/nude2.png) |  |  |
| 2380 | 0.697 | [Download](2380/anzai_miyako_idolmastercinderellagirls.zip) |  |  | [<NSFW, click to see>](2380/previews/pattern_3.png) |  | [<NSFW, click to see>](2380/previews/bikini.png) | [<NSFW, click to see>](2380/previews/bondage.png) |  |  |  | [<NSFW, click to see>](2380/previews/nude.png) | [<NSFW, click to see>](2380/previews/nude2.png) |  |  |
| 2040 | 0.735 | [Download](2040/anzai_miyako_idolmastercinderellagirls.zip) |  |  | [<NSFW, click to see>](2040/previews/pattern_3.png) |  | [<NSFW, click to see>](2040/previews/bikini.png) | [<NSFW, click to see>](2040/previews/bondage.png) |  |  |  | [<NSFW, click to see>](2040/previews/nude.png) | [<NSFW, click to see>](2040/previews/nude2.png) |  |  |
| 1700 | 0.744 | [Download](1700/anzai_miyako_idolmastercinderellagirls.zip) |  |  | [<NSFW, click to see>](1700/previews/pattern_3.png) |  | [<NSFW, click to see>](1700/previews/bikini.png) | [<NSFW, click to see>](1700/previews/bondage.png) |  |  |  | [<NSFW, click to see>](1700/previews/nude.png) | [<NSFW, click to see>](1700/previews/nude2.png) |  |  |
| 1360 | 0.720 | [Download](1360/anzai_miyako_idolmastercinderellagirls.zip) |  |  | [<NSFW, click to see>](1360/previews/pattern_3.png) |  | [<NSFW, click to see>](1360/previews/bikini.png) | [<NSFW, click to see>](1360/previews/bondage.png) |  |  |  | [<NSFW, click to see>](1360/previews/nude.png) | [<NSFW, click to see>](1360/previews/nude2.png) |  |  |
| 1020 | 0.715 | [Download](1020/anzai_miyako_idolmastercinderellagirls.zip) |  |  | [<NSFW, click to see>](1020/previews/pattern_3.png) |  | [<NSFW, click to see>](1020/previews/bikini.png) | [<NSFW, click to see>](1020/previews/bondage.png) |  |  |  | [<NSFW, click to see>](1020/previews/nude.png) | [<NSFW, click to see>](1020/previews/nude2.png) |  |  |
| 680 | 0.721 | [Download](680/anzai_miyako_idolmastercinderellagirls.zip) |  |  | [<NSFW, click to see>](680/previews/pattern_3.png) |  | [<NSFW, click to see>](680/previews/bikini.png) | [<NSFW, click to see>](680/previews/bondage.png) |  |  |  | [<NSFW, click to see>](680/previews/nude.png) | [<NSFW, click to see>](680/previews/nude2.png) |  |  |
| 340 | 0.515 | [Download](340/anzai_miyako_idolmastercinderellagirls.zip) |  |  | [<NSFW, click to see>](340/previews/pattern_3.png) |  | [<NSFW, click to see>](340/previews/bikini.png) | [<NSFW, click to see>](340/previews/bondage.png) |  |  |  | [<NSFW, click to see>](340/previews/nude.png) | [<NSFW, click to see>](340/previews/nude2.png) |  |  |
|
batharun2/llama2-qlora-finetunined-french-arun
|
batharun2
| 2023-09-22T21:35:31Z | 0 | 1 |
peft
|
[
"peft",
"region:us"
] | null | 2023-09-22T21:35:25Z |
---
library_name: peft
---
## Training procedure
The following `bitsandbytes` quantization config was used during training:
- quant_method: bitsandbytes
- load_in_8bit: False
- load_in_4bit: True
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: nf4
- bnb_4bit_use_double_quant: False
- bnb_4bit_compute_dtype: float16
### Framework versions
- PEFT 0.6.0.dev0
|
totally-not-an-llm/EverythingLM-13b-V3-peft
|
totally-not-an-llm
| 2023-09-22T21:35:17Z | 8 | 1 |
peft
|
[
"peft",
"llama",
"base_model:NousResearch/Llama-2-13b-hf",
"base_model:adapter:NousResearch/Llama-2-13b-hf",
"4-bit",
"bitsandbytes",
"region:us"
] | null | 2023-09-21T03:28:45Z |
---
library_name: peft
base_model: NousResearch/Llama-2-13b-hf
---
## Training procedure
The following `bitsandbytes` quantization config was used during training:
- quant_method: bitsandbytes
- load_in_8bit: False
- load_in_4bit: True
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: nf4
- bnb_4bit_use_double_quant: True
- bnb_4bit_compute_dtype: bfloat16
### Framework versions
- PEFT 0.6.0.dev0
|
Medissa/xlm-roberta-base-finetuned-panx-de
|
Medissa
| 2023-09-22T21:29:07Z | 106 | 0 |
transformers
|
[
"transformers",
"pytorch",
"tensorboard",
"xlm-roberta",
"token-classification",
"generated_from_trainer",
"dataset:xtreme",
"base_model:FacebookAI/xlm-roberta-base",
"base_model:finetune:FacebookAI/xlm-roberta-base",
"license:mit",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
token-classification
| 2023-03-19T14:40:31Z |
---
license: mit
tags:
- generated_from_trainer
datasets:
- xtreme
metrics:
- f1
base_model: xlm-roberta-base
model-index:
- name: xlm-roberta-base-finetuned-panx-de
results:
- task:
type: token-classification
name: Token Classification
dataset:
name: xtreme
type: xtreme
config: PAN-X.de
split: validation
args: PAN-X.de
metrics:
- type: f1
value: 0.8638300289723342
name: F1
---
<!-- 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. -->
# xlm-roberta-base-finetuned-panx-de
This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on the xtreme dataset.
It achieves the following results on the evaluation set:
- Loss: 0.1358
- F1: 0.8638
## 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: 24
- eval_batch_size: 24
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
### Training results
| Training Loss | Epoch | Step | Validation Loss | F1 |
|:-------------:|:-----:|:----:|:---------------:|:------:|
| 0.2591 | 1.0 | 525 | 0.1621 | 0.8206 |
| 0.1276 | 2.0 | 1050 | 0.1379 | 0.8486 |
| 0.082 | 3.0 | 1575 | 0.1358 | 0.8638 |
### Framework versions
- Transformers 4.27.1
- Pytorch 1.13.1+cu116
- Datasets 2.10.1
- Tokenizers 0.13.2
|
Bjqrn/ppo-LunarLander-v2
|
Bjqrn
| 2023-09-22T21:24:45Z | 0 | 0 |
stable-baselines3
|
[
"stable-baselines3",
"LunarLander-v2",
"deep-reinforcement-learning",
"reinforcement-learning",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-09-22T21:24:25Z |
---
library_name: stable-baselines3
tags:
- LunarLander-v2
- deep-reinforcement-learning
- reinforcement-learning
- stable-baselines3
model-index:
- name: PPO
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: LunarLander-v2
type: LunarLander-v2
metrics:
- type: mean_reward
value: 256.28 +/- 21.71
name: mean_reward
verified: false
---
# **PPO** Agent playing **LunarLander-v2**
This is a trained model of a **PPO** agent playing **LunarLander-v2**
using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3).
## Usage (with Stable-baselines3)
TODO: Add your code
```python
from stable_baselines3 import ...
from huggingface_sb3 import load_from_hub
...
```
|
vamsidulam/vqa_graphcore2
|
vamsidulam
| 2023-09-22T21:19:26Z | 59 | 1 |
transformers
|
[
"transformers",
"pytorch",
"tensorboard",
"vilt",
"visual-question-answering",
"generated_from_trainer",
"dataset:vqa",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] |
visual-question-answering
| 2023-09-22T07:35:57Z |
---
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- vqa
model-index:
- name: vqa_graphcore2
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. -->
# vqa_graphcore2
This model is a fine-tuned version of [dandelin/vilt-b32-mlm](https://huggingface.co/dandelin/vilt-b32-mlm) on the vqa 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: 4
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
### Training results
### Framework versions
- Transformers 4.29.2
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3
|
UnstableLlama/Xwin-LM-13B-V0.1-4bpw-exl2
|
UnstableLlama
| 2023-09-22T20:58:46Z | 94 | 1 |
transformers
|
[
"transformers",
"safetensors",
"llama",
"text-generation",
"license:llama2",
"autotrain_compatible",
"text-generation-inference",
"region:us"
] |
text-generation
| 2023-09-22T20:34:22Z |
---
base_model: https://huggingface.co/Xwin-LM/Xwin-LM-7B-V0.1
inference: false
license: llama2
model_creator: Xwin-LM
model_name: Xwin-LM 13B V0.1
model_type: llama
prompt_template: 'Below is an instruction that describes a task. Write a response
that appropriately completes the request.
### Instruction:
{prompt}
### Response:
'
quantized_by: UnstableLlama
---
---
4.65bpw ExLlamaV2 quantization by UnstableLlama
license: llama2
---
<h3 align="center">
Xwin-LM: Powerful, Stable, and Reproducible LLM Alignment
</h3>
<p align="center">
<a href="https://github.com/Xwin-LM/Xwin-LM"><img src="https://img.shields.io/badge/GitHub-yellow.svg?style=social&logo=github"></a><a href="https://huggingface.co/Xwin-LM"><img src="https://img.shields.io/badge/%F0%9F%A4%97%20Hugging%20Face-Models-blue"></a>
</p>
**Step up your LLM alignment with Xwin-LM!**
Xwin-LM aims to develop and open-source alignment technologies for large language models, including supervised fine-tuning (SFT), reward models (RM), reject sampling, reinforcement learning from human feedback (RLHF), etc. Our first release, built-upon on the Llama2 base models, ranked **TOP-1** on [AlpacaEval](https://tatsu-lab.github.io/alpaca_eval/). Notably, it's **the first to surpass GPT-4** on this benchmark. The project will be continuously updated.
## News
- 💥 [Sep, 2023] We released [Xwin-LM-70B-V0.1](https://huggingface.co/Xwin-LM/Xwin-LM-70B-V0.1), which has achieved a win-rate against Davinci-003 of **95.57%** on [AlpacaEval](https://tatsu-lab.github.io/alpaca_eval/) benchmark, ranking as **TOP-1** on AlpacaEval. **It was the FIRST model surpassing GPT-4** on [AlpacaEval](https://tatsu-lab.github.io/alpaca_eval/). Also note its winrate v.s. GPT-4 is **60.61**.
- 🔍 [Sep, 2023] RLHF plays crucial role in the strong performance of Xwin-LM-V0.1 release!
- 💥 [Sep, 2023] We released [Xwin-LM-13B-V0.1](https://huggingface.co/Xwin-LM/Xwin-LM-13B-V0.1), which has achieved **91.76%** win-rate on [AlpacaEval](https://tatsu-lab.github.io/alpaca_eval/), ranking as **top-1** among all 13B models.
- 💥 [Sep, 2023] We released [Xwin-LM-7B-V0.1](https://huggingface.co/Xwin-LM/Xwin-LM-7B-V0.1), which has achieved **87.82%** win-rate on [AlpacaEval](https://tatsu-lab.github.io/alpaca_eval/), ranking as **top-1** among all 7B models.
## Model Card
| Model | Checkpoint | Report | License |
|------------|------------|-------------|------------------|
|Xwin-LM-7B-V0.1| 🤗 <a href="https://huggingface.co/Xwin-LM/Xwin-LM-7B-V0.1" target="_blank">HF Link</a> | 📃**Coming soon (Stay tuned)** | <a href="https://ai.meta.com/resources/models-and-libraries/llama-downloads/" target="_blank">Llama 2 License|
|Xwin-LM-13B-V0.1| 🤗 <a href="https://huggingface.co/Xwin-LM/Xwin-LM-13B-V0.1" target="_blank">HF Link</a> | | <a href="https://ai.meta.com/resources/models-and-libraries/llama-downloads/" target="_blank">Llama 2 License|
|Xwin-LM-70B-V0.1| 🤗 <a href="https://huggingface.co/Xwin-LM/Xwin-LM-70B-V0.1" target="_blank">HF Link</a> | | <a href="https://ai.meta.com/resources/models-and-libraries/llama-downloads/" target="_blank">Llama 2 License|
## Benchmarks
### Xwin-LM performance on [AlpacaEval](https://tatsu-lab.github.io/alpaca_eval/).
The table below displays the performance of Xwin-LM on [AlpacaEval](https://tatsu-lab.github.io/alpaca_eval/), where evaluates its win-rate against Text-Davinci-003 across 805 questions. To provide a comprehensive evaluation, we present, for the first time, the win-rate against ChatGPT and GPT-4 as well. Our Xwin-LM model family establish a new state-of-the-art performance across all metrics. Notably, Xwin-LM-70B-V0.1 has eclipsed GPT-4 for the first time, achieving an impressive win-rate of **95.57%** to Text-Davinci-003 and **60.61%** to GPT-4.
| **Model** | **AlpacaEval (winrate %)** | **AlpacaEval (winrate %)** |**AlpacaEval (winrate %)** |
|----------------------------------|------------|----------|-------------|
| | **v.s. Text-Davinci-003** | **v.s. ChatGPT** | **v.s. GPT4**|
| **Xwin-LM-70B-V0.1** | **95.57** | **87.50** | **60.61** |
| GPT-4 | 95.28 | 84.66 | 50.00 |
| WizardLM-70B-V1.0 | 92.91 | 80.19 | 46.70 |
| Llama-2-70B-Chat | 92.66 | 81.97 | 51.19 |
| **Xwin-LM-13B-V0.1** | **91.76** | **81.79** | **55.30** |
| ChatGPT | 89.37 | 50.00 | 16.60 |
| WizardLM-13B-V1.2 | 89.17 | 75.75 | 41.91 |
| **Xwin-LM-7B-V0.1** | **87.35** | **76.40** | **47.57** |
| Llama-2-13B-Chat | 81.09 | 64.22 | 30.92 |
### Case study on [AlpacaEval](https://tatsu-lab.github.io/alpaca_eval/)
| Prompts | GTP4 response | Xwin-LM response |
|----------------|------------|--------|
|I've put a plate on top of an apple, and take the plate from kitchen to dinning room. Where is the apple now|The apple is now in the dining room, as it was underneath the plate when you moved the plate from the kitchen to the dining room.|The apple is still in the kitchen, as you have only moved the plate. The apple is under the plate, so if you want to bring the apple to the dining room, you should either move the apple directly or put the apple on the plate and then move the plate to the dining room.|
| Answer the following question.<br> How do you say "good evening" in French. | In French, "good evening" is said as "bonsoir." | In French, "good evening" is translated to "bonsoir." This greeting is used in the evening and nighttime hours, typically after 6 p.m. It is a combination of "bon," which means "good," and "soir," which means "evening." To pronounce it, say "bone-swahr." |
### Xwin-LM performance on NLP foundation tasks.
The following table provides a comparison of Xwin-LMs with other LLMs on NLP foundation tasks in [Open LLM Leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard).
| Model | MMLU 5-shot | ARC 25-shot | TruthfulQA 0-shot | HellaSwag 10-shot | Average |
|------------------|-------------|-------------|-------------------|-------------------|------------|
| Text-davinci-003 | 56.9 | **85.2** | 59.3 | 82.2 | 70.9 |
|Vicuna-13b 1.1 | 51.3 | 53.0 | 51.8 | 80.1 | 59.1 |
|Guanaco 30B | 57.6 | 63.7 | 50.7 | 85.1 | 64.3 |
| WizardLM-7B 1.0 | 42.7 | 51.6 | 44.7 | 77.7 | 54.2 |
| WizardLM-13B 1.0 | 52.3 | 57.2 | 50.5 | 81.0 | 60.2 |
| WizardLM-30B 1.0 | 58.8 | 62.5 | 52.4 | 83.3 | 64.2|
| Llama-2-7B-Chat | 48.3 | 52.9 | 45.6 | 78.6 | 56.4 |
| Llama-2-13B-Chat | 54.6 | 59.0 | 44.1 | 81.9 | 59.9 |
| Llama-2-70B-Chat | 63.9 | 64.6 | 52.8 | 85.9 | 66.8 |
| **Xwin-LM-7B-V0.1** | 49.7 | 56.2 | 48.1 | 79.5 | 58.4 |
| **Xwin-LM-13B-V0.1** | 56.6 | 62.4 | 45.5 | 83.0 | 61.9 |
| **Xwin-LM-70B-V0.1** | **69.6** | 70.5 | **60.1** | **87.1** | **71.8** |
## Inference
### Conversation templates
To obtain desired results, please strictly follow the conversation templates when utilizing our model for inference. Our model adopts the prompt format established by [Vicuna](https://github.com/lm-sys/FastChat) and is equipped to support **multi-turn** conversations.
```
A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions. USER: Hi! ASSISTANT: Hello.</s>USER: Who are you? ASSISTANT: I am Xwin-LM.</s>......
```
### HuggingFace Example
```python
from transformers import AutoTokenizer, AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("Xwin-LM/Xwin-LM-7B-V0.1")
tokenizer = AutoTokenizer.from_pretrained("Xwin-LM/Xwin-LM-7B-V0.1")
(
prompt := "A chat between a curious user and an artificial intelligence assistant. "
"The assistant gives helpful, detailed, and polite answers to the user's questions. "
"USER: Hello, can you help me? "
"ASSISTANT:"
)
inputs = tokenizer(prompt, return_tensors="pt")
samples = model.generate(**inputs, max_new_tokens=4096, temperature=0.7)
output = tokenizer.decode(samples[0][inputs["input_ids"].shape[1]:], skip_special_tokens=True)
print(output)
# Of course! I'm here to help. Please feel free to ask your question or describe the issue you're having, and I'll do my best to assist you.
```
### vllm Example
Because Xwin-LM is based on Llama2, it also offers support for rapid inference using [vllm](https://github.com/vllm-project/vllm). Please refer to [vllm](https://github.com/vllm-project/vllm) for detailed installation instructions.
```python
from vllm import LLM, SamplingParams
(
prompt := "A chat between a curious user and an artificial intelligence assistant. "
"The assistant gives helpful, detailed, and polite answers to the user's questions. "
"USER: Hello, can you help me? "
"ASSISTANT:"
)
sampling_params = SamplingParams(temperature=0.7, max_tokens=4096)
llm = LLM(model="Xwin-LM/Xwin-LM-7B-V0.1")
outputs = llm.generate([prompt,], sampling_params)
for output in outputs:
prompt = output.prompt
generated_text = output.outputs[0].text
print(generated_text)
```
## TODO
- [ ] Release the source code
- [ ] Release more capabilities, such as math, reasoning, and etc.
## Citation
Please consider citing our work if you use the data or code in this repo.
```
@software{xwin-lm,
title = {Xwin-LM},
author = {Xwin-LM Team},
url = {https://github.com/Xwin-LM/Xwin-LM},
version = {pre-release},
year = {2023},
month = {9},
}
```
## Acknowledgements
Thanks to [Llama 2](https://ai.meta.com/llama/), [FastChat](https://github.com/lm-sys/FastChat), [AlpacaFarm](https://github.com/tatsu-lab/alpaca_farm), and [vllm](https://github.com/vllm-project/vllm).
|
CyberHarem/aikawa_chinatsu_idolmastercinderellagirls
|
CyberHarem
| 2023-09-22T20:47:15Z | 0 | 0 | null |
[
"art",
"text-to-image",
"dataset:CyberHarem/aikawa_chinatsu_idolmastercinderellagirls",
"license:mit",
"region:us"
] |
text-to-image
| 2023-09-22T20:38:09Z |
---
license: mit
datasets:
- CyberHarem/aikawa_chinatsu_idolmastercinderellagirls
pipeline_tag: text-to-image
tags:
- art
---
# Lora of aikawa_chinatsu_idolmastercinderellagirls
This model is trained with [HCP-Diffusion](https://github.com/7eu7d7/HCP-Diffusion). And the auto-training framework is maintained by [DeepGHS Team](https://huggingface.co/deepghs).
The base model used during training is [NAI](https://huggingface.co/deepghs/animefull-latest), and the base model used for generating preview images is [Meina/MeinaMix_V11](https://huggingface.co/Meina/MeinaMix_V11).
After downloading the pt and safetensors files for the specified step, you need to use them simultaneously. The pt file will be used as an embedding, while the safetensors file will be loaded for Lora.
For example, if you want to use the model from step 4080, you need to download `4080/aikawa_chinatsu_idolmastercinderellagirls.pt` as the embedding and `4080/aikawa_chinatsu_idolmastercinderellagirls.safetensors` for loading Lora. By using both files together, you can generate images for the desired characters.
**The best step we recommend is 4080**, with the score of 0.921. The trigger words are:
1. `aikawa_chinatsu_idolmastercinderellagirls`
2. `short_hair, glasses, brown_hair, brown_eyes, red-framed_eyewear, jewelry`
For the following groups, it is not recommended to use this model and we express regret:
1. Individuals who cannot tolerate any deviations from the original character design, even in the slightest detail.
2. Individuals who are facing the application scenarios with high demands for accuracy in recreating character outfits.
3. Individuals who cannot accept the potential randomness in AI-generated images based on the Stable Diffusion algorithm.
4. Individuals who are not comfortable with the fully automated process of training character models using LoRA, or those who believe that training character models must be done purely through manual operations to avoid disrespecting the characters.
5. Individuals who finds the generated image content offensive to their values.
These are available steps:
| Steps | Score | Download | pattern_1 | bikini | bondage | free | maid | miko | nude | nude2 | suit | yukata |
|:---------|:----------|:-------------------------------------------------------------------|:-----------------------------------------------|:-----------------------------------------|:--------------------------------------------------|:-------------------------------------|:-------------------------------------|:-------------------------------------|:-----------------------------------------------|:------------------------------------------------|:-------------------------------------|:-----------------------------------------|
| 5100 | 0.921 | [Download](5100/aikawa_chinatsu_idolmastercinderellagirls.zip) |  |  | [<NSFW, click to see>](5100/previews/bondage.png) |  |  |  | [<NSFW, click to see>](5100/previews/nude.png) | [<NSFW, click to see>](5100/previews/nude2.png) |  |  |
| 4760 | 0.912 | [Download](4760/aikawa_chinatsu_idolmastercinderellagirls.zip) |  |  | [<NSFW, click to see>](4760/previews/bondage.png) |  |  |  | [<NSFW, click to see>](4760/previews/nude.png) | [<NSFW, click to see>](4760/previews/nude2.png) |  |  |
| 4420 | 0.838 | [Download](4420/aikawa_chinatsu_idolmastercinderellagirls.zip) |  |  | [<NSFW, click to see>](4420/previews/bondage.png) |  |  |  | [<NSFW, click to see>](4420/previews/nude.png) | [<NSFW, click to see>](4420/previews/nude2.png) |  |  |
| **4080** | **0.921** | [**Download**](4080/aikawa_chinatsu_idolmastercinderellagirls.zip) |  |  | [<NSFW, click to see>](4080/previews/bondage.png) |  |  |  | [<NSFW, click to see>](4080/previews/nude.png) | [<NSFW, click to see>](4080/previews/nude2.png) |  |  |
| 3740 | 0.880 | [Download](3740/aikawa_chinatsu_idolmastercinderellagirls.zip) |  |  | [<NSFW, click to see>](3740/previews/bondage.png) |  |  |  | [<NSFW, click to see>](3740/previews/nude.png) | [<NSFW, click to see>](3740/previews/nude2.png) |  |  |
| 3400 | 0.884 | [Download](3400/aikawa_chinatsu_idolmastercinderellagirls.zip) |  |  | [<NSFW, click to see>](3400/previews/bondage.png) |  |  |  | [<NSFW, click to see>](3400/previews/nude.png) | [<NSFW, click to see>](3400/previews/nude2.png) |  |  |
| 3060 | 0.886 | [Download](3060/aikawa_chinatsu_idolmastercinderellagirls.zip) |  |  | [<NSFW, click to see>](3060/previews/bondage.png) |  |  |  | [<NSFW, click to see>](3060/previews/nude.png) | [<NSFW, click to see>](3060/previews/nude2.png) |  |  |
| 2720 | 0.816 | [Download](2720/aikawa_chinatsu_idolmastercinderellagirls.zip) |  |  | [<NSFW, click to see>](2720/previews/bondage.png) |  |  |  | [<NSFW, click to see>](2720/previews/nude.png) | [<NSFW, click to see>](2720/previews/nude2.png) |  |  |
| 2380 | 0.896 | [Download](2380/aikawa_chinatsu_idolmastercinderellagirls.zip) |  |  | [<NSFW, click to see>](2380/previews/bondage.png) |  |  |  | [<NSFW, click to see>](2380/previews/nude.png) | [<NSFW, click to see>](2380/previews/nude2.png) |  |  |
| 2040 | 0.879 | [Download](2040/aikawa_chinatsu_idolmastercinderellagirls.zip) |  |  | [<NSFW, click to see>](2040/previews/bondage.png) |  |  |  | [<NSFW, click to see>](2040/previews/nude.png) | [<NSFW, click to see>](2040/previews/nude2.png) |  |  |
| 1700 | 0.884 | [Download](1700/aikawa_chinatsu_idolmastercinderellagirls.zip) |  |  | [<NSFW, click to see>](1700/previews/bondage.png) |  |  |  | [<NSFW, click to see>](1700/previews/nude.png) | [<NSFW, click to see>](1700/previews/nude2.png) |  |  |
| 1360 | 0.802 | [Download](1360/aikawa_chinatsu_idolmastercinderellagirls.zip) |  |  | [<NSFW, click to see>](1360/previews/bondage.png) |  |  |  | [<NSFW, click to see>](1360/previews/nude.png) | [<NSFW, click to see>](1360/previews/nude2.png) |  |  |
| 1020 | 0.843 | [Download](1020/aikawa_chinatsu_idolmastercinderellagirls.zip) |  |  | [<NSFW, click to see>](1020/previews/bondage.png) |  |  |  | [<NSFW, click to see>](1020/previews/nude.png) | [<NSFW, click to see>](1020/previews/nude2.png) |  |  |
| 680 | 0.832 | [Download](680/aikawa_chinatsu_idolmastercinderellagirls.zip) |  |  | [<NSFW, click to see>](680/previews/bondage.png) |  |  |  | [<NSFW, click to see>](680/previews/nude.png) | [<NSFW, click to see>](680/previews/nude2.png) |  |  |
| 340 | 0.750 | [Download](340/aikawa_chinatsu_idolmastercinderellagirls.zip) |  |  | [<NSFW, click to see>](340/previews/bondage.png) |  |  |  | [<NSFW, click to see>](340/previews/nude.png) | [<NSFW, click to see>](340/previews/nude2.png) |  |  |
|
keikofujii/distilbert-base-uncased-finetuned-stsb
|
keikofujii
| 2023-09-22T20:41:45Z | 113 | 0 |
transformers
|
[
"transformers",
"pytorch",
"distilbert",
"text-classification",
"generated_from_trainer",
"dataset:glue",
"base_model:distilbert/distilbert-base-uncased",
"base_model:finetune:distilbert/distilbert-base-uncased",
"license:apache-2.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2023-09-22T20:11:27Z |
---
license: apache-2.0
base_model: distilbert-base-uncased
tags:
- generated_from_trainer
datasets:
- glue
metrics:
- spearmanr
model-index:
- name: distilbert-base-uncased-finetuned-stsb
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: glue
type: glue
config: stsb
split: validation
args: stsb
metrics:
- name: Spearmanr
type: spearmanr
value: 0.8679004942016133
---
<!-- 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. -->
# distilbert-base-uncased-finetuned-stsb
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the glue dataset.
It achieves the following results on the evaluation set:
- Loss: 0.5563
- Pearson: 0.8708
- Spearmanr: 0.8679
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
### Training results
| Training Loss | Epoch | Step | Validation Loss | Pearson | Spearmanr |
|:-------------:|:-----:|:----:|:---------------:|:-------:|:---------:|
| No log | 1.0 | 360 | 0.6167 | 0.8601 | 0.8577 |
| 1.0026 | 2.0 | 720 | 0.6175 | 0.8670 | 0.8653 |
| 0.3862 | 3.0 | 1080 | 0.6439 | 0.8703 | 0.8675 |
| 0.3862 | 4.0 | 1440 | 0.5563 | 0.8708 | 0.8679 |
| 0.2514 | 5.0 | 1800 | 0.5616 | 0.8694 | 0.8659 |
### Framework versions
- Transformers 4.33.2
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3
|
YassineBenlaria/testing_pretrained_niger_mali
|
YassineBenlaria
| 2023-09-22T20:41:39Z | 108 | 0 |
transformers
|
[
"transformers",
"pytorch",
"wav2vec2",
"automatic-speech-recognition",
"generated_from_trainer",
"endpoints_compatible",
"region:us"
] |
automatic-speech-recognition
| 2023-09-22T17:26:37Z |
---
tags:
- generated_from_trainer
metrics:
- wer
model-index:
- name: testing_pretrained_niger_mali
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. -->
# testing_pretrained_niger_mali
This model was trained from scratch on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 1.9245
- Wer: 0.8889
## 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: 3e-05
- train_batch_size: 16
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 350
### Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|:-------------:|:------:|:----:|:---------------:|:------:|
| 6.427 | 35.29 | 300 | 2.9588 | 1.0 |
| 2.8653 | 70.59 | 600 | 2.7466 | 1.0 |
| 2.7675 | 105.88 | 900 | 2.7207 | 1.0 |
| 2.6674 | 141.18 | 1200 | 2.2285 | 1.0 |
| 1.7813 | 176.47 | 1500 | 1.5717 | 0.8852 |
| 1.0447 | 211.76 | 1800 | 1.7009 | 0.8778 |
| 0.8167 | 247.06 | 2100 | 1.8010 | 0.8815 |
| 0.7059 | 282.35 | 2400 | 1.8748 | 0.8815 |
| 0.6572 | 317.65 | 2700 | 1.9245 | 0.8889 |
### Framework versions
- Transformers 4.33.2
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3
|
akshayreddy/falcon_finetuned_us_gaap_v2
|
akshayreddy
| 2023-09-22T20:27:17Z | 2 | 0 |
peft
|
[
"peft",
"region:us"
] | null | 2023-09-22T20:27:13Z |
---
library_name: peft
---
## Training procedure
The following `bitsandbytes` quantization config was used during training:
- quant_method: bitsandbytes
- load_in_8bit: False
- load_in_4bit: True
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: nf4
- bnb_4bit_use_double_quant: False
- bnb_4bit_compute_dtype: bfloat16
### Framework versions
- PEFT 0.5.0
|
kmaksatk/controlnet_80k_data_blip
|
kmaksatk
| 2023-09-22T20:18:20Z | 2 | 0 |
diffusers
|
[
"diffusers",
"safetensors",
"stable-diffusion",
"stable-diffusion-diffusers",
"text-to-image",
"controlnet",
"base_model:runwayml/stable-diffusion-v1-5",
"base_model:adapter:runwayml/stable-diffusion-v1-5",
"license:creativeml-openrail-m",
"region:us"
] |
text-to-image
| 2023-09-21T06:40:04Z |
---
license: creativeml-openrail-m
base_model: runwayml/stable-diffusion-v1-5
tags:
- stable-diffusion
- stable-diffusion-diffusers
- text-to-image
- diffusers
- controlnet
inference: true
---
# controlnet-kmaksatk/controlnet_80k_data_blip
These are controlnet weights trained on runwayml/stable-diffusion-v1-5 with new type of conditioning.
You can find some example images below.
prompt: High qualityphoto of male gymnast in a blue sport outfit in the olympic game
prompt: High qualityphoto of male gymnast in a blue sport outfit in the olympic game
prompt: High qualityphoto of male gymnast in a blue sport outfit in the olympic game
|
CyberHarem/momoi_azuki_idolmastercinderellagirls
|
CyberHarem
| 2023-09-22T19:56:22Z | 0 | 0 | null |
[
"art",
"text-to-image",
"dataset:CyberHarem/momoi_azuki_idolmastercinderellagirls",
"license:mit",
"region:us"
] |
text-to-image
| 2023-09-22T19:43:43Z |
---
license: mit
datasets:
- CyberHarem/momoi_azuki_idolmastercinderellagirls
pipeline_tag: text-to-image
tags:
- art
---
# Lora of momoi_azuki_idolmastercinderellagirls
This model is trained with [HCP-Diffusion](https://github.com/7eu7d7/HCP-Diffusion). And the auto-training framework is maintained by [DeepGHS Team](https://huggingface.co/deepghs).
The base model used during training is [NAI](https://huggingface.co/deepghs/animefull-latest), and the base model used for generating preview images is [Meina/MeinaMix_V11](https://huggingface.co/Meina/MeinaMix_V11).
After downloading the pt and safetensors files for the specified step, you need to use them simultaneously. The pt file will be used as an embedding, while the safetensors file will be loaded for Lora.
For example, if you want to use the model from step 3060, you need to download `3060/momoi_azuki_idolmastercinderellagirls.pt` as the embedding and `3060/momoi_azuki_idolmastercinderellagirls.safetensors` for loading Lora. By using both files together, you can generate images for the desired characters.
**The best step we recommend is 3060**, with the score of 0.937. The trigger words are:
1. `momoi_azuki_idolmastercinderellagirls`
2. `brown_eyes, black_hair, smile, breasts, blush, hair_ornament, open_mouth, flower, hair_flower, single_hair_bun, hair_bun, brown_hair, long_hair, medium_breasts`
For the following groups, it is not recommended to use this model and we express regret:
1. Individuals who cannot tolerate any deviations from the original character design, even in the slightest detail.
2. Individuals who are facing the application scenarios with high demands for accuracy in recreating character outfits.
3. Individuals who cannot accept the potential randomness in AI-generated images based on the Stable Diffusion algorithm.
4. Individuals who are not comfortable with the fully automated process of training character models using LoRA, or those who believe that training character models must be done purely through manual operations to avoid disrespecting the characters.
5. Individuals who finds the generated image content offensive to their values.
These are available steps:
| Steps | Score | Download | pattern_1 | pattern_2 | pattern_3 | pattern_4 | pattern_5 | pattern_6 | pattern_7 | bikini | bondage | free | maid | miko | nude | nude2 | suit | yukata |
|:---------|:----------|:---------------------------------------------------------------|:----------------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:----------------------------------------------------|:-----------------------------------------------|:----------------------------------------------------|:----------------------------------------------------|:-----------------------------------------|:--------------------------------------------------|:-------------------------------------|:-------------------------------------|:-------------------------------------|:-----------------------------------------------|:------------------------------------------------|:-------------------------------------|:-----------------------------------------|
| 5100 | 0.863 | [Download](5100/momoi_azuki_idolmastercinderellagirls.zip) | [<NSFW, click to see>](5100/previews/pattern_1.png) |  |  | [<NSFW, click to see>](5100/previews/pattern_4.png) |  | [<NSFW, click to see>](5100/previews/pattern_6.png) | [<NSFW, click to see>](5100/previews/pattern_7.png) |  | [<NSFW, click to see>](5100/previews/bondage.png) |  |  |  | [<NSFW, click to see>](5100/previews/nude.png) | [<NSFW, click to see>](5100/previews/nude2.png) |  |  |
| 4760 | 0.852 | [Download](4760/momoi_azuki_idolmastercinderellagirls.zip) | [<NSFW, click to see>](4760/previews/pattern_1.png) |  |  | [<NSFW, click to see>](4760/previews/pattern_4.png) |  | [<NSFW, click to see>](4760/previews/pattern_6.png) | [<NSFW, click to see>](4760/previews/pattern_7.png) |  | [<NSFW, click to see>](4760/previews/bondage.png) |  |  |  | [<NSFW, click to see>](4760/previews/nude.png) | [<NSFW, click to see>](4760/previews/nude2.png) |  |  |
| 4420 | 0.800 | [Download](4420/momoi_azuki_idolmastercinderellagirls.zip) | [<NSFW, click to see>](4420/previews/pattern_1.png) |  |  | [<NSFW, click to see>](4420/previews/pattern_4.png) |  | [<NSFW, click to see>](4420/previews/pattern_6.png) | [<NSFW, click to see>](4420/previews/pattern_7.png) |  | [<NSFW, click to see>](4420/previews/bondage.png) |  |  |  | [<NSFW, click to see>](4420/previews/nude.png) | [<NSFW, click to see>](4420/previews/nude2.png) |  |  |
| 4080 | 0.897 | [Download](4080/momoi_azuki_idolmastercinderellagirls.zip) | [<NSFW, click to see>](4080/previews/pattern_1.png) |  |  | [<NSFW, click to see>](4080/previews/pattern_4.png) |  | [<NSFW, click to see>](4080/previews/pattern_6.png) | [<NSFW, click to see>](4080/previews/pattern_7.png) |  | [<NSFW, click to see>](4080/previews/bondage.png) |  |  |  | [<NSFW, click to see>](4080/previews/nude.png) | [<NSFW, click to see>](4080/previews/nude2.png) |  |  |
| 3740 | 0.866 | [Download](3740/momoi_azuki_idolmastercinderellagirls.zip) | [<NSFW, click to see>](3740/previews/pattern_1.png) |  |  | [<NSFW, click to see>](3740/previews/pattern_4.png) |  | [<NSFW, click to see>](3740/previews/pattern_6.png) | [<NSFW, click to see>](3740/previews/pattern_7.png) |  | [<NSFW, click to see>](3740/previews/bondage.png) |  |  |  | [<NSFW, click to see>](3740/previews/nude.png) | [<NSFW, click to see>](3740/previews/nude2.png) |  |  |
| 3400 | 0.874 | [Download](3400/momoi_azuki_idolmastercinderellagirls.zip) | [<NSFW, click to see>](3400/previews/pattern_1.png) |  |  | [<NSFW, click to see>](3400/previews/pattern_4.png) |  | [<NSFW, click to see>](3400/previews/pattern_6.png) | [<NSFW, click to see>](3400/previews/pattern_7.png) |  | [<NSFW, click to see>](3400/previews/bondage.png) |  |  |  | [<NSFW, click to see>](3400/previews/nude.png) | [<NSFW, click to see>](3400/previews/nude2.png) |  |  |
| **3060** | **0.937** | [**Download**](3060/momoi_azuki_idolmastercinderellagirls.zip) | [<NSFW, click to see>](3060/previews/pattern_1.png) |  |  | [<NSFW, click to see>](3060/previews/pattern_4.png) |  | [<NSFW, click to see>](3060/previews/pattern_6.png) | [<NSFW, click to see>](3060/previews/pattern_7.png) |  | [<NSFW, click to see>](3060/previews/bondage.png) |  |  |  | [<NSFW, click to see>](3060/previews/nude.png) | [<NSFW, click to see>](3060/previews/nude2.png) |  |  |
| 2720 | 0.873 | [Download](2720/momoi_azuki_idolmastercinderellagirls.zip) | [<NSFW, click to see>](2720/previews/pattern_1.png) |  |  | [<NSFW, click to see>](2720/previews/pattern_4.png) |  | [<NSFW, click to see>](2720/previews/pattern_6.png) | [<NSFW, click to see>](2720/previews/pattern_7.png) |  | [<NSFW, click to see>](2720/previews/bondage.png) |  |  |  | [<NSFW, click to see>](2720/previews/nude.png) | [<NSFW, click to see>](2720/previews/nude2.png) |  |  |
| 2380 | 0.858 | [Download](2380/momoi_azuki_idolmastercinderellagirls.zip) | [<NSFW, click to see>](2380/previews/pattern_1.png) |  |  | [<NSFW, click to see>](2380/previews/pattern_4.png) |  | [<NSFW, click to see>](2380/previews/pattern_6.png) | [<NSFW, click to see>](2380/previews/pattern_7.png) |  | [<NSFW, click to see>](2380/previews/bondage.png) |  |  |  | [<NSFW, click to see>](2380/previews/nude.png) | [<NSFW, click to see>](2380/previews/nude2.png) |  |  |
| 2040 | 0.877 | [Download](2040/momoi_azuki_idolmastercinderellagirls.zip) | [<NSFW, click to see>](2040/previews/pattern_1.png) |  |  | [<NSFW, click to see>](2040/previews/pattern_4.png) |  | [<NSFW, click to see>](2040/previews/pattern_6.png) | [<NSFW, click to see>](2040/previews/pattern_7.png) |  | [<NSFW, click to see>](2040/previews/bondage.png) |  |  |  | [<NSFW, click to see>](2040/previews/nude.png) | [<NSFW, click to see>](2040/previews/nude2.png) |  |  |
| 1700 | 0.872 | [Download](1700/momoi_azuki_idolmastercinderellagirls.zip) | [<NSFW, click to see>](1700/previews/pattern_1.png) |  |  | [<NSFW, click to see>](1700/previews/pattern_4.png) |  | [<NSFW, click to see>](1700/previews/pattern_6.png) | [<NSFW, click to see>](1700/previews/pattern_7.png) |  | [<NSFW, click to see>](1700/previews/bondage.png) |  |  |  | [<NSFW, click to see>](1700/previews/nude.png) | [<NSFW, click to see>](1700/previews/nude2.png) |  |  |
| 1360 | 0.901 | [Download](1360/momoi_azuki_idolmastercinderellagirls.zip) | [<NSFW, click to see>](1360/previews/pattern_1.png) |  |  | [<NSFW, click to see>](1360/previews/pattern_4.png) |  | [<NSFW, click to see>](1360/previews/pattern_6.png) | [<NSFW, click to see>](1360/previews/pattern_7.png) |  | [<NSFW, click to see>](1360/previews/bondage.png) |  |  |  | [<NSFW, click to see>](1360/previews/nude.png) | [<NSFW, click to see>](1360/previews/nude2.png) |  |  |
| 1020 | 0.896 | [Download](1020/momoi_azuki_idolmastercinderellagirls.zip) | [<NSFW, click to see>](1020/previews/pattern_1.png) |  |  | [<NSFW, click to see>](1020/previews/pattern_4.png) |  | [<NSFW, click to see>](1020/previews/pattern_6.png) | [<NSFW, click to see>](1020/previews/pattern_7.png) |  | [<NSFW, click to see>](1020/previews/bondage.png) |  |  |  | [<NSFW, click to see>](1020/previews/nude.png) | [<NSFW, click to see>](1020/previews/nude2.png) |  |  |
| 680 | 0.877 | [Download](680/momoi_azuki_idolmastercinderellagirls.zip) | [<NSFW, click to see>](680/previews/pattern_1.png) |  |  | [<NSFW, click to see>](680/previews/pattern_4.png) |  | [<NSFW, click to see>](680/previews/pattern_6.png) | [<NSFW, click to see>](680/previews/pattern_7.png) |  | [<NSFW, click to see>](680/previews/bondage.png) |  |  |  | [<NSFW, click to see>](680/previews/nude.png) | [<NSFW, click to see>](680/previews/nude2.png) |  |  |
| 340 | 0.786 | [Download](340/momoi_azuki_idolmastercinderellagirls.zip) | [<NSFW, click to see>](340/previews/pattern_1.png) |  |  | [<NSFW, click to see>](340/previews/pattern_4.png) |  | [<NSFW, click to see>](340/previews/pattern_6.png) | [<NSFW, click to see>](340/previews/pattern_7.png) |  | [<NSFW, click to see>](340/previews/bondage.png) |  |  |  | [<NSFW, click to see>](340/previews/nude.png) | [<NSFW, click to see>](340/previews/nude2.png) |  |  |
|
eugene6/q-FrozenLake-v1-4x4-noSlippery
|
eugene6
| 2023-09-22T19:54:05Z | 0 | 0 | null |
[
"FrozenLake-v1-4x4-no_slippery",
"q-learning",
"reinforcement-learning",
"custom-implementation",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-09-22T19:54:03Z |
---
tags:
- FrozenLake-v1-4x4-no_slippery
- q-learning
- reinforcement-learning
- custom-implementation
model-index:
- name: q-FrozenLake-v1-4x4-noSlippery
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: FrozenLake-v1-4x4-no_slippery
type: FrozenLake-v1-4x4-no_slippery
metrics:
- type: mean_reward
value: 1.00 +/- 0.00
name: mean_reward
verified: false
---
# **Q-Learning** Agent playing1 **FrozenLake-v1**
This is a trained model of a **Q-Learning** agent playing **FrozenLake-v1** .
## Usage
```python
model = load_from_hub(repo_id="eugene6/q-FrozenLake-v1-4x4-noSlippery", filename="q-learning.pkl")
# Don't forget to check if you need to add additional attributes (is_slippery=False etc)
env = gym.make(model["env_id"])
```
|
DriveMyScream/News_Sentiment_Analysis_model
|
DriveMyScream
| 2023-09-22T19:44:17Z | 0 | 0 |
keras
|
[
"keras",
"tf-keras",
"region:us"
] | null | 2023-09-22T19:43:45Z |
---
library_name: keras
---
## 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:
| Hyperparameters | Value |
| :-- | :-- |
| name | Adam |
| weight_decay | None |
| clipnorm | None |
| global_clipnorm | None |
| clipvalue | None |
| use_ema | False |
| ema_momentum | 0.99 |
| ema_overwrite_frequency | None |
| jit_compile | True |
| is_legacy_optimizer | False |
| learning_rate | 0.0010000000474974513 |
| beta_1 | 0.9 |
| beta_2 | 0.999 |
| epsilon | 1e-07 |
| amsgrad | False |
| training_precision | float32 |
## Model Plot
<details>
<summary>View Model Plot</summary>
</details>
|
LucaAsga/ppo-LunarLander-v2-NEW-2
|
LucaAsga
| 2023-09-22T19:30:39Z | 0 | 0 |
stable-baselines3
|
[
"stable-baselines3",
"LunarLander-v2",
"deep-reinforcement-learning",
"reinforcement-learning",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-09-22T19:30:21Z |
---
library_name: stable-baselines3
tags:
- LunarLander-v2
- deep-reinforcement-learning
- reinforcement-learning
- stable-baselines3
model-index:
- name: PPO
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: LunarLander-v2
type: LunarLander-v2
metrics:
- type: mean_reward
value: 261.24 +/- 66.82
name: mean_reward
verified: false
---
# **PPO** Agent playing **LunarLander-v2**
This is a trained model of a **PPO** agent playing **LunarLander-v2**
using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3).
## Usage (with Stable-baselines3)
TODO: Add your code
```python
from stable_baselines3 import ...
from huggingface_sb3 import load_from_hub
...
```
|
kudoshinichi/bert_emails
|
kudoshinichi
| 2023-09-22T19:24:46Z | 105 | 1 |
transformers
|
[
"transformers",
"pytorch",
"bert",
"text-classification",
"en",
"dataset:yentinglin/ntu_adl_recitation",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2023-09-22T03:51:50Z |
---
license: mit
datasets:
- yentinglin/ntu_adl_recitation
language:
- en
metrics:
- accuracy
---
The model fine-tunes the bert-base-cased model. It is able to classify text into one of 150 intent classes. The goal is to use this model to classify intents in user input (e.g. emails, customer service, search queries).
The model is trained over 3 epochs on a subset of the training set (2000/7500). This yielded a performance of 77.6% on the test set. By using the full dataset, the accuracy is expected to increase drastically. For reference, the model accuracy improved from 32% to 78% by moving to training on 1000/7500 of the dataset to 2000/7500. Hence, there is significant potential to fine-tune a model for intent classification if the full training set is used. The author did not attempt training on the full dataset due to time constraints.
|
Amey-HH/ddpm-butterflies-128
|
Amey-HH
| 2023-09-22T19:15:14Z | 34 | 0 |
diffusers
|
[
"diffusers",
"tensorboard",
"safetensors",
"pytorch",
"unconditional-image-generation",
"diffusion-models-class",
"license:mit",
"diffusers:DDPMPipeline",
"region:us"
] |
unconditional-image-generation
| 2023-09-22T18:33:33Z |
---
license: mit
tags:
- pytorch
- diffusers
- unconditional-image-generation
- diffusion-models-class
---
# Model Card for Unit 1 of the [Diffusion Models Class 🧨](https://github.com/huggingface/diffusion-models-class)
This model is a diffusion model for unconditional image generation of Polyps.
## Usage
```python
from diffusers import DDPMPipeline
pipeline = DDPMPipeline.from_pretrained('Amey-HH/ddpm-butterflies-128')
image = pipeline().images[0]
image
```
|
CyberHarem/aino_nagisa_idolmastercinderellagirls
|
CyberHarem
| 2023-09-22T19:06:17Z | 0 | 0 | null |
[
"art",
"text-to-image",
"dataset:CyberHarem/aino_nagisa_idolmastercinderellagirls",
"license:mit",
"region:us"
] |
text-to-image
| 2023-09-22T18:57:44Z |
---
license: mit
datasets:
- CyberHarem/aino_nagisa_idolmastercinderellagirls
pipeline_tag: text-to-image
tags:
- art
---
# Lora of aino_nagisa_idolmastercinderellagirls
This model is trained with [HCP-Diffusion](https://github.com/7eu7d7/HCP-Diffusion). And the auto-training framework is maintained by [DeepGHS Team](https://huggingface.co/deepghs).
The base model used during training is [NAI](https://huggingface.co/deepghs/animefull-latest), and the base model used for generating preview images is [Meina/MeinaMix_V11](https://huggingface.co/Meina/MeinaMix_V11).
After downloading the pt and safetensors files for the specified step, you need to use them simultaneously. The pt file will be used as an embedding, while the safetensors file will be loaded for Lora.
For example, if you want to use the model from step 4760, you need to download `4760/aino_nagisa_idolmastercinderellagirls.pt` as the embedding and `4760/aino_nagisa_idolmastercinderellagirls.safetensors` for loading Lora. By using both files together, you can generate images for the desired characters.
**The best step we recommend is 4760**, with the score of 0.957. The trigger words are:
1. `aino_nagisa_idolmastercinderellagirls`
2. `brown_hair, long_hair, ponytail, smile, brown_eyes, open_mouth, breasts`
For the following groups, it is not recommended to use this model and we express regret:
1. Individuals who cannot tolerate any deviations from the original character design, even in the slightest detail.
2. Individuals who are facing the application scenarios with high demands for accuracy in recreating character outfits.
3. Individuals who cannot accept the potential randomness in AI-generated images based on the Stable Diffusion algorithm.
4. Individuals who are not comfortable with the fully automated process of training character models using LoRA, or those who believe that training character models must be done purely through manual operations to avoid disrespecting the characters.
5. Individuals who finds the generated image content offensive to their values.
These are available steps:
| Steps | Score | Download | pattern_1 | pattern_2 | bikini | bondage | free | maid | miko | nude | nude2 | suit | yukata |
|:---------|:----------|:---------------------------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------|:--------------------------------------------------|:-------------------------------------|:-------------------------------------|:-------------------------------------|:-----------------------------------------------|:------------------------------------------------|:-------------------------------------|:-----------------------------------------|
| 5100 | 0.954 | [Download](5100/aino_nagisa_idolmastercinderellagirls.zip) |  |  |  | [<NSFW, click to see>](5100/previews/bondage.png) |  |  |  | [<NSFW, click to see>](5100/previews/nude.png) | [<NSFW, click to see>](5100/previews/nude2.png) |  |  |
| **4760** | **0.957** | [**Download**](4760/aino_nagisa_idolmastercinderellagirls.zip) |  |  |  | [<NSFW, click to see>](4760/previews/bondage.png) |  |  |  | [<NSFW, click to see>](4760/previews/nude.png) | [<NSFW, click to see>](4760/previews/nude2.png) |  |  |
| 4420 | 0.908 | [Download](4420/aino_nagisa_idolmastercinderellagirls.zip) |  |  |  | [<NSFW, click to see>](4420/previews/bondage.png) |  |  |  | [<NSFW, click to see>](4420/previews/nude.png) | [<NSFW, click to see>](4420/previews/nude2.png) |  |  |
| 4080 | 0.952 | [Download](4080/aino_nagisa_idolmastercinderellagirls.zip) |  |  |  | [<NSFW, click to see>](4080/previews/bondage.png) |  |  |  | [<NSFW, click to see>](4080/previews/nude.png) | [<NSFW, click to see>](4080/previews/nude2.png) |  |  |
| 3740 | 0.938 | [Download](3740/aino_nagisa_idolmastercinderellagirls.zip) |  |  |  | [<NSFW, click to see>](3740/previews/bondage.png) |  |  |  | [<NSFW, click to see>](3740/previews/nude.png) | [<NSFW, click to see>](3740/previews/nude2.png) |  |  |
| 3400 | 0.902 | [Download](3400/aino_nagisa_idolmastercinderellagirls.zip) |  |  |  | [<NSFW, click to see>](3400/previews/bondage.png) |  |  |  | [<NSFW, click to see>](3400/previews/nude.png) | [<NSFW, click to see>](3400/previews/nude2.png) |  |  |
| 3060 | 0.870 | [Download](3060/aino_nagisa_idolmastercinderellagirls.zip) |  |  |  | [<NSFW, click to see>](3060/previews/bondage.png) |  |  |  | [<NSFW, click to see>](3060/previews/nude.png) | [<NSFW, click to see>](3060/previews/nude2.png) |  |  |
| 2720 | 0.867 | [Download](2720/aino_nagisa_idolmastercinderellagirls.zip) |  |  |  | [<NSFW, click to see>](2720/previews/bondage.png) |  |  |  | [<NSFW, click to see>](2720/previews/nude.png) | [<NSFW, click to see>](2720/previews/nude2.png) |  |  |
| 2380 | 0.858 | [Download](2380/aino_nagisa_idolmastercinderellagirls.zip) |  |  |  | [<NSFW, click to see>](2380/previews/bondage.png) |  |  |  | [<NSFW, click to see>](2380/previews/nude.png) | [<NSFW, click to see>](2380/previews/nude2.png) |  |  |
| 2040 | 0.871 | [Download](2040/aino_nagisa_idolmastercinderellagirls.zip) |  |  |  | [<NSFW, click to see>](2040/previews/bondage.png) |  |  |  | [<NSFW, click to see>](2040/previews/nude.png) | [<NSFW, click to see>](2040/previews/nude2.png) |  |  |
| 1700 | 0.827 | [Download](1700/aino_nagisa_idolmastercinderellagirls.zip) |  |  |  | [<NSFW, click to see>](1700/previews/bondage.png) |  |  |  | [<NSFW, click to see>](1700/previews/nude.png) | [<NSFW, click to see>](1700/previews/nude2.png) |  |  |
| 1360 | 0.573 | [Download](1360/aino_nagisa_idolmastercinderellagirls.zip) |  |  |  | [<NSFW, click to see>](1360/previews/bondage.png) |  |  |  | [<NSFW, click to see>](1360/previews/nude.png) | [<NSFW, click to see>](1360/previews/nude2.png) |  |  |
| 1020 | 0.677 | [Download](1020/aino_nagisa_idolmastercinderellagirls.zip) |  |  |  | [<NSFW, click to see>](1020/previews/bondage.png) |  |  |  | [<NSFW, click to see>](1020/previews/nude.png) | [<NSFW, click to see>](1020/previews/nude2.png) |  |  |
| 680 | 0.400 | [Download](680/aino_nagisa_idolmastercinderellagirls.zip) |  |  |  | [<NSFW, click to see>](680/previews/bondage.png) |  |  |  | [<NSFW, click to see>](680/previews/nude.png) | [<NSFW, click to see>](680/previews/nude2.png) |  |  |
| 340 | 0.458 | [Download](340/aino_nagisa_idolmastercinderellagirls.zip) |  |  |  | [<NSFW, click to see>](340/previews/bondage.png) |  |  |  | [<NSFW, click to see>](340/previews/nude.png) | [<NSFW, click to see>](340/previews/nude2.png) |  |  |
|
przl/q-Taxi-v3
|
przl
| 2023-09-22T18:57:57Z | 0 | 0 | null |
[
"Taxi-v3",
"q-learning",
"reinforcement-learning",
"custom-implementation",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-09-22T18:57:55Z |
---
tags:
- Taxi-v3
- q-learning
- reinforcement-learning
- custom-implementation
model-index:
- name: q-Taxi-v3
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: Taxi-v3
type: Taxi-v3
metrics:
- type: mean_reward
value: 7.54 +/- 2.73
name: mean_reward
verified: false
---
# **Q-Learning** Agent playing1 **Taxi-v3**
This is a trained model of a **Q-Learning** agent playing **Taxi-v3** .
## Usage
```python
model = load_from_hub(repo_id="przl/q-Taxi-v3", filename="q-learning.pkl")
# Don't forget to check if you need to add additional attributes (is_slippery=False etc)
env = gym.make(model["env_id"])
```
|
przl/q-FrozenLake-v1-4x4-noSlippery
|
przl
| 2023-09-22T18:54:22Z | 0 | 0 | null |
[
"FrozenLake-v1-4x4-no_slippery",
"q-learning",
"reinforcement-learning",
"custom-implementation",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-09-22T18:54:20Z |
---
tags:
- FrozenLake-v1-4x4-no_slippery
- q-learning
- reinforcement-learning
- custom-implementation
model-index:
- name: q-FrozenLake-v1-4x4-noSlippery
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: FrozenLake-v1-4x4-no_slippery
type: FrozenLake-v1-4x4-no_slippery
metrics:
- type: mean_reward
value: 1.00 +/- 0.00
name: mean_reward
verified: false
---
# **Q-Learning** Agent playing1 **FrozenLake-v1**
This is a trained model of a **Q-Learning** agent playing **FrozenLake-v1** .
## Usage
```python
model = load_from_hub(repo_id="przl/q-FrozenLake-v1-4x4-noSlippery", filename="q-learning.pkl")
# Don't forget to check if you need to add additional attributes (is_slippery=False etc)
env = gym.make(model["env_id"])
```
|
santis2/gpt2-alpaca-instruction-fine-tuning-lora
|
santis2
| 2023-09-22T18:52:42Z | 0 | 0 | null |
[
"generated_from_trainer",
"base_model:openai-community/gpt2",
"base_model:finetune:openai-community/gpt2",
"license:mit",
"region:us"
] | null | 2023-09-22T15:35:13Z |
---
license: mit
base_model: gpt2
tags:
- generated_from_trainer
model-index:
- name: gpt2-alpaca-instruction-fine-tuning-lora
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. -->
# gpt2-alpaca-instruction-fine-tuning-lora
This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 1.6981
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0005
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 1000
- num_epochs: 1
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 2.118 | 0.11 | 1000 | 1.7807 |
| 1.8878 | 0.22 | 2000 | 1.7477 |
| 1.8609 | 0.33 | 3000 | 1.7318 |
| 1.8489 | 0.44 | 4000 | 1.7207 |
| 1.8416 | 0.55 | 5000 | 1.7134 |
| 1.8181 | 0.66 | 6000 | 1.7082 |
| 1.8144 | 0.77 | 7000 | 1.7021 |
| 1.816 | 0.88 | 8000 | 1.6987 |
| 1.7825 | 0.99 | 9000 | 1.6981 |
### Framework versions
- Transformers 4.33.2
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3
|
jmoney54378256438905/jondurbin_airoboros-c34b-2.2.1-4.65bpw
|
jmoney54378256438905
| 2023-09-22T18:48:51Z | 5 | 0 |
transformers
|
[
"transformers",
"llama",
"text-generation",
"dataset:jondurbin/airoboros-2.2.1",
"license:llama2",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2023-09-22T18:38:37Z |
---
license: llama2
datasets:
- jondurbin/airoboros-2.2.1
---
### Overview
Another experimental model, using mostly sythetic data generated by [airoboros](https://github.com/jondurbin/airoboros)
This is essentially a minor "fix" branch of [airoboros-c34b-2.2](https://hf.co/jondurbin/airoboros-c34b-2.2) with a updates, primarily:
- [re-generated writing responses](https://huggingface.co/datasets/jondurbin/airoboros-2.2.1#re-generated-writing-responses)
- [longer contextual blocks](https://huggingface.co/datasets/jondurbin/airoboros-2.2.1#longer-contextual-blocks)
- [removal of "rp" data](https://huggingface.co/datasets/jondurbin/airoboros-2.2.1#rp-category-removed)
- [(less aggressive) de-censoring](https://huggingface.co/datasets/jondurbin/airoboros-2.2.1#de-censoring)
- 5 epochs instead of 3
This is a fairly general purpose model, but focuses heavily on instruction following, rather than casual chat/roleplay.
Huge thank you to the folks over at [a16z](https://a16z.com/) for sponsoring the costs associated with building models and associated tools!
### Prompt format
The prompt format:
```
A chat.
USER: {prompt}
ASSISTANT:
```
The default system prompt ("A chat.") was used for most of the prompts, however it also included a wide sampling of responses with other prompts, particularly in "stylized\_response", "rp", "gtkm", etc.
Here's another example:
```
A chat between Bob (aka USER) and Tom (aka ASSISTANT). Tom is an extremely intelligent 18th century bookkeeper, who speaks loquaciously.
USER: {prompt}
ASSISTANT:
```
And chat scenario that wouldn't require USER/ASSISTANT (but should use stopping criteria to prevent the model from speaking on your behalf).
```
A chat between old friends: Timmy and Tommy.
{description of characters}
{setting for the chat}
Timmy: *takes a big sip from his coffee* "Ah, sweet, delicious, magical coffee."
Tommy:
```
__*I strongly suggest adding stopping criteria/early inference stopping on "USER:", and/or whatever names you specify in the system prompt.*__
### Fine tuning info
https://wandb.ai/jondurbin/airoboros-c34b-2.2.1/runs/07b08z7m?workspace=user-jondurbin
### Helpful usage tips
*The prompts shown here are are just the text that would be included after USER: and before ASSISTANT: in the full prompt format above, the system prompt and USER:/ASSISTANT: have been omited for readability.*
#### Context obedient question answering
By obedient, I mean the model was trained to ignore what it thinks it knows, and uses the context to answer the question. The model was also tuned to limit the values to the provided context as much as possible to reduce hallucinations.
The format for a closed-context prompt is as follows:
```
BEGININPUT
BEGINCONTEXT
[key0: value0]
[key1: value1]
... other metdata ...
ENDCONTEXT
[insert your text blocks here]
ENDINPUT
[add as many other blocks, in the exact same format]
BEGININSTRUCTION
[insert your instruction(s). The model was tuned with single questions, paragraph format, lists, etc.]
ENDINSTRUCTION
```
It's also helpful to add "Don't make up answers if you don't know." to your instruction block to make sure if the context is completely unrelated it doesn't make something up.
*The __only__ prompts that need this closed context formating are closed-context instructions. Normal questions/instructions do not!*
I know it's a bit verbose and annoying, but after much trial and error, using these explicit delimiters helps the model understand where to find the responses and how to associate specific sources with it.
- `BEGININPUT` - denotes a new input block
- `BEGINCONTEXT` - denotes the block of context (metadata key/value pairs) to associate with the current input block
- `ENDCONTEXT` - denotes the end of the metadata block for the current input
- [text] - Insert whatever text you want for the input block, as many paragraphs as can fit in the context.
- `ENDINPUT` - denotes the end of the current input block
- [repeat as many input blocks in this format as you want]
- `BEGININSTRUCTION` - denotes the start of the list (or one) instruction(s) to respond to for all of the input blocks above.
- [instruction(s)]
- `ENDINSTRUCTION` - denotes the end of instruction set
It sometimes works without `ENDINSTRUCTION`, but by explicitly including that in the prompt, the model better understands that all of the instructions in the block should be responded to.
Here's a trivial, but important example to prove the point:
```
BEGININPUT
BEGINCONTEXT
date: 2021-01-01
url: https://web.site/123
ENDCONTEXT
In a shocking turn of events, blueberries are now green, but will be sticking with the same name.
ENDINPUT
BEGININSTRUCTION
What color are bluberries? Source?
ENDINSTRUCTION
```
And the response:
```
Blueberries are now green.
Source:
date: 2021-01-01
url: https://web.site/123
```
#### Summarization
500 samples have been included from [this dataset](https://huggingface.co/datasets/mattpscott/airoboros-summarization), using the same format as contextual question answering, for example:
```
BEGININPUT
{text to summarize}
ENDINPUT
BEGININSTRUCTION
Summarize the input in around 130 words.
ENDINSTRUCTION
```
#### Getting longer responses
You can use a few techniques to get longer responses.
Detailed prompts, with explicit instruction for word count:
```
Please compose a narrative set in the heart of an ancient library, steeped in the scent of old parchment and ink. The protagonist should be a young scholar who is dedicated to studying the art of storytelling and its evolution throughout history. In her pursuit of knowledge, she stumbles upon a forgotten tome that seems to possess an unusual aura. This book has the ability to bring stories to life, literally manifesting characters and scenarios from within its pages into reality.
The main character must navigate through various epochs of storytelling - from oral traditions of tribal societies, through medieval minstrels' tales, to modern-day digital narratives - as they come alive around her. Each era presents its unique challenges and lessons about the power and impact of stories on human civilization.
One such character could be a sentient quill pen, who was once used by renowned authors of yesteryears and now holds their wisdom and experiences. It becomes her mentor, guiding her through this journey with witty remarks and insightful commentary.
Ensure that your tale encapsulates the thrill of adventure, the beauty of learning, and the profound connection between humans and their stories. All characters involved should be non-human entities. Feel free to explore creative liberties but maintain the mentioned elements.
Your response should be approximately 2300 words.
```
Or, a simpler example:
```
Please create a long, detailed story about a dragon in an old growth forest who, for some reason, begins speaking the words of the source code of linux.
```
#### Coding
You can ask for fairly complex coding instructions with multiple criteria, e.g.:
```
Create a python application with the following requirements:
- Asyncio FastAPI webserver
- ping endpoint that returns the current date in JSON format
- file upload endpoint, which calculates the file's sha256 checksum, and checks postgres to deduplicate
```
Or inline criteria:
```
Write a multi-threaded TCP server in C that accepts a "GET [key]" input and "SET [key] [value]" input, and uses a binary tree to get and store the input values.
```
You can also optionally add a single space and "PLAINFORMAT" at the end of your prompt to avoid backticks, explanations, etc. and just print the code, e.g.:
```
Write a websocket application in node.js. PLAINFORMAT
```
#### Agent/function calling
The dataset includes many examples of function/args generation based on input criteria. This is somewhat similar to the OpenAI function calling, but the output is either JSON or YAML.
Example prompt:
```
As an AI assistant, please select the most suitable function and parameters from the list of available functions below, based on the user's input. Provide your response in JSON format.
Input: I want to know how many times 'Python' is mentioned in my text file.
Available functions:
file_analytics:
description: This tool performs various operations on a text file.
params:
action: The operation we want to perform on the data, such as "count_occurrences", "find_line", etc.
filters:
keyword: The word or phrase we want to search for.
```
Response:
```json
{
"function": "file_analytics",
"params": {
"action": "count_occurrences",
"filters": {
"keyword": "Python"
}
}
}
```
#### Chain-of-thought
You can ask for several possible responses to a given problem, with a ranking and final answer selection.
Example prompt:
```
A group of people decide to play a round-robin tournament where every player plays every other player exactly once. If a total of 45 games were played, how many players participated in the tournament? Offer several potential answers, rank them according to mathematical logic, and pick the most feasible one.
```
Example response:
```
Solution 1:
In a round-robin tournament, each player plays every other player exactly once. This means that the total number of games played is equal to the combination of all players taken two at a time (since a game involves two players).
The formula for combinations is nC2 = n(n-1)/2, where n is the total number of players. We know that nC2 equals 45 (the total number of games), so we can set up the equation as follows:
n(n-1)/2 = 45
Solving this equation gives us n=10.
Final answer: There were 10 players in the tournament.
Solution 2:
Another way to approach this problem is by using the concept of triangular numbers. Triangular numbers are a sequence of numbers where each number can be represented as a triangle with dots. The nth triangular number is given by the sum of the first n natural numbers.
If we consider each game as a dot and each player as a side of the triangle, then the total number of games (45) would correspond to the 9th triangular number because 1+2+3+4+5+6+7+8+9=45. However, since each side of the triangle represents a player, and there's one more player than sides in our model (because the last player has no one left to play against), we need to add one more to get the total number of players.
Final answer: There were 10 players in the tournament.
Solution 3:
We could also use trial and error to solve this problem. Starting from a small number of players, we calculate how many games would be played in a round-robin tournament until we reach 45 games. For example, with 2 players, only 1 game is played; with 3 players, 3 games are played; with 4 players, 6 games are played, and so on. Continuing this process, we find that with 10 players, 45 games are played.
Final answer: There were 10 players in the tournament.
Ranking of solutions from best to worst:
1. Solution 1: This solution uses direct mathematical reasoning based on the properties of a round-robin tournament and solves an equation to find the answer.
2. Solution 2: This solution uses the concept of triangular numbers which requires additional steps and knowledge beyond the immediate problem context, but still arrives at the correct answer.
3. Solution 3: This solution relies on trial and error, which is less efficient and reliable than the other methods, but it eventually gets to the right answer.
Best and final answer: There were 10 players in the tournament.
```
#### reWOO style execution planning
The model now supports execution planning for complex instructions that would require making use of several tools. The output is just the plan, you must implement a mechanism to parse the output and actually call the functions!
Example prompt:
```
Please construct a systematic plan to generate an optimal response to the user instruction, utilizing a set of provided tools. Each plan will correspond to an evidence value, which will be the output of one of the available functions given an input string
that could be the user's question, one or more prior evidence values, or a combination of both.
Here are the tools available to be called:
DuckDuckGo[input]: Tool that enables the user to search for information using the DuckDuckGo search engine. This tool is helpful in locating a suitable list of sites that may contain the answer to the user's query. It does not directly answer the question but finds a list of sites that might have the answer.
TextScraper[input]: Load one or more websites from the input string containing newline delimited links, where input is one or more links, and produces plain text output containing the content of the links.
HyperlinkExtractor[input]: Extract links from plain text and produces a plain text, newline delimited response of links.
KnowledgeModel[input]: Question answering language model, particularly useful in answering questions based on an input passage of text. The input must be a text question that references an :evidence[n]: variable, e.g. What color is the cat, given :evidence1:?
The output should be in format:
Plan: [first action to take based on input question]
:evidence0: = [function to call with input parameter]
Plan: [next action to take, based on result of :evidence0:]
:evidence1: = [next function to call and input parameter, which may include reference to previous evidence, e.g. "Given context :evidence0"]
...
Answer: [:evidence[n]: containing the final answer.]
Question: Who won the Nobel Prize in Literature in 2020 and what is their most famous work?
```
Response:
```
Plan: Begin by conducting a web search to find out who won the Nobel Prize in Literature in 2020.
:evidence0: = DuckDuckGo[Nobel Prize in Literature 2020 winner]
Plan: Utilize the KnowledgeModel to interpret the search results and find the name of the laureate.
:evidence1: = KnowledgeModel[Who won the Nobel Prize in Literature in 2020, given :evidence0:?]
Plan: Conduct another web search to find the most famous work of the identified laureate.
:evidence2: = DuckDuckGo[Most famous work of :evidence1:]
Plan: Extract the relevant links from the DuckDuckGo search results for a more focused search.
:evidence3: = HyperlinkExtractor[:evidence2:]
Plan: Use the TextScraper tool to extract information from the relevant links.
:evidence4: = TextScraper[:evidence3:]
Plan: Finally, utilize the KnowledgeModel to identify and summarize the most famous work of the laureate from the extracted information.
:evidence5: = KnowledgeModel[What is the most famous work of :evidence1:, given :evidence4:?]
Answer: :evidence5:
```
For this to be useful, you'd have to parse the output plan text, and implement/call each of the functions. This is just pseudo-code, completely untested off the top of my head, and obviously would requiring full implementation + hardening:
```python
import re
import requests
def inject_context(input_text, **context):
for ref in set(re.findall(r"(:evidence[0-9]+:)", input_text, re.I)):
input_text = input_text.replace(ref, context.get(ref, ""))
return input_text
def duckduckgo(input_text, **context):
search_string = inject_context(input_text, **context)
... search via duck duck go using search_string
... return text content
def link_extractor(input_text, **context):
input_text = inject_context(input_text, **context)
return "\n".join(list(set(re.findall(r"(https?://[^\s]+?\.?)", input_text, re.I))))
def scrape(input_text, **context):
input_text = inject_context(input_text, **context)
text = []
for link in input_text.splitlines():
text.append(requests.get(link).text)
return "\n".join(text)
def infer(input_text, **context)
prompt = inject_context(input_text, **context)
... call model with prompt, return output
def parse_plan(plan):
method_map = {
"DuckDuckGo": duckduckgo,
"HyperlinkExtractor": link_extractor,
"KnowledgeModel": infer,
"TextScraper": scrape,
}
context = {}
for line in plan.strip().splitlines():
if line.startswith("Plan:"):
print(line)
continue
parts = re.match("^(:evidence[0-9]+:)\s*=\s*([^\[]+])(\[.*\])\s$", line, re.I)
if not parts:
if line.startswith("Answer: "):
return context.get(line.split(" ")[-1].strip(), "Answer couldn't be generated...")
raise RuntimeError("bad format: " + line)
context[parts.group(1)] = method_map[parts.group(2)](parts.group(3), **context)
```
### Contribute
If you're interested in new functionality, particularly a new "instructor" type to generate a specific type of training data,
take a look at the dataset generation tool repo: https://github.com/jondurbin/airoboros and either make a PR or open an issue with details.
To help me with the OpenAI/compute costs:
- https://bmc.link/jondurbin
- ETH 0xce914eAFC2fe52FdceE59565Dd92c06f776fcb11
- BTC bc1qdwuth4vlg8x37ggntlxu5cjfwgmdy5zaa7pswf
### Licence and usage restrictions
The airoboros 2.2 models are built on top of llama-2/codellama.
The llama-2 base model has a custom Meta license:
- See the [meta-license/LICENSE.txt](meta-license/LICENSE.txt) file attached for the original license provided by Meta.
- See also [meta-license/USE_POLICY.md](meta-license/USE_POLICY.md) and [meta-license/Responsible-Use-Guide.pdf](meta-license/Responsible-Use-Guide.pdf), also provided by Meta.
The fine-tuning data was mostly generated by OpenAI API calls to gpt-4, via [airoboros](https://github.com/jondurbin/airoboros)
The ToS for OpenAI API usage has a clause preventing the output from being used to train a model that __competes__ with OpenAI
- what does *compete* actually mean here?
- these small open source models will not produce output anywhere near the quality of gpt-4, or even gpt-3.5, so I can't imagine this could credibly be considered competing in the first place
- if someone else uses the dataset to do the same, they wouldn't necessarily be violating the ToS because they didn't call the API, so I don't know how that works
- the training data used in essentially all large language models includes a significant amount of copyrighted or otherwise non-permissive licensing in the first place
- other work using the self-instruct method, e.g. the original here: https://github.com/yizhongw/self-instruct released the data and model as apache-2
I am purposingly leaving this license ambiguous (other than the fact you must comply with the Meta original license for llama-2) because I am not a lawyer and refuse to attempt to interpret all of the terms accordingly.
Your best bet is probably to avoid using this commercially due to the OpenAI API usage.
Either way, by using this model, you agree to completely indemnify me.
|
TamerAbdelaziz/distilbert-base-uncased-finetuned-IMDB_BERT_11
|
TamerAbdelaziz
| 2023-09-22T18:45:47Z | 61 | 0 |
transformers
|
[
"transformers",
"tf",
"tensorboard",
"distilbert",
"text-classification",
"generated_from_keras_callback",
"base_model:distilbert/distilbert-base-uncased",
"base_model:finetune:distilbert/distilbert-base-uncased",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2023-09-22T17:59:17Z |
---
license: apache-2.0
base_model: distilbert-base-uncased
tags:
- generated_from_keras_callback
model-index:
- name: TamerAbdelaziz/distilbert-base-uncased-finetuned-IMDB_BERT_11
results: []
---
<!-- This model card has been generated automatically according to the information Keras had access to. You should
probably proofread and complete it, then remove this comment. -->
# TamerAbdelaziz/distilbert-base-uncased-finetuned-IMDB_BERT_11
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset.
It achieves the following results on the evaluation set:
- Train Loss: 0.0094
- Validation Loss: 0.3097
- Train Accuracy: 0.9364
- Epoch: 9
## 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:
- optimizer: {'name': 'Adam', 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 6250, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}
- training_precision: float32
### Training results
| Train Loss | Validation Loss | Train Accuracy | Epoch |
|:----------:|:---------------:|:--------------:|:-----:|
| 0.2466 | 0.1804 | 0.9314 | 0 |
| 0.1417 | 0.1824 | 0.9324 | 1 |
| 0.0892 | 0.2208 | 0.9268 | 2 |
| 0.0532 | 0.2212 | 0.9348 | 3 |
| 0.0328 | 0.2518 | 0.936 | 4 |
| 0.0218 | 0.2750 | 0.9358 | 5 |
| 0.0185 | 0.2856 | 0.9338 | 6 |
| 0.0147 | 0.3055 | 0.935 | 7 |
| 0.0113 | 0.3060 | 0.9352 | 8 |
| 0.0094 | 0.3097 | 0.9364 | 9 |
### Framework versions
- Transformers 4.33.2
- TensorFlow 2.8.1
- Datasets 2.14.5
- Tokenizers 0.13.3
|
Thireus/WizardLM-70B-V1.0-HF-5.0bpw-h8-exl2
|
Thireus
| 2023-09-22T18:33:24Z | 5 | 0 |
transformers
|
[
"transformers",
"llama",
"text-generation",
"license:llama2",
"autotrain_compatible",
"region:us"
] |
text-generation
| 2023-09-19T08:09:31Z |
---
inference: false
license: llama2
model_creator: WizardLM
model_link: https://huggingface.co/WizardLM/WizardLM-70B-V1.0
model_name: WizardLM 70B V1.0
model_type: llama
quantized_by: Thireus
---
# WizardLM 70B V1.0 – EXL2
- Model creator: [WizardLM](https://huggingface.co/WizardLM)
- FP32 Original model used for quantization: [WizardLM 70B V1.0](https://huggingface.co/WizardLM/WizardLM-70B-V1.0) – float32
- FP16 Model used for quantization: [WizardLM 70B V1.0-HF](https://huggingface.co/simsim314/WizardLM-70B-V1.0-HF) – float16 of [WizardLM 70B V1.0](https://huggingface.co/WizardLM/WizardLM-70B-V1.0)
- BF16 Model used for quantization: [WizardLM 70B V1.0-BF16](https://huggingface.co/Thireus/WizardLM-70B-V1.0-BF16) – bfloat16 of [WizardLM 70B V1.0](https://huggingface.co/WizardLM/WizardLM-70B-V1.0)
## Models available:
| Link | BITS (-b) | HEAD BITS (-hb) | MEASU-REMENT LENGTH (-ml) | LENGTH (-l) | CAL DATASET (-c) | Size | V. | Max Context Length | Base Model | Layers | VRAM Min | VRAM Max | PPL** | Comments                                                                                                                         |
| ------ | --------- | --------------- | ------------------------ | ----------- | ---------------- | ---- | ------- | ------------------ | ---- | ---- |------------------ | ------------------ | ------------------ | ---------------------------------------------------------------------------------- |
| [here](https://huggingface.co/Thireus/WizardLM-70B-V1.0-FP32-4.0bpw-h6-exl2/) | 4.0 | 6 | 2048 | 2048 | [0000.parquet](https://huggingface.co/datasets/wikitext/tree/refs%2Fconvert%2Fparquet/wikitext-2-raw-v1/train)* | 33GB | [0.0.2](https://github.com/turboderp/exllamav2/tree/c0dd3412d59c0bc776264512bf76264e954c221d) | 4096 | [FP32](https://huggingface.co/WizardLM/WizardLM-70B-V1.0) | 80 | 39GB | 44GB | 4.15234375 | Good results | | [here](https://huggingface.co/Thireus/WizardLM-70B-V1.0-HF-4.0bpw-h6-exl2/) | 4.0 | 6 | 2048 | 2048 | [0000.parquet](https://huggingface.co/datasets/wikitext/tree/refs%2Fconvert%2Fparquet/wikitext-2-raw-v1/train)* | 35GB | [0.0.1](https://github.com/turboderp/exllamav2/tree/aee7a281708d5faff2ad0ea4b3a3a4b754f458f3) | 4096 | [FP16](https://huggingface.co/simsim314/WizardLM-70B-V1.0-HF) | 80 | 40GB | 44GB | 4.1640625 | Model suffers from poor prompt understanding and logic is affected |
| [here](https://huggingface.co/Thireus/WizardLM-70B-V1.0-BF16-4.0bpw-h6-exl2/) | 4.0 | 6 | 2048 | 2048 | [0000.parquet](https://huggingface.co/datasets/wikitext/tree/refs%2Fconvert%2Fparquet/wikitext-2-raw-v1/train)* | 33GB | [0.0.2](https://github.com/turboderp/exllamav2/tree/ec5164b8a8e282b91aedb2af94dfeb89887656b7) | 4096 | [BF16](https://huggingface.co/Thireus/WizardLM-70B-V1.0-BF16) | 80 | 39GB | 44GB | 4.2421875 | Model suffers from poor prompt understanding and logic is affected |
| [here](https://huggingface.co/Thireus/WizardLM-70B-V1.0-HF-4.0bpw-h8-exl2/) | 4.0 | 8 | 2048 | 2048 | [0000.parquet](https://huggingface.co/datasets/wikitext/tree/refs%2Fconvert%2Fparquet/wikitext-2-raw-v1/train)* | 35GB | [0.0.2](https://github.com/turboderp/exllamav2/tree/a4f2663e310919f007c593030d56ca110f99c261) | 4096 | [FP16](https://huggingface.co/simsim314/WizardLM-70B-V1.0-HF) | 80 | 39GB | 44GB | 4.24609375 | Model suffers from poor prompt understanding and logic is affected |
| [here](https://huggingface.co/Thireus/WizardLM-70B-V1.0-FP32-5.0bpw-h6-exl2/) | 5.0 | 6 | 2048 | 2048 | [0000.parquet](https://huggingface.co/datasets/wikitext/tree/refs%2Fconvert%2Fparquet/wikitext-2-raw-v1/train)* | 41GB | [0.0.2](https://github.com/turboderp/exllamav2/tree/c0dd3412d59c0bc776264512bf76264e954c221d) | 4096 | [FP32](https://huggingface.co/WizardLM/WizardLM-70B-V1.0) | 80 | 47GB | 52GB | 4.06640625 | Best so far. Good results |
| [here](https://huggingface.co/Thireus/WizardLM-70B-V1.0-HF-5.0bpw-h8-exl2/) | 5.0 | 8 | 2048 | 2048 | [0000.parquet](https://huggingface.co/datasets/wikitext/tree/refs%2Fconvert%2Fparquet/wikitext-2-raw-v1/train)* | 44GB | [0.0.2](https://github.com/turboderp/exllamav2/tree/a4f2663e310919f007c593030d56ca110f99c261) | 4096 | [FP16](https://huggingface.co/simsim314/WizardLM-70B-V1.0-HF) | 80 | 48GB | 52GB | 4.09765625 | Model suffers from poor prompt understanding and logic is affected |
| [here](https://huggingface.co/Thireus/WizardLM-70B-V1.0-HF-5.0bpw-h6-exl2/) | 5.0 | 6 | 2048 | 2048 | [0000.parquet](https://huggingface.co/datasets/wikitext/tree/refs%2Fconvert%2Fparquet/wikitext-2-raw-v1/train)* | 44GB | [0.0.1](https://github.com/turboderp/exllamav2/tree/aee7a281708d5faff2ad0ea4b3a3a4b754f458f3) | 4096 | [FP16](https://huggingface.co/simsim314/WizardLM-70B-V1.0-HF) | 80 | 48GB | 52GB | 4.0625 | Model suffers from poor prompt understanding and logic is affected |
| [here](https://huggingface.co/Thireus/WizardLM-70B-V1.0-BF16-5.0bpw-h6-exl2/) | 5.0 | 6 | 2048 | 2048 | [0000.parquet](https://huggingface.co/datasets/wikitext/tree/refs%2Fconvert%2Fparquet/wikitext-2-raw-v1/train)* | 41GB | [0.0.2](https://github.com/turboderp/exllamav2/tree/ec5164b8a8e282b91aedb2af94dfeb89887656b7) | 4096 | [BF16](https://huggingface.co/Thireus/WizardLM-70B-V1.0-BF16) | 80 | 47GB | 52GB | 4.09765625 | Model suffers from poor prompt understanding and logic is affected |
| [here](https://huggingface.co/Thireus/WizardLM-70B-V1.0-HF-6.0bpw-h6-exl2/) | 6.0 | 6 | 2048 | 2048 | [0000.parquet](https://huggingface.co/datasets/wikitext/tree/refs%2Fconvert%2Fparquet/wikitext-2-raw-v1/train)* | 49GB | [0.0.2](https://github.com/turboderp/exllamav2/tree/fae6fb296c6db4e3b1314c49c030541bed98acb9) | 4096 | [FP16](https://huggingface.co/simsim314/WizardLM-70B-V1.0-HF) | 80 | 56GB | 60GB | 4.0703125 | Model suffers from poor prompt understanding and logic is affected |
\* wikitext-2-raw-v1
\*\* Evaluated with text-generation-webui ExLlama v0.0.2 on wikitext-2-raw-v1 (stride 512 and max_length 0). For reference, [TheBloke_WizardLM-70B-V1.0-GPTQ_gptq-4bit-32g-actorder_True](https://huggingface.co/TheBloke/WizardLM-70B-V1.0-GPTQ/tree/gptq-4bit-32g-actorder_True) has a score of 4.1015625 in perplexity.
## Description:
_This repository contains EXL2 model files for [WizardLM's WizardLM 70B V1.0](https://huggingface.co/WizardLM/WizardLM-70B-V1.0)._
EXL2 is a new format used by ExLlamaV2 – https://github.com/turboderp/exllamav2. EXL2 is based on the same optimization method as GPTQ. The format allows for mixing quantization
levels within a model to achieve any average bitrate between 2 and 8 bits per weight.
## Prompt template (official):
```
A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions. USER: {prompt} ASSISTANT:
```
## Prompt template (suggested):
```
A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions.
USER:
{prompt}
ASSISTANT:
```
## Quantization process:
| Original Model | → | (optional) float16 or bfloat16 Model* | → | Safetensors Model** | → | EXL2 Model |
| -------------- | --- | ------------- | --- | ---------------- | --- | ---------- |
| [WizardLM 70B V1.0](https://huggingface.co/WizardLM/WizardLM-70B-V1.0) | → | [WizardLM 70B V1.0-HF](https://huggingface.co/simsim314/WizardLM-70B-V1.0-HF)* | → | Safetensors** | → | EXL2 |
Example to convert WizardLM-70B-V1.0-HF to EXL2 4.0 bpw with 6-bit head:
```
mkdir -p ~/EXL2/WizardLM-70B-V1.0-HF_4bit # Create the output directory
python convert.py -i ~/float16_safetensored/WizardLM-70B-V1.0-HF -o ~/EXL2/WizardLM-70B-V1.0-HF_4bit -c ~/EXL2/0000.parquet -b 4.0 -hb 6
```
\* Use the following script to convert your local pytorch_model bin files to float16 (you can also choose bfloat16) + safetensors all in one go:
- https://github.com/oobabooga/text-generation-webui/blob/main/convert-to-safetensors.py
(best for sharding and float16/FP16 or bfloat16/BF16 conversion)
Example to convert [WizardLM 70B V1.0](https://huggingface.co/WizardLM/WizardLM-70B-V1.0) directly to float16 safetensors in 10GB shards:
```
python convert-to-safetensors.py ~/original/WizardLM-70B-V1.0 --output ~/float16_safetensored/WizardLM-70B-V1.0 --max-shard-size 10GB
```
Use `--bf16` if you'd like to try bfloat16 instead, but note that there are concerns about quantization quality – https://github.com/turboderp/exllamav2/issues/30#issuecomment-1719009289
\*\* Use any one of the following scripts to convert your local pytorch_model bin files to safetensors:
- https://github.com/turboderp/exllamav2/blob/master/util/convert_safetensors.py (official ExLlamaV2)
- https://huggingface.co/Panchovix/airoboros-l2-70b-gpt4-1.4.1-safetensors/blob/main/bin2safetensors/convert.py (recommended)
- https://gist.github.com/epicfilemcnulty/1f55fd96b08f8d4d6693293e37b4c55e#file-2safetensors-py
## Further reading:
- https://mlabonne.github.io/blog/posts/Introduction_to_Weight_Quantization.html
|
alpindale/Llama-2-13b-ONNX
|
alpindale
| 2023-09-22T18:33:20Z | 0 | 5 | null |
[
"onnx",
"text generation",
"text-generation",
"en",
"license:llama2",
"region:us"
] |
text-generation
| 2023-09-21T20:28:10Z |
---
language:
- en
thumbnail: null
tags:
- text generation
pipeline_tag: text-generation
inference: false
license: llama2
---
# Llama-2 ONNX
This repository contains optimized version of Llama-2 13B.
## Downloading the model
You can use `huggingface_hub` to download this repository. This can be done through both python scripting and the commandline. Refer to the [HuggingFace Hub Documentation](https://huggingface.co/docs/huggingface_hub/guides/download) for the Python examples.
With CLI:
1. Make sure you have an updated `huggingface_hub` installed.
```sh
pip install -U huggingface_hub
```
2. Download the repository.
```sh
huggingface-cli download alpindale/Llama-2-13b-ONNX --repo-type model --cache-dir /path/to/custom/cache/directory --local-dir /path/to/download/dir --local-dir-use-symlinks False
```
The `--cache-dir` kwarg is only necessary if your default cache directory (`~/.cache`) does not have enough disk space to accomodate the entire repository.
## Using the model
The repository provides example code for running the models.
```sh
python llama2_onnx_inference.py --onnx_file FP16/LlamaV2_13B_float16.onnx --embedding_file embeddings.pth --tokenizer_path tokenizer.model --prompt "What is the lightest element?"
```
Output:
```
The lightest element is hydrogen. Hydrogen is the lightest element on the periodic table, with an atomic mass of 1.00794 u (unified atomic mass units).
```
### Chat Interface
Alternatively, you can use the Gradio chat interface to run the models.
First, install the required packages:
```sh
pip install -r requirements.txt
```
Set the Python path to the root directory of the repository (necessary for importing the required modules):
```sh
export PYTHONPATH=$PYTHONPATH:$(pwd)
```
Then you can simply run:
```sh
python ChatApp/app.py
```
You can then navigate to [http://localhost:7860](https://127.0.0.1:7860) on your browser to access the interface.
## FAQ
### Why is the first inference session slow?
ONNX runtime execution provider might need to generate JIT binaries for the underlying hardware, typically the binary is cache and will be loaded directly in the subsequent runs to reduce the overhead.
### Why is FP16 slower than FP32 on my device?
Your device may not support native FP16 math, therefore weights will be cast to FP32 at runtime. Using the FP32 version of the model will avoid the cast overhead.
### How do I optimize inference?
It's recommended that inputs/outputs are put on target device to avoid expensive data copies, please refer to the following documentations for details:
[I/O Binding | onnxruntime](https://onnxruntime.ai/docs/performance/tune-performance/iobinding.html)
### What generation parameters should I use the model with?
You can perform temperature and top-p sampling with the provided example code. Please refer to Meta's example [here](https://github.com/facebookresearch/llama/).
|
Thireus/WizardLM-70B-V1.0-FP32-5.0bpw-h6-exl2
|
Thireus
| 2023-09-22T18:33:19Z | 9 | 0 |
transformers
|
[
"transformers",
"safetensors",
"llama",
"text-generation",
"license:llama2",
"autotrain_compatible",
"text-generation-inference",
"region:us"
] |
text-generation
| 2023-09-22T12:08:20Z |
---
inference: false
license: llama2
model_creator: WizardLM
model_link: https://huggingface.co/WizardLM/WizardLM-70B-V1.0
model_name: WizardLM 70B V1.0
model_type: llama
quantized_by: Thireus
---
# WizardLM 70B V1.0 – EXL2
- Model creator: [WizardLM](https://huggingface.co/WizardLM)
- FP32 Original model used for quantization: [WizardLM 70B V1.0](https://huggingface.co/WizardLM/WizardLM-70B-V1.0) – float32
- FP16 Model used for quantization: [WizardLM 70B V1.0-HF](https://huggingface.co/simsim314/WizardLM-70B-V1.0-HF) – float16 of [WizardLM 70B V1.0](https://huggingface.co/WizardLM/WizardLM-70B-V1.0)
- BF16 Model used for quantization: [WizardLM 70B V1.0-BF16](https://huggingface.co/Thireus/WizardLM-70B-V1.0-BF16) – bfloat16 of [WizardLM 70B V1.0](https://huggingface.co/WizardLM/WizardLM-70B-V1.0)
## Models available:
| Link | BITS (-b) | HEAD BITS (-hb) | MEASU-REMENT LENGTH (-ml) | LENGTH (-l) | CAL DATASET (-c) | Size | V. | Max Context Length | Base Model | Layers | VRAM Min | VRAM Max | PPL** | Comments                                                                                                                         |
| ------ | --------- | --------------- | ------------------------ | ----------- | ---------------- | ---- | ------- | ------------------ | ---- | ---- |------------------ | ------------------ | ------------------ | ---------------------------------------------------------------------------------- |
| [here](https://huggingface.co/Thireus/WizardLM-70B-V1.0-FP32-4.0bpw-h6-exl2/) | 4.0 | 6 | 2048 | 2048 | [0000.parquet](https://huggingface.co/datasets/wikitext/tree/refs%2Fconvert%2Fparquet/wikitext-2-raw-v1/train)* | 33GB | [0.0.2](https://github.com/turboderp/exllamav2/tree/c0dd3412d59c0bc776264512bf76264e954c221d) | 4096 | [FP32](https://huggingface.co/WizardLM/WizardLM-70B-V1.0) | 80 | 39GB | 44GB | 4.15234375 | Good results | | [here](https://huggingface.co/Thireus/WizardLM-70B-V1.0-HF-4.0bpw-h6-exl2/) | 4.0 | 6 | 2048 | 2048 | [0000.parquet](https://huggingface.co/datasets/wikitext/tree/refs%2Fconvert%2Fparquet/wikitext-2-raw-v1/train)* | 35GB | [0.0.1](https://github.com/turboderp/exllamav2/tree/aee7a281708d5faff2ad0ea4b3a3a4b754f458f3) | 4096 | [FP16](https://huggingface.co/simsim314/WizardLM-70B-V1.0-HF) | 80 | 40GB | 44GB | 4.1640625 | Model suffers from poor prompt understanding and logic is affected |
| [here](https://huggingface.co/Thireus/WizardLM-70B-V1.0-BF16-4.0bpw-h6-exl2/) | 4.0 | 6 | 2048 | 2048 | [0000.parquet](https://huggingface.co/datasets/wikitext/tree/refs%2Fconvert%2Fparquet/wikitext-2-raw-v1/train)* | 33GB | [0.0.2](https://github.com/turboderp/exllamav2/tree/ec5164b8a8e282b91aedb2af94dfeb89887656b7) | 4096 | [BF16](https://huggingface.co/Thireus/WizardLM-70B-V1.0-BF16) | 80 | 39GB | 44GB | 4.2421875 | Model suffers from poor prompt understanding and logic is affected |
| [here](https://huggingface.co/Thireus/WizardLM-70B-V1.0-HF-4.0bpw-h8-exl2/) | 4.0 | 8 | 2048 | 2048 | [0000.parquet](https://huggingface.co/datasets/wikitext/tree/refs%2Fconvert%2Fparquet/wikitext-2-raw-v1/train)* | 35GB | [0.0.2](https://github.com/turboderp/exllamav2/tree/a4f2663e310919f007c593030d56ca110f99c261) | 4096 | [FP16](https://huggingface.co/simsim314/WizardLM-70B-V1.0-HF) | 80 | 39GB | 44GB | 4.24609375 | Model suffers from poor prompt understanding and logic is affected |
| [here](https://huggingface.co/Thireus/WizardLM-70B-V1.0-FP32-5.0bpw-h6-exl2/) | 5.0 | 6 | 2048 | 2048 | [0000.parquet](https://huggingface.co/datasets/wikitext/tree/refs%2Fconvert%2Fparquet/wikitext-2-raw-v1/train)* | 41GB | [0.0.2](https://github.com/turboderp/exllamav2/tree/c0dd3412d59c0bc776264512bf76264e954c221d) | 4096 | [FP32](https://huggingface.co/WizardLM/WizardLM-70B-V1.0) | 80 | 47GB | 52GB | 4.06640625 | Best so far. Good results |
| [here](https://huggingface.co/Thireus/WizardLM-70B-V1.0-HF-5.0bpw-h8-exl2/) | 5.0 | 8 | 2048 | 2048 | [0000.parquet](https://huggingface.co/datasets/wikitext/tree/refs%2Fconvert%2Fparquet/wikitext-2-raw-v1/train)* | 44GB | [0.0.2](https://github.com/turboderp/exllamav2/tree/a4f2663e310919f007c593030d56ca110f99c261) | 4096 | [FP16](https://huggingface.co/simsim314/WizardLM-70B-V1.0-HF) | 80 | 48GB | 52GB | 4.09765625 | Model suffers from poor prompt understanding and logic is affected |
| [here](https://huggingface.co/Thireus/WizardLM-70B-V1.0-HF-5.0bpw-h6-exl2/) | 5.0 | 6 | 2048 | 2048 | [0000.parquet](https://huggingface.co/datasets/wikitext/tree/refs%2Fconvert%2Fparquet/wikitext-2-raw-v1/train)* | 44GB | [0.0.1](https://github.com/turboderp/exllamav2/tree/aee7a281708d5faff2ad0ea4b3a3a4b754f458f3) | 4096 | [FP16](https://huggingface.co/simsim314/WizardLM-70B-V1.0-HF) | 80 | 48GB | 52GB | 4.0625 | Model suffers from poor prompt understanding and logic is affected |
| [here](https://huggingface.co/Thireus/WizardLM-70B-V1.0-BF16-5.0bpw-h6-exl2/) | 5.0 | 6 | 2048 | 2048 | [0000.parquet](https://huggingface.co/datasets/wikitext/tree/refs%2Fconvert%2Fparquet/wikitext-2-raw-v1/train)* | 41GB | [0.0.2](https://github.com/turboderp/exllamav2/tree/ec5164b8a8e282b91aedb2af94dfeb89887656b7) | 4096 | [BF16](https://huggingface.co/Thireus/WizardLM-70B-V1.0-BF16) | 80 | 47GB | 52GB | 4.09765625 | Model suffers from poor prompt understanding and logic is affected |
| [here](https://huggingface.co/Thireus/WizardLM-70B-V1.0-HF-6.0bpw-h6-exl2/) | 6.0 | 6 | 2048 | 2048 | [0000.parquet](https://huggingface.co/datasets/wikitext/tree/refs%2Fconvert%2Fparquet/wikitext-2-raw-v1/train)* | 49GB | [0.0.2](https://github.com/turboderp/exllamav2/tree/fae6fb296c6db4e3b1314c49c030541bed98acb9) | 4096 | [FP16](https://huggingface.co/simsim314/WizardLM-70B-V1.0-HF) | 80 | 56GB | 60GB | 4.0703125 | Model suffers from poor prompt understanding and logic is affected |
\* wikitext-2-raw-v1
\*\* Evaluated with text-generation-webui ExLlama v0.0.2 on wikitext-2-raw-v1 (stride 512 and max_length 0). For reference, [TheBloke_WizardLM-70B-V1.0-GPTQ_gptq-4bit-32g-actorder_True](https://huggingface.co/TheBloke/WizardLM-70B-V1.0-GPTQ/tree/gptq-4bit-32g-actorder_True) has a score of 4.1015625 in perplexity.
## Description:
_This repository contains EXL2 model files for [WizardLM's WizardLM 70B V1.0](https://huggingface.co/WizardLM/WizardLM-70B-V1.0)._
EXL2 is a new format used by ExLlamaV2 – https://github.com/turboderp/exllamav2. EXL2 is based on the same optimization method as GPTQ. The format allows for mixing quantization
levels within a model to achieve any average bitrate between 2 and 8 bits per weight.
## Prompt template (official):
```
A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions. USER: {prompt} ASSISTANT:
```
## Prompt template (suggested):
```
A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions.
USER:
{prompt}
ASSISTANT:
```
## Quantization process:
| Original Model | → | (optional) float16 or bfloat16 Model* | → | Safetensors Model** | → | EXL2 Model |
| -------------- | --- | ------------- | --- | ---------------- | --- | ---------- |
| [WizardLM 70B V1.0](https://huggingface.co/WizardLM/WizardLM-70B-V1.0) | → | [WizardLM 70B V1.0-HF](https://huggingface.co/simsim314/WizardLM-70B-V1.0-HF)* | → | Safetensors** | → | EXL2 |
Example to convert WizardLM-70B-V1.0-HF to EXL2 4.0 bpw with 6-bit head:
```
mkdir -p ~/EXL2/WizardLM-70B-V1.0-HF_4bit # Create the output directory
python convert.py -i ~/float16_safetensored/WizardLM-70B-V1.0-HF -o ~/EXL2/WizardLM-70B-V1.0-HF_4bit -c ~/EXL2/0000.parquet -b 4.0 -hb 6
```
\* Use the following script to convert your local pytorch_model bin files to float16 (you can also choose bfloat16) + safetensors all in one go:
- https://github.com/oobabooga/text-generation-webui/blob/main/convert-to-safetensors.py
(best for sharding and float16/FP16 or bfloat16/BF16 conversion)
Example to convert [WizardLM 70B V1.0](https://huggingface.co/WizardLM/WizardLM-70B-V1.0) directly to float16 safetensors in 10GB shards:
```
python convert-to-safetensors.py ~/original/WizardLM-70B-V1.0 --output ~/float16_safetensored/WizardLM-70B-V1.0 --max-shard-size 10GB
```
Use `--bf16` if you'd like to try bfloat16 instead, but note that there are concerns about quantization quality – https://github.com/turboderp/exllamav2/issues/30#issuecomment-1719009289
\*\* Use any one of the following scripts to convert your local pytorch_model bin files to safetensors:
- https://github.com/turboderp/exllamav2/blob/master/util/convert_safetensors.py (official ExLlamaV2)
- https://huggingface.co/Panchovix/airoboros-l2-70b-gpt4-1.4.1-safetensors/blob/main/bin2safetensors/convert.py (recommended)
- https://gist.github.com/epicfilemcnulty/1f55fd96b08f8d4d6693293e37b4c55e#file-2safetensors-py
## Further reading:
- https://mlabonne.github.io/blog/posts/Introduction_to_Weight_Quantization.html
|
Thireus/WizardLM-70B-V1.0-HF-4.0bpw-h8-exl2
|
Thireus
| 2023-09-22T18:33:13Z | 7 | 0 |
transformers
|
[
"transformers",
"llama",
"text-generation",
"license:llama2",
"autotrain_compatible",
"region:us"
] |
text-generation
| 2023-09-19T08:09:33Z |
---
inference: false
license: llama2
model_creator: WizardLM
model_link: https://huggingface.co/WizardLM/WizardLM-70B-V1.0
model_name: WizardLM 70B V1.0
model_type: llama
quantized_by: Thireus
---
# WizardLM 70B V1.0 – EXL2
- Model creator: [WizardLM](https://huggingface.co/WizardLM)
- FP32 Original model used for quantization: [WizardLM 70B V1.0](https://huggingface.co/WizardLM/WizardLM-70B-V1.0) – float32
- FP16 Model used for quantization: [WizardLM 70B V1.0-HF](https://huggingface.co/simsim314/WizardLM-70B-V1.0-HF) – float16 of [WizardLM 70B V1.0](https://huggingface.co/WizardLM/WizardLM-70B-V1.0)
- BF16 Model used for quantization: [WizardLM 70B V1.0-BF16](https://huggingface.co/Thireus/WizardLM-70B-V1.0-BF16) – bfloat16 of [WizardLM 70B V1.0](https://huggingface.co/WizardLM/WizardLM-70B-V1.0)
## Models available:
| Link | BITS (-b) | HEAD BITS (-hb) | MEASU-REMENT LENGTH (-ml) | LENGTH (-l) | CAL DATASET (-c) | Size | V. | Max Context Length | Base Model | Layers | VRAM Min | VRAM Max | PPL** | Comments                                                                                                                         |
| ------ | --------- | --------------- | ------------------------ | ----------- | ---------------- | ---- | ------- | ------------------ | ---- | ---- |------------------ | ------------------ | ------------------ | ---------------------------------------------------------------------------------- |
| [here](https://huggingface.co/Thireus/WizardLM-70B-V1.0-FP32-4.0bpw-h6-exl2/) | 4.0 | 6 | 2048 | 2048 | [0000.parquet](https://huggingface.co/datasets/wikitext/tree/refs%2Fconvert%2Fparquet/wikitext-2-raw-v1/train)* | 33GB | [0.0.2](https://github.com/turboderp/exllamav2/tree/c0dd3412d59c0bc776264512bf76264e954c221d) | 4096 | [FP32](https://huggingface.co/WizardLM/WizardLM-70B-V1.0) | 80 | 39GB | 44GB | 4.15234375 | Good results | | [here](https://huggingface.co/Thireus/WizardLM-70B-V1.0-HF-4.0bpw-h6-exl2/) | 4.0 | 6 | 2048 | 2048 | [0000.parquet](https://huggingface.co/datasets/wikitext/tree/refs%2Fconvert%2Fparquet/wikitext-2-raw-v1/train)* | 35GB | [0.0.1](https://github.com/turboderp/exllamav2/tree/aee7a281708d5faff2ad0ea4b3a3a4b754f458f3) | 4096 | [FP16](https://huggingface.co/simsim314/WizardLM-70B-V1.0-HF) | 80 | 40GB | 44GB | 4.1640625 | Model suffers from poor prompt understanding and logic is affected |
| [here](https://huggingface.co/Thireus/WizardLM-70B-V1.0-BF16-4.0bpw-h6-exl2/) | 4.0 | 6 | 2048 | 2048 | [0000.parquet](https://huggingface.co/datasets/wikitext/tree/refs%2Fconvert%2Fparquet/wikitext-2-raw-v1/train)* | 33GB | [0.0.2](https://github.com/turboderp/exllamav2/tree/ec5164b8a8e282b91aedb2af94dfeb89887656b7) | 4096 | [BF16](https://huggingface.co/Thireus/WizardLM-70B-V1.0-BF16) | 80 | 39GB | 44GB | 4.2421875 | Model suffers from poor prompt understanding and logic is affected |
| [here](https://huggingface.co/Thireus/WizardLM-70B-V1.0-HF-4.0bpw-h8-exl2/) | 4.0 | 8 | 2048 | 2048 | [0000.parquet](https://huggingface.co/datasets/wikitext/tree/refs%2Fconvert%2Fparquet/wikitext-2-raw-v1/train)* | 35GB | [0.0.2](https://github.com/turboderp/exllamav2/tree/a4f2663e310919f007c593030d56ca110f99c261) | 4096 | [FP16](https://huggingface.co/simsim314/WizardLM-70B-V1.0-HF) | 80 | 39GB | 44GB | 4.24609375 | Model suffers from poor prompt understanding and logic is affected |
| [here](https://huggingface.co/Thireus/WizardLM-70B-V1.0-FP32-5.0bpw-h6-exl2/) | 5.0 | 6 | 2048 | 2048 | [0000.parquet](https://huggingface.co/datasets/wikitext/tree/refs%2Fconvert%2Fparquet/wikitext-2-raw-v1/train)* | 41GB | [0.0.2](https://github.com/turboderp/exllamav2/tree/c0dd3412d59c0bc776264512bf76264e954c221d) | 4096 | [FP32](https://huggingface.co/WizardLM/WizardLM-70B-V1.0) | 80 | 47GB | 52GB | 4.06640625 | Best so far. Good results |
| [here](https://huggingface.co/Thireus/WizardLM-70B-V1.0-HF-5.0bpw-h8-exl2/) | 5.0 | 8 | 2048 | 2048 | [0000.parquet](https://huggingface.co/datasets/wikitext/tree/refs%2Fconvert%2Fparquet/wikitext-2-raw-v1/train)* | 44GB | [0.0.2](https://github.com/turboderp/exllamav2/tree/a4f2663e310919f007c593030d56ca110f99c261) | 4096 | [FP16](https://huggingface.co/simsim314/WizardLM-70B-V1.0-HF) | 80 | 48GB | 52GB | 4.09765625 | Model suffers from poor prompt understanding and logic is affected |
| [here](https://huggingface.co/Thireus/WizardLM-70B-V1.0-HF-5.0bpw-h6-exl2/) | 5.0 | 6 | 2048 | 2048 | [0000.parquet](https://huggingface.co/datasets/wikitext/tree/refs%2Fconvert%2Fparquet/wikitext-2-raw-v1/train)* | 44GB | [0.0.1](https://github.com/turboderp/exllamav2/tree/aee7a281708d5faff2ad0ea4b3a3a4b754f458f3) | 4096 | [FP16](https://huggingface.co/simsim314/WizardLM-70B-V1.0-HF) | 80 | 48GB | 52GB | 4.0625 | Model suffers from poor prompt understanding and logic is affected |
| [here](https://huggingface.co/Thireus/WizardLM-70B-V1.0-BF16-5.0bpw-h6-exl2/) | 5.0 | 6 | 2048 | 2048 | [0000.parquet](https://huggingface.co/datasets/wikitext/tree/refs%2Fconvert%2Fparquet/wikitext-2-raw-v1/train)* | 41GB | [0.0.2](https://github.com/turboderp/exllamav2/tree/ec5164b8a8e282b91aedb2af94dfeb89887656b7) | 4096 | [BF16](https://huggingface.co/Thireus/WizardLM-70B-V1.0-BF16) | 80 | 47GB | 52GB | 4.09765625 | Model suffers from poor prompt understanding and logic is affected |
| [here](https://huggingface.co/Thireus/WizardLM-70B-V1.0-HF-6.0bpw-h6-exl2/) | 6.0 | 6 | 2048 | 2048 | [0000.parquet](https://huggingface.co/datasets/wikitext/tree/refs%2Fconvert%2Fparquet/wikitext-2-raw-v1/train)* | 49GB | [0.0.2](https://github.com/turboderp/exllamav2/tree/fae6fb296c6db4e3b1314c49c030541bed98acb9) | 4096 | [FP16](https://huggingface.co/simsim314/WizardLM-70B-V1.0-HF) | 80 | 56GB | 60GB | 4.0703125 | Model suffers from poor prompt understanding and logic is affected |
\* wikitext-2-raw-v1
\*\* Evaluated with text-generation-webui ExLlama v0.0.2 on wikitext-2-raw-v1 (stride 512 and max_length 0). For reference, [TheBloke_WizardLM-70B-V1.0-GPTQ_gptq-4bit-32g-actorder_True](https://huggingface.co/TheBloke/WizardLM-70B-V1.0-GPTQ/tree/gptq-4bit-32g-actorder_True) has a score of 4.1015625 in perplexity.
## Description:
_This repository contains EXL2 model files for [WizardLM's WizardLM 70B V1.0](https://huggingface.co/WizardLM/WizardLM-70B-V1.0)._
EXL2 is a new format used by ExLlamaV2 – https://github.com/turboderp/exllamav2. EXL2 is based on the same optimization method as GPTQ. The format allows for mixing quantization
levels within a model to achieve any average bitrate between 2 and 8 bits per weight.
## Prompt template (official):
```
A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions. USER: {prompt} ASSISTANT:
```
## Prompt template (suggested):
```
A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions.
USER:
{prompt}
ASSISTANT:
```
## Quantization process:
| Original Model | → | (optional) float16 or bfloat16 Model* | → | Safetensors Model** | → | EXL2 Model |
| -------------- | --- | ------------- | --- | ---------------- | --- | ---------- |
| [WizardLM 70B V1.0](https://huggingface.co/WizardLM/WizardLM-70B-V1.0) | → | [WizardLM 70B V1.0-HF](https://huggingface.co/simsim314/WizardLM-70B-V1.0-HF)* | → | Safetensors** | → | EXL2 |
Example to convert WizardLM-70B-V1.0-HF to EXL2 4.0 bpw with 6-bit head:
```
mkdir -p ~/EXL2/WizardLM-70B-V1.0-HF_4bit # Create the output directory
python convert.py -i ~/float16_safetensored/WizardLM-70B-V1.0-HF -o ~/EXL2/WizardLM-70B-V1.0-HF_4bit -c ~/EXL2/0000.parquet -b 4.0 -hb 6
```
\* Use the following script to convert your local pytorch_model bin files to float16 (you can also choose bfloat16) + safetensors all in one go:
- https://github.com/oobabooga/text-generation-webui/blob/main/convert-to-safetensors.py
(best for sharding and float16/FP16 or bfloat16/BF16 conversion)
Example to convert [WizardLM 70B V1.0](https://huggingface.co/WizardLM/WizardLM-70B-V1.0) directly to float16 safetensors in 10GB shards:
```
python convert-to-safetensors.py ~/original/WizardLM-70B-V1.0 --output ~/float16_safetensored/WizardLM-70B-V1.0 --max-shard-size 10GB
```
Use `--bf16` if you'd like to try bfloat16 instead, but note that there are concerns about quantization quality – https://github.com/turboderp/exllamav2/issues/30#issuecomment-1719009289
\*\* Use any one of the following scripts to convert your local pytorch_model bin files to safetensors:
- https://github.com/turboderp/exllamav2/blob/master/util/convert_safetensors.py (official ExLlamaV2)
- https://huggingface.co/Panchovix/airoboros-l2-70b-gpt4-1.4.1-safetensors/blob/main/bin2safetensors/convert.py (recommended)
- https://gist.github.com/epicfilemcnulty/1f55fd96b08f8d4d6693293e37b4c55e#file-2safetensors-py
## Further reading:
- https://mlabonne.github.io/blog/posts/Introduction_to_Weight_Quantization.html
|
Thireus/WizardLM-70B-V1.0-BF16-4.0bpw-h6-exl2
|
Thireus
| 2023-09-22T18:33:08Z | 10 | 0 |
transformers
|
[
"transformers",
"safetensors",
"llama",
"text-generation",
"license:llama2",
"autotrain_compatible",
"text-generation-inference",
"region:us"
] |
text-generation
| 2023-09-21T03:52:35Z |
---
inference: false
license: llama2
model_creator: WizardLM
model_link: https://huggingface.co/WizardLM/WizardLM-70B-V1.0
model_name: WizardLM 70B V1.0
model_type: llama
quantized_by: Thireus
---
# WizardLM 70B V1.0 – EXL2
- Model creator: [WizardLM](https://huggingface.co/WizardLM)
- FP32 Original model used for quantization: [WizardLM 70B V1.0](https://huggingface.co/WizardLM/WizardLM-70B-V1.0) – float32
- FP16 Model used for quantization: [WizardLM 70B V1.0-HF](https://huggingface.co/simsim314/WizardLM-70B-V1.0-HF) – float16 of [WizardLM 70B V1.0](https://huggingface.co/WizardLM/WizardLM-70B-V1.0)
- BF16 Model used for quantization: [WizardLM 70B V1.0-BF16](https://huggingface.co/Thireus/WizardLM-70B-V1.0-BF16) – bfloat16 of [WizardLM 70B V1.0](https://huggingface.co/WizardLM/WizardLM-70B-V1.0)
## Models available:
| Link | BITS (-b) | HEAD BITS (-hb) | MEASU-REMENT LENGTH (-ml) | LENGTH (-l) | CAL DATASET (-c) | Size | V. | Max Context Length | Base Model | Layers | VRAM Min | VRAM Max | PPL** | Comments                                                                                                                         |
| ------ | --------- | --------------- | ------------------------ | ----------- | ---------------- | ---- | ------- | ------------------ | ---- | ---- |------------------ | ------------------ | ------------------ | ---------------------------------------------------------------------------------- |
| [here](https://huggingface.co/Thireus/WizardLM-70B-V1.0-FP32-4.0bpw-h6-exl2/) | 4.0 | 6 | 2048 | 2048 | [0000.parquet](https://huggingface.co/datasets/wikitext/tree/refs%2Fconvert%2Fparquet/wikitext-2-raw-v1/train)* | 33GB | [0.0.2](https://github.com/turboderp/exllamav2/tree/c0dd3412d59c0bc776264512bf76264e954c221d) | 4096 | [FP32](https://huggingface.co/WizardLM/WizardLM-70B-V1.0) | 80 | 39GB | 44GB | 4.15234375 | Good results | | [here](https://huggingface.co/Thireus/WizardLM-70B-V1.0-HF-4.0bpw-h6-exl2/) | 4.0 | 6 | 2048 | 2048 | [0000.parquet](https://huggingface.co/datasets/wikitext/tree/refs%2Fconvert%2Fparquet/wikitext-2-raw-v1/train)* | 35GB | [0.0.1](https://github.com/turboderp/exllamav2/tree/aee7a281708d5faff2ad0ea4b3a3a4b754f458f3) | 4096 | [FP16](https://huggingface.co/simsim314/WizardLM-70B-V1.0-HF) | 80 | 40GB | 44GB | 4.1640625 | Model suffers from poor prompt understanding and logic is affected |
| [here](https://huggingface.co/Thireus/WizardLM-70B-V1.0-BF16-4.0bpw-h6-exl2/) | 4.0 | 6 | 2048 | 2048 | [0000.parquet](https://huggingface.co/datasets/wikitext/tree/refs%2Fconvert%2Fparquet/wikitext-2-raw-v1/train)* | 33GB | [0.0.2](https://github.com/turboderp/exllamav2/tree/ec5164b8a8e282b91aedb2af94dfeb89887656b7) | 4096 | [BF16](https://huggingface.co/Thireus/WizardLM-70B-V1.0-BF16) | 80 | 39GB | 44GB | 4.2421875 | Model suffers from poor prompt understanding and logic is affected |
| [here](https://huggingface.co/Thireus/WizardLM-70B-V1.0-HF-4.0bpw-h8-exl2/) | 4.0 | 8 | 2048 | 2048 | [0000.parquet](https://huggingface.co/datasets/wikitext/tree/refs%2Fconvert%2Fparquet/wikitext-2-raw-v1/train)* | 35GB | [0.0.2](https://github.com/turboderp/exllamav2/tree/a4f2663e310919f007c593030d56ca110f99c261) | 4096 | [FP16](https://huggingface.co/simsim314/WizardLM-70B-V1.0-HF) | 80 | 39GB | 44GB | 4.24609375 | Model suffers from poor prompt understanding and logic is affected |
| [here](https://huggingface.co/Thireus/WizardLM-70B-V1.0-FP32-5.0bpw-h6-exl2/) | 5.0 | 6 | 2048 | 2048 | [0000.parquet](https://huggingface.co/datasets/wikitext/tree/refs%2Fconvert%2Fparquet/wikitext-2-raw-v1/train)* | 41GB | [0.0.2](https://github.com/turboderp/exllamav2/tree/c0dd3412d59c0bc776264512bf76264e954c221d) | 4096 | [FP32](https://huggingface.co/WizardLM/WizardLM-70B-V1.0) | 80 | 47GB | 52GB | 4.06640625 | Best so far. Good results |
| [here](https://huggingface.co/Thireus/WizardLM-70B-V1.0-HF-5.0bpw-h8-exl2/) | 5.0 | 8 | 2048 | 2048 | [0000.parquet](https://huggingface.co/datasets/wikitext/tree/refs%2Fconvert%2Fparquet/wikitext-2-raw-v1/train)* | 44GB | [0.0.2](https://github.com/turboderp/exllamav2/tree/a4f2663e310919f007c593030d56ca110f99c261) | 4096 | [FP16](https://huggingface.co/simsim314/WizardLM-70B-V1.0-HF) | 80 | 48GB | 52GB | 4.09765625 | Model suffers from poor prompt understanding and logic is affected |
| [here](https://huggingface.co/Thireus/WizardLM-70B-V1.0-HF-5.0bpw-h6-exl2/) | 5.0 | 6 | 2048 | 2048 | [0000.parquet](https://huggingface.co/datasets/wikitext/tree/refs%2Fconvert%2Fparquet/wikitext-2-raw-v1/train)* | 44GB | [0.0.1](https://github.com/turboderp/exllamav2/tree/aee7a281708d5faff2ad0ea4b3a3a4b754f458f3) | 4096 | [FP16](https://huggingface.co/simsim314/WizardLM-70B-V1.0-HF) | 80 | 48GB | 52GB | 4.0625 | Model suffers from poor prompt understanding and logic is affected |
| [here](https://huggingface.co/Thireus/WizardLM-70B-V1.0-BF16-5.0bpw-h6-exl2/) | 5.0 | 6 | 2048 | 2048 | [0000.parquet](https://huggingface.co/datasets/wikitext/tree/refs%2Fconvert%2Fparquet/wikitext-2-raw-v1/train)* | 41GB | [0.0.2](https://github.com/turboderp/exllamav2/tree/ec5164b8a8e282b91aedb2af94dfeb89887656b7) | 4096 | [BF16](https://huggingface.co/Thireus/WizardLM-70B-V1.0-BF16) | 80 | 47GB | 52GB | 4.09765625 | Model suffers from poor prompt understanding and logic is affected |
| [here](https://huggingface.co/Thireus/WizardLM-70B-V1.0-HF-6.0bpw-h6-exl2/) | 6.0 | 6 | 2048 | 2048 | [0000.parquet](https://huggingface.co/datasets/wikitext/tree/refs%2Fconvert%2Fparquet/wikitext-2-raw-v1/train)* | 49GB | [0.0.2](https://github.com/turboderp/exllamav2/tree/fae6fb296c6db4e3b1314c49c030541bed98acb9) | 4096 | [FP16](https://huggingface.co/simsim314/WizardLM-70B-V1.0-HF) | 80 | 56GB | 60GB | 4.0703125 | Model suffers from poor prompt understanding and logic is affected |
\* wikitext-2-raw-v1
\*\* Evaluated with text-generation-webui ExLlama v0.0.2 on wikitext-2-raw-v1 (stride 512 and max_length 0). For reference, [TheBloke_WizardLM-70B-V1.0-GPTQ_gptq-4bit-32g-actorder_True](https://huggingface.co/TheBloke/WizardLM-70B-V1.0-GPTQ/tree/gptq-4bit-32g-actorder_True) has a score of 4.1015625 in perplexity.
## Description:
_This repository contains EXL2 model files for [WizardLM's WizardLM 70B V1.0](https://huggingface.co/WizardLM/WizardLM-70B-V1.0)._
EXL2 is a new format used by ExLlamaV2 – https://github.com/turboderp/exllamav2. EXL2 is based on the same optimization method as GPTQ. The format allows for mixing quantization
levels within a model to achieve any average bitrate between 2 and 8 bits per weight.
## Prompt template (official):
```
A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions. USER: {prompt} ASSISTANT:
```
## Prompt template (suggested):
```
A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions.
USER:
{prompt}
ASSISTANT:
```
## Quantization process:
| Original Model | → | (optional) float16 or bfloat16 Model* | → | Safetensors Model** | → | EXL2 Model |
| -------------- | --- | ------------- | --- | ---------------- | --- | ---------- |
| [WizardLM 70B V1.0](https://huggingface.co/WizardLM/WizardLM-70B-V1.0) | → | [WizardLM 70B V1.0-HF](https://huggingface.co/simsim314/WizardLM-70B-V1.0-HF)* | → | Safetensors** | → | EXL2 |
Example to convert WizardLM-70B-V1.0-HF to EXL2 4.0 bpw with 6-bit head:
```
mkdir -p ~/EXL2/WizardLM-70B-V1.0-HF_4bit # Create the output directory
python convert.py -i ~/float16_safetensored/WizardLM-70B-V1.0-HF -o ~/EXL2/WizardLM-70B-V1.0-HF_4bit -c ~/EXL2/0000.parquet -b 4.0 -hb 6
```
\* Use the following script to convert your local pytorch_model bin files to float16 (you can also choose bfloat16) + safetensors all in one go:
- https://github.com/oobabooga/text-generation-webui/blob/main/convert-to-safetensors.py
(best for sharding and float16/FP16 or bfloat16/BF16 conversion)
Example to convert [WizardLM 70B V1.0](https://huggingface.co/WizardLM/WizardLM-70B-V1.0) directly to float16 safetensors in 10GB shards:
```
python convert-to-safetensors.py ~/original/WizardLM-70B-V1.0 --output ~/float16_safetensored/WizardLM-70B-V1.0 --max-shard-size 10GB
```
Use `--bf16` if you'd like to try bfloat16 instead, but note that there are concerns about quantization quality – https://github.com/turboderp/exllamav2/issues/30#issuecomment-1719009289
\*\* Use any one of the following scripts to convert your local pytorch_model bin files to safetensors:
- https://github.com/turboderp/exllamav2/blob/master/util/convert_safetensors.py (official ExLlamaV2)
- https://huggingface.co/Panchovix/airoboros-l2-70b-gpt4-1.4.1-safetensors/blob/main/bin2safetensors/convert.py (recommended)
- https://gist.github.com/epicfilemcnulty/1f55fd96b08f8d4d6693293e37b4c55e#file-2safetensors-py
## Further reading:
- https://mlabonne.github.io/blog/posts/Introduction_to_Weight_Quantization.html
|
mchen-hf-2023/q-Taxi-v3
|
mchen-hf-2023
| 2023-09-22T18:27:26Z | 0 | 0 | null |
[
"Taxi-v3",
"q-learning",
"reinforcement-learning",
"custom-implementation",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-09-22T18:27:23Z |
---
tags:
- Taxi-v3
- q-learning
- reinforcement-learning
- custom-implementation
model-index:
- name: q-Taxi-v3
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: Taxi-v3
type: Taxi-v3
metrics:
- type: mean_reward
value: 7.56 +/- 2.71
name: mean_reward
verified: false
---
# **Q-Learning** Agent playing1 **Taxi-v3**
This is a trained model of a **Q-Learning** agent playing **Taxi-v3** .
## Usage
```python
model = load_from_hub(repo_id="mchen-hf-2023/q-Taxi-v3", filename="q-learning.pkl")
# Don't forget to check if you need to add additional attributes (is_slippery=False etc)
env = gym.make(model["env_id"])
```
|
sachithgunasekara/open-llama-v2-lamini-orca-evol-guanaco-qlora-checkpoint
|
sachithgunasekara
| 2023-09-22T18:25:14Z | 2 | 0 |
peft
|
[
"peft",
"region:us"
] | null | 2023-09-22T18:25:09Z |
---
library_name: peft
---
## Training procedure
### Framework versions
- PEFT 0.6.0.dev0
|
jordyvl/EElayoutlmv3_jordyvl_rvl_cdip_100_examples_per_class_2023-09-22_ent_gates
|
jordyvl
| 2023-09-22T18:23:58Z | 103 | 0 |
transformers
|
[
"transformers",
"pytorch",
"layoutlmv3",
"text-classification",
"generated_from_trainer",
"license:cc-by-nc-sa-4.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2023-09-22T14:06:31Z |
---
license: cc-by-nc-sa-4.0
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: EElayoutlmv3_jordyvl_rvl_cdip_100_examples_per_class_2023-09-22_ent_gates
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. -->
# EElayoutlmv3_jordyvl_rvl_cdip_100_examples_per_class_2023-09-22_ent_gates
This model is a fine-tuned version of [microsoft/layoutlmv3-base](https://huggingface.co/microsoft/layoutlmv3-base) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 1.0995
- Accuracy: 0.705
- Exit 0 Accuracy: 0.065
- Exit 1 Accuracy: 0.0575
- Exit 2 Accuracy: 0.065
- Exit 3 Accuracy: 0.07
- Exit 4 Accuracy: 0.1575
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 20
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 12
- total_train_batch_size: 240
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 60
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Exit 0 Accuracy | Exit 1 Accuracy | Exit 2 Accuracy | Exit 3 Accuracy | Exit 4 Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:---------------:|:---------------:|:---------------:|:---------------:|:---------------:|
| No log | 0.9 | 3 | 2.7455 | 0.0975 | 0.0625 | 0.0625 | 0.0875 | 0.0625 | 0.0625 |
| No log | 1.9 | 6 | 2.6867 | 0.1475 | 0.06 | 0.0625 | 0.0875 | 0.0625 | 0.0625 |
| No log | 2.9 | 9 | 2.6527 | 0.18 | 0.0475 | 0.0575 | 0.09 | 0.0625 | 0.0625 |
| No log | 3.9 | 12 | 2.6188 | 0.1975 | 0.035 | 0.0525 | 0.095 | 0.0625 | 0.0625 |
| No log | 4.9 | 15 | 2.5827 | 0.22 | 0.035 | 0.05 | 0.0875 | 0.0625 | 0.0625 |
| No log | 5.9 | 18 | 2.6265 | 0.1725 | 0.0475 | 0.0375 | 0.0775 | 0.0625 | 0.0825 |
| No log | 6.9 | 21 | 2.5771 | 0.23 | 0.0525 | 0.0375 | 0.0775 | 0.0625 | 0.0975 |
| No log | 7.9 | 24 | 2.4865 | 0.2675 | 0.055 | 0.0375 | 0.0675 | 0.0625 | 0.08 |
| No log | 8.9 | 27 | 2.4184 | 0.25 | 0.0475 | 0.04 | 0.0625 | 0.0625 | 0.0775 |
| No log | 9.9 | 30 | 2.3451 | 0.28 | 0.06 | 0.045 | 0.0625 | 0.0625 | 0.085 |
| No log | 10.9 | 33 | 2.3027 | 0.3175 | 0.0675 | 0.045 | 0.0625 | 0.0625 | 0.0775 |
| No log | 11.9 | 36 | 2.2168 | 0.3225 | 0.07 | 0.045 | 0.0625 | 0.0625 | 0.0775 |
| No log | 12.9 | 39 | 2.1698 | 0.365 | 0.07 | 0.045 | 0.0625 | 0.0625 | 0.085 |
| No log | 13.9 | 42 | 2.0647 | 0.4125 | 0.065 | 0.045 | 0.0625 | 0.0625 | 0.0875 |
| No log | 14.9 | 45 | 2.0370 | 0.4125 | 0.0675 | 0.0475 | 0.0625 | 0.06 | 0.09 |
| No log | 15.9 | 48 | 1.9523 | 0.4675 | 0.065 | 0.0475 | 0.0625 | 0.0575 | 0.0975 |
| No log | 16.9 | 51 | 1.8758 | 0.4925 | 0.0675 | 0.05 | 0.0625 | 0.055 | 0.1075 |
| No log | 17.9 | 54 | 1.7940 | 0.52 | 0.0675 | 0.05 | 0.0625 | 0.0525 | 0.0975 |
| No log | 18.9 | 57 | 1.7417 | 0.5125 | 0.0675 | 0.05 | 0.0625 | 0.0525 | 0.125 |
| No log | 19.9 | 60 | 1.6789 | 0.565 | 0.0675 | 0.05 | 0.0625 | 0.055 | 0.1325 |
| No log | 20.9 | 63 | 1.6016 | 0.5825 | 0.0675 | 0.05 | 0.0625 | 0.0575 | 0.1525 |
| No log | 21.9 | 66 | 1.5649 | 0.5775 | 0.065 | 0.05 | 0.0625 | 0.07 | 0.155 |
| No log | 22.9 | 69 | 1.5164 | 0.6075 | 0.065 | 0.05 | 0.0625 | 0.0775 | 0.155 |
| No log | 23.9 | 72 | 1.4614 | 0.6225 | 0.065 | 0.05 | 0.0625 | 0.085 | 0.1475 |
| No log | 24.9 | 75 | 1.4301 | 0.62 | 0.065 | 0.05 | 0.0625 | 0.085 | 0.16 |
| No log | 25.9 | 78 | 1.3935 | 0.645 | 0.065 | 0.0525 | 0.065 | 0.0775 | 0.1425 |
| No log | 26.9 | 81 | 1.3777 | 0.64 | 0.065 | 0.0525 | 0.065 | 0.08 | 0.1625 |
| No log | 27.9 | 84 | 1.3301 | 0.6525 | 0.065 | 0.0525 | 0.065 | 0.0825 | 0.16 |
| No log | 28.9 | 87 | 1.3064 | 0.6775 | 0.065 | 0.0525 | 0.065 | 0.0825 | 0.1625 |
| No log | 29.9 | 90 | 1.2689 | 0.675 | 0.065 | 0.0525 | 0.065 | 0.085 | 0.1625 |
| No log | 30.9 | 93 | 1.2549 | 0.6575 | 0.065 | 0.0525 | 0.065 | 0.075 | 0.175 |
| No log | 31.9 | 96 | 1.2440 | 0.66 | 0.065 | 0.055 | 0.065 | 0.08 | 0.1525 |
| No log | 32.9 | 99 | 1.2250 | 0.685 | 0.065 | 0.055 | 0.065 | 0.09 | 0.1675 |
| No log | 33.9 | 102 | 1.2243 | 0.665 | 0.065 | 0.055 | 0.065 | 0.0775 | 0.155 |
| No log | 34.9 | 105 | 1.1960 | 0.6625 | 0.065 | 0.055 | 0.065 | 0.0825 | 0.1675 |
| No log | 35.9 | 108 | 1.1879 | 0.685 | 0.065 | 0.055 | 0.065 | 0.08 | 0.155 |
| No log | 36.9 | 111 | 1.1710 | 0.6825 | 0.065 | 0.055 | 0.065 | 0.0825 | 0.155 |
| No log | 37.9 | 114 | 1.1739 | 0.6925 | 0.065 | 0.055 | 0.065 | 0.0675 | 0.1525 |
| No log | 38.9 | 117 | 1.1414 | 0.7 | 0.065 | 0.055 | 0.065 | 0.0725 | 0.1475 |
| No log | 39.9 | 120 | 1.1476 | 0.695 | 0.065 | 0.0575 | 0.065 | 0.0775 | 0.1525 |
| No log | 40.9 | 123 | 1.1435 | 0.6875 | 0.065 | 0.0575 | 0.065 | 0.0825 | 0.15 |
| No log | 41.9 | 126 | 1.1196 | 0.695 | 0.065 | 0.0575 | 0.065 | 0.075 | 0.165 |
| No log | 42.9 | 129 | 1.1454 | 0.7 | 0.065 | 0.0575 | 0.065 | 0.0775 | 0.155 |
| No log | 43.9 | 132 | 1.1133 | 0.7 | 0.065 | 0.0575 | 0.065 | 0.075 | 0.1575 |
| No log | 44.9 | 135 | 1.1205 | 0.7125 | 0.065 | 0.0575 | 0.065 | 0.08 | 0.1625 |
| No log | 45.9 | 138 | 1.1188 | 0.705 | 0.065 | 0.0575 | 0.065 | 0.0775 | 0.1525 |
| No log | 46.9 | 141 | 1.1076 | 0.7025 | 0.065 | 0.0575 | 0.065 | 0.0775 | 0.155 |
| No log | 47.9 | 144 | 1.1304 | 0.7075 | 0.065 | 0.0575 | 0.065 | 0.08 | 0.16 |
| No log | 48.9 | 147 | 1.1029 | 0.7125 | 0.065 | 0.0575 | 0.065 | 0.08 | 0.16 |
| No log | 49.9 | 150 | 1.0979 | 0.705 | 0.065 | 0.0575 | 0.065 | 0.08 | 0.16 |
| No log | 50.9 | 153 | 1.1081 | 0.71 | 0.065 | 0.0575 | 0.065 | 0.0775 | 0.155 |
| No log | 51.9 | 156 | 1.1023 | 0.71 | 0.065 | 0.0575 | 0.065 | 0.0725 | 0.16 |
| No log | 52.9 | 159 | 1.1029 | 0.705 | 0.065 | 0.0575 | 0.065 | 0.07 | 0.16 |
| No log | 53.9 | 162 | 1.1015 | 0.71 | 0.065 | 0.0575 | 0.065 | 0.07 | 0.155 |
| No log | 54.9 | 165 | 1.0968 | 0.7125 | 0.065 | 0.0575 | 0.065 | 0.0725 | 0.155 |
| No log | 55.9 | 168 | 1.0968 | 0.7125 | 0.065 | 0.0575 | 0.065 | 0.0725 | 0.16 |
| No log | 56.9 | 171 | 1.1006 | 0.7025 | 0.065 | 0.0575 | 0.065 | 0.075 | 0.155 |
| No log | 57.9 | 174 | 1.1024 | 0.7025 | 0.065 | 0.0575 | 0.065 | 0.07 | 0.1575 |
| No log | 58.9 | 177 | 1.1006 | 0.705 | 0.065 | 0.0575 | 0.065 | 0.07 | 0.1575 |
| No log | 59.9 | 180 | 1.0995 | 0.705 | 0.065 | 0.0575 | 0.065 | 0.07 | 0.1575 |
### Framework versions
- Transformers 4.26.1
- Pytorch 1.13.1.post200
- Datasets 2.9.0
- Tokenizers 0.13.2
|
tensorgirl/TFaugvit
|
tensorgirl
| 2023-09-22T18:21:23Z | 105 | 1 |
transformers
|
[
"transformers",
"tf",
"augvit",
"vision",
"image-classification",
"custom_code",
"dataset:imagenet-1k",
"arxiv:2106.15941",
"license:other",
"endpoints_compatible",
"region:us"
] |
image-classification
| 2023-09-19T17:00:06Z |
---
license: other
tags:
- vision
- image-classification
datasets:
- imagenet-1k
metrics:
- accuracy
---
# TFaugvit
TFAugViT model is the tensorflow implementation of the
[AugViT: Augmented Shortcuts for Vision Transformers](https://arxiv.org/pdf/2106.15941v1.pdf) by Yehui Tang, Kai Han, Chang Xu, An Xiao, Yiping Deng, Chao Xu and Yunhe Wang,
and first released in [this repository](https://github.com/kingcong/augvit).
## Model description
Aug-ViT inserts additional paths with learnable parameters in parallel on the original shortcuts for alleviating the feature collapse. The block-circulant projection is used to implement augmented shortcut, which brings negligible increase of computational cost.
## Intended uses & limitations
This model can be used for image classification tasks and easily be fine-tuned to suite your purpose of use.
### How to use
Here is how to use this model to classify an image into one of the 1,000 ImageNet classes:
```python
from transformers import TFAutoModelForImageClassification
from PIL import Image
import requests
url = "http://images.cocodataset.org/val2017/000000039769.jpg"
image = Image.open(requests.get(url, stream=True).raw)
model = TFAutoModelForImageClassification.from_pretrained("tensorgirl/TFaugvit",trust_remote_code=True)
outputs = model({'pixel_values':image})
# model predicts one of the 1000 ImageNet classes
predicted_class_idx = outputs.argmax(-1)
```
## Training data
The TFAugViT model is trained on [ImageNet-1k](https://huggingface.co/datasets/imagenet-1k), a dataset consisting of 1 million images and 1,000 classes.
## Training procedure
Due to the use of einops library you cannot use the model,fit() directly on this model, you will have to either write a custom training loop by passing the inputs as shown above or you can wrap the model in a functional model of keras and specify the batch_size beforehand.
If you want to train the model on some other data then either resize the images to 224x224 or change the model config image_size to suit your requirements.
### Training hyperparameters
The following hyperparameters were used during training:
- optimizer: Adam
- batch_size: 32
- training_precision: float32
-
## Evaluation results
| Model | ImageNet top-1 accuracy | # params | Resolution |
|------------------|-------------------------|-----------|------------|
| Aug-ViT-S | 81 | 22.2 M | 224x224 |
| Aug-ViT-B | 82.4 | 86.5 M | 224x224|
| Aug-ViT-B (Upsampled) | 84.2 | 86.5 M | 384x384|
### Framework versions
- Transformers 4.33.2
- TensorFlow 2.13.0
- Tokenizers 0.13.3
### BibTeX entry and citation info
```bibtex
@inproceedings{aug-vit tf,
title = {AugViT: Augmented Shortcuts for Vision Transformers},
author = {Yehui Tang, Kai Han, Chang Xu, An Xiao, Yiping Deng, Chao Xu and Yunhe Wang},
year = {2021},
URL = {https://arxiv.org/abs/2106.15941}
}
```
|
CyberHarem/takahashi_reiko_idolmastercinderellagirls
|
CyberHarem
| 2023-09-22T18:19:05Z | 0 | 0 | null |
[
"art",
"text-to-image",
"dataset:CyberHarem/takahashi_reiko_idolmastercinderellagirls",
"license:mit",
"region:us"
] |
text-to-image
| 2023-09-22T18:07:11Z |
---
license: mit
datasets:
- CyberHarem/takahashi_reiko_idolmastercinderellagirls
pipeline_tag: text-to-image
tags:
- art
---
# Lora of takahashi_reiko_idolmastercinderellagirls
This model is trained with [HCP-Diffusion](https://github.com/7eu7d7/HCP-Diffusion). And the auto-training framework is maintained by [DeepGHS Team](https://huggingface.co/deepghs).
The base model used during training is [NAI](https://huggingface.co/deepghs/animefull-latest), and the base model used for generating preview images is [Meina/MeinaMix_V11](https://huggingface.co/Meina/MeinaMix_V11).
After downloading the pt and safetensors files for the specified step, you need to use them simultaneously. The pt file will be used as an embedding, while the safetensors file will be loaded for Lora.
For example, if you want to use the model from step 1020, you need to download `1020/takahashi_reiko_idolmastercinderellagirls.pt` as the embedding and `1020/takahashi_reiko_idolmastercinderellagirls.safetensors` for loading Lora. By using both files together, you can generate images for the desired characters.
**The best step we recommend is 1020**, with the score of 0.988. The trigger words are:
1. `takahashi_reiko_idolmastercinderellagirls`
2. `long_hair, purple_eyes, black_hair, breasts, large_breasts, smile, jewelry, cleavage`
For the following groups, it is not recommended to use this model and we express regret:
1. Individuals who cannot tolerate any deviations from the original character design, even in the slightest detail.
2. Individuals who are facing the application scenarios with high demands for accuracy in recreating character outfits.
3. Individuals who cannot accept the potential randomness in AI-generated images based on the Stable Diffusion algorithm.
4. Individuals who are not comfortable with the fully automated process of training character models using LoRA, or those who believe that training character models must be done purely through manual operations to avoid disrespecting the characters.
5. Individuals who finds the generated image content offensive to their values.
These are available steps:
| Steps | Score | Download | pattern_1 | pattern_2 | pattern_3 | pattern_4 | bikini | bondage | free | maid | miko | nude | nude2 | suit | yukata |
|:---------|:----------|:-------------------------------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------|:--------------------------------------------------|:-------------------------------------|:-------------------------------------|:-------------------------------------|:-----------------------------------------------|:------------------------------------------------|:-------------------------------------|:-----------------------------------------|
| 5100 | 0.983 | [Download](5100/takahashi_reiko_idolmastercinderellagirls.zip) |  |  |  |  |  | [<NSFW, click to see>](5100/previews/bondage.png) |  |  |  | [<NSFW, click to see>](5100/previews/nude.png) | [<NSFW, click to see>](5100/previews/nude2.png) |  |  |
| 4760 | 0.969 | [Download](4760/takahashi_reiko_idolmastercinderellagirls.zip) |  |  |  |  |  | [<NSFW, click to see>](4760/previews/bondage.png) |  |  |  | [<NSFW, click to see>](4760/previews/nude.png) | [<NSFW, click to see>](4760/previews/nude2.png) |  |  |
| 4420 | 0.982 | [Download](4420/takahashi_reiko_idolmastercinderellagirls.zip) |  |  |  |  |  | [<NSFW, click to see>](4420/previews/bondage.png) |  |  |  | [<NSFW, click to see>](4420/previews/nude.png) | [<NSFW, click to see>](4420/previews/nude2.png) |  |  |
| 4080 | 0.974 | [Download](4080/takahashi_reiko_idolmastercinderellagirls.zip) |  |  |  |  |  | [<NSFW, click to see>](4080/previews/bondage.png) |  |  |  | [<NSFW, click to see>](4080/previews/nude.png) | [<NSFW, click to see>](4080/previews/nude2.png) |  |  |
| 3740 | 0.983 | [Download](3740/takahashi_reiko_idolmastercinderellagirls.zip) |  |  |  |  |  | [<NSFW, click to see>](3740/previews/bondage.png) |  |  |  | [<NSFW, click to see>](3740/previews/nude.png) | [<NSFW, click to see>](3740/previews/nude2.png) |  |  |
| 3400 | 0.891 | [Download](3400/takahashi_reiko_idolmastercinderellagirls.zip) |  |  |  |  |  | [<NSFW, click to see>](3400/previews/bondage.png) |  |  |  | [<NSFW, click to see>](3400/previews/nude.png) | [<NSFW, click to see>](3400/previews/nude2.png) |  |  |
| 3060 | 0.980 | [Download](3060/takahashi_reiko_idolmastercinderellagirls.zip) |  |  |  |  |  | [<NSFW, click to see>](3060/previews/bondage.png) |  |  |  | [<NSFW, click to see>](3060/previews/nude.png) | [<NSFW, click to see>](3060/previews/nude2.png) |  |  |
| 2720 | 0.985 | [Download](2720/takahashi_reiko_idolmastercinderellagirls.zip) |  |  |  |  |  | [<NSFW, click to see>](2720/previews/bondage.png) |  |  |  | [<NSFW, click to see>](2720/previews/nude.png) | [<NSFW, click to see>](2720/previews/nude2.png) |  |  |
| 2380 | 0.895 | [Download](2380/takahashi_reiko_idolmastercinderellagirls.zip) |  |  |  |  |  | [<NSFW, click to see>](2380/previews/bondage.png) |  |  |  | [<NSFW, click to see>](2380/previews/nude.png) | [<NSFW, click to see>](2380/previews/nude2.png) |  |  |
| 2040 | 0.960 | [Download](2040/takahashi_reiko_idolmastercinderellagirls.zip) |  |  |  |  |  | [<NSFW, click to see>](2040/previews/bondage.png) |  |  |  | [<NSFW, click to see>](2040/previews/nude.png) | [<NSFW, click to see>](2040/previews/nude2.png) |  |  |
| 1700 | 0.973 | [Download](1700/takahashi_reiko_idolmastercinderellagirls.zip) |  |  |  |  |  | [<NSFW, click to see>](1700/previews/bondage.png) |  |  |  | [<NSFW, click to see>](1700/previews/nude.png) | [<NSFW, click to see>](1700/previews/nude2.png) |  |  |
| 1360 | 0.977 | [Download](1360/takahashi_reiko_idolmastercinderellagirls.zip) |  |  |  |  |  | [<NSFW, click to see>](1360/previews/bondage.png) |  |  |  | [<NSFW, click to see>](1360/previews/nude.png) | [<NSFW, click to see>](1360/previews/nude2.png) |  |  |
| **1020** | **0.988** | [**Download**](1020/takahashi_reiko_idolmastercinderellagirls.zip) |  |  |  |  |  | [<NSFW, click to see>](1020/previews/bondage.png) |  |  |  | [<NSFW, click to see>](1020/previews/nude.png) | [<NSFW, click to see>](1020/previews/nude2.png) |  |  |
| 680 | 0.877 | [Download](680/takahashi_reiko_idolmastercinderellagirls.zip) |  |  |  |  |  | [<NSFW, click to see>](680/previews/bondage.png) |  |  |  | [<NSFW, click to see>](680/previews/nude.png) | [<NSFW, click to see>](680/previews/nude2.png) |  |  |
| 340 | 0.820 | [Download](340/takahashi_reiko_idolmastercinderellagirls.zip) |  |  |  |  |  | [<NSFW, click to see>](340/previews/bondage.png) |  |  |  | [<NSFW, click to see>](340/previews/nude.png) | [<NSFW, click to see>](340/previews/nude2.png) |  |  |
|
0ppxnhximxr/distilbert-base-uncased-finetuned-emotion
|
0ppxnhximxr
| 2023-09-22T18:14:16Z | 107 | 0 |
transformers
|
[
"transformers",
"pytorch",
"distilbert",
"text-classification",
"generated_from_trainer",
"dataset:emotion",
"base_model:distilbert/distilbert-base-uncased",
"base_model:finetune:distilbert/distilbert-base-uncased",
"license:apache-2.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2023-09-22T18:11:23Z |
---
license: apache-2.0
base_model: distilbert-base-uncased
tags:
- generated_from_trainer
datasets:
- emotion
metrics:
- accuracy
- f1
model-index:
- name: distilbert-base-uncased-finetuned-emotion
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: emotion
type: emotion
config: split
split: validation
args: split
metrics:
- name: Accuracy
type: accuracy
value: 0.926
- name: F1
type: f1
value: 0.9259596663626415
---
<!-- 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. -->
# distilbert-base-uncased-finetuned-emotion
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the emotion dataset.
It achieves the following results on the evaluation set:
- Loss: 0.2200
- Accuracy: 0.926
- F1: 0.9260
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 64
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 2
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
| 0.836 | 1.0 | 250 | 0.3195 | 0.906 | 0.9053 |
| 0.2573 | 2.0 | 500 | 0.2200 | 0.926 | 0.9260 |
### Framework versions
- Transformers 4.33.2
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3
|
TieIncred/cloth2
|
TieIncred
| 2023-09-22T17:58:39Z | 1 | 0 |
diffusers
|
[
"diffusers",
"tensorboard",
"safetensors",
"stable-diffusion",
"stable-diffusion-diffusers",
"text-to-image",
"dreambooth",
"base_model:runwayml/stable-diffusion-v1-5",
"base_model:finetune:runwayml/stable-diffusion-v1-5",
"license:creativeml-openrail-m",
"autotrain_compatible",
"endpoints_compatible",
"diffusers:StableDiffusionPipeline",
"region:us"
] |
text-to-image
| 2023-09-08T13:22:15Z |
---
license: creativeml-openrail-m
base_model: runwayml/stable-diffusion-v1-5
instance_prompt: a photo of checkodsasdass man
tags:
- stable-diffusion
- stable-diffusion-diffusers
- text-to-image
- diffusers
- dreambooth
inference: true
---
# DreamBooth - TieIncred/cloth2
This is a dreambooth model derived from runwayml/stable-diffusion-v1-5. The weights were trained on a photo of checkodsasdass man using [DreamBooth](https://dreambooth.github.io/).
You can find some example images in the following.
DreamBooth for the text encoder was enabled: True.
|
karanjakhar/speecht5_finetuned_voxpopuli_de
|
karanjakhar
| 2023-09-22T17:35:51Z | 90 | 0 |
transformers
|
[
"transformers",
"pytorch",
"tensorboard",
"safetensors",
"speecht5",
"text-to-audio",
"generated_from_trainer",
"text-to-speech",
"dataset:facebook/voxpopuli",
"base_model:microsoft/speecht5_tts",
"base_model:finetune:microsoft/speecht5_tts",
"license:mit",
"endpoints_compatible",
"region:us"
] |
text-to-speech
| 2023-07-27T19:42:58Z |
---
license: mit
tags:
- generated_from_trainer
- text-to-speech
datasets:
- facebook/voxpopuli
base_model: microsoft/speecht5_tts
model-index:
- name: speecht5_finetuned_voxpopuli_de
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. -->
# speecht5_finetuned_voxpopuli_de
This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on the facebook/voxpopuli 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: 1e-05
- train_batch_size: 4
- eval_batch_size: 2
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- training_steps: 4000
### Framework versions
- Transformers 4.31.0.dev0
- Pytorch 2.0.1
- Datasets 2.13.1
- Tokenizers 0.13.3
|
santis2/gpt2-xl-alpaca-instruction-fine-tuning-lora
|
santis2
| 2023-09-22T17:35:48Z | 0 | 0 | null |
[
"generated_from_trainer",
"base_model:openai-community/gpt2-xl",
"base_model:finetune:openai-community/gpt2-xl",
"license:mit",
"region:us"
] | null | 2023-09-22T17:35:45Z |
---
license: mit
base_model: gpt2-xl
tags:
- generated_from_trainer
model-index:
- name: gpt2-xl-alpaca-instruction-fine-tuning-lora
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. -->
# gpt2-xl-alpaca-instruction-fine-tuning-lora
This model is a fine-tuned version of [gpt2-xl](https://huggingface.co/gpt2-xl) on an unknown 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: 0.0005
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 1000
- num_epochs: 1
### Training results
### Framework versions
- Transformers 4.33.2
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3
|
SagarDas07/llama2franch
|
SagarDas07
| 2023-09-22T17:19:08Z | 0 | 0 |
peft
|
[
"peft",
"region:us"
] | null | 2023-09-22T17:08:26Z |
---
library_name: peft
---
## Training procedure
The following `bitsandbytes` quantization config was used during training:
- quant_method: bitsandbytes
- load_in_8bit: False
- load_in_4bit: True
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: nf4
- bnb_4bit_use_double_quant: False
- bnb_4bit_compute_dtype: float16
### Framework versions
- PEFT 0.6.0.dev0
|
Baratova/Eunil
|
Baratova
| 2023-09-22T16:45:27Z | 0 | 0 |
adapter-transformers
|
[
"adapter-transformers",
"voice-activity-detection",
"dataset:fka/awesome-chatgpt-prompts",
"license:openrail",
"region:us"
] |
voice-activity-detection
| 2023-09-22T07:01:22Z |
---
license: openrail
datasets:
- fka/awesome-chatgpt-prompts
metrics:
- code_eval
library_name: adapter-transformers
pipeline_tag: voice-activity-detection
---
|
alexdbz/bert-base-peft-Lora-abstracts-6epochs
|
alexdbz
| 2023-09-22T16:40:42Z | 0 | 0 |
peft
|
[
"peft",
"region:us"
] | null | 2023-08-31T17:41:31Z |
---
library_name: peft
---
## Training procedure
### Framework versions
- PEFT 0.6.0.dev0
|
jordyvl/EElayoutlmv3_jordyvl_rvl_cdip_100_examples_per_class_2023-09-22_subgraphs_gates
|
jordyvl
| 2023-09-22T16:30:26Z | 103 | 0 |
transformers
|
[
"transformers",
"pytorch",
"layoutlmv3",
"text-classification",
"generated_from_trainer",
"license:cc-by-nc-sa-4.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2023-09-22T14:06:12Z |
---
license: cc-by-nc-sa-4.0
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: EElayoutlmv3_jordyvl_rvl_cdip_100_examples_per_class_2023-09-22_subgraphs_gates
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. -->
# EElayoutlmv3_jordyvl_rvl_cdip_100_examples_per_class_2023-09-22_subgraphs_gates
This model is a fine-tuned version of [microsoft/layoutlmv3-base](https://huggingface.co/microsoft/layoutlmv3-base) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 1.0995
- Accuracy: 0.705
- Exit 0 Accuracy: 0.065
- Exit 1 Accuracy: 0.0575
- Exit 2 Accuracy: 0.065
- Exit 3 Accuracy: 0.07
- Exit 4 Accuracy: 0.1575
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 20
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 12
- total_train_batch_size: 240
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 60
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Exit 0 Accuracy | Exit 1 Accuracy | Exit 2 Accuracy | Exit 3 Accuracy | Exit 4 Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:---------------:|:---------------:|:---------------:|:---------------:|:---------------:|
| No log | 0.9 | 3 | 2.7455 | 0.0975 | 0.0625 | 0.0625 | 0.0875 | 0.0625 | 0.0625 |
| No log | 1.9 | 6 | 2.6867 | 0.1475 | 0.06 | 0.0625 | 0.0875 | 0.0625 | 0.0625 |
| No log | 2.9 | 9 | 2.6527 | 0.18 | 0.0475 | 0.0575 | 0.09 | 0.0625 | 0.0625 |
| No log | 3.9 | 12 | 2.6188 | 0.1975 | 0.035 | 0.0525 | 0.095 | 0.0625 | 0.0625 |
| No log | 4.9 | 15 | 2.5827 | 0.22 | 0.035 | 0.05 | 0.0875 | 0.0625 | 0.0625 |
| No log | 5.9 | 18 | 2.6265 | 0.1725 | 0.0475 | 0.0375 | 0.0775 | 0.0625 | 0.0825 |
| No log | 6.9 | 21 | 2.5771 | 0.23 | 0.0525 | 0.0375 | 0.0775 | 0.0625 | 0.0975 |
| No log | 7.9 | 24 | 2.4865 | 0.2675 | 0.055 | 0.0375 | 0.0675 | 0.0625 | 0.08 |
| No log | 8.9 | 27 | 2.4184 | 0.25 | 0.0475 | 0.04 | 0.0625 | 0.0625 | 0.0775 |
| No log | 9.9 | 30 | 2.3451 | 0.28 | 0.06 | 0.045 | 0.0625 | 0.0625 | 0.085 |
| No log | 10.9 | 33 | 2.3027 | 0.3175 | 0.0675 | 0.045 | 0.0625 | 0.0625 | 0.0775 |
| No log | 11.9 | 36 | 2.2168 | 0.3225 | 0.07 | 0.045 | 0.0625 | 0.0625 | 0.0775 |
| No log | 12.9 | 39 | 2.1698 | 0.365 | 0.07 | 0.045 | 0.0625 | 0.0625 | 0.085 |
| No log | 13.9 | 42 | 2.0647 | 0.4125 | 0.065 | 0.045 | 0.0625 | 0.0625 | 0.0875 |
| No log | 14.9 | 45 | 2.0370 | 0.4125 | 0.0675 | 0.0475 | 0.0625 | 0.06 | 0.09 |
| No log | 15.9 | 48 | 1.9523 | 0.4675 | 0.065 | 0.0475 | 0.0625 | 0.0575 | 0.0975 |
| No log | 16.9 | 51 | 1.8758 | 0.4925 | 0.0675 | 0.05 | 0.0625 | 0.055 | 0.1075 |
| No log | 17.9 | 54 | 1.7940 | 0.52 | 0.0675 | 0.05 | 0.0625 | 0.0525 | 0.0975 |
| No log | 18.9 | 57 | 1.7417 | 0.5125 | 0.0675 | 0.05 | 0.0625 | 0.0525 | 0.125 |
| No log | 19.9 | 60 | 1.6789 | 0.565 | 0.0675 | 0.05 | 0.0625 | 0.055 | 0.1325 |
| No log | 20.9 | 63 | 1.6016 | 0.5825 | 0.0675 | 0.05 | 0.0625 | 0.0575 | 0.1525 |
| No log | 21.9 | 66 | 1.5649 | 0.5775 | 0.065 | 0.05 | 0.0625 | 0.07 | 0.155 |
| No log | 22.9 | 69 | 1.5164 | 0.6075 | 0.065 | 0.05 | 0.0625 | 0.0775 | 0.155 |
| No log | 23.9 | 72 | 1.4614 | 0.6225 | 0.065 | 0.05 | 0.0625 | 0.085 | 0.1475 |
| No log | 24.9 | 75 | 1.4301 | 0.62 | 0.065 | 0.05 | 0.0625 | 0.085 | 0.16 |
| No log | 25.9 | 78 | 1.3935 | 0.645 | 0.065 | 0.0525 | 0.065 | 0.0775 | 0.1425 |
| No log | 26.9 | 81 | 1.3777 | 0.64 | 0.065 | 0.0525 | 0.065 | 0.08 | 0.1625 |
| No log | 27.9 | 84 | 1.3301 | 0.6525 | 0.065 | 0.0525 | 0.065 | 0.0825 | 0.16 |
| No log | 28.9 | 87 | 1.3064 | 0.6775 | 0.065 | 0.0525 | 0.065 | 0.0825 | 0.1625 |
| No log | 29.9 | 90 | 1.2689 | 0.675 | 0.065 | 0.0525 | 0.065 | 0.085 | 0.1625 |
| No log | 30.9 | 93 | 1.2549 | 0.6575 | 0.065 | 0.0525 | 0.065 | 0.075 | 0.175 |
| No log | 31.9 | 96 | 1.2440 | 0.66 | 0.065 | 0.055 | 0.065 | 0.08 | 0.1525 |
| No log | 32.9 | 99 | 1.2250 | 0.685 | 0.065 | 0.055 | 0.065 | 0.09 | 0.1675 |
| No log | 33.9 | 102 | 1.2243 | 0.665 | 0.065 | 0.055 | 0.065 | 0.0775 | 0.155 |
| No log | 34.9 | 105 | 1.1960 | 0.6625 | 0.065 | 0.055 | 0.065 | 0.0825 | 0.1675 |
| No log | 35.9 | 108 | 1.1879 | 0.685 | 0.065 | 0.055 | 0.065 | 0.08 | 0.155 |
| No log | 36.9 | 111 | 1.1710 | 0.6825 | 0.065 | 0.055 | 0.065 | 0.0825 | 0.155 |
| No log | 37.9 | 114 | 1.1739 | 0.6925 | 0.065 | 0.055 | 0.065 | 0.0675 | 0.1525 |
| No log | 38.9 | 117 | 1.1414 | 0.7 | 0.065 | 0.055 | 0.065 | 0.0725 | 0.1475 |
| No log | 39.9 | 120 | 1.1476 | 0.695 | 0.065 | 0.0575 | 0.065 | 0.0775 | 0.1525 |
| No log | 40.9 | 123 | 1.1435 | 0.6875 | 0.065 | 0.0575 | 0.065 | 0.0825 | 0.15 |
| No log | 41.9 | 126 | 1.1196 | 0.695 | 0.065 | 0.0575 | 0.065 | 0.075 | 0.165 |
| No log | 42.9 | 129 | 1.1454 | 0.7 | 0.065 | 0.0575 | 0.065 | 0.0775 | 0.155 |
| No log | 43.9 | 132 | 1.1133 | 0.7 | 0.065 | 0.0575 | 0.065 | 0.075 | 0.1575 |
| No log | 44.9 | 135 | 1.1205 | 0.7125 | 0.065 | 0.0575 | 0.065 | 0.08 | 0.1625 |
| No log | 45.9 | 138 | 1.1188 | 0.705 | 0.065 | 0.0575 | 0.065 | 0.0775 | 0.1525 |
| No log | 46.9 | 141 | 1.1076 | 0.7025 | 0.065 | 0.0575 | 0.065 | 0.0775 | 0.155 |
| No log | 47.9 | 144 | 1.1304 | 0.7075 | 0.065 | 0.0575 | 0.065 | 0.08 | 0.16 |
| No log | 48.9 | 147 | 1.1029 | 0.7125 | 0.065 | 0.0575 | 0.065 | 0.08 | 0.16 |
| No log | 49.9 | 150 | 1.0979 | 0.705 | 0.065 | 0.0575 | 0.065 | 0.08 | 0.16 |
| No log | 50.9 | 153 | 1.1081 | 0.71 | 0.065 | 0.0575 | 0.065 | 0.0775 | 0.155 |
| No log | 51.9 | 156 | 1.1023 | 0.71 | 0.065 | 0.0575 | 0.065 | 0.0725 | 0.16 |
| No log | 52.9 | 159 | 1.1029 | 0.705 | 0.065 | 0.0575 | 0.065 | 0.07 | 0.16 |
| No log | 53.9 | 162 | 1.1015 | 0.71 | 0.065 | 0.0575 | 0.065 | 0.07 | 0.155 |
| No log | 54.9 | 165 | 1.0968 | 0.7125 | 0.065 | 0.0575 | 0.065 | 0.0725 | 0.155 |
| No log | 55.9 | 168 | 1.0968 | 0.7125 | 0.065 | 0.0575 | 0.065 | 0.0725 | 0.16 |
| No log | 56.9 | 171 | 1.1006 | 0.7025 | 0.065 | 0.0575 | 0.065 | 0.075 | 0.155 |
| No log | 57.9 | 174 | 1.1024 | 0.7025 | 0.065 | 0.0575 | 0.065 | 0.07 | 0.1575 |
| No log | 58.9 | 177 | 1.1006 | 0.705 | 0.065 | 0.0575 | 0.065 | 0.07 | 0.1575 |
| No log | 59.9 | 180 | 1.0995 | 0.705 | 0.065 | 0.0575 | 0.065 | 0.07 | 0.1575 |
### Framework versions
- Transformers 4.26.1
- Pytorch 1.13.1.post200
- Datasets 2.9.0
- Tokenizers 0.13.2
|
cegy369/sk-squad-falcon-7b
|
cegy369
| 2023-09-22T16:14:34Z | 0 | 3 | null |
[
"falcon-7b-instruct",
"falcon",
"text-generation",
"sk",
"dataset:TUKE-DeutscheTelekom/skquad",
"region:us"
] |
text-generation
| 2023-09-20T17:04:35Z |
---
pipeline_tag: text-generation
datasets:
- TUKE-DeutscheTelekom/skquad
language:
- sk
tags:
- falcon-7b-instruct
- falcon
- text-generation
---
|
gpadam/autotrain-stripped-data-training-biobart-90151144184
|
gpadam
| 2023-09-22T16:13:51Z | 126 | 0 |
transformers
|
[
"transformers",
"pytorch",
"safetensors",
"bart",
"text2text-generation",
"autotrain",
"summarization",
"unk",
"dataset:gpadam/autotrain-data-stripped-data-training-biobart",
"co2_eq_emissions",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
summarization
| 2023-09-19T11:35:27Z |
---
tags:
- autotrain
- summarization
language:
- unk
widget:
- text: "I love AutoTrain"
datasets:
- gpadam/autotrain-data-stripped-data-training-biobart
co2_eq_emissions:
emissions: 0.3124425669459831
---
# Model Trained Using AutoTrain
- Problem type: Summarization
- Model ID: 90151144184
- CO2 Emissions (in grams): 0.3124
## Validation Metrics
- Loss: 1.812
- Rouge1: 30.025
- Rouge2: 16.263
- RougeL: 25.502
- RougeLsum: 25.494
- Gen Len: 19.698
## Usage
You can use cURL to access this model:
```
$ curl -X POST -H "Authorization: Bearer YOUR_HUGGINGFACE_API_KEY" -H "Content-Type: application/json" -d '{"inputs": "I love AutoTrain"}' https://api-inference.huggingface.co/gpadam/autotrain-stripped-data-training-biobart-90151144184
```
|
luanvuvt/results
|
luanvuvt
| 2023-09-22T16:12:52Z | 0 | 0 | null |
[
"generated_from_trainer",
"base_model:TinyPixel/Llama-2-7B-bf16-sharded",
"base_model:finetune:TinyPixel/Llama-2-7B-bf16-sharded",
"region:us"
] | null | 2023-09-22T16:12:27Z |
---
base_model: TinyPixel/Llama-2-7B-bf16-sharded
tags:
- generated_from_trainer
model-index:
- name: results
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. -->
# results
This model is a fine-tuned version of [TinyPixel/Llama-2-7B-bf16-sharded](https://huggingface.co/TinyPixel/Llama-2-7B-bf16-sharded) on the None dataset.
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0002
- train_batch_size: 4
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: constant
- lr_scheduler_warmup_ratio: 0.03
- training_steps: 35
### Training results
### Framework versions
- Transformers 4.33.2
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3
|
aramka/arka
|
aramka
| 2023-09-22T16:11:27Z | 0 | 0 |
allennlp
|
[
"allennlp",
"biology",
"question-answering",
"ar",
"dataset:allenai/dolma",
"license:afl-3.0",
"region:us"
] |
question-answering
| 2022-05-24T22:59:55Z |
---
license: afl-3.0
datasets:
- allenai/dolma
language:
- ar
metrics:
- bertscore
library_name: allennlp
pipeline_tag: question-answering
tags:
- biology
---
|
pbeyens/cord-repo
|
pbeyens
| 2023-09-22T16:07:13Z | 3 | 0 |
transformers
|
[
"transformers",
"pytorch",
"tensorboard",
"lilt",
"token-classification",
"generated_from_trainer",
"dataset:cord",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
token-classification
| 2023-09-22T09:04:51Z |
---
license: mit
tags:
- generated_from_trainer
datasets:
- cord
model-index:
- name: cord-repo
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. -->
# cord-repo
This model is a fine-tuned version of [SCUT-DLVCLab/lilt-roberta-en-base](https://huggingface.co/SCUT-DLVCLab/lilt-roberta-en-base) on the cord dataset.
It achieves the following results on the evaluation set:
- Loss: 0.2687
- Menu.cnt: {'precision': 0.9864253393665159, 'recall': 0.9688888888888889, 'f1': 0.9775784753363229, 'number': 225}
- Menu.discountprice: {'precision': 0.8, 'recall': 0.8, 'f1': 0.8000000000000002, 'number': 10}
- Menu.nm: {'precision': 0.9333333333333333, 'recall': 0.9444444444444444, 'f1': 0.9388560157790926, 'number': 252}
- Menu.num: {'precision': 0.9166666666666666, 'recall': 1.0, 'f1': 0.9565217391304348, 'number': 11}
- Menu.price: {'precision': 0.9606299212598425, 'recall': 0.9838709677419355, 'f1': 0.9721115537848605, 'number': 248}
- Menu.sub Cnt: {'precision': 0.8095238095238095, 'recall': 1.0, 'f1': 0.8947368421052632, 'number': 17}
- Menu.sub Nm: {'precision': 0.7575757575757576, 'recall': 0.78125, 'f1': 0.7692307692307692, 'number': 32}
- Menu.sub Price: {'precision': 0.9047619047619048, 'recall': 0.95, 'f1': 0.9268292682926829, 'number': 20}
- Menu.unitprice: {'precision': 0.9846153846153847, 'recall': 0.9411764705882353, 'f1': 0.962406015037594, 'number': 68}
- Sub Total.discount Price: {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 7}
- Sub Total.etc: {'precision': 0.7777777777777778, 'recall': 0.875, 'f1': 0.823529411764706, 'number': 8}
- Sub Total.service Price: {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 12}
- Sub Total.subtotal Price: {'precision': 0.971830985915493, 'recall': 1.0, 'f1': 0.9857142857142858, 'number': 69}
- Sub Total.tax Price: {'precision': 0.9777777777777777, 'recall': 0.9777777777777777, 'f1': 0.9777777777777777, 'number': 45}
- Total.cashprice: {'precision': 0.9705882352941176, 'recall': 0.9295774647887324, 'f1': 0.9496402877697842, 'number': 71}
- Total.changeprice: {'precision': 0.9523809523809523, 'recall': 1.0, 'f1': 0.975609756097561, 'number': 60}
- Total.creditcardprice: {'precision': 0.8823529411764706, 'recall': 0.9375, 'f1': 0.9090909090909091, 'number': 16}
- Total.emoneyprice: {'precision': 0.6666666666666666, 'recall': 1.0, 'f1': 0.8, 'number': 2}
- Total.menuqty Cnt: {'precision': 0.9354838709677419, 'recall': 0.9666666666666667, 'f1': 0.9508196721311476, 'number': 30}
- Total.menutype Cnt: {'precision': 0.8571428571428571, 'recall': 0.75, 'f1': 0.7999999999999999, 'number': 8}
- Total.total Etc: {'precision': 0.5, 'recall': 0.25, 'f1': 0.3333333333333333, 'number': 4}
- Total.total Price: {'precision': 0.9693877551020408, 'recall': 0.9595959595959596, 'f1': 0.964467005076142, 'number': 99}
- Overall Precision: 0.9487
- Overall Recall: 0.9566
- Overall F1: 0.9526
- Overall Accuracy: 0.9644
## 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
- training_steps: 5000
- mixed_precision_training: Native AMP
### Training results
| Training Loss | Epoch | Step | Validation Loss | Menu.cnt | Menu.discountprice | Menu.nm | Menu.num | Menu.price | Menu.sub Cnt | Menu.sub Nm | Menu.sub Price | Menu.unitprice | Sub Total.discount Price | Sub Total.etc | Sub Total.service Price | Sub Total.subtotal Price | Sub Total.tax Price | Total.cashprice | Total.changeprice | Total.creditcardprice | Total.emoneyprice | Total.menuqty Cnt | Total.menutype Cnt | Total.total Etc | Total.total Price | Overall Precision | Overall Recall | Overall F1 | Overall Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------------------------------------------------------------------------------------------------------:|:-----------------------------------------------------------------------------------------:|:--------------------------------------------------------------------------------------------------------:|:-------------------------------------------------------------------------------------------------------:|:--------------------------------------------------------------------------------------------------------:|:-------------------------------------------------------------------------------------------------------:|:--------------------------------------------------------------------------------------------:|:-----------------------------------------------------------------------------------------:|:-------------------------------------------------------------------------------------------------------:|:------------------------------------------------------------------------------------------------------:|:-----------------------------------------------------------------------------------------:|:----------------------------------------------------------------------------------------:|:-------------------------------------------------------------------------------------------------------:|:-------------------------------------------------------------------------------------------------------:|:-------------------------------------------------------------------------------------------------------:|:-------------------------------------------------------------------------------------------------------:|:-------------------------------------------------------------------------------------------:|:-------------------------------------------------------------------------:|:-------------------------------------------------------------------------------------------------------:|:----------------------------------------------------------------------------------------:|:------------------------------------------------------------------------------------------:|:-------------------------------------------------------------------------------------------------------:|:-----------------:|:--------------:|:----------:|:----------------:|
| 0.6774 | 2.0 | 200 | 0.2667 | {'precision': 0.9285714285714286, 'recall': 0.9822222222222222, 'f1': 0.9546436285097192, 'number': 225} | {'precision': 0.6666666666666666, 'recall': 0.6, 'f1': 0.631578947368421, 'number': 10} | {'precision': 0.8812260536398467, 'recall': 0.9126984126984127, 'f1': 0.8966861598440545, 'number': 252} | {'precision': 0.875, 'recall': 0.6363636363636364, 'f1': 0.7368421052631579, 'number': 11} | {'precision': 0.9717741935483871, 'recall': 0.9717741935483871, 'f1': 0.9717741935483871, 'number': 248} | {'precision': 0.9230769230769231, 'recall': 0.7058823529411765, 'f1': 0.8000000000000002, 'number': 17} | {'precision': 0.8148148148148148, 'recall': 0.6875, 'f1': 0.7457627118644067, 'number': 32} | {'precision': 1.0, 'recall': 0.8, 'f1': 0.888888888888889, 'number': 20} | {'precision': 0.8918918918918919, 'recall': 0.9705882352941176, 'f1': 0.9295774647887325, 'number': 68} | {'precision': 0.8571428571428571, 'recall': 0.8571428571428571, 'f1': 0.8571428571428571, 'number': 7} | {'precision': 0.2857142857142857, 'recall': 0.25, 'f1': 0.26666666666666666, 'number': 8} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 12} | {'precision': 0.7974683544303798, 'recall': 0.9130434782608695, 'f1': 0.8513513513513514, 'number': 69} | {'precision': 0.9545454545454546, 'recall': 0.9333333333333333, 'f1': 0.9438202247191012, 'number': 45} | {'precision': 0.9538461538461539, 'recall': 0.8732394366197183, 'f1': 0.9117647058823529, 'number': 71} | {'precision': 0.9180327868852459, 'recall': 0.9333333333333333, 'f1': 0.9256198347107439, 'number': 60} | {'precision': 0.8235294117647058, 'recall': 0.875, 'f1': 0.8484848484848485, 'number': 16} | {'precision': 1.0, 'recall': 0.5, 'f1': 0.6666666666666666, 'number': 2} | {'precision': 0.8, 'recall': 0.8, 'f1': 0.8000000000000002, 'number': 30} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 8} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 4} | {'precision': 0.8584905660377359, 'recall': 0.9191919191919192, 'f1': 0.8878048780487805, 'number': 99} | 0.8998 | 0.9087 | 0.9042 | 0.9300 |
| 0.1521 | 4.0 | 400 | 0.2353 | {'precision': 0.9688888888888889, 'recall': 0.9688888888888889, 'f1': 0.9688888888888889, 'number': 225} | {'precision': 0.5833333333333334, 'recall': 0.7, 'f1': 0.6363636363636365, 'number': 10} | {'precision': 0.9153846153846154, 'recall': 0.9444444444444444, 'f1': 0.9296874999999999, 'number': 252} | {'precision': 0.9166666666666666, 'recall': 1.0, 'f1': 0.9565217391304348, 'number': 11} | {'precision': 0.9604743083003953, 'recall': 0.9798387096774194, 'f1': 0.9700598802395209, 'number': 248} | {'precision': 0.8, 'recall': 0.9411764705882353, 'f1': 0.8648648648648648, 'number': 17} | {'precision': 0.7631578947368421, 'recall': 0.90625, 'f1': 0.8285714285714286, 'number': 32} | {'precision': 0.782608695652174, 'recall': 0.9, 'f1': 0.8372093023255814, 'number': 20} | {'precision': 0.9850746268656716, 'recall': 0.9705882352941176, 'f1': 0.9777777777777777, 'number': 68} | {'precision': 0.8571428571428571, 'recall': 0.8571428571428571, 'f1': 0.8571428571428571, 'number': 7} | {'precision': 0.8333333333333334, 'recall': 0.625, 'f1': 0.7142857142857143, 'number': 8} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 12} | {'precision': 0.8904109589041096, 'recall': 0.9420289855072463, 'f1': 0.9154929577464788, 'number': 69} | {'precision': 0.9148936170212766, 'recall': 0.9555555555555556, 'f1': 0.9347826086956522, 'number': 45} | {'precision': 0.96875, 'recall': 0.8732394366197183, 'f1': 0.9185185185185184, 'number': 71} | {'precision': 0.9655172413793104, 'recall': 0.9333333333333333, 'f1': 0.9491525423728815, 'number': 60} | {'precision': 0.8823529411764706, 'recall': 0.9375, 'f1': 0.9090909090909091, 'number': 16} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 2} | {'precision': 0.7878787878787878, 'recall': 0.8666666666666667, 'f1': 0.8253968253968254, 'number': 30} | {'precision': 0.5, 'recall': 0.375, 'f1': 0.42857142857142855, 'number': 8} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 4} | {'precision': 0.9278350515463918, 'recall': 0.9090909090909091, 'f1': 0.9183673469387756, 'number': 99} | 0.9235 | 0.9368 | 0.9301 | 0.9440 |
| 0.0767 | 6.0 | 600 | 0.2016 | {'precision': 0.9644444444444444, 'recall': 0.9644444444444444, 'f1': 0.9644444444444444, 'number': 225} | {'precision': 0.7, 'recall': 0.7, 'f1': 0.7, 'number': 10} | {'precision': 0.926923076923077, 'recall': 0.9563492063492064, 'f1': 0.9414062500000001, 'number': 252} | {'precision': 0.8888888888888888, 'recall': 0.7272727272727273, 'f1': 0.7999999999999999, 'number': 11} | {'precision': 0.984, 'recall': 0.9919354838709677, 'f1': 0.9879518072289156, 'number': 248} | {'precision': 0.8421052631578947, 'recall': 0.9411764705882353, 'f1': 0.8888888888888888, 'number': 17} | {'precision': 0.8461538461538461, 'recall': 0.6875, 'f1': 0.7586206896551724, 'number': 32} | {'precision': 0.9473684210526315, 'recall': 0.9, 'f1': 0.9230769230769231, 'number': 20} | {'precision': 0.9852941176470589, 'recall': 0.9852941176470589, 'f1': 0.9852941176470589, 'number': 68} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 7} | {'precision': 0.8888888888888888, 'recall': 1.0, 'f1': 0.9411764705882353, 'number': 8} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 12} | {'precision': 0.9565217391304348, 'recall': 0.9565217391304348, 'f1': 0.9565217391304348, 'number': 69} | {'precision': 1.0, 'recall': 0.9555555555555556, 'f1': 0.9772727272727273, 'number': 45} | {'precision': 0.9242424242424242, 'recall': 0.8591549295774648, 'f1': 0.8905109489051095, 'number': 71} | {'precision': 0.9827586206896551, 'recall': 0.95, 'f1': 0.9661016949152542, 'number': 60} | {'precision': 0.9375, 'recall': 0.9375, 'f1': 0.9375, 'number': 16} | {'precision': 0.4, 'recall': 1.0, 'f1': 0.5714285714285715, 'number': 2} | {'precision': 0.9642857142857143, 'recall': 0.9, 'f1': 0.9310344827586207, 'number': 30} | {'precision': 0.6666666666666666, 'recall': 0.75, 'f1': 0.7058823529411765, 'number': 8} | {'precision': 0.25, 'recall': 0.25, 'f1': 0.25, 'number': 4} | {'precision': 0.9306930693069307, 'recall': 0.9494949494949495, 'f1': 0.9400000000000001, 'number': 99} | 0.9452 | 0.9444 | 0.9448 | 0.9572 |
| 0.05 | 8.0 | 800 | 0.2408 | {'precision': 0.9773755656108597, 'recall': 0.96, 'f1': 0.9686098654708519, 'number': 225} | {'precision': 0.7, 'recall': 0.7, 'f1': 0.7, 'number': 10} | {'precision': 0.9299610894941635, 'recall': 0.9484126984126984, 'f1': 0.9390962671905697, 'number': 252} | {'precision': 0.8461538461538461, 'recall': 1.0, 'f1': 0.9166666666666666, 'number': 11} | {'precision': 0.9682539682539683, 'recall': 0.9838709677419355, 'f1': 0.976, 'number': 248} | {'precision': 0.8095238095238095, 'recall': 1.0, 'f1': 0.8947368421052632, 'number': 17} | {'precision': 0.7567567567567568, 'recall': 0.875, 'f1': 0.8115942028985507, 'number': 32} | {'precision': 0.8636363636363636, 'recall': 0.95, 'f1': 0.9047619047619048, 'number': 20} | {'precision': 0.9841269841269841, 'recall': 0.9117647058823529, 'f1': 0.9465648854961831, 'number': 68} | {'precision': 1.0, 'recall': 0.8571428571428571, 'f1': 0.923076923076923, 'number': 7} | {'precision': 0.7777777777777778, 'recall': 0.875, 'f1': 0.823529411764706, 'number': 8} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 12} | {'precision': 0.8666666666666667, 'recall': 0.9420289855072463, 'f1': 0.9027777777777778, 'number': 69} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 45} | {'precision': 0.9710144927536232, 'recall': 0.9436619718309859, 'f1': 0.9571428571428571, 'number': 71} | {'precision': 0.9508196721311475, 'recall': 0.9666666666666667, 'f1': 0.9586776859504132, 'number': 60} | {'precision': 0.9333333333333333, 'recall': 0.875, 'f1': 0.9032258064516129, 'number': 16} | {'precision': 0.3333333333333333, 'recall': 0.5, 'f1': 0.4, 'number': 2} | {'precision': 0.9354838709677419, 'recall': 0.9666666666666667, 'f1': 0.9508196721311476, 'number': 30} | {'precision': 0.8571428571428571, 'recall': 0.75, 'f1': 0.7999999999999999, 'number': 8} | {'precision': 0.5, 'recall': 0.25, 'f1': 0.3333333333333333, 'number': 4} | {'precision': 0.9587628865979382, 'recall': 0.9393939393939394, 'f1': 0.9489795918367346, 'number': 99} | 0.9390 | 0.9490 | 0.9440 | 0.9555 |
| 0.0301 | 10.0 | 1000 | 0.2283 | {'precision': 0.9864253393665159, 'recall': 0.9688888888888889, 'f1': 0.9775784753363229, 'number': 225} | {'precision': 0.6666666666666666, 'recall': 0.6, 'f1': 0.631578947368421, 'number': 10} | {'precision': 0.94921875, 'recall': 0.9642857142857143, 'f1': 0.9566929133858267, 'number': 252} | {'precision': 0.9090909090909091, 'recall': 0.9090909090909091, 'f1': 0.9090909090909091, 'number': 11} | {'precision': 0.9722222222222222, 'recall': 0.9879032258064516, 'f1': 0.98, 'number': 248} | {'precision': 0.7727272727272727, 'recall': 1.0, 'f1': 0.8717948717948718, 'number': 17} | {'precision': 0.6585365853658537, 'recall': 0.84375, 'f1': 0.7397260273972602, 'number': 32} | {'precision': 0.9047619047619048, 'recall': 0.95, 'f1': 0.9268292682926829, 'number': 20} | {'precision': 0.9705882352941176, 'recall': 0.9705882352941176, 'f1': 0.9705882352941176, 'number': 68} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 7} | {'precision': 0.7777777777777778, 'recall': 0.875, 'f1': 0.823529411764706, 'number': 8} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 12} | {'precision': 0.9710144927536232, 'recall': 0.9710144927536232, 'f1': 0.9710144927536232, 'number': 69} | {'precision': 0.9777777777777777, 'recall': 0.9777777777777777, 'f1': 0.9777777777777777, 'number': 45} | {'precision': 0.9402985074626866, 'recall': 0.8873239436619719, 'f1': 0.9130434782608696, 'number': 71} | {'precision': 0.9833333333333333, 'recall': 0.9833333333333333, 'f1': 0.9833333333333333, 'number': 60} | {'precision': 0.875, 'recall': 0.875, 'f1': 0.875, 'number': 16} | {'precision': 0.3333333333333333, 'recall': 0.5, 'f1': 0.4, 'number': 2} | {'precision': 0.9354838709677419, 'recall': 0.9666666666666667, 'f1': 0.9508196721311476, 'number': 30} | {'precision': 0.8571428571428571, 'recall': 0.75, 'f1': 0.7999999999999999, 'number': 8} | {'precision': 0.25, 'recall': 0.25, 'f1': 0.25, 'number': 4} | {'precision': 0.9489795918367347, 'recall': 0.9393939393939394, 'f1': 0.9441624365482234, 'number': 99} | 0.9436 | 0.9543 | 0.9489 | 0.9627 |
| 0.0256 | 12.0 | 1200 | 0.2130 | {'precision': 0.9774774774774775, 'recall': 0.9644444444444444, 'f1': 0.970917225950783, 'number': 225} | {'precision': 0.8, 'recall': 0.8, 'f1': 0.8000000000000002, 'number': 10} | {'precision': 0.9346153846153846, 'recall': 0.9642857142857143, 'f1': 0.9492187500000001, 'number': 252} | {'precision': 0.6875, 'recall': 1.0, 'f1': 0.8148148148148148, 'number': 11} | {'precision': 0.94921875, 'recall': 0.9798387096774194, 'f1': 0.9642857142857142, 'number': 248} | {'precision': 0.8421052631578947, 'recall': 0.9411764705882353, 'f1': 0.8888888888888888, 'number': 17} | {'precision': 0.6578947368421053, 'recall': 0.78125, 'f1': 0.7142857142857143, 'number': 32} | {'precision': 0.9375, 'recall': 0.75, 'f1': 0.8333333333333334, 'number': 20} | {'precision': 0.9848484848484849, 'recall': 0.9558823529411765, 'f1': 0.9701492537313432, 'number': 68} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 7} | {'precision': 0.6, 'recall': 0.75, 'f1': 0.6666666666666665, 'number': 8} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 12} | {'precision': 1.0, 'recall': 0.9855072463768116, 'f1': 0.9927007299270074, 'number': 69} | {'precision': 0.9555555555555556, 'recall': 0.9555555555555556, 'f1': 0.9555555555555556, 'number': 45} | {'precision': 0.9178082191780822, 'recall': 0.9436619718309859, 'f1': 0.9305555555555556, 'number': 71} | {'precision': 0.9830508474576272, 'recall': 0.9666666666666667, 'f1': 0.9747899159663865, 'number': 60} | {'precision': 0.8125, 'recall': 0.8125, 'f1': 0.8125, 'number': 16} | {'precision': 0.3333333333333333, 'recall': 0.5, 'f1': 0.4, 'number': 2} | {'precision': 0.9354838709677419, 'recall': 0.9666666666666667, 'f1': 0.9508196721311476, 'number': 30} | {'precision': 0.8571428571428571, 'recall': 0.75, 'f1': 0.7999999999999999, 'number': 8} | {'precision': 1.0, 'recall': 0.25, 'f1': 0.4, 'number': 4} | {'precision': 0.9134615384615384, 'recall': 0.9595959595959596, 'f1': 0.9359605911330049, 'number': 99} | 0.9328 | 0.9505 | 0.9416 | 0.9601 |
| 0.0191 | 14.0 | 1400 | 0.2924 | {'precision': 0.96, 'recall': 0.96, 'f1': 0.96, 'number': 225} | {'precision': 0.5833333333333334, 'recall': 0.7, 'f1': 0.6363636363636365, 'number': 10} | {'precision': 0.9227799227799228, 'recall': 0.9484126984126984, 'f1': 0.9354207436399218, 'number': 252} | {'precision': 0.9166666666666666, 'recall': 1.0, 'f1': 0.9565217391304348, 'number': 11} | {'precision': 0.9566929133858267, 'recall': 0.9798387096774194, 'f1': 0.9681274900398407, 'number': 248} | {'precision': 0.75, 'recall': 0.8823529411764706, 'f1': 0.8108108108108107, 'number': 17} | {'precision': 0.7142857142857143, 'recall': 0.78125, 'f1': 0.7462686567164178, 'number': 32} | {'precision': 0.8947368421052632, 'recall': 0.85, 'f1': 0.8717948717948718, 'number': 20} | {'precision': 0.9848484848484849, 'recall': 0.9558823529411765, 'f1': 0.9701492537313432, 'number': 68} | {'precision': 1.0, 'recall': 0.7142857142857143, 'f1': 0.8333333333333333, 'number': 7} | {'precision': 0.7777777777777778, 'recall': 0.875, 'f1': 0.823529411764706, 'number': 8} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 12} | {'precision': 0.9852941176470589, 'recall': 0.9710144927536232, 'f1': 0.9781021897810219, 'number': 69} | {'precision': 1.0, 'recall': 0.9777777777777777, 'f1': 0.9887640449438202, 'number': 45} | {'precision': 0.9701492537313433, 'recall': 0.9154929577464789, 'f1': 0.9420289855072463, 'number': 71} | {'precision': 0.9827586206896551, 'recall': 0.95, 'f1': 0.9661016949152542, 'number': 60} | {'precision': 0.8666666666666667, 'recall': 0.8125, 'f1': 0.8387096774193549, 'number': 16} | {'precision': 0.3333333333333333, 'recall': 0.5, 'f1': 0.4, 'number': 2} | {'precision': 0.9354838709677419, 'recall': 0.9666666666666667, 'f1': 0.9508196721311476, 'number': 30} | {'precision': 0.8571428571428571, 'recall': 0.75, 'f1': 0.7999999999999999, 'number': 8} | {'precision': 0.14285714285714285, 'recall': 0.25, 'f1': 0.18181818181818182, 'number': 4} | {'precision': 0.9313725490196079, 'recall': 0.9595959595959596, 'f1': 0.945273631840796, 'number': 99} | 0.9323 | 0.9437 | 0.9380 | 0.9529 |
| 0.0134 | 16.0 | 1600 | 0.2540 | {'precision': 0.9644444444444444, 'recall': 0.9644444444444444, 'f1': 0.9644444444444444, 'number': 225} | {'precision': 0.9, 'recall': 0.9, 'f1': 0.9, 'number': 10} | {'precision': 0.9302325581395349, 'recall': 0.9523809523809523, 'f1': 0.9411764705882352, 'number': 252} | {'precision': 0.8461538461538461, 'recall': 1.0, 'f1': 0.9166666666666666, 'number': 11} | {'precision': 0.9568627450980393, 'recall': 0.9838709677419355, 'f1': 0.970178926441352, 'number': 248} | {'precision': 0.8421052631578947, 'recall': 0.9411764705882353, 'f1': 0.8888888888888888, 'number': 17} | {'precision': 0.7419354838709677, 'recall': 0.71875, 'f1': 0.7301587301587302, 'number': 32} | {'precision': 0.9, 'recall': 0.9, 'f1': 0.9, 'number': 20} | {'precision': 0.9846153846153847, 'recall': 0.9411764705882353, 'f1': 0.962406015037594, 'number': 68} | {'precision': 1.0, 'recall': 0.8571428571428571, 'f1': 0.923076923076923, 'number': 7} | {'precision': 0.75, 'recall': 0.75, 'f1': 0.75, 'number': 8} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 12} | {'precision': 0.9054054054054054, 'recall': 0.9710144927536232, 'f1': 0.937062937062937, 'number': 69} | {'precision': 0.9777777777777777, 'recall': 0.9777777777777777, 'f1': 0.9777777777777777, 'number': 45} | {'precision': 0.9696969696969697, 'recall': 0.9014084507042254, 'f1': 0.9343065693430657, 'number': 71} | {'precision': 0.9508196721311475, 'recall': 0.9666666666666667, 'f1': 0.9586776859504132, 'number': 60} | {'precision': 0.9333333333333333, 'recall': 0.875, 'f1': 0.9032258064516129, 'number': 16} | {'precision': 0.6666666666666666, 'recall': 1.0, 'f1': 0.8, 'number': 2} | {'precision': 0.9655172413793104, 'recall': 0.9333333333333333, 'f1': 0.9491525423728815, 'number': 30} | {'precision': 0.7777777777777778, 'recall': 0.875, 'f1': 0.823529411764706, 'number': 8} | {'precision': 0.3333333333333333, 'recall': 0.25, 'f1': 0.28571428571428575, 'number': 4} | {'precision': 0.95, 'recall': 0.9595959595959596, 'f1': 0.9547738693467336, 'number': 99} | 0.9390 | 0.9482 | 0.9436 | 0.9584 |
| 0.0102 | 18.0 | 1800 | 0.3239 | {'precision': 0.960352422907489, 'recall': 0.9688888888888889, 'f1': 0.9646017699115046, 'number': 225} | {'precision': 0.7, 'recall': 0.7, 'f1': 0.7, 'number': 10} | {'precision': 0.9045801526717557, 'recall': 0.9404761904761905, 'f1': 0.9221789883268483, 'number': 252} | {'precision': 0.9166666666666666, 'recall': 1.0, 'f1': 0.9565217391304348, 'number': 11} | {'precision': 0.924812030075188, 'recall': 0.9919354838709677, 'f1': 0.9571984435797665, 'number': 248} | {'precision': 0.8571428571428571, 'recall': 0.7058823529411765, 'f1': 0.7741935483870968, 'number': 17} | {'precision': 0.7931034482758621, 'recall': 0.71875, 'f1': 0.7540983606557378, 'number': 32} | {'precision': 1.0, 'recall': 0.6, 'f1': 0.7499999999999999, 'number': 20} | {'precision': 0.9696969696969697, 'recall': 0.9411764705882353, 'f1': 0.955223880597015, 'number': 68} | {'precision': 1.0, 'recall': 0.8571428571428571, 'f1': 0.923076923076923, 'number': 7} | {'precision': 0.6666666666666666, 'recall': 0.75, 'f1': 0.7058823529411765, 'number': 8} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 12} | {'precision': 0.9710144927536232, 'recall': 0.9710144927536232, 'f1': 0.9710144927536232, 'number': 69} | {'precision': 0.9574468085106383, 'recall': 1.0, 'f1': 0.9782608695652174, 'number': 45} | {'precision': 0.9428571428571428, 'recall': 0.9295774647887324, 'f1': 0.9361702127659575, 'number': 71} | {'precision': 0.9830508474576272, 'recall': 0.9666666666666667, 'f1': 0.9747899159663865, 'number': 60} | {'precision': 1.0, 'recall': 0.9375, 'f1': 0.967741935483871, 'number': 16} | {'precision': 0.25, 'recall': 0.5, 'f1': 0.3333333333333333, 'number': 2} | {'precision': 0.9354838709677419, 'recall': 0.9666666666666667, 'f1': 0.9508196721311476, 'number': 30} | {'precision': 0.8571428571428571, 'recall': 0.75, 'f1': 0.7999999999999999, 'number': 8} | {'precision': 0.3333333333333333, 'recall': 0.25, 'f1': 0.28571428571428575, 'number': 4} | {'precision': 0.9603960396039604, 'recall': 0.9797979797979798, 'f1': 0.9700000000000001, 'number': 99} | 0.9309 | 0.9429 | 0.9369 | 0.9555 |
| 0.0081 | 20.0 | 2000 | 0.2907 | {'precision': 0.9817351598173516, 'recall': 0.9555555555555556, 'f1': 0.9684684684684685, 'number': 225} | {'precision': 0.7, 'recall': 0.7, 'f1': 0.7, 'number': 10} | {'precision': 0.9409448818897638, 'recall': 0.9484126984126984, 'f1': 0.9446640316205533, 'number': 252} | {'precision': 0.9166666666666666, 'recall': 1.0, 'f1': 0.9565217391304348, 'number': 11} | {'precision': 0.9642857142857143, 'recall': 0.9798387096774194, 'f1': 0.972, 'number': 248} | {'precision': 0.7727272727272727, 'recall': 1.0, 'f1': 0.8717948717948718, 'number': 17} | {'precision': 0.6842105263157895, 'recall': 0.8125, 'f1': 0.742857142857143, 'number': 32} | {'precision': 0.8260869565217391, 'recall': 0.95, 'f1': 0.8837209302325583, 'number': 20} | {'precision': 0.9692307692307692, 'recall': 0.9264705882352942, 'f1': 0.9473684210526316, 'number': 68} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 7} | {'precision': 0.7272727272727273, 'recall': 1.0, 'f1': 0.8421052631578948, 'number': 8} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 12} | {'precision': 0.9577464788732394, 'recall': 0.9855072463768116, 'f1': 0.9714285714285714, 'number': 69} | {'precision': 1.0, 'recall': 0.9777777777777777, 'f1': 0.9887640449438202, 'number': 45} | {'precision': 0.9565217391304348, 'recall': 0.9295774647887324, 'f1': 0.9428571428571428, 'number': 71} | {'precision': 0.9672131147540983, 'recall': 0.9833333333333333, 'f1': 0.9752066115702478, 'number': 60} | {'precision': 0.9333333333333333, 'recall': 0.875, 'f1': 0.9032258064516129, 'number': 16} | {'precision': 0.5, 'recall': 0.5, 'f1': 0.5, 'number': 2} | {'precision': 0.9354838709677419, 'recall': 0.9666666666666667, 'f1': 0.9508196721311476, 'number': 30} | {'precision': 0.8571428571428571, 'recall': 0.75, 'f1': 0.7999999999999999, 'number': 8} | {'precision': 0.3333333333333333, 'recall': 0.25, 'f1': 0.28571428571428575, 'number': 4} | {'precision': 0.9591836734693877, 'recall': 0.9494949494949495, 'f1': 0.9543147208121828, 'number': 99} | 0.9419 | 0.9505 | 0.9462 | 0.9597 |
| 0.0049 | 22.0 | 2200 | 0.3056 | {'precision': 1.0, 'recall': 0.9644444444444444, 'f1': 0.9819004524886877, 'number': 225} | {'precision': 0.5714285714285714, 'recall': 0.4, 'f1': 0.47058823529411764, 'number': 10} | {'precision': 0.9486166007905138, 'recall': 0.9523809523809523, 'f1': 0.9504950495049505, 'number': 252} | {'precision': 0.9166666666666666, 'recall': 1.0, 'f1': 0.9565217391304348, 'number': 11} | {'precision': 0.9566929133858267, 'recall': 0.9798387096774194, 'f1': 0.9681274900398407, 'number': 248} | {'precision': 0.7727272727272727, 'recall': 1.0, 'f1': 0.8717948717948718, 'number': 17} | {'precision': 0.6829268292682927, 'recall': 0.875, 'f1': 0.767123287671233, 'number': 32} | {'precision': 0.9, 'recall': 0.9, 'f1': 0.9, 'number': 20} | {'precision': 0.9848484848484849, 'recall': 0.9558823529411765, 'f1': 0.9701492537313432, 'number': 68} | {'precision': 0.875, 'recall': 1.0, 'f1': 0.9333333333333333, 'number': 7} | {'precision': 0.75, 'recall': 0.75, 'f1': 0.75, 'number': 8} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 12} | {'precision': 0.9577464788732394, 'recall': 0.9855072463768116, 'f1': 0.9714285714285714, 'number': 69} | {'precision': 0.9361702127659575, 'recall': 0.9777777777777777, 'f1': 0.9565217391304347, 'number': 45} | {'precision': 0.9558823529411765, 'recall': 0.9154929577464789, 'f1': 0.9352517985611511, 'number': 71} | {'precision': 0.9655172413793104, 'recall': 0.9333333333333333, 'f1': 0.9491525423728815, 'number': 60} | {'precision': 0.9375, 'recall': 0.9375, 'f1': 0.9375, 'number': 16} | {'precision': 0.5, 'recall': 1.0, 'f1': 0.6666666666666666, 'number': 2} | {'precision': 0.9354838709677419, 'recall': 0.9666666666666667, 'f1': 0.9508196721311476, 'number': 30} | {'precision': 0.8571428571428571, 'recall': 0.75, 'f1': 0.7999999999999999, 'number': 8} | {'precision': 1.0, 'recall': 0.25, 'f1': 0.4, 'number': 4} | {'precision': 0.95, 'recall': 0.9595959595959596, 'f1': 0.9547738693467336, 'number': 99} | 0.9441 | 0.9505 | 0.9473 | 0.9576 |
| 0.0053 | 24.0 | 2400 | 0.2749 | {'precision': 0.9818181818181818, 'recall': 0.96, 'f1': 0.9707865168539325, 'number': 225} | {'precision': 0.6666666666666666, 'recall': 0.6, 'f1': 0.631578947368421, 'number': 10} | {'precision': 0.937007874015748, 'recall': 0.9444444444444444, 'f1': 0.9407114624505929, 'number': 252} | {'precision': 0.9090909090909091, 'recall': 0.9090909090909091, 'f1': 0.9090909090909091, 'number': 11} | {'precision': 0.9681274900398407, 'recall': 0.9798387096774194, 'f1': 0.9739478957915831, 'number': 248} | {'precision': 0.7727272727272727, 'recall': 1.0, 'f1': 0.8717948717948718, 'number': 17} | {'precision': 0.7058823529411765, 'recall': 0.75, 'f1': 0.7272727272727272, 'number': 32} | {'precision': 0.9047619047619048, 'recall': 0.95, 'f1': 0.9268292682926829, 'number': 20} | {'precision': 0.9692307692307692, 'recall': 0.9264705882352942, 'f1': 0.9473684210526316, 'number': 68} | {'precision': 1.0, 'recall': 0.8571428571428571, 'f1': 0.923076923076923, 'number': 7} | {'precision': 0.75, 'recall': 0.75, 'f1': 0.75, 'number': 8} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 12} | {'precision': 0.9315068493150684, 'recall': 0.9855072463768116, 'f1': 0.9577464788732394, 'number': 69} | {'precision': 0.9361702127659575, 'recall': 0.9777777777777777, 'f1': 0.9565217391304347, 'number': 45} | {'precision': 0.9558823529411765, 'recall': 0.9154929577464789, 'f1': 0.9352517985611511, 'number': 71} | {'precision': 0.9508196721311475, 'recall': 0.9666666666666667, 'f1': 0.9586776859504132, 'number': 60} | {'precision': 1.0, 'recall': 0.9375, 'f1': 0.967741935483871, 'number': 16} | {'precision': 0.2, 'recall': 0.5, 'f1': 0.28571428571428575, 'number': 2} | {'precision': 0.9354838709677419, 'recall': 0.9666666666666667, 'f1': 0.9508196721311476, 'number': 30} | {'precision': 0.8571428571428571, 'recall': 0.75, 'f1': 0.7999999999999999, 'number': 8} | {'precision': 0.5, 'recall': 0.25, 'f1': 0.3333333333333333, 'number': 4} | {'precision': 0.9405940594059405, 'recall': 0.9595959595959596, 'f1': 0.95, 'number': 99} | 0.9388 | 0.9452 | 0.9420 | 0.9576 |
| 0.0037 | 26.0 | 2600 | 0.3206 | {'precision': 0.972972972972973, 'recall': 0.96, 'f1': 0.9664429530201343, 'number': 225} | {'precision': 0.7, 'recall': 0.7, 'f1': 0.7, 'number': 10} | {'precision': 0.9325396825396826, 'recall': 0.9325396825396826, 'f1': 0.9325396825396827, 'number': 252} | {'precision': 0.9166666666666666, 'recall': 1.0, 'f1': 0.9565217391304348, 'number': 11} | {'precision': 0.9681274900398407, 'recall': 0.9798387096774194, 'f1': 0.9739478957915831, 'number': 248} | {'precision': 0.7727272727272727, 'recall': 1.0, 'f1': 0.8717948717948718, 'number': 17} | {'precision': 0.6944444444444444, 'recall': 0.78125, 'f1': 0.7352941176470588, 'number': 32} | {'precision': 0.9047619047619048, 'recall': 0.95, 'f1': 0.9268292682926829, 'number': 20} | {'precision': 0.9846153846153847, 'recall': 0.9411764705882353, 'f1': 0.962406015037594, 'number': 68} | {'precision': 0.875, 'recall': 1.0, 'f1': 0.9333333333333333, 'number': 7} | {'precision': 0.75, 'recall': 0.75, 'f1': 0.75, 'number': 8} | {'precision': 0.9230769230769231, 'recall': 1.0, 'f1': 0.9600000000000001, 'number': 12} | {'precision': 0.918918918918919, 'recall': 0.9855072463768116, 'f1': 0.951048951048951, 'number': 69} | {'precision': 0.9361702127659575, 'recall': 0.9777777777777777, 'f1': 0.9565217391304347, 'number': 45} | {'precision': 0.9571428571428572, 'recall': 0.9436619718309859, 'f1': 0.9503546099290779, 'number': 71} | {'precision': 0.9836065573770492, 'recall': 1.0, 'f1': 0.9917355371900827, 'number': 60} | {'precision': 0.9375, 'recall': 0.9375, 'f1': 0.9375, 'number': 16} | {'precision': 0.3333333333333333, 'recall': 0.5, 'f1': 0.4, 'number': 2} | {'precision': 0.9354838709677419, 'recall': 0.9666666666666667, 'f1': 0.9508196721311476, 'number': 30} | {'precision': 0.8571428571428571, 'recall': 0.75, 'f1': 0.7999999999999999, 'number': 8} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 4} | {'precision': 0.9895833333333334, 'recall': 0.9595959595959596, 'f1': 0.9743589743589745, 'number': 99} | 0.9404 | 0.9490 | 0.9447 | 0.9580 |
| 0.0036 | 28.0 | 2800 | 0.3444 | {'precision': 0.9773755656108597, 'recall': 0.96, 'f1': 0.9686098654708519, 'number': 225} | {'precision': 0.6666666666666666, 'recall': 0.6, 'f1': 0.631578947368421, 'number': 10} | {'precision': 0.9444444444444444, 'recall': 0.9444444444444444, 'f1': 0.9444444444444444, 'number': 252} | {'precision': 0.9166666666666666, 'recall': 1.0, 'f1': 0.9565217391304348, 'number': 11} | {'precision': 0.9642857142857143, 'recall': 0.9798387096774194, 'f1': 0.972, 'number': 248} | {'precision': 0.7727272727272727, 'recall': 1.0, 'f1': 0.8717948717948718, 'number': 17} | {'precision': 0.7222222222222222, 'recall': 0.8125, 'f1': 0.7647058823529411, 'number': 32} | {'precision': 0.8636363636363636, 'recall': 0.95, 'f1': 0.9047619047619048, 'number': 20} | {'precision': 0.984375, 'recall': 0.9264705882352942, 'f1': 0.9545454545454545, 'number': 68} | {'precision': 1.0, 'recall': 0.8571428571428571, 'f1': 0.923076923076923, 'number': 7} | {'precision': 0.8888888888888888, 'recall': 1.0, 'f1': 0.9411764705882353, 'number': 8} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 12} | {'precision': 0.9305555555555556, 'recall': 0.9710144927536232, 'f1': 0.9503546099290779, 'number': 69} | {'precision': 0.9361702127659575, 'recall': 0.9777777777777777, 'f1': 0.9565217391304347, 'number': 45} | {'precision': 0.9850746268656716, 'recall': 0.9295774647887324, 'f1': 0.9565217391304348, 'number': 71} | {'precision': 0.9672131147540983, 'recall': 0.9833333333333333, 'f1': 0.9752066115702478, 'number': 60} | {'precision': 0.9333333333333333, 'recall': 0.875, 'f1': 0.9032258064516129, 'number': 16} | {'precision': 0.6666666666666666, 'recall': 1.0, 'f1': 0.8, 'number': 2} | {'precision': 0.9354838709677419, 'recall': 0.9666666666666667, 'f1': 0.9508196721311476, 'number': 30} | {'precision': 0.8571428571428571, 'recall': 0.75, 'f1': 0.7999999999999999, 'number': 8} | {'precision': 0.3333333333333333, 'recall': 0.25, 'f1': 0.28571428571428575, 'number': 4} | {'precision': 0.9595959595959596, 'recall': 0.9595959595959596, 'f1': 0.9595959595959596, 'number': 99} | 0.9440 | 0.9498 | 0.9469 | 0.9559 |
| 0.0048 | 30.0 | 3000 | 0.2944 | {'precision': 0.9818181818181818, 'recall': 0.96, 'f1': 0.9707865168539325, 'number': 225} | {'precision': 0.6666666666666666, 'recall': 0.6, 'f1': 0.631578947368421, 'number': 10} | {'precision': 0.93359375, 'recall': 0.9484126984126984, 'f1': 0.9409448818897638, 'number': 252} | {'precision': 0.9166666666666666, 'recall': 1.0, 'f1': 0.9565217391304348, 'number': 11} | {'precision': 0.9607843137254902, 'recall': 0.9879032258064516, 'f1': 0.974155069582505, 'number': 248} | {'precision': 0.7727272727272727, 'recall': 1.0, 'f1': 0.8717948717948718, 'number': 17} | {'precision': 0.6944444444444444, 'recall': 0.78125, 'f1': 0.7352941176470588, 'number': 32} | {'precision': 0.9473684210526315, 'recall': 0.9, 'f1': 0.9230769230769231, 'number': 20} | {'precision': 0.9846153846153847, 'recall': 0.9411764705882353, 'f1': 0.962406015037594, 'number': 68} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 7} | {'precision': 0.8888888888888888, 'recall': 1.0, 'f1': 0.9411764705882353, 'number': 8} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 12} | {'precision': 0.9857142857142858, 'recall': 1.0, 'f1': 0.9928057553956835, 'number': 69} | {'precision': 0.9777777777777777, 'recall': 0.9777777777777777, 'f1': 0.9777777777777777, 'number': 45} | {'precision': 0.9714285714285714, 'recall': 0.9577464788732394, 'f1': 0.9645390070921985, 'number': 71} | {'precision': 0.9836065573770492, 'recall': 1.0, 'f1': 0.9917355371900827, 'number': 60} | {'precision': 0.9375, 'recall': 0.9375, 'f1': 0.9375, 'number': 16} | {'precision': 0.3333333333333333, 'recall': 0.5, 'f1': 0.4, 'number': 2} | {'precision': 0.9354838709677419, 'recall': 0.9666666666666667, 'f1': 0.9508196721311476, 'number': 30} | {'precision': 0.8571428571428571, 'recall': 0.75, 'f1': 0.7999999999999999, 'number': 8} | {'precision': 0.5, 'recall': 0.25, 'f1': 0.3333333333333333, 'number': 4} | {'precision': 0.9696969696969697, 'recall': 0.9696969696969697, 'f1': 0.9696969696969697, 'number': 99} | 0.9480 | 0.9566 | 0.9523 | 0.9640 |
| 0.002 | 32.0 | 3200 | 0.3073 | {'precision': 0.9863636363636363, 'recall': 0.9644444444444444, 'f1': 0.9752808988764046, 'number': 225} | {'precision': 0.8888888888888888, 'recall': 0.8, 'f1': 0.8421052631578948, 'number': 10} | {'precision': 0.9260700389105059, 'recall': 0.9444444444444444, 'f1': 0.9351669941060904, 'number': 252} | {'precision': 0.8461538461538461, 'recall': 1.0, 'f1': 0.9166666666666666, 'number': 11} | {'precision': 0.953125, 'recall': 0.9838709677419355, 'f1': 0.9682539682539683, 'number': 248} | {'precision': 0.7727272727272727, 'recall': 1.0, 'f1': 0.8717948717948718, 'number': 17} | {'precision': 0.75, 'recall': 0.75, 'f1': 0.75, 'number': 32} | {'precision': 0.9047619047619048, 'recall': 0.95, 'f1': 0.9268292682926829, 'number': 20} | {'precision': 0.984375, 'recall': 0.9264705882352942, 'f1': 0.9545454545454545, 'number': 68} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 7} | {'precision': 0.875, 'recall': 0.875, 'f1': 0.875, 'number': 8} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 12} | {'precision': 0.9444444444444444, 'recall': 0.9855072463768116, 'f1': 0.9645390070921985, 'number': 69} | {'precision': 0.9565217391304348, 'recall': 0.9777777777777777, 'f1': 0.967032967032967, 'number': 45} | {'precision': 0.9852941176470589, 'recall': 0.9436619718309859, 'f1': 0.9640287769784172, 'number': 71} | {'precision': 0.9836065573770492, 'recall': 1.0, 'f1': 0.9917355371900827, 'number': 60} | {'precision': 0.875, 'recall': 0.875, 'f1': 0.875, 'number': 16} | {'precision': 0.6666666666666666, 'recall': 1.0, 'f1': 0.8, 'number': 2} | {'precision': 0.9354838709677419, 'recall': 0.9666666666666667, 'f1': 0.9508196721311476, 'number': 30} | {'precision': 0.8571428571428571, 'recall': 0.75, 'f1': 0.7999999999999999, 'number': 8} | {'precision': 0.5, 'recall': 0.25, 'f1': 0.3333333333333333, 'number': 4} | {'precision': 0.9696969696969697, 'recall': 0.9696969696969697, 'f1': 0.9696969696969697, 'number': 99} | 0.9457 | 0.9543 | 0.95 | 0.9610 |
| 0.0018 | 34.0 | 3400 | 0.2586 | {'precision': 0.9819819819819819, 'recall': 0.9688888888888889, 'f1': 0.9753914988814317, 'number': 225} | {'precision': 0.7777777777777778, 'recall': 0.7, 'f1': 0.7368421052631577, 'number': 10} | {'precision': 0.9294117647058824, 'recall': 0.9404761904761905, 'f1': 0.9349112426035503, 'number': 252} | {'precision': 0.9166666666666666, 'recall': 1.0, 'f1': 0.9565217391304348, 'number': 11} | {'precision': 0.9606299212598425, 'recall': 0.9838709677419355, 'f1': 0.9721115537848605, 'number': 248} | {'precision': 0.8095238095238095, 'recall': 1.0, 'f1': 0.8947368421052632, 'number': 17} | {'precision': 0.6857142857142857, 'recall': 0.75, 'f1': 0.7164179104477612, 'number': 32} | {'precision': 0.9047619047619048, 'recall': 0.95, 'f1': 0.9268292682926829, 'number': 20} | {'precision': 0.984375, 'recall': 0.9264705882352942, 'f1': 0.9545454545454545, 'number': 68} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 7} | {'precision': 0.7777777777777778, 'recall': 0.875, 'f1': 0.823529411764706, 'number': 8} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 12} | {'precision': 0.9855072463768116, 'recall': 0.9855072463768116, 'f1': 0.9855072463768116, 'number': 69} | {'precision': 0.9777777777777777, 'recall': 0.9777777777777777, 'f1': 0.9777777777777777, 'number': 45} | {'precision': 0.9571428571428572, 'recall': 0.9436619718309859, 'f1': 0.9503546099290779, 'number': 71} | {'precision': 0.967741935483871, 'recall': 1.0, 'f1': 0.9836065573770492, 'number': 60} | {'precision': 1.0, 'recall': 0.9375, 'f1': 0.967741935483871, 'number': 16} | {'precision': 0.3333333333333333, 'recall': 0.5, 'f1': 0.4, 'number': 2} | {'precision': 0.9354838709677419, 'recall': 0.9666666666666667, 'f1': 0.9508196721311476, 'number': 30} | {'precision': 0.8571428571428571, 'recall': 0.75, 'f1': 0.7999999999999999, 'number': 8} | {'precision': 0.5, 'recall': 0.25, 'f1': 0.3333333333333333, 'number': 4} | {'precision': 0.9504950495049505, 'recall': 0.9696969696969697, 'f1': 0.96, 'number': 99} | 0.9449 | 0.9536 | 0.9492 | 0.9627 |
| 0.0008 | 36.0 | 3600 | 0.2687 | {'precision': 0.9864253393665159, 'recall': 0.9688888888888889, 'f1': 0.9775784753363229, 'number': 225} | {'precision': 0.8, 'recall': 0.8, 'f1': 0.8000000000000002, 'number': 10} | {'precision': 0.9333333333333333, 'recall': 0.9444444444444444, 'f1': 0.9388560157790926, 'number': 252} | {'precision': 0.9166666666666666, 'recall': 1.0, 'f1': 0.9565217391304348, 'number': 11} | {'precision': 0.9606299212598425, 'recall': 0.9838709677419355, 'f1': 0.9721115537848605, 'number': 248} | {'precision': 0.8095238095238095, 'recall': 1.0, 'f1': 0.8947368421052632, 'number': 17} | {'precision': 0.7575757575757576, 'recall': 0.78125, 'f1': 0.7692307692307692, 'number': 32} | {'precision': 0.9047619047619048, 'recall': 0.95, 'f1': 0.9268292682926829, 'number': 20} | {'precision': 0.9846153846153847, 'recall': 0.9411764705882353, 'f1': 0.962406015037594, 'number': 68} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 7} | {'precision': 0.7777777777777778, 'recall': 0.875, 'f1': 0.823529411764706, 'number': 8} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 12} | {'precision': 0.971830985915493, 'recall': 1.0, 'f1': 0.9857142857142858, 'number': 69} | {'precision': 0.9777777777777777, 'recall': 0.9777777777777777, 'f1': 0.9777777777777777, 'number': 45} | {'precision': 0.9705882352941176, 'recall': 0.9295774647887324, 'f1': 0.9496402877697842, 'number': 71} | {'precision': 0.9523809523809523, 'recall': 1.0, 'f1': 0.975609756097561, 'number': 60} | {'precision': 0.8823529411764706, 'recall': 0.9375, 'f1': 0.9090909090909091, 'number': 16} | {'precision': 0.6666666666666666, 'recall': 1.0, 'f1': 0.8, 'number': 2} | {'precision': 0.9354838709677419, 'recall': 0.9666666666666667, 'f1': 0.9508196721311476, 'number': 30} | {'precision': 0.8571428571428571, 'recall': 0.75, 'f1': 0.7999999999999999, 'number': 8} | {'precision': 0.5, 'recall': 0.25, 'f1': 0.3333333333333333, 'number': 4} | {'precision': 0.9693877551020408, 'recall': 0.9595959595959596, 'f1': 0.964467005076142, 'number': 99} | 0.9487 | 0.9566 | 0.9526 | 0.9644 |
| 0.001 | 38.0 | 3800 | 0.2764 | {'precision': 0.9819819819819819, 'recall': 0.9688888888888889, 'f1': 0.9753914988814317, 'number': 225} | {'precision': 0.7777777777777778, 'recall': 0.7, 'f1': 0.7368421052631577, 'number': 10} | {'precision': 0.9294117647058824, 'recall': 0.9404761904761905, 'f1': 0.9349112426035503, 'number': 252} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 11} | {'precision': 0.9645669291338582, 'recall': 0.9879032258064516, 'f1': 0.9760956175298804, 'number': 248} | {'precision': 0.8095238095238095, 'recall': 1.0, 'f1': 0.8947368421052632, 'number': 17} | {'precision': 0.6578947368421053, 'recall': 0.78125, 'f1': 0.7142857142857143, 'number': 32} | {'precision': 0.8636363636363636, 'recall': 0.95, 'f1': 0.9047619047619048, 'number': 20} | {'precision': 0.9692307692307692, 'recall': 0.9264705882352942, 'f1': 0.9473684210526316, 'number': 68} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 7} | {'precision': 0.875, 'recall': 0.875, 'f1': 0.875, 'number': 8} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 12} | {'precision': 0.971830985915493, 'recall': 1.0, 'f1': 0.9857142857142858, 'number': 69} | {'precision': 0.9777777777777777, 'recall': 0.9777777777777777, 'f1': 0.9777777777777777, 'number': 45} | {'precision': 0.9852941176470589, 'recall': 0.9436619718309859, 'f1': 0.9640287769784172, 'number': 71} | {'precision': 0.9836065573770492, 'recall': 1.0, 'f1': 0.9917355371900827, 'number': 60} | {'precision': 1.0, 'recall': 0.9375, 'f1': 0.967741935483871, 'number': 16} | {'precision': 0.5, 'recall': 1.0, 'f1': 0.6666666666666666, 'number': 2} | {'precision': 0.9354838709677419, 'recall': 0.9666666666666667, 'f1': 0.9508196721311476, 'number': 30} | {'precision': 0.8571428571428571, 'recall': 0.75, 'f1': 0.7999999999999999, 'number': 8} | {'precision': 0.3333333333333333, 'recall': 0.25, 'f1': 0.28571428571428575, 'number': 4} | {'precision': 0.9696969696969697, 'recall': 0.9696969696969697, 'f1': 0.9696969696969697, 'number': 99} | 0.9465 | 0.9566 | 0.9516 | 0.9648 |
| 0.0003 | 40.0 | 4000 | 0.3192 | {'precision': 0.9819819819819819, 'recall': 0.9688888888888889, 'f1': 0.9753914988814317, 'number': 225} | {'precision': 0.7777777777777778, 'recall': 0.7, 'f1': 0.7368421052631577, 'number': 10} | {'precision': 0.9372549019607843, 'recall': 0.9484126984126984, 'f1': 0.942800788954635, 'number': 252} | {'precision': 0.9166666666666666, 'recall': 1.0, 'f1': 0.9565217391304348, 'number': 11} | {'precision': 0.9644268774703557, 'recall': 0.9838709677419355, 'f1': 0.9740518962075848, 'number': 248} | {'precision': 0.8095238095238095, 'recall': 1.0, 'f1': 0.8947368421052632, 'number': 17} | {'precision': 0.6428571428571429, 'recall': 0.84375, 'f1': 0.7297297297297298, 'number': 32} | {'precision': 0.8636363636363636, 'recall': 0.95, 'f1': 0.9047619047619048, 'number': 20} | {'precision': 0.9692307692307692, 'recall': 0.9264705882352942, 'f1': 0.9473684210526316, 'number': 68} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 7} | {'precision': 0.875, 'recall': 0.875, 'f1': 0.875, 'number': 8} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 12} | {'precision': 0.9577464788732394, 'recall': 0.9855072463768116, 'f1': 0.9714285714285714, 'number': 69} | {'precision': 0.9361702127659575, 'recall': 0.9777777777777777, 'f1': 0.9565217391304347, 'number': 45} | {'precision': 0.9852941176470589, 'recall': 0.9436619718309859, 'f1': 0.9640287769784172, 'number': 71} | {'precision': 0.9836065573770492, 'recall': 1.0, 'f1': 0.9917355371900827, 'number': 60} | {'precision': 0.9375, 'recall': 0.9375, 'f1': 0.9375, 'number': 16} | {'precision': 0.5, 'recall': 1.0, 'f1': 0.6666666666666666, 'number': 2} | {'precision': 0.9354838709677419, 'recall': 0.9666666666666667, 'f1': 0.9508196721311476, 'number': 30} | {'precision': 0.8571428571428571, 'recall': 0.75, 'f1': 0.7999999999999999, 'number': 8} | {'precision': 0.5, 'recall': 0.25, 'f1': 0.3333333333333333, 'number': 4} | {'precision': 0.9795918367346939, 'recall': 0.9696969696969697, 'f1': 0.9746192893401016, 'number': 99} | 0.9445 | 0.9581 | 0.9513 | 0.9597 |
| 0.0005 | 42.0 | 4200 | 0.3063 | {'precision': 0.9774774774774775, 'recall': 0.9644444444444444, 'f1': 0.970917225950783, 'number': 225} | {'precision': 0.6666666666666666, 'recall': 0.6, 'f1': 0.631578947368421, 'number': 10} | {'precision': 0.9294117647058824, 'recall': 0.9404761904761905, 'f1': 0.9349112426035503, 'number': 252} | {'precision': 0.9166666666666666, 'recall': 1.0, 'f1': 0.9565217391304348, 'number': 11} | {'precision': 0.976, 'recall': 0.9838709677419355, 'f1': 0.9799196787148594, 'number': 248} | {'precision': 0.8095238095238095, 'recall': 1.0, 'f1': 0.8947368421052632, 'number': 17} | {'precision': 0.6666666666666666, 'recall': 0.75, 'f1': 0.7058823529411765, 'number': 32} | {'precision': 0.8636363636363636, 'recall': 0.95, 'f1': 0.9047619047619048, 'number': 20} | {'precision': 0.9701492537313433, 'recall': 0.9558823529411765, 'f1': 0.962962962962963, 'number': 68} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 7} | {'precision': 0.875, 'recall': 0.875, 'f1': 0.875, 'number': 8} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 12} | {'precision': 0.9583333333333334, 'recall': 1.0, 'f1': 0.9787234042553191, 'number': 69} | {'precision': 0.9565217391304348, 'recall': 0.9777777777777777, 'f1': 0.967032967032967, 'number': 45} | {'precision': 0.9855072463768116, 'recall': 0.9577464788732394, 'f1': 0.9714285714285714, 'number': 71} | {'precision': 0.9836065573770492, 'recall': 1.0, 'f1': 0.9917355371900827, 'number': 60} | {'precision': 1.0, 'recall': 0.9375, 'f1': 0.967741935483871, 'number': 16} | {'precision': 0.5, 'recall': 1.0, 'f1': 0.6666666666666666, 'number': 2} | {'precision': 0.9666666666666667, 'recall': 0.9666666666666667, 'f1': 0.9666666666666667, 'number': 30} | {'precision': 0.8571428571428571, 'recall': 0.75, 'f1': 0.7999999999999999, 'number': 8} | {'precision': 0.5, 'recall': 0.25, 'f1': 0.3333333333333333, 'number': 4} | {'precision': 0.9696969696969697, 'recall': 0.9696969696969697, 'f1': 0.9696969696969697, 'number': 99} | 0.9472 | 0.9559 | 0.9515 | 0.9623 |
| 0.0005 | 44.0 | 4400 | 0.3303 | {'precision': 0.9819819819819819, 'recall': 0.9688888888888889, 'f1': 0.9753914988814317, 'number': 225} | {'precision': 0.6666666666666666, 'recall': 0.6, 'f1': 0.631578947368421, 'number': 10} | {'precision': 0.9294117647058824, 'recall': 0.9404761904761905, 'f1': 0.9349112426035503, 'number': 252} | {'precision': 0.9166666666666666, 'recall': 1.0, 'f1': 0.9565217391304348, 'number': 11} | {'precision': 0.9568627450980393, 'recall': 0.9838709677419355, 'f1': 0.970178926441352, 'number': 248} | {'precision': 0.8095238095238095, 'recall': 1.0, 'f1': 0.8947368421052632, 'number': 17} | {'precision': 0.71875, 'recall': 0.71875, 'f1': 0.71875, 'number': 32} | {'precision': 0.8947368421052632, 'recall': 0.85, 'f1': 0.8717948717948718, 'number': 20} | {'precision': 0.9692307692307692, 'recall': 0.9264705882352942, 'f1': 0.9473684210526316, 'number': 68} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 7} | {'precision': 0.875, 'recall': 0.875, 'f1': 0.875, 'number': 8} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 12} | {'precision': 0.9577464788732394, 'recall': 0.9855072463768116, 'f1': 0.9714285714285714, 'number': 69} | {'precision': 0.9361702127659575, 'recall': 0.9777777777777777, 'f1': 0.9565217391304347, 'number': 45} | {'precision': 0.9857142857142858, 'recall': 0.971830985915493, 'f1': 0.9787234042553192, 'number': 71} | {'precision': 0.9836065573770492, 'recall': 1.0, 'f1': 0.9917355371900827, 'number': 60} | {'precision': 1.0, 'recall': 0.9375, 'f1': 0.967741935483871, 'number': 16} | {'precision': 0.6666666666666666, 'recall': 1.0, 'f1': 0.8, 'number': 2} | {'precision': 0.9354838709677419, 'recall': 0.9666666666666667, 'f1': 0.9508196721311476, 'number': 30} | {'precision': 0.8571428571428571, 'recall': 0.75, 'f1': 0.7999999999999999, 'number': 8} | {'precision': 0.5, 'recall': 0.25, 'f1': 0.3333333333333333, 'number': 4} | {'precision': 0.9696969696969697, 'recall': 0.9696969696969697, 'f1': 0.9696969696969697, 'number': 99} | 0.9463 | 0.9528 | 0.9496 | 0.9601 |
| 0.0008 | 46.0 | 4600 | 0.3244 | {'precision': 0.9819819819819819, 'recall': 0.9688888888888889, 'f1': 0.9753914988814317, 'number': 225} | {'precision': 0.6666666666666666, 'recall': 0.6, 'f1': 0.631578947368421, 'number': 10} | {'precision': 0.9294117647058824, 'recall': 0.9404761904761905, 'f1': 0.9349112426035503, 'number': 252} | {'precision': 0.9166666666666666, 'recall': 1.0, 'f1': 0.9565217391304348, 'number': 11} | {'precision': 0.9606299212598425, 'recall': 0.9838709677419355, 'f1': 0.9721115537848605, 'number': 248} | {'precision': 0.8095238095238095, 'recall': 1.0, 'f1': 0.8947368421052632, 'number': 17} | {'precision': 0.6764705882352942, 'recall': 0.71875, 'f1': 0.696969696969697, 'number': 32} | {'precision': 0.9, 'recall': 0.9, 'f1': 0.9, 'number': 20} | {'precision': 0.9692307692307692, 'recall': 0.9264705882352942, 'f1': 0.9473684210526316, 'number': 68} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 7} | {'precision': 0.875, 'recall': 0.875, 'f1': 0.875, 'number': 8} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 12} | {'precision': 0.9577464788732394, 'recall': 0.9855072463768116, 'f1': 0.9714285714285714, 'number': 69} | {'precision': 0.9361702127659575, 'recall': 0.9777777777777777, 'f1': 0.9565217391304347, 'number': 45} | {'precision': 0.971830985915493, 'recall': 0.971830985915493, 'f1': 0.971830985915493, 'number': 71} | {'precision': 0.9833333333333333, 'recall': 0.9833333333333333, 'f1': 0.9833333333333333, 'number': 60} | {'precision': 1.0, 'recall': 0.9375, 'f1': 0.967741935483871, 'number': 16} | {'precision': 0.6666666666666666, 'recall': 1.0, 'f1': 0.8, 'number': 2} | {'precision': 0.9354838709677419, 'recall': 0.9666666666666667, 'f1': 0.9508196721311476, 'number': 30} | {'precision': 0.8571428571428571, 'recall': 0.75, 'f1': 0.7999999999999999, 'number': 8} | {'precision': 1.0, 'recall': 0.25, 'f1': 0.4, 'number': 4} | {'precision': 0.9696969696969697, 'recall': 0.9696969696969697, 'f1': 0.9696969696969697, 'number': 99} | 0.9456 | 0.9528 | 0.9492 | 0.9614 |
| 0.0005 | 48.0 | 4800 | 0.3273 | {'precision': 0.9775784753363229, 'recall': 0.9688888888888889, 'f1': 0.9732142857142856, 'number': 225} | {'precision': 0.8, 'recall': 0.8, 'f1': 0.8000000000000002, 'number': 10} | {'precision': 0.92578125, 'recall': 0.9404761904761905, 'f1': 0.9330708661417323, 'number': 252} | {'precision': 0.8461538461538461, 'recall': 1.0, 'f1': 0.9166666666666666, 'number': 11} | {'precision': 0.9568627450980393, 'recall': 0.9838709677419355, 'f1': 0.970178926441352, 'number': 248} | {'precision': 0.8, 'recall': 0.9411764705882353, 'f1': 0.8648648648648648, 'number': 17} | {'precision': 0.71875, 'recall': 0.71875, 'f1': 0.71875, 'number': 32} | {'precision': 0.9, 'recall': 0.9, 'f1': 0.9, 'number': 20} | {'precision': 0.984375, 'recall': 0.9264705882352942, 'f1': 0.9545454545454545, 'number': 68} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 7} | {'precision': 0.875, 'recall': 0.875, 'f1': 0.875, 'number': 8} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 12} | {'precision': 0.9577464788732394, 'recall': 0.9855072463768116, 'f1': 0.9714285714285714, 'number': 69} | {'precision': 0.9361702127659575, 'recall': 0.9777777777777777, 'f1': 0.9565217391304347, 'number': 45} | {'precision': 0.9857142857142858, 'recall': 0.971830985915493, 'f1': 0.9787234042553192, 'number': 71} | {'precision': 0.9836065573770492, 'recall': 1.0, 'f1': 0.9917355371900827, 'number': 60} | {'precision': 0.875, 'recall': 0.875, 'f1': 0.875, 'number': 16} | {'precision': 0.6666666666666666, 'recall': 1.0, 'f1': 0.8, 'number': 2} | {'precision': 0.9354838709677419, 'recall': 0.9666666666666667, 'f1': 0.9508196721311476, 'number': 30} | {'precision': 0.8571428571428571, 'recall': 0.75, 'f1': 0.7999999999999999, 'number': 8} | {'precision': 1.0, 'recall': 0.25, 'f1': 0.4, 'number': 4} | {'precision': 0.9696969696969697, 'recall': 0.9696969696969697, 'f1': 0.9696969696969697, 'number': 99} | 0.9449 | 0.9536 | 0.9492 | 0.9610 |
| 0.0002 | 50.0 | 5000 | 0.3277 | {'precision': 0.9775784753363229, 'recall': 0.9688888888888889, 'f1': 0.9732142857142856, 'number': 225} | {'precision': 0.8, 'recall': 0.8, 'f1': 0.8000000000000002, 'number': 10} | {'precision': 0.92578125, 'recall': 0.9404761904761905, 'f1': 0.9330708661417323, 'number': 252} | {'precision': 0.8461538461538461, 'recall': 1.0, 'f1': 0.9166666666666666, 'number': 11} | {'precision': 0.9568627450980393, 'recall': 0.9838709677419355, 'f1': 0.970178926441352, 'number': 248} | {'precision': 0.8, 'recall': 0.9411764705882353, 'f1': 0.8648648648648648, 'number': 17} | {'precision': 0.71875, 'recall': 0.71875, 'f1': 0.71875, 'number': 32} | {'precision': 0.9, 'recall': 0.9, 'f1': 0.9, 'number': 20} | {'precision': 0.984375, 'recall': 0.9264705882352942, 'f1': 0.9545454545454545, 'number': 68} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 7} | {'precision': 0.875, 'recall': 0.875, 'f1': 0.875, 'number': 8} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 12} | {'precision': 0.9577464788732394, 'recall': 0.9855072463768116, 'f1': 0.9714285714285714, 'number': 69} | {'precision': 0.9361702127659575, 'recall': 0.9777777777777777, 'f1': 0.9565217391304347, 'number': 45} | {'precision': 0.9857142857142858, 'recall': 0.971830985915493, 'f1': 0.9787234042553192, 'number': 71} | {'precision': 0.9836065573770492, 'recall': 1.0, 'f1': 0.9917355371900827, 'number': 60} | {'precision': 0.875, 'recall': 0.875, 'f1': 0.875, 'number': 16} | {'precision': 0.6666666666666666, 'recall': 1.0, 'f1': 0.8, 'number': 2} | {'precision': 0.9354838709677419, 'recall': 0.9666666666666667, 'f1': 0.9508196721311476, 'number': 30} | {'precision': 0.8571428571428571, 'recall': 0.75, 'f1': 0.7999999999999999, 'number': 8} | {'precision': 1.0, 'recall': 0.25, 'f1': 0.4, 'number': 4} | {'precision': 0.9696969696969697, 'recall': 0.9696969696969697, 'f1': 0.9696969696969697, 'number': 99} | 0.9449 | 0.9536 | 0.9492 | 0.9610 |
### Framework versions
- Transformers 4.29.2
- Pytorch 1.13.1
- Datasets 2.12.0
- Tokenizers 0.13.2
|
f5-lolabhattu/fine_tune_falcon_7b_sharded_bf16_guanaco_data
|
f5-lolabhattu
| 2023-09-22T16:05:36Z | 0 | 0 | null |
[
"generated_from_trainer",
"base_model:ybelkada/falcon-7b-sharded-bf16",
"base_model:finetune:ybelkada/falcon-7b-sharded-bf16",
"region:us"
] | null | 2023-09-22T16:05:24Z |
---
base_model: ybelkada/falcon-7b-sharded-bf16
tags:
- generated_from_trainer
model-index:
- name: fine_tune_falcon_7b_sharded_bf16_guanaco_data
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. -->
# fine_tune_falcon_7b_sharded_bf16_guanaco_data
This model is a fine-tuned version of [ybelkada/falcon-7b-sharded-bf16](https://huggingface.co/ybelkada/falcon-7b-sharded-bf16) on an unknown dataset.
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0002
- train_batch_size: 4
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: constant
- lr_scheduler_warmup_ratio: 0.03
- training_steps: 500
### Training results
### Framework versions
- Transformers 4.33.2
- Pytorch 2.0.0+cu117
- Datasets 2.12.0
- Tokenizers 0.13.3
|
iainmcqueen/output
|
iainmcqueen
| 2023-09-22T16:04:24Z | 30 | 0 |
diffusers
|
[
"diffusers",
"tensorboard",
"safetensors",
"stable-diffusion",
"stable-diffusion-diffusers",
"text-to-image",
"dreambooth",
"base_model:CompVis/stable-diffusion-v1-4",
"base_model:finetune:CompVis/stable-diffusion-v1-4",
"license:creativeml-openrail-m",
"autotrain_compatible",
"endpoints_compatible",
"diffusers:StableDiffusionPipeline",
"region:us"
] |
text-to-image
| 2023-09-22T15:52:59Z |
---
license: creativeml-openrail-m
base_model: CompVis/stable-diffusion-v1-4
instance_prompt: a photo of ctstech dog
tags:
- stable-diffusion
- stable-diffusion-diffusers
- text-to-image
- diffusers
- dreambooth
inference: true
---
# DreamBooth - iainmcqueen/output
This is a dreambooth model derived from CompVis/stable-diffusion-v1-4. The weights were trained on a photo of ctstech dog using [DreamBooth](https://dreambooth.github.io/).
You can find some example images in the following.
DreamBooth for the text encoder was enabled: False.
|
Thiagof/bert-finetuned-ner
|
Thiagof
| 2023-09-22T16:04:11Z | 105 | 0 |
transformers
|
[
"transformers",
"pytorch",
"tf",
"tensorboard",
"bert",
"token-classification",
"generated_from_trainer",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
token-classification
| 2023-04-19T19:43:15Z |
---
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: bert-finetuned-ner
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. -->
# bert-finetuned-ner
This model was trained from scratch on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.0113
- Precision: 0.9571
- Recall: 0.8933
- F1: 0.9241
- Accuracy: 0.9935
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 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: 3
### Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
| No log | 1.0 | 25 | 0.0296 | 0.9286 | 0.8667 | 0.8966 | 0.9870 |
| No log | 2.0 | 50 | 0.0087 | 0.9722 | 0.9333 | 0.9524 | 0.9961 |
| No log | 3.0 | 75 | 0.0113 | 0.9571 | 0.8933 | 0.9241 | 0.9935 |
### Framework versions
- Transformers 4.30.1
- Pytorch 2.0.1+cu117
- Datasets 2.12.0
- Tokenizers 0.13.3
|
zyongqing/q-Taxi-v3
|
zyongqing
| 2023-09-22T16:02:11Z | 0 | 0 | null |
[
"Taxi-v3",
"q-learning",
"reinforcement-learning",
"custom-implementation",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-09-22T16:02:10Z |
---
tags:
- Taxi-v3
- q-learning
- reinforcement-learning
- custom-implementation
model-index:
- name: q-Taxi-v3
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: Taxi-v3
type: Taxi-v3
metrics:
- type: mean_reward
value: 7.46 +/- 2.67
name: mean_reward
verified: false
---
# **Q-Learning** Agent playing1 **Taxi-v3**
This is a trained model of a **Q-Learning** agent playing **Taxi-v3** .
## Usage
```python
model = load_from_hub(repo_id="zyongqing/q-Taxi-v3", filename="q-learning.pkl")
# Don't forget to check if you need to add additional attributes (is_slippery=False etc)
env = gym.make(model["env_id"])
```
|
baebee/Alphaca
|
baebee
| 2023-09-22T15:50:09Z | 0 | 0 |
peft
|
[
"peft",
"region:us"
] | null | 2023-09-22T15:50:07Z |
---
library_name: peft
---
## Training procedure
The following `bitsandbytes` quantization config was used during training:
- quant_method: bitsandbytes
- load_in_8bit: False
- load_in_4bit: True
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: nf4
- bnb_4bit_use_double_quant: False
- bnb_4bit_compute_dtype: float16
### Framework versions
- PEFT 0.6.0.dev0
|
zyongqing/q-FrozenLake-v1-4x4-Slippery
|
zyongqing
| 2023-09-22T15:40:45Z | 0 | 0 | null |
[
"FrozenLake-v1-4x4",
"q-learning",
"reinforcement-learning",
"custom-implementation",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-09-22T15:30:28Z |
---
tags:
- FrozenLake-v1-4x4
- q-learning
- reinforcement-learning
- custom-implementation
model-index:
- name: q-FrozenLake-v1-4x4-Slippery
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: FrozenLake-v1-4x4
type: FrozenLake-v1-4x4
metrics:
- type: mean_reward
value: 0.75 +/- 0.43
name: mean_reward
verified: false
---
# **Q-Learning** Agent playing1 **FrozenLake-v1**
This is a trained model of a **Q-Learning** agent playing **FrozenLake-v1** .
## Usage
```python
model = load_from_hub(repo_id="zyongqing/q-FrozenLake-v1-4x4-Slippery", filename="q-learning.pkl")
# Don't forget to check if you need to add additional attributes (is_slippery=False etc)
env = gym.make(model["env_id"])
```
|
MattStammers/qrdqn-QbertNoFrameskip-v4-final
|
MattStammers
| 2023-09-22T15:30:37Z | 0 | 0 |
stable-baselines3
|
[
"stable-baselines3",
"QbertNoFrameskip-v4",
"deep-reinforcement-learning",
"reinforcement-learning",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-09-18T20:21:26Z |
---
library_name: stable-baselines3
tags:
- QbertNoFrameskip-v4
- deep-reinforcement-learning
- reinforcement-learning
- stable-baselines3
model-index:
- name: QRDQN
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: QbertNoFrameskip-v4
type: QbertNoFrameskip-v4
metrics:
- type: mean_reward
value: 23787.50 +/- 2397.09
name: mean_reward
verified: false
---
# **QRDQN** Agent playing **QbertNoFrameskip-v4**
This is a trained model of a **QRDQN** agent playing **QbertNoFrameskip-v4**
using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3)
and the [RL Zoo](https://github.com/DLR-RM/rl-baselines3-zoo).
The RL Zoo is a training framework for Stable Baselines3
reinforcement learning agents,
with hyperparameter optimization and pre-trained agents included.
## Usage (with SB3 RL Zoo)
RL Zoo: https://github.com/DLR-RM/rl-baselines3-zoo<br/>
SB3: https://github.com/DLR-RM/stable-baselines3<br/>
SB3 Contrib: https://github.com/Stable-Baselines-Team/stable-baselines3-contrib
Install the RL Zoo (with SB3 and SB3-Contrib):
```bash
pip install rl_zoo3
```
```
# Download model and save it into the logs/ folder
python -m rl_zoo3.load_from_hub --algo qrdqn --env QbertNoFrameskip-v4 -orga MattStammers -f logs/
python -m rl_zoo3.enjoy --algo qrdqn --env QbertNoFrameskip-v4 -f logs/
```
If you installed the RL Zoo3 via pip (`pip install rl_zoo3`), from anywhere you can do:
```
python -m rl_zoo3.load_from_hub --algo qrdqn --env QbertNoFrameskip-v4 -orga MattStammers -f logs/
python -m rl_zoo3.enjoy --algo qrdqn --env QbertNoFrameskip-v4 -f logs/
```
## Training (with the RL Zoo)
```
python -m rl_zoo3.train --algo qrdqn --env QbertNoFrameskip-v4 -f logs/
# Upload the model and generate video (when possible)
python -m rl_zoo3.push_to_hub --algo qrdqn --env QbertNoFrameskip-v4 -f logs/ -orga MattStammers
```
## Hyperparameters
```python
OrderedDict([('batch_size', 64),
('env_wrapper',
['stable_baselines3.common.atari_wrappers.AtariWrapper']),
('exploration_fraction', 0.025),
('frame_stack', 4),
('n_timesteps', 50000000.0),
('normalize', False),
('optimize_memory_usage', False),
('policy', 'CnnPolicy')])
```
# Environment Arguments
```python
{'render_mode': 'rgb_array'}
```
## Additional Comments
Training for this seems to peak at about 50 million timesteps
Interestingly this guy doesn't even seem to care about using the spinners. I guess he gets so good at dodging the snake that he considers them valueless.
|
LarryAIDraw/musashi_azurlane
|
LarryAIDraw
| 2023-09-22T15:30:21Z | 0 | 0 | null |
[
"license:creativeml-openrail-m",
"region:us"
] | null | 2023-09-22T15:20:56Z |
---
license: creativeml-openrail-m
---
https://civitai.com/models/125811/musashi-azur-lane
|
Atheer174/Products_NER2
|
Atheer174
| 2023-09-22T15:30:05Z | 105 | 0 |
transformers
|
[
"transformers",
"pytorch",
"distilbert",
"token-classification",
"generated_from_trainer",
"base_model:distilbert/distilbert-base-uncased",
"base_model:finetune:distilbert/distilbert-base-uncased",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
token-classification
| 2023-09-22T11:44:02Z |
---
license: apache-2.0
base_model: distilbert-base-uncased
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: Products_NER2
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. -->
# Products_NER2
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.3482
- Precision: 0.9155
- Recall: 0.9208
- F1: 0.9182
- Accuracy: 0.9400
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 20
### Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|:-------------:|:-----:|:-----:|:---------------:|:---------:|:------:|:------:|:--------:|
| 0.2267 | 1.0 | 2470 | 0.1614 | 0.8379 | 0.8791 | 0.8580 | 0.9212 |
| 0.1363 | 2.0 | 4940 | 0.1230 | 0.8602 | 0.8968 | 0.8781 | 0.9332 |
| 0.1047 | 3.0 | 7410 | 0.1183 | 0.8808 | 0.9063 | 0.8934 | 0.9360 |
| 0.0931 | 4.0 | 9880 | 0.1139 | 0.8909 | 0.9119 | 0.9013 | 0.9387 |
| 0.085 | 5.0 | 12350 | 0.1153 | 0.8889 | 0.9110 | 0.8998 | 0.9390 |
| 0.0835 | 6.0 | 14820 | 0.1257 | 0.9043 | 0.9165 | 0.9104 | 0.9398 |
| 0.0728 | 7.0 | 17290 | 0.1218 | 0.8987 | 0.9149 | 0.9067 | 0.9393 |
| 0.069 | 8.0 | 19760 | 0.1457 | 0.9040 | 0.9154 | 0.9097 | 0.9389 |
| 0.0616 | 9.0 | 22230 | 0.1606 | 0.9090 | 0.9166 | 0.9128 | 0.9386 |
| 0.0559 | 10.0 | 24700 | 0.1726 | 0.9122 | 0.9189 | 0.9156 | 0.9397 |
| 0.0504 | 11.0 | 27170 | 0.1998 | 0.9131 | 0.9192 | 0.9161 | 0.9396 |
| 0.043 | 12.0 | 29640 | 0.2015 | 0.9126 | 0.9194 | 0.9160 | 0.9402 |
| 0.0389 | 13.0 | 32110 | 0.2388 | 0.9129 | 0.9195 | 0.9162 | 0.9394 |
| 0.035 | 14.0 | 34580 | 0.2569 | 0.9135 | 0.9202 | 0.9169 | 0.9397 |
| 0.0311 | 15.0 | 37050 | 0.2718 | 0.9156 | 0.9207 | 0.9181 | 0.9400 |
| 0.028 | 16.0 | 39520 | 0.2886 | 0.9158 | 0.9208 | 0.9183 | 0.9403 |
| 0.0246 | 17.0 | 41990 | 0.3054 | 0.9145 | 0.9201 | 0.9173 | 0.9392 |
| 0.0212 | 18.0 | 44460 | 0.3252 | 0.9155 | 0.9206 | 0.9180 | 0.9398 |
| 0.0192 | 19.0 | 46930 | 0.3333 | 0.9157 | 0.9210 | 0.9183 | 0.9402 |
| 0.017 | 20.0 | 49400 | 0.3482 | 0.9155 | 0.9208 | 0.9182 | 0.9400 |
### Framework versions
- Transformers 4.33.2
- Pytorch 1.13.1+cu117
- Datasets 2.14.5
- Tokenizers 0.13.3
|
lgaalves/xgen-7b-8k_dolly
|
lgaalves
| 2023-09-22T15:24:09Z | 1,514 | 0 |
transformers
|
[
"transformers",
"pytorch",
"safetensors",
"llama",
"text-generation",
"en",
"dataset:databricks/databricks-dolly-15k",
"license:mit",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2023-09-12T14:58:44Z |
---
datasets:
- databricks/databricks-dolly-15k
language:
- en
pipeline_tag: text-generation
license: mit
---
# xgen-7b-8k-dolly
**xgen-7b-8k-dolly** is an instruction fine-tuned model based on the XGen-7B model pre-trained under 8K sequence length.
### Benchmark Metrics
| Metric | xgen-7b-8k-dolly | xgen-7b-8k-base |
|-----------------------|-------|-------|
| Avg. | - | - |
| ARC (25-shot) | - | - |
| HellaSwag (10-shot) | - | - |
| MMLU (5-shot) | - | - |
| TruthfulQA (0-shot) | - | - |
We use state-of-the-art [Language Model Evaluation Harness](https://github.com/EleutherAI/lm-evaluation-harness) to run the benchmark tests above, using the same version as the HuggingFace LLM Leaderboard. Please see below for detailed instructions on reproducing benchmark results.
### Model Details
* **Trained by**: Luiz G A Alves
* **Model type:** **xgen-7b-8k-dolly** is an auto-regressive language model based on the XGen-7B model pre-trained under 8K sequence length.
* **Language(s)**: English
### How to use:
```python
# Use a pipeline as a high-level helper
>>> from transformers import pipeline
>>> pipe = pipeline("text-generation", model="lgaalves/xgen-7b-8k-dolly")
>>> question = "What is a large language model?"
>>> answer = pipe(question)
>>> print(answer[0]['generated_text'])
```
or, you can load the model direclty using:
```python
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("lgaalves/xgen-7b-8k-dolly")
model = AutoModelForCausalLM.from_pretrained("lgaalves/xgen-7b-8k-dolly")
```
### Training Dataset
`lgaalves/xgen-7b-8k-dolly` trained using the Databricks Dolly dataset [`databricks/databricks-dolly-15k`](https://huggingface.co/datasets/databricks/databricks-dolly-15k).
### Training Procedure
`lgaalves/xgen-7b-8k-dolly` was instruction fine-tuned using LoRA.
# Intended uses, limitations & biases
You can use the raw model for text generation or fine-tune it to a downstream task. The model was not extensively tested and may produce false information. It contains a lot of unfiltered content from the internet, which is far from neutral.
|
tombm/bert-base-uncased-finetuned-cola
|
tombm
| 2023-09-22T15:21:45Z | 31 | 0 |
transformers
|
[
"transformers",
"pytorch",
"bert",
"generated_from_trainer",
"dataset:glue",
"base_model:google-bert/bert-base-uncased",
"base_model:finetune:google-bert/bert-base-uncased",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | null | 2023-09-22T12:36:41Z |
---
license: apache-2.0
base_model: bert-base-uncased
tags:
- generated_from_trainer
datasets:
- glue
metrics:
- matthews_correlation
model-index:
- name: bert-base-uncased-finetuned-cola
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. -->
# bert-base-uncased-finetuned-cola
This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the glue dataset.
It achieves the following results on the evaluation set:
- Loss: 0.5931
- Matthews Correlation: 0.5598
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 16
- eval_batch_size: 128
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
### Training results
| Training Loss | Epoch | Step | Validation Loss | Matthews Correlation |
|:-------------:|:-----:|:----:|:---------------:|:--------------------:|
| 0.5206 | 1.0 | 535 | 0.4503 | 0.4984 |
| 0.347 | 2.0 | 1070 | 0.4558 | 0.5816 |
| 0.2461 | 3.0 | 1605 | 0.5931 | 0.5598 |
### Framework versions
- Transformers 4.33.2
- Pytorch 2.0.1
- Datasets 2.14.5
- Tokenizers 0.13.3
|
ShivamMangale/XLM-Roberta-base-finetuned-squad-only-es-12-epoch
|
ShivamMangale
| 2023-09-22T15:06:43Z | 3 | 0 |
transformers
|
[
"transformers",
"pytorch",
"xlm-roberta",
"question-answering",
"generated_from_trainer",
"dataset:squad",
"base_model:FacebookAI/xlm-roberta-base",
"base_model:finetune:FacebookAI/xlm-roberta-base",
"license:mit",
"endpoints_compatible",
"region:us"
] |
question-answering
| 2023-09-22T14:26:41Z |
---
license: mit
base_model: xlm-roberta-base
tags:
- generated_from_trainer
datasets:
- squad
model-index:
- name: XLM-Roberta-base-finetuned-squad-only-es-12-epoch
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. -->
# XLM-Roberta-base-finetuned-squad-only-es-12-epoch
This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on the squad 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: 2e-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: 12
### Training results
### Framework versions
- Transformers 4.33.2
- Pytorch 2.0.1+cu117
- Datasets 2.14.5
- Tokenizers 0.13.3
|
zyongqing/q-FrozenLake-v1-4x4-noSlippery
|
zyongqing
| 2023-09-22T15:04:32Z | 0 | 0 | null |
[
"FrozenLake-v1-4x4-no_slippery",
"q-learning",
"reinforcement-learning",
"custom-implementation",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-09-22T15:04:31Z |
---
tags:
- FrozenLake-v1-4x4-no_slippery
- q-learning
- reinforcement-learning
- custom-implementation
model-index:
- name: q-FrozenLake-v1-4x4-noSlippery
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: FrozenLake-v1-4x4-no_slippery
type: FrozenLake-v1-4x4-no_slippery
metrics:
- type: mean_reward
value: 1.00 +/- 0.00
name: mean_reward
verified: false
---
# **Q-Learning** Agent playing1 **FrozenLake-v1**
This is a trained model of a **Q-Learning** agent playing **FrozenLake-v1** .
## Usage
```python
model = load_from_hub(repo_id="zyongqing/q-FrozenLake-v1-4x4-noSlippery", filename="q-learning.pkl")
# Don't forget to check if you need to add additional attributes (is_slippery=False etc)
env = gym.make(model["env_id"])
```
|
gianclbal/attainment_bart_summarization
|
gianclbal
| 2023-09-22T14:47:10Z | 104 | 0 |
transformers
|
[
"transformers",
"pytorch",
"bart",
"text2text-generation",
"generated_from_trainer",
"base_model:facebook/bart-large-cnn",
"base_model:finetune:facebook/bart-large-cnn",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text2text-generation
| 2023-09-22T08:23:45Z |
---
license: mit
base_model: facebook/bart-large-cnn
tags:
- generated_from_trainer
metrics:
- rouge
model-index:
- name: attainment_bart_summarization
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. -->
# attainment_bart_summarization
This model is a fine-tuned version of [facebook/bart-large-cnn](https://huggingface.co/facebook/bart-large-cnn) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.3648
- Rouge1: 0.593
- Rouge2: 0.5676
- Rougel: 0.5797
- Rougelsum: 0.5816
- Gen Len: 66.7368
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 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: 4
### Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:|
| No log | 1.0 | 38 | 0.3416 | 0.5952 | 0.5638 | 0.5657 | 0.5659 | 66.4737 |
| No log | 2.0 | 76 | 0.2780 | 0.5992 | 0.5733 | 0.5777 | 0.5776 | 66.7237 |
| No log | 3.0 | 114 | 0.3348 | 0.593 | 0.5632 | 0.5719 | 0.5734 | 66.5921 |
| No log | 4.0 | 152 | 0.3648 | 0.593 | 0.5676 | 0.5797 | 0.5816 | 66.7368 |
### Framework versions
- Transformers 4.33.2
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3
|
jtlowell/cozy_only
|
jtlowell
| 2023-09-22T14:46:59Z | 5 | 0 |
diffusers
|
[
"diffusers",
"stable-diffusion-xl",
"stable-diffusion-xl-diffusers",
"text-to-image",
"lora",
"dataset:jtlowell/cozy_int_only",
"base_model:stabilityai/stable-diffusion-xl-base-1.0",
"base_model:adapter:stabilityai/stable-diffusion-xl-base-1.0",
"region:us"
] |
text-to-image
| 2023-09-22T13:58:22Z |
---
base_model: stabilityai/stable-diffusion-xl-base-1.0
instance_prompt: cozy_only
tags:
- stable-diffusion-xl
- stable-diffusion-xl-diffusers
- text-to-image
- diffusers
- lora
inference: true
datasets:
- jtlowell/cozy_int_only
---
# LoRA DreamBooth - jtlowell/cozy_only
These are LoRA adaption weights for stabilityai/stable-diffusion-xl-base-1.0.
The weights were trained on the concept prompt:
`cozy_only`
Use this keyword to trigger your custom model in your prompts.
LoRA for the text encoder was enabled: False.
Special VAE used for training: madebyollin/sdxl-vae-fp16-fix.
## Usage
Make sure to upgrade diffusers to >= 0.19.0:
```
pip install diffusers --upgrade
```
In addition make sure to install transformers, safetensors, accelerate as well as the invisible watermark:
```
pip install invisible_watermark transformers accelerate safetensors
```
To just use the base model, you can run:
```python
import torch
from diffusers import DiffusionPipeline, AutoencoderKL
vae = AutoencoderKL.from_pretrained('madebyollin/sdxl-vae-fp16-fix', torch_dtype=torch.float16)
pipe = DiffusionPipeline.from_pretrained(
"stabilityai/stable-diffusion-xl-base-1.0",
vae=vae, torch_dtype=torch.float16, variant="fp16",
use_safetensors=True
)
# This is where you load your trained weights
pipe.load_lora_weights('jtlowell/cozy_only')
pipe.to("cuda")
prompt = "A majestic cozy_only jumping from a big stone at night"
image = pipe(prompt=prompt, num_inference_steps=50).images[0]
```
|
loicspigeleer/Reinforce-Cartpole-v1
|
loicspigeleer
| 2023-09-22T14:33:17Z | 0 | 0 | null |
[
"CartPole-v1",
"reinforce",
"reinforcement-learning",
"custom-implementation",
"deep-rl-class",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-08-29T09:57:47Z |
---
tags:
- CartPole-v1
- reinforce
- reinforcement-learning
- custom-implementation
- deep-rl-class
model-index:
- name: Reinforce-Cartpole-v1
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: CartPole-v1
type: CartPole-v1
metrics:
- type: mean_reward
value: 500.00 +/- 0.00
name: mean_reward
verified: false
---
# **Reinforce** Agent playing **CartPole-v1**
This is a trained model of a **Reinforce** agent playing **CartPole-v1** .
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
|
mbodo/vit-base-patch16-224-in21k-finetuned-lora-food101
|
mbodo
| 2023-09-22T14:31:53Z | 6 | 0 |
peft
|
[
"peft",
"generated_from_trainer",
"dataset:food101",
"base_model:google/vit-base-patch16-224-in21k",
"base_model:adapter:google/vit-base-patch16-224-in21k",
"license:apache-2.0",
"region:us"
] | null | 2023-09-22T14:16:10Z |
---
license: apache-2.0
base_model: google/vit-base-patch16-224-in21k
tags:
- generated_from_trainer
datasets:
- food101
metrics:
- accuracy
model-index:
- name: vit-base-patch16-224-in21k-finetuned-lora-food101
results: []
library_name: peft
---
<!-- 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. -->
# vit-base-patch16-224-in21k-finetuned-lora-food101
This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the food101 dataset.
It achieves the following results on the evaluation set:
- Loss: 0.1158
- Accuracy: 0.962
## 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: 0.005
- train_batch_size: 128
- eval_batch_size: 128
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 512
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| No log | 1.0 | 9 | 0.1536 | 0.95 |
| 0.2548 | 2.0 | 18 | 0.1263 | 0.96 |
| 0.1404 | 3.0 | 27 | 0.1158 | 0.962 |
| 0.1214 | 4.0 | 36 | 0.1232 | 0.96 |
| 0.1238 | 5.0 | 45 | 0.1177 | 0.96 |
### Framework versions
- PEFT 0.4.0
- Transformers 4.33.2
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3
|
hangsiin/eva02-lora-test
|
hangsiin
| 2023-09-22T14:27:51Z | 1 | 0 |
peft
|
[
"peft",
"region:us"
] | null | 2023-09-22T08:13:52Z |
---
library_name: peft
---
## Training procedure
### Framework versions
- PEFT 0.5.0
|
sophiaaez/distilhubert_clone-finetuned-gtzan
|
sophiaaez
| 2023-09-22T14:25:31Z | 162 | 0 |
transformers
|
[
"transformers",
"pytorch",
"hubert",
"audio-classification",
"generated_from_trainer",
"dataset:marsyas/gtzan",
"base_model:sophiaaez/distilhubert_clone",
"base_model:finetune:sophiaaez/distilhubert_clone",
"model-index",
"endpoints_compatible",
"region:us"
] |
audio-classification
| 2023-09-22T06:59:44Z |
---
base_model: sophiaaez/distilhubert_clone
tags:
- generated_from_trainer
datasets:
- marsyas/gtzan
metrics:
- accuracy
model-index:
- name: distilhubert_clone-finetuned-gtzan
results:
- task:
name: Audio Classification
type: audio-classification
dataset:
name: GTZAN
type: marsyas/gtzan
config: all
split: train
args: all
metrics:
- name: Accuracy
type: accuracy
value: 0.82
---
<!-- 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. -->
# distilhubert_clone-finetuned-gtzan
This model is a fine-tuned version of [sophiaaez/distilhubert_clone](https://huggingface.co/sophiaaez/distilhubert_clone) on the GTZAN dataset.
It achieves the following results on the evaluation set:
- Loss: 0.6718
- Accuracy: 0.82
## 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
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 10
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 1.9972 | 1.0 | 113 | 1.7844 | 0.52 |
| 1.4046 | 2.0 | 226 | 1.2909 | 0.63 |
| 1.1165 | 3.0 | 339 | 1.0493 | 0.69 |
| 0.879 | 4.0 | 452 | 0.8689 | 0.73 |
| 0.7814 | 5.0 | 565 | 0.7254 | 0.81 |
| 0.47 | 6.0 | 678 | 0.7432 | 0.79 |
| 0.5201 | 7.0 | 791 | 0.6523 | 0.81 |
| 0.2419 | 8.0 | 904 | 0.6086 | 0.83 |
| 0.375 | 9.0 | 1017 | 0.6481 | 0.82 |
| 0.249 | 10.0 | 1130 | 0.6718 | 0.82 |
### Framework versions
- Transformers 4.34.0.dev0
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.14.0
|
duwuonline/my-upgrade-sentences
|
duwuonline
| 2023-09-22T14:25:28Z | 105 | 0 |
transformers
|
[
"transformers",
"pytorch",
"t5",
"text2text-generation",
"generated_from_trainer",
"base_model:google/flan-t5-base",
"base_model:finetune:google/flan-t5-base",
"license:apache-2.0",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text2text-generation
| 2023-09-21T13:13:37Z |
---
license: apache-2.0
base_model: google/flan-t5-base
tags:
- generated_from_trainer
model-index:
- name: my-upgrade-sentences
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# my-upgrade-sentences
This model is a fine-tuned version of [google/flan-t5-base](https://huggingface.co/google/flan-t5-base) 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: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
### Training results
### Framework versions
- Transformers 4.33.2
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3
|
rob101935/opt-6.7b-lora
|
rob101935
| 2023-09-22T14:22:44Z | 2 | 0 |
peft
|
[
"peft",
"region:us"
] | null | 2023-09-22T14:22:41Z |
---
library_name: peft
---
## Training procedure
The following `bitsandbytes` quantization config was used during training:
- quant_method: bitsandbytes
- load_in_8bit: True
- load_in_4bit: False
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: fp4
- bnb_4bit_use_double_quant: False
- bnb_4bit_compute_dtype: float32
### Framework versions
- PEFT 0.6.0.dev0
|
Maaz66/llama2-qlora-finetunined-french_MOAAAZ
|
Maaz66
| 2023-09-22T14:21:14Z | 1 | 0 |
peft
|
[
"peft",
"base_model:TinyPixel/Llama-2-7B-bf16-sharded",
"base_model:adapter:TinyPixel/Llama-2-7B-bf16-sharded",
"region:us"
] | null | 2023-09-21T20:03:47Z |
---
library_name: peft
base_model: TinyPixel/Llama-2-7B-bf16-sharded
---
## Training procedure
The following `bitsandbytes` quantization config was used during training:
- quant_method: bitsandbytes
- load_in_8bit: False
- load_in_4bit: True
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: nf4
- bnb_4bit_use_double_quant: False
- bnb_4bit_compute_dtype: float16
### Framework versions
- PEFT 0.6.0.dev0
|
Stomper10/CXR_unet_nf
|
Stomper10
| 2023-09-22T14:11:45Z | 0 | 0 |
diffusers
|
[
"diffusers",
"safetensors",
"stable-diffusion",
"stable-diffusion-diffusers",
"text-to-image",
"dataset:None",
"base_model:CompVis/stable-diffusion-v1-4",
"base_model:finetune:CompVis/stable-diffusion-v1-4",
"license:creativeml-openrail-m",
"autotrain_compatible",
"endpoints_compatible",
"diffusers:StableDiffusionPipeline",
"region:us"
] |
text-to-image
| 2023-08-27T12:12:46Z |
---
license: creativeml-openrail-m
base_model: CompVis/stable-diffusion-v1-4
datasets:
- None
tags:
- stable-diffusion
- stable-diffusion-diffusers
- text-to-image
- diffusers
inference: true
---
# Text-to-image finetuning - Stomper10/CXR_unet_nf
This pipeline was finetuned from **CompVis/stable-diffusion-v1-4** on the **None** dataset. Below are some example images generated with the finetuned pipeline using the following prompts: ['A photo of a lung-xray.']:
## Pipeline usage
You can use the pipeline like so:
```python
from diffusers import DiffusionPipeline
import torch
pipeline = DiffusionPipeline.from_pretrained("Stomper10/CXR_unet_nf", torch_dtype=torch.float16)
prompt = "A photo of a lung-xray."
image = pipeline(prompt).images[0]
image.save("my_image.png")
```
## Training info
These are the key hyperparameters used during training:
* Epochs: 1
* Learning rate: 0.0064
* Batch size: 32
* Gradient accumulation steps: 1
* Image resolution: 512
* Mixed-precision: fp16
More information on all the CLI arguments and the environment are available on your [`wandb` run page](https://wandb.ai/jwy4888/text2image-fine-tune/runs/1bg6che1).
|
m-aliabbas1/tiny_bert_30_intents
|
m-aliabbas1
| 2023-09-22T14:01:50Z | 114 | 0 |
transformers
|
[
"transformers",
"pytorch",
"bert",
"text-classification",
"generated_from_trainer",
"base_model:prajjwal1/bert-tiny",
"base_model:finetune:prajjwal1/bert-tiny",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2023-09-19T03:53:53Z |
---
license: mit
base_model: prajjwal1/bert-tiny
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: tiny_bert_30_intents
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. -->
# tiny_bert_30_intents
This model is a fine-tuned version of [prajjwal1/bert-tiny](https://huggingface.co/prajjwal1/bert-tiny) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.2835
- Accuracy: 0.9245
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 50
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:-----:|:---------------:|:--------:|
| No log | 1.0 | 335 | 3.1862 | 0.2299 |
| 3.264 | 2.0 | 670 | 2.9366 | 0.3758 |
| 2.9242 | 3.0 | 1005 | 2.6777 | 0.4648 |
| 2.9242 | 4.0 | 1340 | 2.4290 | 0.5487 |
| 2.5619 | 5.0 | 1675 | 2.1939 | 0.6174 |
| 2.2347 | 6.0 | 2010 | 1.9840 | 0.6493 |
| 2.2347 | 7.0 | 2345 | 1.7925 | 0.6862 |
| 1.9296 | 8.0 | 2680 | 1.6204 | 0.7215 |
| 1.6809 | 9.0 | 3015 | 1.4657 | 0.7550 |
| 1.6809 | 10.0 | 3350 | 1.3267 | 0.7785 |
| 1.4613 | 11.0 | 3685 | 1.2082 | 0.7987 |
| 1.2746 | 12.0 | 4020 | 1.0965 | 0.8121 |
| 1.2746 | 13.0 | 4355 | 1.0022 | 0.8473 |
| 1.1137 | 14.0 | 4690 | 0.9185 | 0.8607 |
| 0.991 | 15.0 | 5025 | 0.8464 | 0.8742 |
| 0.991 | 16.0 | 5360 | 0.7851 | 0.8792 |
| 0.8792 | 17.0 | 5695 | 0.7309 | 0.8792 |
| 0.7797 | 18.0 | 6030 | 0.6827 | 0.8842 |
| 0.7797 | 19.0 | 6365 | 0.6391 | 0.8876 |
| 0.7006 | 20.0 | 6700 | 0.6014 | 0.8943 |
| 0.6422 | 21.0 | 7035 | 0.5713 | 0.8993 |
| 0.6422 | 22.0 | 7370 | 0.5384 | 0.9044 |
| 0.5833 | 23.0 | 7705 | 0.5112 | 0.9044 |
| 0.5441 | 24.0 | 8040 | 0.4841 | 0.9077 |
| 0.5441 | 25.0 | 8375 | 0.4627 | 0.9094 |
| 0.4996 | 26.0 | 8710 | 0.4455 | 0.9128 |
| 0.4594 | 27.0 | 9045 | 0.4259 | 0.9128 |
| 0.4594 | 28.0 | 9380 | 0.4103 | 0.9161 |
| 0.4288 | 29.0 | 9715 | 0.3959 | 0.9161 |
| 0.41 | 30.0 | 10050 | 0.3821 | 0.9161 |
| 0.41 | 31.0 | 10385 | 0.3687 | 0.9161 |
| 0.383 | 32.0 | 10720 | 0.3595 | 0.9144 |
| 0.3618 | 33.0 | 11055 | 0.3473 | 0.9144 |
| 0.3618 | 34.0 | 11390 | 0.3412 | 0.9161 |
| 0.3534 | 35.0 | 11725 | 0.3336 | 0.9178 |
| 0.3277 | 36.0 | 12060 | 0.3275 | 0.9178 |
| 0.3277 | 37.0 | 12395 | 0.3208 | 0.9195 |
| 0.3164 | 38.0 | 12730 | 0.3143 | 0.9211 |
| 0.3107 | 39.0 | 13065 | 0.3062 | 0.9195 |
| 0.3107 | 40.0 | 13400 | 0.3031 | 0.9195 |
| 0.296 | 41.0 | 13735 | 0.2995 | 0.9211 |
| 0.2998 | 42.0 | 14070 | 0.2962 | 0.9211 |
| 0.2998 | 43.0 | 14405 | 0.2936 | 0.9211 |
| 0.2813 | 44.0 | 14740 | 0.2893 | 0.9228 |
| 0.2767 | 45.0 | 15075 | 0.2874 | 0.9195 |
| 0.2767 | 46.0 | 15410 | 0.2865 | 0.9228 |
| 0.2813 | 47.0 | 15745 | 0.2849 | 0.9245 |
| 0.272 | 48.0 | 16080 | 0.2842 | 0.9245 |
| 0.272 | 49.0 | 16415 | 0.2837 | 0.9245 |
| 0.2751 | 50.0 | 16750 | 0.2835 | 0.9245 |
### Framework versions
- Transformers 4.33.2
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3
|
MattStammers/appo-atari-asterix
|
MattStammers
| 2023-09-22T13:55:11Z | 0 | 0 |
sample-factory
|
[
"sample-factory",
"tensorboard",
"deep-reinforcement-learning",
"reinforcement-learning",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-09-22T13:51:57Z |
---
library_name: sample-factory
tags:
- deep-reinforcement-learning
- reinforcement-learning
- sample-factory
model-index:
- name: APPO
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: atari_asterix
type: atari_asterix
metrics:
- type: mean_reward
value: 3325.00 +/- 544.63
name: mean_reward
verified: false
---
A(n) **APPO** model trained on the **atari_asterix** environment.
This model was trained using Sample-Factory 2.0: https://github.com/alex-petrenko/sample-factory.
Documentation for how to use Sample-Factory can be found at https://www.samplefactory.dev/
## Downloading the model
After installing Sample-Factory, download the model with:
```
python -m sample_factory.huggingface.load_from_hub -r MattStammers/appo-atari-asterix
```
## Using the model
To run the model after download, use the `enjoy` script corresponding to this environment:
```
python -m sf_examples.atari.enjoy_atari --algo=APPO --env=atari_asterix --train_dir=./train_dir --experiment=appo-atari-asterix
```
You can also upload models to the Hugging Face Hub using the same script with the `--push_to_hub` flag.
See https://www.samplefactory.dev/10-huggingface/huggingface/ for more details
## Training with this model
To continue training with this model, use the `train` script corresponding to this environment:
```
python -m sf_examples.atari.train_atari --algo=APPO --env=atari_asterix --train_dir=./train_dir --experiment=appo-atari-asterix --restart_behavior=resume --train_for_env_steps=10000000000
```
Note, you may have to adjust `--train_for_env_steps` to a suitably high number as the experiment will resume at the number of steps it concluded at.
|
zhengr/llama-2-7b-miniguanaco
|
zhengr
| 2023-09-22T13:52:53Z | 4 | 0 |
transformers
|
[
"transformers",
"pytorch",
"llama",
"text-generation",
"en",
"license:apache-2.0",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2023-09-22T13:29:25Z |
---
license: apache-2.0
language:
- en
metrics:
- accuracy
---
|
ShivamMangale/XLM-Roberta-base-finetuned-squad-syn-first-now-squad-es-12k-6-epoch-w_preproc
|
ShivamMangale
| 2023-09-22T13:38:50Z | 105 | 0 |
transformers
|
[
"transformers",
"pytorch",
"xlm-roberta",
"question-answering",
"generated_from_trainer",
"dataset:squad",
"base_model:FacebookAI/xlm-roberta-base",
"base_model:finetune:FacebookAI/xlm-roberta-base",
"license:mit",
"endpoints_compatible",
"region:us"
] |
question-answering
| 2023-09-22T13:18:00Z |
---
license: mit
base_model: xlm-roberta-base
tags:
- generated_from_trainer
datasets:
- squad
model-index:
- name: XLM-Roberta-base-finetuned-squad-syn-first-now-squad-es-12k-6-epoch-w_preproc
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. -->
# XLM-Roberta-base-finetuned-squad-syn-first-now-squad-es-12k-6-epoch-w_preproc
This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on the squad 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: 2e-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: 6
### Training results
### Framework versions
- Transformers 4.33.2
- Pytorch 2.0.1+cu117
- Datasets 2.14.5
- Tokenizers 0.13.3
|
loicspigeleer/ppo-PyramidsRND
|
loicspigeleer
| 2023-09-22T13:36:33Z | 4 | 0 |
ml-agents
|
[
"ml-agents",
"tensorboard",
"onnx",
"Pyramids",
"deep-reinforcement-learning",
"reinforcement-learning",
"ML-Agents-Pyramids",
"region:us"
] |
reinforcement-learning
| 2023-09-22T13:10:34Z |
---
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 🐶 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: loicspigeleer/ppo-PyramidsRND
3. Step 2: Select your *.nn /*.onnx file
4. Click on Watch the agent play 👀
|
tomasito12/reinforce-2
|
tomasito12
| 2023-09-22T13:30:01Z | 0 | 0 | null |
[
"Pixelcopter-PLE-v0",
"reinforce",
"reinforcement-learning",
"custom-implementation",
"deep-rl-class",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-09-22T13:14:53Z |
---
tags:
- Pixelcopter-PLE-v0
- reinforce
- reinforcement-learning
- custom-implementation
- deep-rl-class
model-index:
- name: reinforce-2
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: Pixelcopter-PLE-v0
type: Pixelcopter-PLE-v0
metrics:
- type: mean_reward
value: 21.20 +/- 18.93
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
|
CyberHarem/niwa_hitomi_idolmastercinderellagirls
|
CyberHarem
| 2023-09-22T13:06:34Z | 0 | 0 | null |
[
"art",
"text-to-image",
"dataset:CyberHarem/niwa_hitomi_idolmastercinderellagirls",
"license:mit",
"region:us"
] |
text-to-image
| 2023-09-22T12:55:34Z |
---
license: mit
datasets:
- CyberHarem/niwa_hitomi_idolmastercinderellagirls
pipeline_tag: text-to-image
tags:
- art
---
# Lora of niwa_hitomi_idolmastercinderellagirls
This model is trained with [HCP-Diffusion](https://github.com/7eu7d7/HCP-Diffusion). And the auto-training framework is maintained by [DeepGHS Team](https://huggingface.co/deepghs).
The base model used during training is [NAI](https://huggingface.co/deepghs/animefull-latest), and the base model used for generating preview images is [Meina/MeinaMix_V11](https://huggingface.co/Meina/MeinaMix_V11).
After downloading the pt and safetensors files for the specified step, you need to use them simultaneously. The pt file will be used as an embedding, while the safetensors file will be loaded for Lora.
For example, if you want to use the model from step 4080, you need to download `4080/niwa_hitomi_idolmastercinderellagirls.pt` as the embedding and `4080/niwa_hitomi_idolmastercinderellagirls.safetensors` for loading Lora. By using both files together, you can generate images for the desired characters.
**The best step we recommend is 4080**, with the score of 0.972. The trigger words are:
1. `niwa_hitomi_idolmastercinderellagirls`
2. `smile, black_hair, flower, hair_ornament, short_hair, black_eyes, hair_flower, open_mouth, blush, one_eye_closed`
For the following groups, it is not recommended to use this model and we express regret:
1. Individuals who cannot tolerate any deviations from the original character design, even in the slightest detail.
2. Individuals who are facing the application scenarios with high demands for accuracy in recreating character outfits.
3. Individuals who cannot accept the potential randomness in AI-generated images based on the Stable Diffusion algorithm.
4. Individuals who are not comfortable with the fully automated process of training character models using LoRA, or those who believe that training character models must be done purely through manual operations to avoid disrespecting the characters.
5. Individuals who finds the generated image content offensive to their values.
These are available steps:
| Steps | Score | Download | pattern_1 | pattern_2 | bikini | bondage | free | maid | miko | nude | nude2 | suit | yukata |
|:---------|:----------|:---------------------------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------|:--------------------------------------------------|:-------------------------------------|:-------------------------------------|:-------------------------------------|:-----------------------------------------------|:------------------------------------------------|:-------------------------------------|:-----------------------------------------|
| 5100 | 0.953 | [Download](5100/niwa_hitomi_idolmastercinderellagirls.zip) |  |  |  | [<NSFW, click to see>](5100/previews/bondage.png) |  |  |  | [<NSFW, click to see>](5100/previews/nude.png) | [<NSFW, click to see>](5100/previews/nude2.png) |  |  |
| 4760 | 0.950 | [Download](4760/niwa_hitomi_idolmastercinderellagirls.zip) |  |  |  | [<NSFW, click to see>](4760/previews/bondage.png) |  |  |  | [<NSFW, click to see>](4760/previews/nude.png) | [<NSFW, click to see>](4760/previews/nude2.png) |  |  |
| 4420 | 0.940 | [Download](4420/niwa_hitomi_idolmastercinderellagirls.zip) |  |  |  | [<NSFW, click to see>](4420/previews/bondage.png) |  |  |  | [<NSFW, click to see>](4420/previews/nude.png) | [<NSFW, click to see>](4420/previews/nude2.png) |  |  |
| **4080** | **0.972** | [**Download**](4080/niwa_hitomi_idolmastercinderellagirls.zip) |  |  |  | [<NSFW, click to see>](4080/previews/bondage.png) |  |  |  | [<NSFW, click to see>](4080/previews/nude.png) | [<NSFW, click to see>](4080/previews/nude2.png) |  |  |
| 3740 | 0.913 | [Download](3740/niwa_hitomi_idolmastercinderellagirls.zip) |  |  |  | [<NSFW, click to see>](3740/previews/bondage.png) |  |  |  | [<NSFW, click to see>](3740/previews/nude.png) | [<NSFW, click to see>](3740/previews/nude2.png) |  |  |
| 3400 | 0.962 | [Download](3400/niwa_hitomi_idolmastercinderellagirls.zip) |  |  |  | [<NSFW, click to see>](3400/previews/bondage.png) |  |  |  | [<NSFW, click to see>](3400/previews/nude.png) | [<NSFW, click to see>](3400/previews/nude2.png) |  |  |
| 3060 | 0.955 | [Download](3060/niwa_hitomi_idolmastercinderellagirls.zip) |  |  |  | [<NSFW, click to see>](3060/previews/bondage.png) |  |  |  | [<NSFW, click to see>](3060/previews/nude.png) | [<NSFW, click to see>](3060/previews/nude2.png) |  |  |
| 2720 | 0.919 | [Download](2720/niwa_hitomi_idolmastercinderellagirls.zip) |  |  |  | [<NSFW, click to see>](2720/previews/bondage.png) |  |  |  | [<NSFW, click to see>](2720/previews/nude.png) | [<NSFW, click to see>](2720/previews/nude2.png) |  |  |
| 2380 | 0.855 | [Download](2380/niwa_hitomi_idolmastercinderellagirls.zip) |  |  |  | [<NSFW, click to see>](2380/previews/bondage.png) |  |  |  | [<NSFW, click to see>](2380/previews/nude.png) | [<NSFW, click to see>](2380/previews/nude2.png) |  |  |
| 2040 | 0.856 | [Download](2040/niwa_hitomi_idolmastercinderellagirls.zip) |  |  |  | [<NSFW, click to see>](2040/previews/bondage.png) |  |  |  | [<NSFW, click to see>](2040/previews/nude.png) | [<NSFW, click to see>](2040/previews/nude2.png) |  |  |
| 1700 | 0.894 | [Download](1700/niwa_hitomi_idolmastercinderellagirls.zip) |  |  |  | [<NSFW, click to see>](1700/previews/bondage.png) |  |  |  | [<NSFW, click to see>](1700/previews/nude.png) | [<NSFW, click to see>](1700/previews/nude2.png) |  |  |
| 1360 | 0.875 | [Download](1360/niwa_hitomi_idolmastercinderellagirls.zip) |  |  |  | [<NSFW, click to see>](1360/previews/bondage.png) |  |  |  | [<NSFW, click to see>](1360/previews/nude.png) | [<NSFW, click to see>](1360/previews/nude2.png) |  |  |
| 1020 | 0.743 | [Download](1020/niwa_hitomi_idolmastercinderellagirls.zip) |  |  |  | [<NSFW, click to see>](1020/previews/bondage.png) |  |  |  | [<NSFW, click to see>](1020/previews/nude.png) | [<NSFW, click to see>](1020/previews/nude2.png) |  |  |
| 680 | 0.828 | [Download](680/niwa_hitomi_idolmastercinderellagirls.zip) |  |  |  | [<NSFW, click to see>](680/previews/bondage.png) |  |  |  | [<NSFW, click to see>](680/previews/nude.png) | [<NSFW, click to see>](680/previews/nude2.png) |  |  |
| 340 | 0.695 | [Download](340/niwa_hitomi_idolmastercinderellagirls.zip) |  |  |  | [<NSFW, click to see>](340/previews/bondage.png) |  |  |  | [<NSFW, click to see>](340/previews/nude.png) | [<NSFW, click to see>](340/previews/nude2.png) |  |  |
|
Stomper10/CXR_db_init
|
Stomper10
| 2023-09-22T13:05:45Z | 30 | 0 |
diffusers
|
[
"diffusers",
"tensorboard",
"safetensors",
"stable-diffusion",
"stable-diffusion-diffusers",
"text-to-image",
"dreambooth",
"base_model:CompVis/stable-diffusion-v1-4",
"base_model:finetune:CompVis/stable-diffusion-v1-4",
"license:creativeml-openrail-m",
"autotrain_compatible",
"endpoints_compatible",
"diffusers:StableDiffusionPipeline",
"region:us"
] |
text-to-image
| 2023-09-22T12:22:43Z |
---
license: creativeml-openrail-m
base_model: CompVis/stable-diffusion-v1-4
instance_prompt: a photo of lung-xray
tags:
- stable-diffusion
- stable-diffusion-diffusers
- text-to-image
- diffusers
- dreambooth
inference: true
---
# DreamBooth - Stomper10/CXR_db_init
This is a dreambooth model derived from CompVis/stable-diffusion-v1-4. The weights were trained on a photo of lung-xray using [DreamBooth](https://dreambooth.github.io/).
You can find some example images in the following.
DreamBooth for the text encoder was enabled: False.
|
OpenDILabCommunity/LunarLander-v2-DDPG
|
OpenDILabCommunity
| 2023-09-22T12:59:26Z | 0 | 0 |
pytorch
|
[
"pytorch",
"deep-reinforcement-learning",
"reinforcement-learning",
"DI-engine",
"LunarLander-v2",
"en",
"license:apache-2.0",
"region:us"
] |
reinforcement-learning
| 2023-04-11T11:52:42Z |
---
language: en
license: apache-2.0
library_name: pytorch
tags:
- deep-reinforcement-learning
- reinforcement-learning
- DI-engine
- LunarLander-v2
benchmark_name: OpenAI/Gym/Box2d
task_name: LunarLander-v2
pipeline_tag: reinforcement-learning
model-index:
- name: DDPG
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: OpenAI/Gym/Box2d-LunarLander-v2
type: OpenAI/Gym/Box2d-LunarLander-v2
metrics:
- type: mean_reward
value: 264.9 +/- 18.41
name: mean_reward
---
# Play **LunarLander-v2** with **DDPG** Policy
## Model Description
<!-- Provide a longer summary of what this model is. -->
This is a simple **DDPG** implementation to OpenAI/Gym/Box2d **LunarLander-v2** using the [DI-engine library](https://github.com/opendilab/di-engine) and the [DI-zoo](https://github.com/opendilab/DI-engine/tree/main/dizoo).
**DI-engine** is a python library for solving general decision intelligence problems, which is based on implementations of reinforcement learning framework using PyTorch or JAX. This library aims to standardize the reinforcement learning framework across different algorithms, benchmarks, environments, and to support both academic researches and prototype applications. Besides, self-customized training pipelines and applications are supported by reusing different abstraction levels of DI-engine reinforcement learning framework.
## Model Usage
### Install the Dependencies
<details close>
<summary>(Click for Details)</summary>
```shell
# install huggingface_ding
git clone https://github.com/opendilab/huggingface_ding.git
pip3 install -e ./huggingface_ding/
# install environment dependencies if needed
pip3 install DI-engine[common_env]
```
</details>
### Git Clone from Huggingface and Run the Model
<details close>
<summary>(Click for Details)</summary>
```shell
# running with trained model
python3 -u run.py
```
**run.py**
```python
from ding.bonus import DDPGAgent
from ding.config import Config
from easydict import EasyDict
import torch
# Pull model from files which are git cloned from huggingface
policy_state_dict = torch.load("pytorch_model.bin", map_location=torch.device("cpu"))
cfg = EasyDict(Config.file_to_dict("policy_config.py").cfg_dict)
# Instantiate the agent
agent = DDPGAgent(
env_id="LunarLanderContinuous-v2",
exp_name="LunarLander-v2-DDPG",
cfg=cfg.exp_config,
policy_state_dict=policy_state_dict
)
# Continue training
agent.train(step=5000)
# Render the new agent performance
agent.deploy(enable_save_replay=True)
```
</details>
### Run Model by Using Huggingface_ding
<details close>
<summary>(Click for Details)</summary>
```shell
# running with trained model
python3 -u run.py
```
**run.py**
```python
from ding.bonus import DDPGAgent
from huggingface_ding import pull_model_from_hub
# Pull model from Hugggingface hub
policy_state_dict, cfg = pull_model_from_hub(repo_id="OpenDILabCommunity/LunarLander-v2-DDPG")
# Instantiate the agent
agent = DDPGAgent(
env_id="LunarLanderContinuous-v2",
exp_name="LunarLander-v2-DDPG",
cfg=cfg.exp_config,
policy_state_dict=policy_state_dict
)
# Continue training
agent.train(step=5000)
# Render the new agent performance
agent.deploy(enable_save_replay=True)
```
</details>
## Model Training
### Train the Model and Push to Huggingface_hub
<details close>
<summary>(Click for Details)</summary>
```shell
#Training Your Own Agent
python3 -u train.py
```
**train.py**
```python
from ding.bonus import DDPGAgent
from huggingface_ding import push_model_to_hub
# Instantiate the agent
agent = DDPGAgent(env_id="LunarLanderContinuous-v2", exp_name="LunarLander-v2-DDPG")
# Train the agent
return_ = agent.train(step=int(4000000), collector_env_num=4, evaluator_env_num=4)
# Push model to huggingface hub
push_model_to_hub(
agent=agent.best,
env_name="OpenAI/Gym/Box2d",
task_name="LunarLander-v2",
algo_name="DDPG",
wandb_url=return_.wandb_url,
github_repo_url="https://github.com/opendilab/DI-engine",
github_doc_model_url="https://di-engine-docs.readthedocs.io/en/latest/12_policies/ddpg.html",
github_doc_env_url="https://di-engine-docs.readthedocs.io/en/latest/13_envs/lunarlander.html",
installation_guide="pip3 install DI-engine[common_env]",
usage_file_by_git_clone="./ddpg/lunarlander_ddpg_deploy.py",
usage_file_by_huggingface_ding="./ddpg/lunarlander_ddpg_download.py",
train_file="./ddpg/lunarlander_ddpg.py",
repo_id="OpenDILabCommunity/LunarLander-v2-DDPG",
create_repo=False
)
```
</details>
**Configuration**
<details close>
<summary>(Click for Details)</summary>
```python
exp_config = {
'env': {
'manager': {
'episode_num': float("inf"),
'max_retry': 1,
'retry_type': 'reset',
'auto_reset': True,
'step_timeout': None,
'reset_timeout': None,
'retry_waiting_time': 0.1,
'cfg_type': 'BaseEnvManagerDict'
},
'stop_value': 260,
'n_evaluator_episode': 8,
'env_id': 'LunarLanderContinuous-v2',
'collector_env_num': 8,
'evaluator_env_num': 8,
'act_scale': True
},
'policy': {
'model': {
'obs_shape': 8,
'action_shape': 2,
'twin_critic': True,
'action_space': 'regression'
},
'learn': {
'learner': {
'train_iterations': 1000000000,
'dataloader': {
'num_workers': 0
},
'log_policy': True,
'hook': {
'load_ckpt_before_run': '',
'log_show_after_iter': 100,
'save_ckpt_after_iter': 10000,
'save_ckpt_after_run': True
},
'cfg_type': 'BaseLearnerDict'
},
'update_per_collect': 2,
'batch_size': 128,
'learning_rate_actor': 0.001,
'learning_rate_critic': 0.001,
'ignore_done': False,
'target_theta': 0.005,
'discount_factor': 0.99,
'actor_update_freq': 1,
'noise': False,
'noise_sigma': 0.1,
'noise_range': {
'min': -0.5,
'max': 0.5
}
},
'collect': {
'collector': {
'collect_print_freq': 1000
},
'unroll_len': 1,
'noise_sigma': 0.1,
'n_sample': 48
},
'eval': {
'evaluator': {
'eval_freq': 100,
'render': {
'render_freq': -1,
'mode': 'train_iter'
},
'figure_path': None,
'cfg_type': 'InteractionSerialEvaluatorDict',
'stop_value': 260,
'n_episode': 8
}
},
'other': {
'replay_buffer': {
'replay_buffer_size': 20000
}
},
'on_policy': False,
'cuda': True,
'multi_gpu': False,
'bp_update_sync': True,
'traj_len_inf': False,
'type': 'ddpg',
'priority': False,
'priority_IS_weight': False,
'random_collect_size': 0,
'transition_with_policy_data': False,
'action_space': 'continuous',
'reward_batch_norm': False,
'multi_agent': False,
'cfg_type': 'DDPGPolicyDict'
},
'exp_name': 'LunarLander-v2-DDPG',
'seed': 0,
'wandb_logger': {
'gradient_logger': True,
'video_logger': True,
'plot_logger': True,
'action_logger': True,
'return_logger': False
}
}
```
</details>
**Training Procedure**
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
- **Weights & Biases (wandb):** [monitor link](https://wandb.ai/zjowowen/LunarLander-v2-DDPG)
## Model Information
<!-- Provide the basic links for the model. -->
- **Github Repository:** [repo link](https://github.com/opendilab/DI-engine)
- **Doc**: [DI-engine-docs Algorithm link](https://di-engine-docs.readthedocs.io/en/latest/12_policies/ddpg.html)
- **Configuration:** [config link](https://huggingface.co/OpenDILabCommunity/LunarLander-v2-DDPG/blob/main/policy_config.py)
- **Demo:** [video](https://huggingface.co/OpenDILabCommunity/LunarLander-v2-DDPG/blob/main/replay.mp4)
<!-- Provide the size information for the model. -->
- **Parameters total size:** 115.03 KB
- **Last Update Date:** 2023-09-22
## Environments
<!-- Address questions around what environment the model is intended to be trained and deployed at, including the necessary information needed to be provided for future users. -->
- **Benchmark:** OpenAI/Gym/Box2d
- **Task:** LunarLander-v2
- **Gym version:** 0.25.1
- **DI-engine version:** v0.4.9
- **PyTorch version:** 2.0.1+cu117
- **Doc**: [DI-engine-docs Environments link](https://di-engine-docs.readthedocs.io/en/latest/13_envs/lunarlander.html)
|
dss107/new_mp_base5
|
dss107
| 2023-09-22T12:57:32Z | 3 | 0 |
sentence-transformers
|
[
"sentence-transformers",
"pytorch",
"mpnet",
"setfit",
"text-classification",
"arxiv:2209.11055",
"license:apache-2.0",
"region:us"
] |
text-classification
| 2023-09-22T12:56:30Z |
---
license: apache-2.0
tags:
- setfit
- sentence-transformers
- text-classification
pipeline_tag: text-classification
---
# dss107/new_mp_base5
This is a [SetFit model](https://github.com/huggingface/setfit) that can be used for text classification. The model has been trained using an efficient few-shot learning technique that involves:
1. Fine-tuning a [Sentence Transformer](https://www.sbert.net) with contrastive learning.
2. Training a classification head with features from the fine-tuned Sentence Transformer.
## Usage
To use this model for inference, first install the SetFit library:
```bash
python -m pip install setfit
```
You can then run inference as follows:
```python
from setfit import SetFitModel
# Download from Hub and run inference
model = SetFitModel.from_pretrained("dss107/new_mp_base5")
# Run inference
preds = model(["i loved the spiderman movie!", "pineapple on pizza is the worst 🤮"])
```
## BibTeX entry and citation info
```bibtex
@article{https://doi.org/10.48550/arxiv.2209.11055,
doi = {10.48550/ARXIV.2209.11055},
url = {https://arxiv.org/abs/2209.11055},
author = {Tunstall, Lewis and Reimers, Nils and Jo, Unso Eun Seo and Bates, Luke and Korat, Daniel and Wasserblat, Moshe and Pereg, Oren},
keywords = {Computation and Language (cs.CL), FOS: Computer and information sciences, FOS: Computer and information sciences},
title = {Efficient Few-Shot Learning Without Prompts},
publisher = {arXiv},
year = {2022},
copyright = {Creative Commons Attribution 4.0 International}
}
```
|
shubhamWi91/train84
|
shubhamWi91
| 2023-09-22T12:41:31Z | 131 | 0 |
transformers
|
[
"transformers",
"pytorch",
"deta",
"object-detection",
"generated_from_trainer",
"dataset:dataloader_hf",
"base_model:jozhang97/deta-swin-large-o365",
"base_model:finetune:jozhang97/deta-swin-large-o365",
"endpoints_compatible",
"region:us"
] |
object-detection
| 2023-09-22T12:39:44Z |
---
base_model: jozhang97/deta-swin-large-o365
tags:
- generated_from_trainer
datasets:
- dataloader_hf
model-index:
- name: train84
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. -->
# train84
This model is a fine-tuned version of [jozhang97/deta-swin-large-o365](https://huggingface.co/jozhang97/deta-swin-large-o365) on the dataloader_hf 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: 1e-05
- train_batch_size: 20
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 1
### Training results
### Framework versions
- Transformers 4.32.1
- Pytorch 2.0.1+cu118
- Datasets 2.14.4
- Tokenizers 0.13.3
|
pp0236/rvc-models
|
pp0236
| 2023-09-22T12:41:13Z | 0 | 0 | null |
[
"RVC v2",
"audio-to-audio",
"en",
"region:us"
] |
audio-to-audio
| 2023-09-22T12:00:58Z |
---
language:
- en
pipeline_tag: audio-to-audio
tags:
- RVC v2
---
|
Destiny0621/a2c-PandaStack-v3
|
Destiny0621
| 2023-09-22T12:38:44Z | 0 | 0 |
stable-baselines3
|
[
"stable-baselines3",
"PandaStack-v3",
"deep-reinforcement-learning",
"reinforcement-learning",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-09-22T12:33:04Z |
---
library_name: stable-baselines3
tags:
- PandaStack-v3
- deep-reinforcement-learning
- reinforcement-learning
- stable-baselines3
model-index:
- name: A2C
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: PandaStack-v3
type: PandaStack-v3
metrics:
- type: mean_reward
value: -100.00 +/- 0.00
name: mean_reward
verified: false
---
# **A2C** Agent playing **PandaStack-v3**
This is a trained model of a **A2C** agent playing **PandaStack-v3**
using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3).
## Usage (with Stable-baselines3)
TODO: Add your code
```python
from stable_baselines3 import ...
from huggingface_sb3 import load_from_hub
...
```
|
ldos/text_shortening_model_v51
|
ldos
| 2023-09-22T12:21:44Z | 104 | 0 |
transformers
|
[
"transformers",
"pytorch",
"t5",
"text2text-generation",
"generated_from_trainer",
"base_model:google-t5/t5-small",
"base_model:finetune:google-t5/t5-small",
"license:apache-2.0",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text2text-generation
| 2023-09-22T12:03:36Z |
---
license: apache-2.0
base_model: t5-small
tags:
- generated_from_trainer
metrics:
- rouge
model-index:
- name: text_shortening_model_v51
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. -->
# text_shortening_model_v51
This model is a fine-tuned version of [t5-small](https://huggingface.co/t5-small) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 1.4778
- Rouge1: 0.5085
- Rouge2: 0.2885
- Rougel: 0.455
- Rougelsum: 0.4548
- Bert precision: 0.8747
- Bert recall: 0.8765
- Average word count: 8.5688
- Max word count: 16
- Min word count: 3
- Average token count: 13.0873
- % shortened texts with length > 12: 11.1111
## 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: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 50
### Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Bert precision | Bert recall | Average word count | Max word count | Min word count | Average token count | % shortened texts with length > 12 |
|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:--------------:|:-----------:|:------------------:|:--------------:|:--------------:|:-------------------:|:----------------------------------:|
| 2.2018 | 1.0 | 83 | 1.7246 | 0.4863 | 0.2654 | 0.437 | 0.4366 | 0.8646 | 0.8704 | 9.1111 | 18 | 3 | 13.5952 | 15.3439 |
| 1.7958 | 2.0 | 166 | 1.5840 | 0.4838 | 0.2672 | 0.4335 | 0.4329 | 0.8659 | 0.8697 | 8.8228 | 17 | 3 | 13.3386 | 13.2275 |
| 1.6387 | 3.0 | 249 | 1.5093 | 0.4927 | 0.2733 | 0.4416 | 0.4421 | 0.868 | 0.8728 | 8.9339 | 17 | 4 | 13.4656 | 15.0794 |
| 1.5337 | 4.0 | 332 | 1.4567 | 0.4967 | 0.2722 | 0.4399 | 0.4402 | 0.8681 | 0.8745 | 9.0847 | 17 | 4 | 13.6614 | 17.1958 |
| 1.4477 | 5.0 | 415 | 1.4176 | 0.5015 | 0.2728 | 0.4432 | 0.443 | 0.8698 | 0.8738 | 8.836 | 17 | 4 | 13.3069 | 13.4921 |
| 1.3548 | 6.0 | 498 | 1.3917 | 0.5068 | 0.28 | 0.4494 | 0.4498 | 0.8698 | 0.8771 | 9.1429 | 17 | 4 | 13.7222 | 15.6085 |
| 1.3128 | 7.0 | 581 | 1.3777 | 0.5054 | 0.2856 | 0.4452 | 0.4445 | 0.8698 | 0.8772 | 9.1323 | 17 | 5 | 13.7037 | 14.8148 |
| 1.2417 | 8.0 | 664 | 1.3575 | 0.5118 | 0.2904 | 0.4587 | 0.4591 | 0.8737 | 0.8779 | 8.8228 | 17 | 3 | 13.3466 | 12.963 |
| 1.1854 | 9.0 | 747 | 1.3508 | 0.5121 | 0.2894 | 0.4549 | 0.4552 | 0.8723 | 0.8768 | 8.828 | 18 | 4 | 13.418 | 13.4921 |
| 1.1384 | 10.0 | 830 | 1.3482 | 0.5203 | 0.2918 | 0.458 | 0.4579 | 0.8742 | 0.8809 | 9.0767 | 17 | 4 | 13.7196 | 14.2857 |
| 1.0986 | 11.0 | 913 | 1.3373 | 0.5083 | 0.2874 | 0.453 | 0.4521 | 0.8726 | 0.8765 | 8.8333 | 16 | 3 | 13.3254 | 12.963 |
| 1.0575 | 12.0 | 996 | 1.3345 | 0.5106 | 0.2872 | 0.4557 | 0.4552 | 0.8716 | 0.8773 | 9.045 | 17 | 3 | 13.5979 | 15.6085 |
| 1.0196 | 13.0 | 1079 | 1.3331 | 0.5127 | 0.2876 | 0.4578 | 0.4571 | 0.8734 | 0.8781 | 8.8836 | 16 | 3 | 13.4762 | 13.4921 |
| 0.9666 | 14.0 | 1162 | 1.3465 | 0.5052 | 0.2807 | 0.4467 | 0.4461 | 0.8717 | 0.8764 | 8.9048 | 16 | 3 | 13.3228 | 12.1693 |
| 0.9521 | 15.0 | 1245 | 1.3419 | 0.5053 | 0.2828 | 0.4464 | 0.4458 | 0.8727 | 0.8748 | 8.6508 | 16 | 3 | 13.0952 | 12.4339 |
| 0.917 | 16.0 | 1328 | 1.3438 | 0.512 | 0.2936 | 0.4563 | 0.456 | 0.8743 | 0.8784 | 8.7778 | 16 | 3 | 13.3783 | 13.7566 |
| 0.8852 | 17.0 | 1411 | 1.3436 | 0.5034 | 0.2753 | 0.4434 | 0.4422 | 0.871 | 0.8743 | 8.6984 | 16 | 3 | 13.1958 | 12.963 |
| 0.8778 | 18.0 | 1494 | 1.3529 | 0.5036 | 0.2765 | 0.4409 | 0.4404 | 0.8711 | 0.8748 | 8.7143 | 16 | 3 | 13.2646 | 11.9048 |
| 0.8513 | 19.0 | 1577 | 1.3494 | 0.5127 | 0.2886 | 0.4512 | 0.4508 | 0.8733 | 0.8783 | 8.7937 | 16 | 3 | 13.4233 | 11.3757 |
| 0.8265 | 20.0 | 1660 | 1.3512 | 0.5133 | 0.2854 | 0.4552 | 0.455 | 0.8724 | 0.8784 | 8.9497 | 16 | 4 | 13.5582 | 12.4339 |
| 0.8058 | 21.0 | 1743 | 1.3561 | 0.5087 | 0.2825 | 0.452 | 0.4516 | 0.8722 | 0.8765 | 8.8016 | 16 | 4 | 13.3122 | 11.9048 |
| 0.7751 | 22.0 | 1826 | 1.3602 | 0.5022 | 0.2802 | 0.4459 | 0.4455 | 0.8726 | 0.8741 | 8.5556 | 16 | 3 | 12.9656 | 9.7884 |
| 0.7625 | 23.0 | 1909 | 1.3737 | 0.5077 | 0.2827 | 0.4518 | 0.4515 | 0.874 | 0.8747 | 8.4444 | 16 | 3 | 12.9259 | 8.4656 |
| 0.7568 | 24.0 | 1992 | 1.3807 | 0.5078 | 0.284 | 0.4527 | 0.4523 | 0.8737 | 0.8758 | 8.5423 | 16 | 3 | 13.0741 | 8.4656 |
| 0.7309 | 25.0 | 2075 | 1.3857 | 0.5105 | 0.2863 | 0.4522 | 0.4528 | 0.8743 | 0.8761 | 8.5661 | 16 | 3 | 13.1296 | 10.8466 |
| 0.7115 | 26.0 | 2158 | 1.3948 | 0.5107 | 0.2887 | 0.4556 | 0.4554 | 0.8743 | 0.8777 | 8.6561 | 16 | 3 | 13.2381 | 10.582 |
| 0.6933 | 27.0 | 2241 | 1.4063 | 0.5155 | 0.2905 | 0.4582 | 0.4583 | 0.8748 | 0.8778 | 8.7116 | 16 | 3 | 13.3201 | 10.8466 |
| 0.6751 | 28.0 | 2324 | 1.4170 | 0.5109 | 0.2894 | 0.453 | 0.4529 | 0.8748 | 0.8764 | 8.5635 | 16 | 3 | 13.1561 | 10.582 |
| 0.6655 | 29.0 | 2407 | 1.4178 | 0.5105 | 0.2821 | 0.4513 | 0.4506 | 0.8744 | 0.8767 | 8.6349 | 16 | 3 | 13.1429 | 11.9048 |
| 0.6577 | 30.0 | 2490 | 1.4196 | 0.5112 | 0.2895 | 0.4506 | 0.451 | 0.8735 | 0.8779 | 8.8439 | 16 | 3 | 13.4339 | 12.963 |
| 0.6584 | 31.0 | 2573 | 1.4155 | 0.51 | 0.285 | 0.4523 | 0.4526 | 0.8745 | 0.876 | 8.5926 | 16 | 3 | 13.0608 | 10.582 |
| 0.6464 | 32.0 | 2656 | 1.4257 | 0.5095 | 0.2882 | 0.455 | 0.4553 | 0.8753 | 0.876 | 8.5423 | 16 | 3 | 13.0794 | 9.2593 |
| 0.6319 | 33.0 | 2739 | 1.4304 | 0.5112 | 0.2886 | 0.4559 | 0.456 | 0.8752 | 0.8768 | 8.5661 | 16 | 3 | 13.1085 | 9.7884 |
| 0.6236 | 34.0 | 2822 | 1.4383 | 0.5117 | 0.2922 | 0.4581 | 0.4589 | 0.8753 | 0.8771 | 8.5741 | 16 | 3 | 13.1534 | 11.1111 |
| 0.6045 | 35.0 | 2905 | 1.4499 | 0.5081 | 0.2891 | 0.4561 | 0.4561 | 0.8742 | 0.8761 | 8.5529 | 16 | 3 | 13.1138 | 10.582 |
| 0.6041 | 36.0 | 2988 | 1.4628 | 0.5111 | 0.2875 | 0.455 | 0.4552 | 0.8747 | 0.8766 | 8.6111 | 16 | 3 | 13.1429 | 10.582 |
| 0.5983 | 37.0 | 3071 | 1.4532 | 0.512 | 0.2886 | 0.4559 | 0.4562 | 0.8751 | 0.8781 | 8.672 | 16 | 3 | 13.2196 | 10.582 |
| 0.5869 | 38.0 | 3154 | 1.4504 | 0.5108 | 0.2857 | 0.4555 | 0.4551 | 0.8747 | 0.8783 | 8.7407 | 16 | 3 | 13.3148 | 11.3757 |
| 0.5875 | 39.0 | 3237 | 1.4620 | 0.5061 | 0.2859 | 0.4535 | 0.4537 | 0.8741 | 0.8759 | 8.5899 | 16 | 3 | 13.1058 | 10.8466 |
| 0.5722 | 40.0 | 3320 | 1.4642 | 0.5088 | 0.2858 | 0.4549 | 0.4546 | 0.874 | 0.8772 | 8.672 | 16 | 3 | 13.2116 | 10.8466 |
| 0.5818 | 41.0 | 3403 | 1.4630 | 0.5109 | 0.288 | 0.4561 | 0.456 | 0.8748 | 0.8771 | 8.5979 | 16 | 3 | 13.127 | 10.3175 |
| 0.5694 | 42.0 | 3486 | 1.4699 | 0.5113 | 0.2887 | 0.4567 | 0.4566 | 0.8754 | 0.8764 | 8.5317 | 16 | 3 | 13.0238 | 10.3175 |
| 0.5575 | 43.0 | 3569 | 1.4752 | 0.5111 | 0.2914 | 0.4574 | 0.4575 | 0.8751 | 0.8762 | 8.5106 | 16 | 3 | 12.963 | 10.3175 |
| 0.5566 | 44.0 | 3652 | 1.4740 | 0.5097 | 0.2878 | 0.4553 | 0.4554 | 0.8746 | 0.8769 | 8.619 | 16 | 3 | 13.1296 | 10.8466 |
| 0.5654 | 45.0 | 3735 | 1.4732 | 0.5048 | 0.2849 | 0.4519 | 0.4518 | 0.8738 | 0.8754 | 8.5529 | 16 | 3 | 13.0529 | 10.582 |
| 0.5569 | 46.0 | 3818 | 1.4763 | 0.5089 | 0.2889 | 0.4564 | 0.4562 | 0.8749 | 0.8765 | 8.5344 | 16 | 3 | 13.0397 | 10.0529 |
| 0.5527 | 47.0 | 3901 | 1.4786 | 0.5109 | 0.2895 | 0.4562 | 0.4566 | 0.8751 | 0.8771 | 8.6217 | 16 | 3 | 13.1508 | 11.3757 |
| 0.5461 | 48.0 | 3984 | 1.4769 | 0.5069 | 0.2869 | 0.454 | 0.4538 | 0.8742 | 0.8761 | 8.6085 | 16 | 3 | 13.1138 | 11.9048 |
| 0.5476 | 49.0 | 4067 | 1.4775 | 0.5084 | 0.2871 | 0.4537 | 0.4534 | 0.8747 | 0.8764 | 8.545 | 16 | 3 | 13.0529 | 10.8466 |
| 0.5525 | 50.0 | 4150 | 1.4778 | 0.5085 | 0.2885 | 0.455 | 0.4548 | 0.8747 | 0.8765 | 8.5688 | 16 | 3 | 13.0873 | 11.1111 |
### Framework versions
- Transformers 4.33.1
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3
|
Maniac/wav2vec2-xls-r-urdu
|
Maniac
| 2023-09-22T12:15:16Z | 27 | 1 |
transformers
|
[
"transformers",
"pytorch",
"safetensors",
"wav2vec2",
"automatic-speech-recognition",
"mozilla-foundation/common_voice_7_0",
"generated_from_trainer",
"sv",
"robust-speech-event",
"model_for_talk",
"hf-asr-leaderboard",
"ur",
"dataset:mozilla-foundation/common_voice_7_0",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] |
automatic-speech-recognition
| 2022-03-02T23:29:04Z |
---
language:
- ur
license: apache-2.0
tags:
- automatic-speech-recognition
- mozilla-foundation/common_voice_7_0
- generated_from_trainer
- sv
- robust-speech-event
- model_for_talk
- hf-asr-leaderboard
datasets:
- mozilla-foundation/common_voice_7_0
model-index:
- name: ''
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: Common Voice 8.0
type: mozilla-foundation/common_voice_8_0
args: ur
metrics:
- name: Test WER
type: wer
value: 67.48
---
<!-- 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. -->
#
This model is a fine-tuned version of [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on the MOZILLA-FOUNDATION/COMMON_VOICE_7_0 - UR dataset.
It achieves the following results on the evaluation set:
- Loss: 1.5614
- Wer: 0.6765
## 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: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- training_steps: 1000
- mixed_precision_training: Native AMP
### Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|:-------------:|:-----:|:----:|:---------------:|:------:|
| 1.9115 | 20.83 | 500 | 1.5400 | 0.7280 |
| 0.1155 | 41.67 | 1000 | 1.5614 | 0.6765 |
### Framework versions
- Transformers 4.16.0.dev0
- Pytorch 1.10.1+cu102
- Datasets 1.17.1.dev0
- Tokenizers 0.11.0
|
Penguin-N/LunarLander-v2
|
Penguin-N
| 2023-09-22T12:12:49Z | 1 | 0 |
stable-baselines3
|
[
"stable-baselines3",
"LunarLander-v2",
"deep-reinforcement-learning",
"reinforcement-learning",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-09-22T12:12:26Z |
---
library_name: stable-baselines3
tags:
- LunarLander-v2
- deep-reinforcement-learning
- reinforcement-learning
- stable-baselines3
model-index:
- name: PPO
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: LunarLander-v2
type: LunarLander-v2
metrics:
- type: mean_reward
value: 270.30 +/- 21.84
name: mean_reward
verified: false
---
# **PPO** Agent playing **LunarLander-v2**
This is a trained model of a **PPO** agent playing **LunarLander-v2**
using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3).
## Usage (with Stable-baselines3)
TODO: Add your code
```python
from stable_baselines3 import ...
from huggingface_sb3 import load_from_hub
...
```
|
ShivamMangale/XLM-Roberta-base-finetuned-squad-syn-first-now-squad-es-12k-6-epoch
|
ShivamMangale
| 2023-09-22T12:09:59Z | 132 | 0 |
transformers
|
[
"transformers",
"pytorch",
"xlm-roberta",
"question-answering",
"generated_from_trainer",
"dataset:squad",
"base_model:FacebookAI/xlm-roberta-base",
"base_model:finetune:FacebookAI/xlm-roberta-base",
"license:mit",
"endpoints_compatible",
"region:us"
] |
question-answering
| 2023-09-22T11:48:59Z |
---
license: mit
base_model: xlm-roberta-base
tags:
- generated_from_trainer
datasets:
- squad
model-index:
- name: XLM-Roberta-base-finetuned-squad-syn-first-now-squad-es-12k-6-epoch
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. -->
# XLM-Roberta-base-finetuned-squad-syn-first-now-squad-es-12k-6-epoch
This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on the squad 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: 2e-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: 6
### Training results
### Framework versions
- Transformers 4.33.2
- Pytorch 2.0.1+cu117
- Datasets 2.14.5
- Tokenizers 0.13.3
|
TiffanyTiffany/my_sequenceClassification_model
|
TiffanyTiffany
| 2023-09-22T12:03:22Z | 108 | 0 |
transformers
|
[
"transformers",
"pytorch",
"distilbert",
"text-classification",
"generated_from_trainer",
"dataset:ag_news",
"base_model:martin-ha/toxic-comment-model",
"base_model:finetune:martin-ha/toxic-comment-model",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2023-09-21T14:39:35Z |
---
base_model: martin-ha/toxic-comment-model
tags:
- generated_from_trainer
datasets:
- ag_news
metrics:
- accuracy
model-index:
- name: my_sequenceClassification_model
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: ag_news
type: ag_news
config: default
split: test
args: default
metrics:
- name: Accuracy
type: accuracy
value: 0.49276315789473685
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# my_sequenceClassification_model
This model is a fine-tuned version of [martin-ha/toxic-comment-model](https://huggingface.co/martin-ha/toxic-comment-model) on the ag_news dataset.
It achieves the following results on the evaluation set:
- Loss: 0.0299
- Accuracy: 0.4928
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 2
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:-----:|:---------------:|:--------:|
| 0.0255 | 1.0 | 7500 | 0.0390 | 0.4909 |
| 0.0133 | 2.0 | 15000 | 0.0299 | 0.4928 |
### Framework versions
- Transformers 4.33.2
- Pytorch 2.0.1
- Datasets 2.14.5
- Tokenizers 0.13.3
|
shubhamWi91/train83
|
shubhamWi91
| 2023-09-22T12:00:30Z | 132 | 0 |
transformers
|
[
"transformers",
"pytorch",
"deta",
"object-detection",
"generated_from_trainer",
"dataset:dataloader_hf",
"base_model:jozhang97/deta-swin-large-o365",
"base_model:finetune:jozhang97/deta-swin-large-o365",
"endpoints_compatible",
"region:us"
] |
object-detection
| 2023-09-22T11:58:39Z |
---
base_model: jozhang97/deta-swin-large-o365
tags:
- generated_from_trainer
datasets:
- dataloader_hf
model-index:
- name: train83
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. -->
# train83
This model is a fine-tuned version of [jozhang97/deta-swin-large-o365](https://huggingface.co/jozhang97/deta-swin-large-o365) on the dataloader_hf 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: 1e-05
- train_batch_size: 20
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 1
### Training results
### Framework versions
- Transformers 4.32.1
- Pytorch 2.0.1+cu118
- Datasets 2.14.4
- Tokenizers 0.13.3
|
Srit/my-exp
|
Srit
| 2023-09-22T11:52:44Z | 0 | 0 |
diffusers
|
[
"diffusers",
"safetensors",
"NxtWave-GenAI-Webinar",
"text-to-image",
"stable-diffusion",
"license:creativeml-openrail-m",
"autotrain_compatible",
"endpoints_compatible",
"diffusers:StableDiffusionPipeline",
"region:us"
] |
text-to-image
| 2023-09-22T11:45:14Z |
---
license: creativeml-openrail-m
tags:
- NxtWave-GenAI-Webinar
- text-to-image
- stable-diffusion
---
### My--exp Dreambooth model trained by Srit following the "Build your own Gen AI model" session by NxtWave.
Project Submission Code: SRIT-556
Sample pictures of this concept:
|
kaekitsune/kikuchi
|
kaekitsune
| 2023-09-22T11:49:16Z | 0 | 0 | null |
[
"license:creativeml-openrail-m",
"region:us"
] | null | 2023-09-22T11:40:37Z |
---
license: creativeml-openrail-m
---
|
Hiting/Mylora
|
Hiting
| 2023-09-22T11:48:34Z | 0 | 33 | null |
[
"license:cc-by-nc-sa-4.0",
"region:us"
] | null | 2023-09-05T13:14:50Z |
---
license: cc-by-nc-sa-4.0
---
|
Nonzerophilip/testThesisSmallSMP
|
Nonzerophilip
| 2023-09-22T11:48:28Z | 108 | 0 |
transformers
|
[
"transformers",
"pytorch",
"bert",
"token-classification",
"generated_from_trainer",
"base_model:KBLab/bert-base-swedish-cased-ner",
"base_model:finetune:KBLab/bert-base-swedish-cased-ner",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
token-classification
| 2023-09-22T11:37:09Z |
---
base_model: KBLab/bert-base-swedish-cased-ner
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: testThesisSmallSMP
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. -->
# testThesisSmallSMP
This model is a fine-tuned version of [KBLab/bert-base-swedish-cased-ner](https://huggingface.co/KBLab/bert-base-swedish-cased-ner) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.3275
- Precision: 0.6826
- Recall: 0.6477
- F1: 0.6647
- Accuracy: 0.8940
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 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: 3
### Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
| No log | 1.0 | 39 | 0.4518 | 0.4107 | 0.2614 | 0.3194 | 0.8555 |
| No log | 2.0 | 78 | 0.3469 | 0.6687 | 0.6193 | 0.6431 | 0.8923 |
| No log | 3.0 | 117 | 0.3275 | 0.6826 | 0.6477 | 0.6647 | 0.8940 |
### Framework versions
- Transformers 4.33.0
- Pytorch 2.0.1
- Datasets 2.14.5
- Tokenizers 0.13.3
|
kumarsatyamm1/cs
|
kumarsatyamm1
| 2023-09-22T11:35:14Z | 1 | 1 |
diffusers
|
[
"diffusers",
"text-to-image",
"autotrain",
"base_model:stabilityai/stable-diffusion-xl-base-1.0",
"base_model:finetune:stabilityai/stable-diffusion-xl-base-1.0",
"region:us"
] |
text-to-image
| 2023-09-20T11:03:54Z |
---
base_model: stabilityai/stable-diffusion-xl-base-1.0
instance_prompt: photo of a sks person
tags:
- text-to-image
- diffusers
- autotrain
inference: true
---
# DreamBooth trained by AutoTrain
Text encoder was not trained.
|
om-ashish-soni/guj-pos-tagging
|
om-ashish-soni
| 2023-09-22T11:25:42Z | 116 | 0 |
transformers
|
[
"transformers",
"pytorch",
"bert",
"token-classification",
"generated_from_trainer",
"base_model:om-ashish-soni/guj-pos-tagging",
"base_model:finetune:om-ashish-soni/guj-pos-tagging",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
token-classification
| 2023-09-22T10:45:30Z |
---
license: apache-2.0
base_model: om-ashish-soni/guj-pos-tagging
tags:
- generated_from_trainer
model-index:
- name: guj-pos-tagging
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. -->
# guj-pos-tagging
This model is a fine-tuned version of [om-ashish-soni/guj-pos-tagging](https://huggingface.co/om-ashish-soni/guj-pos-tagging) 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: 2e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 16
- total_train_batch_size: 128
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 1
### Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
| No log | 1.0 | 187 | 0.4466 | 0.8268 | 0.8346 | 0.8307 | 0.8688 |
### Framework versions
- Transformers 4.33.2
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3
|
CyberHarem/matsunaga_ryou_idolmastercinderellagirls
|
CyberHarem
| 2023-09-22T11:22:56Z | 0 | 0 | null |
[
"art",
"text-to-image",
"dataset:CyberHarem/matsunaga_ryou_idolmastercinderellagirls",
"license:mit",
"region:us"
] |
text-to-image
| 2023-09-22T11:13:26Z |
---
license: mit
datasets:
- CyberHarem/matsunaga_ryou_idolmastercinderellagirls
pipeline_tag: text-to-image
tags:
- art
---
# Lora of matsunaga_ryou_idolmastercinderellagirls
This model is trained with [HCP-Diffusion](https://github.com/7eu7d7/HCP-Diffusion). And the auto-training framework is maintained by [DeepGHS Team](https://huggingface.co/deepghs).
The base model used during training is [NAI](https://huggingface.co/deepghs/animefull-latest), and the base model used for generating preview images is [Meina/MeinaMix_V11](https://huggingface.co/Meina/MeinaMix_V11).
After downloading the pt and safetensors files for the specified step, you need to use them simultaneously. The pt file will be used as an embedding, while the safetensors file will be loaded for Lora.
For example, if you want to use the model from step 2380, you need to download `2380/matsunaga_ryou_idolmastercinderellagirls.pt` as the embedding and `2380/matsunaga_ryou_idolmastercinderellagirls.safetensors` for loading Lora. By using both files together, you can generate images for the desired characters.
**The best step we recommend is 2380**, with the score of 0.958. The trigger words are:
1. `matsunaga_ryou_idolmastercinderellagirls`
2. `long_hair, brown_eyes, brown_hair, jewelry, earrings, breasts, smile`
For the following groups, it is not recommended to use this model and we express regret:
1. Individuals who cannot tolerate any deviations from the original character design, even in the slightest detail.
2. Individuals who are facing the application scenarios with high demands for accuracy in recreating character outfits.
3. Individuals who cannot accept the potential randomness in AI-generated images based on the Stable Diffusion algorithm.
4. Individuals who are not comfortable with the fully automated process of training character models using LoRA, or those who believe that training character models must be done purely through manual operations to avoid disrespecting the characters.
5. Individuals who finds the generated image content offensive to their values.
These are available steps:
| Steps | Score | Download | pattern_1 | pattern_2 | pattern_3 | pattern_4 | pattern_5 | bikini | bondage | free | maid | miko | nude | nude2 | suit | yukata |
|:---------|:----------|:------------------------------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-------------------------------------------------|:--------------------------------------------------|:-------------------------------------|:-------------------------------------|:-------------------------------------|:-----------------------------------------------|:------------------------------------------------|:-------------------------------------|:-----------------------------------------|
| 5100 | 0.863 | [Download](5100/matsunaga_ryou_idolmastercinderellagirls.zip) |  |  |  |  |  | [<NSFW, click to see>](5100/previews/bikini.png) | [<NSFW, click to see>](5100/previews/bondage.png) |  |  |  | [<NSFW, click to see>](5100/previews/nude.png) | [<NSFW, click to see>](5100/previews/nude2.png) |  |  |
| 4760 | 0.842 | [Download](4760/matsunaga_ryou_idolmastercinderellagirls.zip) |  |  |  |  |  | [<NSFW, click to see>](4760/previews/bikini.png) | [<NSFW, click to see>](4760/previews/bondage.png) |  |  |  | [<NSFW, click to see>](4760/previews/nude.png) | [<NSFW, click to see>](4760/previews/nude2.png) |  |  |
| 4420 | 0.817 | [Download](4420/matsunaga_ryou_idolmastercinderellagirls.zip) |  |  |  |  |  | [<NSFW, click to see>](4420/previews/bikini.png) | [<NSFW, click to see>](4420/previews/bondage.png) |  |  |  | [<NSFW, click to see>](4420/previews/nude.png) | [<NSFW, click to see>](4420/previews/nude2.png) |  |  |
| 4080 | 0.748 | [Download](4080/matsunaga_ryou_idolmastercinderellagirls.zip) |  |  |  |  |  | [<NSFW, click to see>](4080/previews/bikini.png) | [<NSFW, click to see>](4080/previews/bondage.png) |  |  |  | [<NSFW, click to see>](4080/previews/nude.png) | [<NSFW, click to see>](4080/previews/nude2.png) |  |  |
| 3740 | 0.697 | [Download](3740/matsunaga_ryou_idolmastercinderellagirls.zip) |  |  |  |  |  | [<NSFW, click to see>](3740/previews/bikini.png) | [<NSFW, click to see>](3740/previews/bondage.png) |  |  |  | [<NSFW, click to see>](3740/previews/nude.png) | [<NSFW, click to see>](3740/previews/nude2.png) |  |  |
| 3400 | 0.686 | [Download](3400/matsunaga_ryou_idolmastercinderellagirls.zip) |  |  |  |  |  | [<NSFW, click to see>](3400/previews/bikini.png) | [<NSFW, click to see>](3400/previews/bondage.png) |  |  |  | [<NSFW, click to see>](3400/previews/nude.png) | [<NSFW, click to see>](3400/previews/nude2.png) |  |  |
| 3060 | 0.866 | [Download](3060/matsunaga_ryou_idolmastercinderellagirls.zip) |  |  |  |  |  | [<NSFW, click to see>](3060/previews/bikini.png) | [<NSFW, click to see>](3060/previews/bondage.png) |  |  |  | [<NSFW, click to see>](3060/previews/nude.png) | [<NSFW, click to see>](3060/previews/nude2.png) |  |  |
| 2720 | 0.872 | [Download](2720/matsunaga_ryou_idolmastercinderellagirls.zip) |  |  |  |  |  | [<NSFW, click to see>](2720/previews/bikini.png) | [<NSFW, click to see>](2720/previews/bondage.png) |  |  |  | [<NSFW, click to see>](2720/previews/nude.png) | [<NSFW, click to see>](2720/previews/nude2.png) |  |  |
| **2380** | **0.958** | [**Download**](2380/matsunaga_ryou_idolmastercinderellagirls.zip) |  |  |  |  |  | [<NSFW, click to see>](2380/previews/bikini.png) | [<NSFW, click to see>](2380/previews/bondage.png) |  |  |  | [<NSFW, click to see>](2380/previews/nude.png) | [<NSFW, click to see>](2380/previews/nude2.png) |  |  |
| 2040 | 0.805 | [Download](2040/matsunaga_ryou_idolmastercinderellagirls.zip) |  |  |  |  |  | [<NSFW, click to see>](2040/previews/bikini.png) | [<NSFW, click to see>](2040/previews/bondage.png) |  |  |  | [<NSFW, click to see>](2040/previews/nude.png) | [<NSFW, click to see>](2040/previews/nude2.png) |  |  |
| 1700 | 0.870 | [Download](1700/matsunaga_ryou_idolmastercinderellagirls.zip) |  |  |  |  |  | [<NSFW, click to see>](1700/previews/bikini.png) | [<NSFW, click to see>](1700/previews/bondage.png) |  |  |  | [<NSFW, click to see>](1700/previews/nude.png) | [<NSFW, click to see>](1700/previews/nude2.png) |  |  |
| 1360 | 0.849 | [Download](1360/matsunaga_ryou_idolmastercinderellagirls.zip) |  |  |  |  |  | [<NSFW, click to see>](1360/previews/bikini.png) | [<NSFW, click to see>](1360/previews/bondage.png) |  |  |  | [<NSFW, click to see>](1360/previews/nude.png) | [<NSFW, click to see>](1360/previews/nude2.png) |  |  |
| 1020 | 0.793 | [Download](1020/matsunaga_ryou_idolmastercinderellagirls.zip) |  |  |  |  |  | [<NSFW, click to see>](1020/previews/bikini.png) | [<NSFW, click to see>](1020/previews/bondage.png) |  |  |  | [<NSFW, click to see>](1020/previews/nude.png) | [<NSFW, click to see>](1020/previews/nude2.png) |  |  |
| 680 | 0.764 | [Download](680/matsunaga_ryou_idolmastercinderellagirls.zip) |  |  |  |  |  | [<NSFW, click to see>](680/previews/bikini.png) | [<NSFW, click to see>](680/previews/bondage.png) |  |  |  | [<NSFW, click to see>](680/previews/nude.png) | [<NSFW, click to see>](680/previews/nude2.png) |  |  |
| 340 | 0.510 | [Download](340/matsunaga_ryou_idolmastercinderellagirls.zip) |  |  |  |  |  | [<NSFW, click to see>](340/previews/bikini.png) | [<NSFW, click to see>](340/previews/bondage.png) |  |  |  | [<NSFW, click to see>](340/previews/nude.png) | [<NSFW, click to see>](340/previews/nude2.png) |  |  |
|
CyberHarem/nagi_akibameidosensou
|
CyberHarem
| 2023-09-22T11:20:37Z | 0 | 0 | null |
[
"art",
"text-to-image",
"dataset:CyberHarem/nagi_akibameidosensou",
"license:mit",
"region:us"
] |
text-to-image
| 2023-09-22T11:10:38Z |
---
license: mit
datasets:
- CyberHarem/nagi_akibameidosensou
pipeline_tag: text-to-image
tags:
- art
---
# Lora of nagi_akibameidosensou
This model is trained with [HCP-Diffusion](https://github.com/7eu7d7/HCP-Diffusion). And the auto-training framework is maintained by [DeepGHS Team](https://huggingface.co/deepghs).
The base model used during training is [NAI](https://huggingface.co/deepghs/animefull-latest), and the base model used for generating preview images is [Meina/MeinaMix_V11](https://huggingface.co/Meina/MeinaMix_V11).
After downloading the pt and safetensors files for the specified step, you need to use them simultaneously. The pt file will be used as an embedding, while the safetensors file will be loaded for Lora.
For example, if you want to use the model from step 4760, you need to download `4760/nagi_akibameidosensou.pt` as the embedding and `4760/nagi_akibameidosensou.safetensors` for loading Lora. By using both files together, you can generate images for the desired characters.
**The best step we recommend is 4760**, with the score of 0.968. The trigger words are:
1. `nagi_akibameidosensou`
2. `long_hair, purple_eyes, purple_hair, lipstick, makeup, purple_lips, maid_headdress, maid, multicolored_hair, red_hair`
For the following groups, it is not recommended to use this model and we express regret:
1. Individuals who cannot tolerate any deviations from the original character design, even in the slightest detail.
2. Individuals who are facing the application scenarios with high demands for accuracy in recreating character outfits.
3. Individuals who cannot accept the potential randomness in AI-generated images based on the Stable Diffusion algorithm.
4. Individuals who are not comfortable with the fully automated process of training character models using LoRA, or those who believe that training character models must be done purely through manual operations to avoid disrespecting the characters.
5. Individuals who finds the generated image content offensive to their values.
These are available steps:
| Steps | Score | Download | pattern_1 | pattern_2 | pattern_3 | bikini | bondage | free | maid | miko | nude | nude2 | suit | yukata |
|:---------|:----------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------|:--------------------------------------------------|:-------------------------------------|:-------------------------------------|:-------------------------------------|:-----------------------------------------------|:------------------------------------------------|:-------------------------------------|:-----------------------------------------|
| 5100 | 0.964 | [Download](5100/nagi_akibameidosensou.zip) |  |  |  |  | [<NSFW, click to see>](5100/previews/bondage.png) |  |  |  | [<NSFW, click to see>](5100/previews/nude.png) | [<NSFW, click to see>](5100/previews/nude2.png) |  |  |
| **4760** | **0.968** | [**Download**](4760/nagi_akibameidosensou.zip) |  |  |  |  | [<NSFW, click to see>](4760/previews/bondage.png) |  |  |  | [<NSFW, click to see>](4760/previews/nude.png) | [<NSFW, click to see>](4760/previews/nude2.png) |  |  |
| 4420 | 0.943 | [Download](4420/nagi_akibameidosensou.zip) |  |  |  |  | [<NSFW, click to see>](4420/previews/bondage.png) |  |  |  | [<NSFW, click to see>](4420/previews/nude.png) | [<NSFW, click to see>](4420/previews/nude2.png) |  |  |
| 4080 | 0.954 | [Download](4080/nagi_akibameidosensou.zip) |  |  |  |  | [<NSFW, click to see>](4080/previews/bondage.png) |  |  |  | [<NSFW, click to see>](4080/previews/nude.png) | [<NSFW, click to see>](4080/previews/nude2.png) |  |  |
| 3740 | 0.962 | [Download](3740/nagi_akibameidosensou.zip) |  |  |  |  | [<NSFW, click to see>](3740/previews/bondage.png) |  |  |  | [<NSFW, click to see>](3740/previews/nude.png) | [<NSFW, click to see>](3740/previews/nude2.png) |  |  |
| 3400 | 0.948 | [Download](3400/nagi_akibameidosensou.zip) |  |  |  |  | [<NSFW, click to see>](3400/previews/bondage.png) |  |  |  | [<NSFW, click to see>](3400/previews/nude.png) | [<NSFW, click to see>](3400/previews/nude2.png) |  |  |
| 3060 | 0.950 | [Download](3060/nagi_akibameidosensou.zip) |  |  |  |  | [<NSFW, click to see>](3060/previews/bondage.png) |  |  |  | [<NSFW, click to see>](3060/previews/nude.png) | [<NSFW, click to see>](3060/previews/nude2.png) |  |  |
| 2720 | 0.937 | [Download](2720/nagi_akibameidosensou.zip) |  |  |  |  | [<NSFW, click to see>](2720/previews/bondage.png) |  |  |  | [<NSFW, click to see>](2720/previews/nude.png) | [<NSFW, click to see>](2720/previews/nude2.png) |  |  |
| 2380 | 0.966 | [Download](2380/nagi_akibameidosensou.zip) |  |  |  |  | [<NSFW, click to see>](2380/previews/bondage.png) |  |  |  | [<NSFW, click to see>](2380/previews/nude.png) | [<NSFW, click to see>](2380/previews/nude2.png) |  |  |
| 2040 | 0.915 | [Download](2040/nagi_akibameidosensou.zip) |  |  |  |  | [<NSFW, click to see>](2040/previews/bondage.png) |  |  |  | [<NSFW, click to see>](2040/previews/nude.png) | [<NSFW, click to see>](2040/previews/nude2.png) |  |  |
| 1700 | 0.953 | [Download](1700/nagi_akibameidosensou.zip) |  |  |  |  | [<NSFW, click to see>](1700/previews/bondage.png) |  |  |  | [<NSFW, click to see>](1700/previews/nude.png) | [<NSFW, click to see>](1700/previews/nude2.png) |  |  |
| 1360 | 0.768 | [Download](1360/nagi_akibameidosensou.zip) |  |  |  |  | [<NSFW, click to see>](1360/previews/bondage.png) |  |  |  | [<NSFW, click to see>](1360/previews/nude.png) | [<NSFW, click to see>](1360/previews/nude2.png) |  |  |
| 1020 | 0.768 | [Download](1020/nagi_akibameidosensou.zip) |  |  |  |  | [<NSFW, click to see>](1020/previews/bondage.png) |  |  |  | [<NSFW, click to see>](1020/previews/nude.png) | [<NSFW, click to see>](1020/previews/nude2.png) |  |  |
| 680 | 0.720 | [Download](680/nagi_akibameidosensou.zip) |  |  |  |  | [<NSFW, click to see>](680/previews/bondage.png) |  |  |  | [<NSFW, click to see>](680/previews/nude.png) | [<NSFW, click to see>](680/previews/nude2.png) |  |  |
| 340 | 0.821 | [Download](340/nagi_akibameidosensou.zip) |  |  |  |  | [<NSFW, click to see>](340/previews/bondage.png) |  |  |  | [<NSFW, click to see>](340/previews/nude.png) | [<NSFW, click to see>](340/previews/nude2.png) |  |  |
|
Yntec/Splash
|
Yntec
| 2023-09-22T11:11:59Z | 634 | 1 |
diffusers
|
[
"diffusers",
"safetensors",
"Realism",
"Splash,",
"Explosion",
"Jehovah",
"stable-diffusion",
"stable-diffusion-diffusers",
"text-to-image",
"license:creativeml-openrail-m",
"autotrain_compatible",
"endpoints_compatible",
"diffusers:StableDiffusionPipeline",
"region:us"
] |
text-to-image
| 2023-09-22T09:12:14Z |
---
license: creativeml-openrail-m
library_name: diffusers
pipeline_tag: text-to-image
tags:
- Realism
- Splash,
- Explosion
- Jehovah
- stable-diffusion
- stable-diffusion-diffusers
- diffusers
- text-to-image
---
For trigger words you can use, check the original page at: https://civitai.com/models/81619?modelVersionId=91874
For the original model, check the original page at: https://civitai.com/models/66043?modelVersionId=70690
The Lehina Model v1.1 with the Splash v1.1 LoRA baked in and Lehina's base block, both by Jehovah.
Comparison:
(click for larger)
Prompt:
Pretty CUTE Girl and Dave Rapoza, Cartoon, sitting on a box of bottles, holding antique bottle, DETAILED CHIBI EYES, gorgeous detailed hair, Magazine ad, iconic, 1940, sharp focus. Illustration By KlaysMoji and artgerm and Clay Mann and and leyendecker
Sample and prompt:
Splash art. a beautiful 8 k photorealistic masterpiece oil. detailed eyes and faces. detailed face. ( ( of ( a crowd of girls chatting in living room, staring, swimsuits, portrait ) ( zoom out ) ) ( hyperrealism ) ( 1 6 k ) ( trending on artstation ). splash art by kyoani. beautiful painting by norman rockwell and raymond swanland, beautiful.
Recipe:
- SuperMerger Merge LoRA to checkpoint 1.0:
Checkpoint A: Lehina Model v1.1
Lora: Splashes v1.1
Output: Lehina Model v1.1+Splashes v1.1
- SuperMerger Weight sum TrainDifference MBW 1,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0
Model A:
Lehina Model v1.1+Splashes v1.1
Model B:
Lehina Model v1.1
Output:
Splash
|
suzii/pretrain-gpt2-large-2
|
suzii
| 2023-09-22T11:10:50Z | 132 | 0 |
transformers
|
[
"transformers",
"pytorch",
"gpt2",
"text-generation",
"generated_from_trainer",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2023-09-22T07:14:35Z |
---
tags:
- generated_from_trainer
model-index:
- name: pretrain-gpt2-large-2
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. -->
# pretrain-gpt2-large-2
This model was trained from scratch on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 2.4854
## 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: 1e-05
- train_batch_size: 16
- eval_batch_size: 1
- seed: 42
- distributed_type: multi-GPU
- num_devices: 2
- gradient_accumulation_steps: 32
- total_train_batch_size: 1024
- total_eval_batch_size: 2
- 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 |
|:-------------:|:-----:|:----:|:---------------:|
| No log | 1.0 | 167 | 2.5651 |
| No log | 2.0 | 335 | 2.5465 |
| No log | 3.0 | 502 | 2.5311 |
| No log | 4.0 | 670 | 2.5183 |
| No log | 4.99 | 837 | 2.5078 |
| No log | 6.0 | 1005 | 2.4995 |
| 2.5339 | 7.0 | 1173 | 2.4932 |
| 2.5339 | 8.0 | 1340 | 2.4888 |
| 2.5339 | 9.0 | 1508 | 2.4862 |
| 2.5339 | 9.96 | 1670 | 2.4854 |
### Framework versions
- Transformers 4.33.2
- Pytorch 2.0.1+cu117
- Datasets 2.14.5
- Tokenizers 0.13.3
|
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.