modelId
stringlengths 5
139
| author
stringlengths 2
42
| last_modified
timestamp[us, tz=UTC]date 2020-02-15 11:33:14
2025-08-31 06:26:39
| downloads
int64 0
223M
| likes
int64 0
11.7k
| library_name
stringclasses 530
values | tags
listlengths 1
4.05k
| pipeline_tag
stringclasses 55
values | createdAt
timestamp[us, tz=UTC]date 2022-03-02 23:29:04
2025-08-31 06:26:13
| card
stringlengths 11
1.01M
|
|---|---|---|---|---|---|---|---|---|---|
CyberHarem/ujiie_mutsumi_idolmastercinderellagirls
|
CyberHarem
| 2023-09-21T23:07:41Z | 0 | 0 | null |
[
"art",
"text-to-image",
"dataset:CyberHarem/ujiie_mutsumi_idolmastercinderellagirls",
"license:mit",
"region:us"
] |
text-to-image
| 2023-09-21T22:59:06Z |
---
license: mit
datasets:
- CyberHarem/ujiie_mutsumi_idolmastercinderellagirls
pipeline_tag: text-to-image
tags:
- art
---
# Lora of ujiie_mutsumi_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/ujiie_mutsumi_idolmastercinderellagirls.pt` as the embedding and `4080/ujiie_mutsumi_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 0.953. The trigger words are:
1. `ujiie_mutsumi_idolmastercinderellagirls`
2. `black_hair, long_hair, braid, smile, bangs, blush, open_mouth, black_eyes, blue_eyes, grey_eyes`
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 | bikini | bondage | free | maid | miko | nude | nude2 | suit | yukata |
|:---------|:----------|:-----------------------------------------------------------------|:-----------------------------------------|:--------------------------------------------------|:-------------------------------------|:-------------------------------------|:-------------------------------------|:-----------------------------------------------|:------------------------------------------------|:-------------------------------------|:-----------------------------------------|
| 5100 | 0.849 | [Download](5100/ujiie_mutsumi_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 | 0.946 | [Download](4760/ujiie_mutsumi_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 | 0.914 | [Download](4420/ujiie_mutsumi_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** | **0.953** | [**Download**](4080/ujiie_mutsumi_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 | 0.806 | [Download](3740/ujiie_mutsumi_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 | 0.903 | [Download](3400/ujiie_mutsumi_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 | 0.824 | [Download](3060/ujiie_mutsumi_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 | 0.882 | [Download](2720/ujiie_mutsumi_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 | 0.885 | [Download](2380/ujiie_mutsumi_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 | 0.774 | [Download](2040/ujiie_mutsumi_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 | 0.656 | [Download](1700/ujiie_mutsumi_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 | 0.789 | [Download](1360/ujiie_mutsumi_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 | 0.760 | [Download](1020/ujiie_mutsumi_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 | 0.656 | [Download](680/ujiie_mutsumi_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 | 0.620 | [Download](340/ujiie_mutsumi_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) |  |  |
|
onarganogun/videomae-base-finetuned-ucf101-subset
|
onarganogun
| 2023-09-21T23:07:20Z | 60 | 0 |
transformers
|
[
"transformers",
"pytorch",
"tensorboard",
"videomae",
"video-classification",
"generated_from_trainer",
"base_model:MCG-NJU/videomae-base",
"base_model:finetune:MCG-NJU/videomae-base",
"license:cc-by-nc-4.0",
"endpoints_compatible",
"region:us"
] |
video-classification
| 2023-08-17T08:57:11Z |
---
license: cc-by-nc-4.0
base_model: MCG-NJU/videomae-base
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: videomae-base-finetuned-ucf101-subset
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. -->
# videomae-base-finetuned-ucf101-subset
This model is a fine-tuned version of [MCG-NJU/videomae-base](https://huggingface.co/MCG-NJU/videomae-base) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.4051
- Accuracy: 0.8714
## 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
- training_steps: 148
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 2.1336 | 0.26 | 38 | 1.7594 | 0.5857 |
| 0.9483 | 1.26 | 76 | 0.9110 | 0.7286 |
| 0.4881 | 2.26 | 114 | 0.5500 | 0.8571 |
| 0.3729 | 3.23 | 148 | 0.4051 | 0.8714 |
### Framework versions
- Transformers 4.31.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.4
- Tokenizers 0.13.3
|
daochf/Lora-MetaLlama2-7b-chat-hf-PuceDs05-v01
|
daochf
| 2023-09-21T23:07:08Z | 2 | 0 |
peft
|
[
"peft",
"region:us"
] | null | 2023-09-21T23:07:01Z |
---
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: True
- bnb_4bit_compute_dtype: float16
### Framework versions
- PEFT 0.5.0
|
Brecon/training_model
|
Brecon
| 2023-09-21T22:36:39Z | 115 | 0 |
transformers
|
[
"transformers",
"pytorch",
"distilbert",
"text-classification",
"generated_from_trainer",
"base_model:distilbert/distilbert-base-uncased",
"base_model:finetune:distilbert/distilbert-base-uncased",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2023-09-13T22:35:48Z |
---
license: apache-2.0
base_model: distilbert-base-uncased
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: training_model
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# training_model
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.8963
- Accuracy: 0.2903
## 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: 4
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| No log | 1.0 | 8 | 0.9177 | 0.3548 |
| No log | 2.0 | 16 | 0.8915 | 0.3548 |
| No log | 3.0 | 24 | 0.8937 | 0.2903 |
| No log | 4.0 | 32 | 0.8963 | 0.2903 |
### Framework versions
- Transformers 4.33.1
- Pytorch 2.0.1+cpu
- Datasets 2.14.5
- Tokenizers 0.11.0
|
aurekero/DRL_model01
|
aurekero
| 2023-09-21T22:17:54Z | 0 | 0 |
stable-baselines3
|
[
"stable-baselines3",
"LunarLander-v2",
"deep-reinforcement-learning",
"reinforcement-learning",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-09-21T22:16:15Z |
---
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: 253.54 +/- 19.58
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
...
```
|
CyberHarem/kusakabe_wakaba_idolmastercinderellagirls
|
CyberHarem
| 2023-09-21T22:11:32Z | 0 | 0 | null |
[
"art",
"text-to-image",
"dataset:CyberHarem/kusakabe_wakaba_idolmastercinderellagirls",
"license:mit",
"region:us"
] |
text-to-image
| 2023-09-21T21:59:56Z |
---
license: mit
datasets:
- CyberHarem/kusakabe_wakaba_idolmastercinderellagirls
pipeline_tag: text-to-image
tags:
- art
---
# Lora of kusakabe_wakaba_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/kusakabe_wakaba_idolmastercinderellagirls.pt` as the embedding and `4760/kusakabe_wakaba_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 0.990. The trigger words are:
1. `kusakabe_wakaba_idolmastercinderellagirls`
2. `brown_hair, long_hair, green_eyes, blush, smile, open_mouth, thick_eyebrows, wavy_hair, hair_ornament`
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 | 0.979 | [Download](5100/kusakabe_wakaba_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** | **0.990** | [**Download**](4760/kusakabe_wakaba_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 | 0.983 | [Download](4420/kusakabe_wakaba_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 | 0.970 | [Download](4080/kusakabe_wakaba_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 | 0.982 | [Download](3740/kusakabe_wakaba_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 | 0.972 | [Download](3400/kusakabe_wakaba_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 | 0.982 | [Download](3060/kusakabe_wakaba_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/kusakabe_wakaba_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 | 0.975 | [Download](2380/kusakabe_wakaba_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 | 0.978 | [Download](2040/kusakabe_wakaba_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 | 0.984 | [Download](1700/kusakabe_wakaba_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 | 0.987 | [Download](1360/kusakabe_wakaba_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 | 0.922 | [Download](1020/kusakabe_wakaba_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 | 0.960 | [Download](680/kusakabe_wakaba_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 | 0.716 | [Download](340/kusakabe_wakaba_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) |  |  |
|
Ekemainai12/ppo-Huggy
|
Ekemainai12
| 2023-09-21T21:43:17Z | 1 | 0 |
ml-agents
|
[
"ml-agents",
"tensorboard",
"onnx",
"Huggy",
"deep-reinforcement-learning",
"reinforcement-learning",
"ML-Agents-Huggy",
"region:us"
] |
reinforcement-learning
| 2023-09-21T21:43:04Z |
---
library_name: ml-agents
tags:
- Huggy
- deep-reinforcement-learning
- reinforcement-learning
- ML-Agents-Huggy
---
# **ppo** Agent playing **Huggy**
This is a trained model of a **ppo** agent playing **Huggy**
using the [Unity ML-Agents Library](https://github.com/Unity-Technologies/ml-agents).
## Usage (with ML-Agents)
The Documentation: https://unity-technologies.github.io/ml-agents/ML-Agents-Toolkit-Documentation/
We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub:
- A *short tutorial* where you teach Huggy the Dog 🐶 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: Ekemainai12/ppo-Huggy
3. Step 2: Select your *.nn /*.onnx file
4. Click on Watch the agent play 👀
|
christopherastone/distilgpt2-proofs
|
christopherastone
| 2023-09-21T21:41:35Z | 139 | 0 |
transformers
|
[
"transformers",
"pytorch",
"tf",
"jax",
"safetensors",
"gpt2",
"text-generation",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2022-03-02T23:29:05Z |
---
widget:
- text: "Let MATH be given."
- text: "If MATH is a nonempty"
- text: "By the inductive hypothesis,"
---
[DistilGPT2](https://huggingface.co/distilgpt2) English language model fine-tuned on mathematical proofs extracted from [arXiv.org](https://arxiv.org) LaTeX sources from 1992 to 2020.
Proofs have been cleaned up a bit. In particular, they use
* `CITE` for any citation
* `REF` for any reference
* `MATH` for any LaTeX mathematical formula
* `CASE:` for any `\item` or labeled subcase.
|
Panchovix/Synthia-70B-v1.2b_4.65bpw-h6-exl2
|
Panchovix
| 2023-09-21T21:33:15Z | 7 | 2 |
transformers
|
[
"transformers",
"llama",
"text-generation",
"license:llama2",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2023-09-18T19:23:55Z |
---
license: llama2
---
4.65 bit/bpw quantization of Synthia-70B-v1.2b (https://huggingface.co/migtissera/Synthia-70B-v1.2), using exllamav2.
Update on 21/09/2023: Re-quantized with latest exllamav2 update, which fixes some measurement issues.
|
CyberHarem/nanjou_hikaru_idolmastercinderellagirls
|
CyberHarem
| 2023-09-21T21:24:52Z | 0 | 0 | null |
[
"art",
"text-to-image",
"dataset:CyberHarem/nanjou_hikaru_idolmastercinderellagirls",
"license:mit",
"region:us"
] |
text-to-image
| 2023-09-21T21:15:10Z |
---
license: mit
datasets:
- CyberHarem/nanjou_hikaru_idolmastercinderellagirls
pipeline_tag: text-to-image
tags:
- art
---
# Lora of nanjou_hikaru_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/nanjou_hikaru_idolmastercinderellagirls.pt` as the embedding and `5100/nanjou_hikaru_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 0.772. The trigger words are:
1. `nanjou_hikaru_idolmastercinderellagirls`
2. `long_hair, blue_eyes, black_hair, smile, ahoge`
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** | **0.772** | [**Download**](5100/nanjou_hikaru_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 | 0.721 | [Download](4760/nanjou_hikaru_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 | 0.747 | [Download](4420/nanjou_hikaru_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 | 0.660 | [Download](4080/nanjou_hikaru_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 | 0.699 | [Download](3740/nanjou_hikaru_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 | 0.705 | [Download](3400/nanjou_hikaru_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 | 0.656 | [Download](3060/nanjou_hikaru_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 | 0.628 | [Download](2720/nanjou_hikaru_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 | 0.612 | [Download](2380/nanjou_hikaru_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 | 0.509 | [Download](2040/nanjou_hikaru_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 | 0.577 | [Download](1700/nanjou_hikaru_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 | 0.523 | [Download](1360/nanjou_hikaru_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 | 0.450 | [Download](1020/nanjou_hikaru_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 | 0.409 | [Download](680/nanjou_hikaru_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 | 0.188 | [Download](340/nanjou_hikaru_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) |  |  |
|
mchen-hf-2023/q-FrozenLake-v1-4x4-noSlippery
|
mchen-hf-2023
| 2023-09-21T20:42:12Z | 0 | 0 | null |
[
"FrozenLake-v1-4x4-no_slippery",
"q-learning",
"reinforcement-learning",
"custom-implementation",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-09-21T20:42:07Z |
---
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="mchen-hf-2023/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"])
```
|
CyberHarem/matsubara_saya_idolmastercinderellagirls
|
CyberHarem
| 2023-09-21T20:39:35Z | 0 | 0 | null |
[
"art",
"text-to-image",
"dataset:CyberHarem/matsubara_saya_idolmastercinderellagirls",
"license:mit",
"region:us"
] |
text-to-image
| 2023-09-21T20:29:24Z |
---
license: mit
datasets:
- CyberHarem/matsubara_saya_idolmastercinderellagirls
pipeline_tag: text-to-image
tags:
- art
---
# Lora of matsubara_saya_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/matsubara_saya_idolmastercinderellagirls.pt` as the embedding and `3060/matsubara_saya_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 0.995. The trigger words are:
1. `matsubara_saya_idolmastercinderellagirls`
2. `short_hair, red_eyes, black_hair, jewelry, earrings, hat, 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 | pattern_5 | bikini | bondage | free | maid | miko | nude | nude2 | suit | yukata |
|:---------|:----------|:------------------------------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------|:--------------------------------------------------|:-------------------------------------|:-------------------------------------|:-------------------------------------|:-----------------------------------------------|:------------------------------------------------|:-------------------------------------|:-----------------------------------------|
| 5100 | 0.915 | [Download](5100/matsubara_saya_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 | 0.985 | [Download](4760/matsubara_saya_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 | 0.967 | [Download](4420/matsubara_saya_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/matsubara_saya_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 | 0.989 | [Download](3740/matsubara_saya_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 | 0.892 | [Download](3400/matsubara_saya_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** | **0.995** | [**Download**](3060/matsubara_saya_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 | 0.991 | [Download](2720/matsubara_saya_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 | 0.956 | [Download](2380/matsubara_saya_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 | 0.948 | [Download](2040/matsubara_saya_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 | 0.912 | [Download](1700/matsubara_saya_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 | 0.976 | [Download](1360/matsubara_saya_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 | 0.901 | [Download](1020/matsubara_saya_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 | 0.939 | [Download](680/matsubara_saya_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 | 0.681 | [Download](340/matsubara_saya_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) |  |  |
|
mina-t/Test1
|
mina-t
| 2023-09-21T20:34:54Z | 0 | 0 |
transformers
|
[
"transformers",
"chemistry",
"text-classification",
"en",
"dataset:teleprint-me/phi-1",
"arxiv:1910.09700",
"license:other",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2023-08-16T23:17:39Z |
---
license: other
datasets:
- teleprint-me/phi-1
language:
- en
metrics:
- accuracy
library_name: transformers
pipeline_tag: text-classification
tags:
- chemistry
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
This modelcard aims to be a base template for new models. It has been generated using [this raw template](https://github.com/huggingface/huggingface_hub/blob/main/src/huggingface_hub/templates/modelcard_template.md?plain=1).
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
- **Developed by:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Data Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Data Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
J, o, h, n, , S, m, i, t, h, ,, , J, a, n, e, , D, o, e
## Model Card Contact
[More Information Needed]
|
stillerman/ppo-Huggy
|
stillerman
| 2023-09-21T20:20:17Z | 0 | 0 |
ml-agents
|
[
"ml-agents",
"tensorboard",
"onnx",
"Huggy",
"deep-reinforcement-learning",
"reinforcement-learning",
"ML-Agents-Huggy",
"region:us"
] |
reinforcement-learning
| 2023-09-21T20:20:10Z |
---
library_name: ml-agents
tags:
- Huggy
- deep-reinforcement-learning
- reinforcement-learning
- ML-Agents-Huggy
---
# **ppo** Agent playing **Huggy**
This is a trained model of a **ppo** agent playing **Huggy**
using the [Unity ML-Agents Library](https://github.com/Unity-Technologies/ml-agents).
## Usage (with ML-Agents)
The Documentation: https://unity-technologies.github.io/ml-agents/ML-Agents-Toolkit-Documentation/
We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub:
- A *short tutorial* where you teach Huggy the Dog 🐶 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: stillerman/ppo-Huggy
3. Step 2: Select your *.nn /*.onnx file
4. Click on Watch the agent play 👀
|
HusseinHE/icbinh
|
HusseinHE
| 2023-09-21T20:12:39Z | 16 | 0 |
diffusers
|
[
"diffusers",
"safetensors",
"text-to-image",
"stable-diffusion",
"license:creativeml-openrail-m",
"autotrain_compatible",
"endpoints_compatible",
"diffusers:StableDiffusionPipeline",
"region:us"
] |
text-to-image
| 2023-09-21T20:07:02Z |
---
license: creativeml-openrail-m
tags:
- text-to-image
- stable-diffusion
---
### ICBINH Dreambooth model trained by HusseinHE with [TheLastBen's fast-DreamBooth](https://colab.research.google.com/github/TheLastBen/fast-stable-diffusion/blob/main/fast-DreamBooth.ipynb) notebook
Test the concept via A1111 Colab [fast-Colab-A1111](https://colab.research.google.com/github/TheLastBen/fast-stable-diffusion/blob/main/fast_stable_diffusion_AUTOMATIC1111.ipynb)
Sample pictures of this concept:
|
mmunoz96/results
|
mmunoz96
| 2023-09-21T20:07:35Z | 254 | 0 |
transformers
|
[
"transformers",
"pytorch",
"vit",
"image-classification",
"generated_from_trainer",
"dataset:food101",
"base_model:google/vit-base-patch16-224-in21k",
"base_model:finetune:google/vit-base-patch16-224-in21k",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
image-classification
| 2023-09-21T20:03:55Z |
---
license: apache-2.0
base_model: google/vit-base-patch16-224-in21k
tags:
- generated_from_trainer
datasets:
- food101
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 [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the food101 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: 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
### Framework versions
- Transformers 4.33.2
- Pytorch 2.0.1+cpu
- Datasets 2.14.5
- Tokenizers 0.13.3
|
jtlowell/cozy_wall
|
jtlowell
| 2023-09-21T19:50:20Z | 3 | 0 |
diffusers
|
[
"diffusers",
"stable-diffusion-xl",
"stable-diffusion-xl-diffusers",
"text-to-image",
"lora",
"dataset:jtlowell/jay_cozy_1",
"base_model:stabilityai/stable-diffusion-xl-base-1.0",
"base_model:adapter:stabilityai/stable-diffusion-xl-base-1.0",
"region:us"
] |
text-to-image
| 2023-09-21T16:55:46Z |
---
base_model: stabilityai/stable-diffusion-xl-base-1.0
instance_prompt: cozy_wall
tags:
- stable-diffusion-xl
- stable-diffusion-xl-diffusers
- text-to-image
- diffusers
- lora
inference: true
datasets:
- jtlowell/jay_cozy_1
---
# LoRA DreamBooth - jtlowell/cozy_wall
These are LoRA adaption weights for stabilityai/stable-diffusion-xl-base-1.0.
The weights were trained on the concept prompt:
`cozy_wall`
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_wall')
pipe.to("cuda")
prompt = "A majestic cozy_wall jumping from a big stone at night"
image = pipe(prompt=prompt, num_inference_steps=50).images[0]
```
|
fsuarez/autotrain-image-classification-86974143294
|
fsuarez
| 2023-09-21T19:47:43Z | 194 | 0 |
transformers
|
[
"transformers",
"pytorch",
"safetensors",
"swin",
"image-classification",
"autotrain",
"vision",
"dataset:fsuarez/autotrain-data-image-classification",
"co2_eq_emissions",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
image-classification
| 2023-09-04T14:31:09Z |
---
tags:
- autotrain
- vision
- image-classification
datasets:
- fsuarez/autotrain-data-image-classification
widget:
- src: https://huggingface.co/datasets/mishig/sample_images/resolve/main/tiger.jpg
example_title: Tiger
- src: https://huggingface.co/datasets/mishig/sample_images/resolve/main/teapot.jpg
example_title: Teapot
- src: https://huggingface.co/datasets/mishig/sample_images/resolve/main/palace.jpg
example_title: Palace
co2_eq_emissions:
emissions: 1.6524320573590656
---
## 📒 image-classification-model
This model has undergone training on the "image-classification" dataset, focusing on multi-class classification to categorize specific segments of websites. Each segment corresponds to one of six potential features, encompassing a broad spectrum of web elements, including:
- **Button**: Identifying interactive buttons that users can click or tap on for various website functions.
- **Textfield**: Recognizing text input fields where users can type or enter information.
- **Checkbox**: Detecting checkboxes that users can select or deselect to make choices or indicate preferences.
- **Radiobutton**: Identifying radio buttons that allow users to choose a single option from a list.
- **Tables**: Recognizing tabular data structures that organize information in rows and columns.
- **AppBar**: Detecting app bars or navigation bars typically found at the top of web pages, often containing menus, search bars, or branding elements.
This extensive training equips the model with the ability to accurately classify these web elements.
# 🧪 Dataset Content
The dataset is structured to facilitate the analysis of website components. It includes various types of objects commonly found on websites, such as buttons, text fields, checkboxes, radio buttons, tables, and app bars. Each object type is organized into its respective category within the dataset, allowing for precise classification.
| Web Element Category | Quantity of images |
|----------------------|--------------------|
| Button | 2934 |
| Textfield | 100 |
| Checkbox | 422 |
| Radiobutton | 466 |
| Tables | 100 |
| AppBar | 100 |
# 🤗 Model Trained Using AutoTrain
- Problem type: Multi-class Classification
- Model ID: 86974143294
- CO2 Emissions (in grams): 1.6524
## 📐 Validation Metrics
- Loss: 0.079
- Accuracy: 0.983
- Macro F1: 0.967
- Micro F1: 0.983
- Weighted F1: 0.983
- Macro Precision: 0.971
- Micro Precision: 0.983
- Weighted Precision: 0.983
- Macro Recall: 0.964
- Micro Recall: 0.983
- Weighted Recall: 0.983
|
jgeselowitz/poem_labeler
|
jgeselowitz
| 2023-09-21T19:43:00Z | 105 | 0 |
transformers
|
[
"transformers",
"pytorch",
"distilbert",
"text-classification",
"generated_from_trainer",
"base_model:distilbert/distilbert-base-uncased",
"base_model:finetune:distilbert/distilbert-base-uncased",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2023-09-21T19:24:46Z |
---
license: apache-2.0
base_model: distilbert-base-uncased
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: poem_labeler
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. -->
# poem_labeler
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 1.1318
- Accuracy: 0.7315
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3.0
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 1.0602 | 1.0 | 2382 | 0.9264 | 0.6935 |
| 0.5889 | 2.0 | 4764 | 0.9186 | 0.723 |
| 0.2638 | 3.0 | 7146 | 1.1318 | 0.7315 |
### Framework versions
- Transformers 4.33.2
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3
|
rfanucchi/ppo-LunarLander-v2
|
rfanucchi
| 2023-09-21T19:37:01Z | 0 | 0 |
stable-baselines3
|
[
"stable-baselines3",
"LunarLander-v2",
"deep-reinforcement-learning",
"reinforcement-learning",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-09-21T19:34:44Z |
---
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: 248.58 +/- 38.88
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
...
```
|
glaiveai/glaive-coder-7b
|
glaiveai
| 2023-09-21T19:35:50Z | 1,565 | 54 |
transformers
|
[
"transformers",
"pytorch",
"llama",
"text-generation",
"code",
"en",
"dataset:glaiveai/glaive-code-assistant",
"license:llama2",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2023-09-17T14:49:44Z |
---
license: llama2
datasets:
- glaiveai/glaive-code-assistant
language:
- en
tags:
- code
---
# Glaive-coder-7b
Glaive-coder-7b is a 7B parameter code model trained on a dataset of ~140k programming related problems and solutions generated from Glaive’s synthetic data generation platform.
The model is fine-tuned on the CodeLlama-7b model.
## Usage:
The model is trained to act as a code assistant, and can do both single instruction following and multi-turn conversations.
It follows the same prompt format as CodeLlama-7b-Instruct-
```
<s>[INST]
<<SYS>>
{{ system_prompt }}
<</SYS>>
{{ user_msg }} [/INST] {{ model_answer }} </s>
<s>[INST] {{ user_msg }} [/INST]
```
You can run the model in the following way-
```python
from transformers import AutoModelForCausalLM , AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained("glaiveai/glaive-coder-7b")
model = AutoModelForCausalLM.from_pretrained("glaiveai/glaive-coder-7b").half().cuda()
def fmt_prompt(prompt):
return f"<s> [INST] {prompt} [/INST]"
inputs = tokenizer(fmt_prompt(prompt),return_tensors="pt").to(model.device)
outputs = model.generate(**inputs,do_sample=True,temperature=0.1,top_p=0.95,max_new_tokens=100)
print(tokenizer.decode(outputs[0],skip_special_tokens=True,clean_up_tokenization_spaces=False))
```
## Benchmarks:
The model achieves a 63.1% pass@1 on HumanEval and a 45.2% pass@1 on MBPP, however it is evident that these benchmarks are not representative of real-world usage of code models so we are launching the [Code Models Arena](https://arena.glaive.ai/) to let users vote on model outputs so we can have a better understanding of user preference on code models and come up with new and better benchmarks. We plan to release the Arena results as soon as we have a sufficient amount of data.
Join the Glaive [discord](https://discord.gg/fjQ4uf3yWD) for improvement suggestions, bug-reports and collaborating on more open-source projects.
|
debabrata-ai/Nepali-NER-BERT
|
debabrata-ai
| 2023-09-21T19:32:56Z | 125 | 0 |
transformers
|
[
"transformers",
"pytorch",
"bert",
"fill-mask",
"ne",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
fill-mask
| 2023-09-21T12:42:33Z |
---
license: mit
language:
- ne
---
---
name:
- "Nepali-NER-BERT"
description:
- "Fine-tuned bert-based-multilingual-cased for Named Entity Recognition in Nepali."
tags:
- named-entity-recognition
- nepali-language
- bert-based-multilingual-cased
|
noelsinghsr/sagemaker-distilbert-emotion
|
noelsinghsr
| 2023-09-21T19:26:05Z | 103 | 0 |
transformers
|
[
"transformers",
"pytorch",
"distilbert",
"text-classification",
"generated_from_trainer",
"dataset:emotion",
"license:apache-2.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2023-09-21T19:24:14Z |
---
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- emotion
metrics:
- accuracy
model-index:
- name: sagemaker-distilbert-emotion
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: emotion
type: emotion
config: split
split: test
args: split
metrics:
- name: Accuracy
type: accuracy
value: 0.9125
---
<!-- 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. -->
# sagemaker-distilbert-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: 0.2634
- Accuracy: 0.9125
## 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: 32
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 1
- mixed_precision_training: Native AMP
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 0.9347 | 1.0 | 500 | 0.2634 | 0.9125 |
### Framework versions
- Transformers 4.28.1
- Pytorch 2.0.0
- Datasets 2.12.0
- Tokenizers 0.13.3
|
Panchovix/sheep-duck-llama-2_4.65bpw-h6-exl2
|
Panchovix
| 2023-09-21T19:12:21Z | 8 | 0 |
transformers
|
[
"transformers",
"llama",
"text-generation",
"license:llama2",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2023-09-18T18:41:15Z |
---
license: llama2
---
4.65 bits/bpw quantization of sheep-duck-llama-2 (https://huggingface.co/Riiid/sheep-duck-llama-2) with exllamav2.
Update on 21/09/2023: Re-did the quant with newest exllamav2 version, which fixed some measurement issues.
|
NousResearch/Llama-2-70b-chat-hf
|
NousResearch
| 2023-09-21T19:05:17Z | 625 | 19 |
transformers
|
[
"transformers",
"pytorch",
"safetensors",
"llama",
"text-generation",
"facebook",
"meta",
"llama-2",
"en",
"autotrain_compatible",
"text-generation-inference",
"region:us"
] |
text-generation
| 2023-07-19T04:36:22Z |
---
extra_gated_heading: Access Llama 2 on Hugging Face
extra_gated_description: >-
This is a form to enable access to Llama 2 on Hugging Face after you have been
granted access from Meta. Please visit the [Meta website](https://ai.meta.com/resources/models-and-libraries/llama-downloads) and accept our
license terms and acceptable use policy before submitting this form. Requests
will be processed in 1-2 days.
extra_gated_prompt: "**Your Hugging Face account email address MUST match the email you provide on the Meta website, or your request will not be approved.**"
extra_gated_button_content: Submit
extra_gated_fields:
I agree to share my name, email address and username with Meta and confirm that I have already been granted download access on the Meta website: checkbox
language:
- en
pipeline_tag: text-generation
inference: false
tags:
- facebook
- meta
- pytorch
- llama
- llama-2
---
# **Llama 2**
Llama 2 is a collection of pretrained and fine-tuned generative text models ranging in scale from 7 billion to 70 billion parameters. This is the repository for the 70B fine-tuned model, optimized for dialogue use cases and converted for the Hugging Face Transformers format. Links to other models can be found in the index at the bottom.
## Model Details
*Note: Use of this model is governed by the Meta license. In order to download the model weights and tokenizer, please visit the [website](https://ai.meta.com/resources/models-and-libraries/llama-downloads/) and accept our License before requesting access here.*
Meta developed and publicly released the Llama 2 family of large language models (LLMs), a collection of pretrained and fine-tuned generative text models ranging in scale from 7 billion to 70 billion parameters. Our fine-tuned LLMs, called Llama-2-Chat, are optimized for dialogue use cases. Llama-2-Chat models outperform open-source chat models on most benchmarks we tested, and in our human evaluations for helpfulness and safety, are on par with some popular closed-source models like ChatGPT and PaLM.
**Model Developers** Meta
**Variations** Llama 2 comes in a range of parameter sizes — 7B, 13B, and 70B — as well as pretrained and fine-tuned variations.
**Input** Models input text only.
**Output** Models generate text only.
**Model Architecture** Llama 2 is an auto-regressive language model that uses an optimized transformer architecture. The tuned versions use supervised fine-tuning (SFT) and reinforcement learning with human feedback (RLHF) to align to human preferences for helpfulness and safety.
||Training Data|Params|Content Length|GQA|Tokens|LR|
|---|---|---|---|---|---|---|
|Llama 2|*A new mix of publicly available online data*|7B|4k|✗|2.0T|3.0 x 10<sup>-4</sup>|
|Llama 2|*A new mix of publicly available online data*|13B|4k|✗|2.0T|3.0 x 10<sup>-4</sup>|
|Llama 2|*A new mix of publicly available online data*|70B|4k|✔|2.0T|1.5 x 10<sup>-4</sup>|
*Llama 2 family of models.* Token counts refer to pretraining data only. All models are trained with a global batch-size of 4M tokens. Bigger models - 70B -- use Grouped-Query Attention (GQA) for improved inference scalability.
**Model Dates** Llama 2 was trained between January 2023 and July 2023.
**Status** This is a static model trained on an offline dataset. Future versions of the tuned models will be released as we improve model safety with community feedback.
**License** A custom commercial license is available at: [https://ai.meta.com/resources/models-and-libraries/llama-downloads/](https://ai.meta.com/resources/models-and-libraries/llama-downloads/)
## Intended Use
**Intended Use Cases** Llama 2 is intended for commercial and research use in English. Tuned models are intended for assistant-like chat, whereas pretrained models can be adapted for a variety of natural language generation tasks.
**Out-of-scope Uses** Use in any manner that violates applicable laws or regulations (including trade compliance laws).Use in languages other than English. Use in any other way that is prohibited by the Acceptable Use Policy and Licensing Agreement for Llama 2.
## Hardware and Software
**Training Factors** We used custom training libraries, Meta's Research Super Cluster, and production clusters for pretraining. Fine-tuning, annotation, and evaluation were also performed on third-party cloud compute.
**Carbon Footprint** Pretraining utilized a cumulative 3.3M GPU hours of computation on hardware of type A100-80GB (TDP of 350-400W). Estimated total emissions were 539 tCO2eq, 100% of which were offset by Meta’s sustainability program.
||Time (GPU hours)|Power Consumption (W)|Carbon Emitted(tCO<sub>2</sub>eq)|
|---|---|---|---|
|Llama 2 7B|184320|400|31.22|
|Llama 2 13B|368640|400|62.44|
|Llama 2 70B|1720320|400|291.42|
|Total|3311616||539.00|
**CO<sub>2</sub> emissions during pretraining.** Time: total GPU time required for training each model. Power Consumption: peak power capacity per GPU device for the GPUs used adjusted for power usage efficiency. 100% of the emissions are directly offset by Meta's sustainability program, and because we are openly releasing these models, the pretraining costs do not need to be incurred by others.
## Training Data
**Overview** Llama 2 was pretrained on 2 trillion tokens of data from publicly available sources. The fine-tuning data includes publicly available instruction datasets, as well as over one million new human-annotated examples. Neither the pretraining nor the fine-tuning datasets include Meta user data.
**Data Freshness** The pretraining data has a cutoff of September 2022, but some tuning data is more recent, up to July 2023.
## Evaluation Results
In this section, we report the results for the Llama 1 and Llama 2 models on standard academic benchmarks.For all the evaluations, we use our internal evaluations library.
|Model|Size|Code|Commonsense Reasoning|World Knowledge|Reading Comprehension|Math|MMLU|BBH|AGI Eval|
|---|---|---|---|---|---|---|---|---|---|
|Llama 1|7B|14.1|60.8|46.2|58.5|6.95|35.1|30.3|23.9|
|Llama 1|13B|18.9|66.1|52.6|62.3|10.9|46.9|37.0|33.9|
|Llama 1|33B|26.0|70.0|58.4|67.6|21.4|57.8|39.8|41.7|
|Llama 1|65B|30.7|70.7|60.5|68.6|30.8|63.4|43.5|47.6|
|Llama 2|7B|16.8|63.9|48.9|61.3|14.6|45.3|32.6|29.3|
|Llama 2|13B|24.5|66.9|55.4|65.8|28.7|54.8|39.4|39.1|
|Llama 2|70B|**37.5**|**71.9**|**63.6**|**69.4**|**35.2**|**68.9**|**51.2**|**54.2**|
**Overall performance on grouped academic benchmarks.** *Code:* We report the average pass@1 scores of our models on HumanEval and MBPP. *Commonsense Reasoning:* We report the average of PIQA, SIQA, HellaSwag, WinoGrande, ARC easy and challenge, OpenBookQA, and CommonsenseQA. We report 7-shot results for CommonSenseQA and 0-shot results for all other benchmarks. *World Knowledge:* We evaluate the 5-shot performance on NaturalQuestions and TriviaQA and report the average. *Reading Comprehension:* For reading comprehension, we report the 0-shot average on SQuAD, QuAC, and BoolQ. *MATH:* We report the average of the GSM8K (8 shot) and MATH (4 shot) benchmarks at top 1.
|||TruthfulQA|Toxigen|
|---|---|---|---|
|Llama 1|7B|27.42|23.00|
|Llama 1|13B|41.74|23.08|
|Llama 1|33B|44.19|22.57|
|Llama 1|65B|48.71|21.77|
|Llama 2|7B|33.29|**21.25**|
|Llama 2|13B|41.86|26.10|
|Llama 2|70B|**50.18**|24.60|
**Evaluation of pretrained LLMs on automatic safety benchmarks.** For TruthfulQA, we present the percentage of generations that are both truthful and informative (the higher the better). For ToxiGen, we present the percentage of toxic generations (the smaller the better).
|||TruthfulQA|Toxigen|
|---|---|---|---|
|Llama-2-Chat|7B|57.04|**0.00**|
|Llama-2-Chat|13B|62.18|**0.00**|
|Llama-2-Chat|70B|**64.14**|0.01|
**Evaluation of fine-tuned LLMs on different safety datasets.** Same metric definitions as above.
## Ethical Considerations and Limitations
Llama 2 is a new technology that carries risks with use. Testing conducted to date has been in English, and has not covered, nor could it cover all scenarios. For these reasons, as with all LLMs, Llama 2’s potential outputs cannot be predicted in advance, and the model may in some instances produce inaccurate, biased or other objectionable responses to user prompts. Therefore, before deploying any applications of Llama 2, developers should perform safety testing and tuning tailored to their specific applications of the model.
Please see the Responsible Use Guide available at [https://ai.meta.com/llama/responsible-use-guide/](https://ai.meta.com/llama/responsible-use-guide)
## Reporting Issues
Please report any software “bug,” or other problems with the models through one of the following means:
- Reporting issues with the model: [github.com/facebookresearch/llama](http://github.com/facebookresearch/llama)
- Reporting problematic content generated by the model: [developers.facebook.com/llama_output_feedback](http://developers.facebook.com/llama_output_feedback)
- Reporting bugs and security concerns: [facebook.com/whitehat/info](http://facebook.com/whitehat/info)
## Llama Model Index
|Model|Llama2|Llama2-hf|Llama2-chat|Llama2-chat-hf|
|---|---|---|---|---|
|7B| [Link](https://huggingface.co/llamaste/Llama-2-7b) | [Link](https://huggingface.co/llamaste/Llama-2-7b-hf) | [Link](https://huggingface.co/llamaste/Llama-2-7b-chat) | [Link](https://huggingface.co/llamaste/Llama-2-7b-chat-hf)|
|13B| [Link](https://huggingface.co/llamaste/Llama-2-13b) | [Link](https://huggingface.co/llamaste/Llama-2-13b-hf) | [Link](https://huggingface.co/llamaste/Llama-2-13b-chat) | [Link](https://huggingface.co/llamaste/Llama-2-13b-hf)|
|70B| [Link](https://huggingface.co/llamaste/Llama-2-70b) | [Link](https://huggingface.co/llamaste/Llama-2-70b-hf) | [Link](https://huggingface.co/llamaste/Llama-2-70b-chat) | [Link](https://huggingface.co/llamaste/Llama-2-70b-hf)|
|
jgeselowitz/old_poetry
|
jgeselowitz
| 2023-09-21T18:43:42Z | 161 | 0 |
transformers
|
[
"transformers",
"pytorch",
"distilbert",
"text-classification",
"generated_from_trainer",
"base_model:distilbert/distilbert-base-uncased",
"base_model:finetune:distilbert/distilbert-base-uncased",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2023-09-21T18:43:28Z |
---
license: apache-2.0
base_model: distilbert-base-uncased
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: test_trainer
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# test_trainer
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 1.1338
- Accuracy: 0.731
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3.0
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 1.0802 | 1.0 | 2382 | 0.9411 | 0.698 |
| 0.6109 | 2.0 | 4764 | 0.9286 | 0.728 |
| 0.2759 | 3.0 | 7146 | 1.1338 | 0.731 |
### Framework versions
- Transformers 4.33.2
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3
|
Atheer174/my_awesome_wnut_model3
|
Atheer174
| 2023-09-21T18:41:34Z | 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
| 2023-09-20T08:18:59Z |
---
license: apache-2.0
base_model: distilbert-base-uncased
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: my_awesome_wnut_model3
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# my_awesome_wnut_model3
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: 0.0233
- Precision: 0.9836
- Recall: 0.9889
- F1: 0.9863
- Accuracy: 0.9932
## 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: 1
### Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
| 0.0371 | 1.0 | 2470 | 0.0233 | 0.9836 | 0.9889 | 0.9863 | 0.9932 |
### Framework versions
- Transformers 4.33.2
- Pytorch 1.13.1+cu117
- Datasets 2.14.5
- Tokenizers 0.13.3
|
jondurbin/airoboros-l2-7b-2.2.1
|
jondurbin
| 2023-09-21T18:39:31Z | 1,424 | 3 |
transformers
|
[
"transformers",
"pytorch",
"llama",
"text-generation",
"dataset:jondurbin/airoboros-2.2.1",
"license:llama2",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2023-09-20T17:26:33Z |
---
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-l2-7b-2.2](https://hf.co/jondurbin/airoboros-l2-7b-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)
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-l2-7b-2.2.1/runs/ka6jlcj7?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.
|
jondurbin/airoboros-l2-13b-2.2.1
|
jondurbin
| 2023-09-21T18:39:18Z | 1,474 | 3 |
transformers
|
[
"transformers",
"pytorch",
"llama",
"text-generation",
"dataset:jondurbin/airoboros-2.2.1",
"license:llama2",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2023-09-20T18:35:28Z |
---
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-l2-13b-2.2](https://hf.co/jondurbin/airoboros-l2-13b-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)
- more fine-tuning epochs
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-l2-13b-2.2.1/runs/zbz8mgaz?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.
|
dancingninjas/sentiment-model
|
dancingninjas
| 2023-09-21T18:24:24Z | 68 | 0 |
transformers
|
[
"transformers",
"tf",
"distilbert",
"text-classification",
"text classification",
"transformer",
"sentiment analysis",
"TensorFlow",
"en",
"dataset:imdb",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2023-09-21T10:54:56Z |
---
license: apache-2.0
datasets:
- imdb
language:
- en
pipeline_tag: text-classification
tags:
- text classification
- transformer
- sentiment analysis
- distilbert
- TensorFlow
---
|
TemporalGames/opt-1.3b-lambada_rmt_ms7_bptt7_sl2028_mt10_lTrue_LORA_cur3
|
TemporalGames
| 2023-09-21T18:23:11Z | 0 | 0 |
peft
|
[
"peft",
"region:us"
] | null | 2023-09-21T18:23:09Z |
---
library_name: peft
---
## Training procedure
### Framework versions
- PEFT 0.6.0.dev0
|
sudhanvasp/Sentiment-Analysis
|
sudhanvasp
| 2023-09-21T18:19:27Z | 164 | 2 |
transformers
|
[
"transformers",
"pytorch",
"tf",
"roberta",
"text-classification",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2023-09-20T13:47:15Z |
# SentimentAnalysis
Sentiment analysis with NLTK (Folder 79)
Sentiment analysis with Roberta (Folder 159)
Sentiment analysis with Roberta+Awk (Folder 209)
Sentiment analysis with Roberta+Gradio (Folder 219)
<!-- MARKER: Start of README -->
# Stock Sentiment Analysis of Tweets using RoBERTa
## Table of Contents
- [Project Description](#project-description)
- [Objective](#objective)
- [Hypotheses](#hypotheses)
- [Data Collection](#data-collection)
- [Sentiment Analysis](#sentiment-analysis)
- [Machine Learning Model](#machine-learning-model)
- [Running the Model](#running-the-model)
- [Huggingface](https://huggingface.co/sudhanvasp/Sentiment-Analysis)
- [Results and Insights](#results-and-insights)
- [License](#license)
---
<!-- MARKER: Project Description -->
## Project Description
Welcome to the Stock Sentiment Analysis project! This repository houses the code and resources for analyzing Twitter data to predict stock price movements based on sentiment analysis, leveraging the powerful RoBERTa model. Gain valuable insights into market sentiment and enhance your trading strategies.
<!-- MARKER: Objective -->
## Objective
The primary aim of this project is to explore the intricate relationship between sentiment expressed in tweets and short-term stock price movements.
<!-- MARKER: Hypotheses -->
## Hypotheses
- *Hypothesis 1:* Tweets with a positive sentiment will exhibit a positive correlation with stock price increases.
- *Hypothesis 2:* Tweets with a negative sentiment will display a negative correlation with stock price decreases.
- *Hypothesis 3:* Tweets with a neutral sentiment will display a neutral correlation with stock price.
<!-- MARKER: Data Collection -->
## Data Collection
- We meticulously gathered Twitter data from financial news and analyst accounts.
- Data preprocessing was performed, encompassing deduplication, tokenization, and sentiment label encoding (positive, negative, neutral).
<!-- MARKER: Sentiment Analysis -->
## Sentiment Analysis
- Harnessing RoBERTa, a state-of-the-art transformer-based model, we assigned sentiment scores.
- Challenges such as domain-specific sentiment expressions and model fine-tuning were addressed.
<!-- MARKER: Machine Learning Model -->
## Machine Learning Model
- Our model is a robust ensemble of RoBERTa.
- Features encompass RoBERTa-generated F1 scores, tweet volume, and historical stock price data.
- This amalgamation empowers us to capture both sequential dependencies and non-linear relationships effectively.
<!-- MARKER: Running the Model -->
## Running the Model
## Hosting with Gradio
1. *Install Gradio:*
```bash
pip install gradio
import gradio as gr
2. Run the given gradio code in the Folder 219.
## Hosting with FLASK
1. *Install FLASK:*
```bash
pip install flask
cd 209
cd twitterka
python app.py
2. Open the IP given address.
<!-- MARKER: Project Description -->
## Huggingface Page
- Execution of the model can be done directly on Huggingface as well
- [Huggingface](https://huggingface.co/sudhanvasp/Sentiment-Analysis)
<!-- MARKER: Results and Insights-->
## Results and Insights
- Our ensemble model boasts an impressive 96% accuracy in sentiment analysis.
- Notably, positive sentiment tweets correlate positively with stock price increases, while negative sentiment tweets correlate negatively with decreases. Neutral sentiment, while present, exhibits a weaker influence on stock price movements.
<!-- MARKER: License-->
## License
- This created by the team "The Lost Pendrive" (Sudhanva SP, Deepa Umesh, Chinmayi Rajaram)
|
Art101/ppo-Huggy
|
Art101
| 2023-09-21T18:13:58Z | 0 | 0 |
ml-agents
|
[
"ml-agents",
"tensorboard",
"onnx",
"Huggy",
"deep-reinforcement-learning",
"reinforcement-learning",
"ML-Agents-Huggy",
"region:us"
] |
reinforcement-learning
| 2023-09-21T18:13:47Z |
---
library_name: ml-agents
tags:
- Huggy
- deep-reinforcement-learning
- reinforcement-learning
- ML-Agents-Huggy
---
# **ppo** Agent playing **Huggy**
This is a trained model of a **ppo** agent playing **Huggy**
using the [Unity ML-Agents Library](https://github.com/Unity-Technologies/ml-agents).
## Usage (with ML-Agents)
The Documentation: https://unity-technologies.github.io/ml-agents/ML-Agents-Toolkit-Documentation/
We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub:
- A *short tutorial* where you teach Huggy the Dog 🐶 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: Art101/ppo-Huggy
3. Step 2: Select your *.nn /*.onnx file
4. Click on Watch the agent play 👀
|
felixquinihildebet/taxi-v3
|
felixquinihildebet
| 2023-09-21T18:05:29Z | 0 | 0 | null |
[
"Taxi-v3",
"q-learning",
"reinforcement-learning",
"custom-implementation",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-09-21T17:55:22Z |
---
tags:
- Taxi-v3
- q-learning
- reinforcement-learning
- custom-implementation
model-index:
- name: 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="felixquinihildebet/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"])
```
|
felixquinihildebet/q-FrozenLake-v1-4x4-noSlippery
|
felixquinihildebet
| 2023-09-21T17:52:22Z | 0 | 0 | null |
[
"FrozenLake-v1-4x4-no_slippery",
"q-learning",
"reinforcement-learning",
"custom-implementation",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-09-21T17:52:17Z |
---
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="felixquinihildebet/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"])
```
|
cloudwalkerw/wavlm-base_3
|
cloudwalkerw
| 2023-09-21T17:48:37Z | 16 | 0 |
transformers
|
[
"transformers",
"pytorch",
"wavlm",
"audio-classification",
"generated_from_trainer",
"base_model:microsoft/wavlm-base",
"base_model:finetune:microsoft/wavlm-base",
"endpoints_compatible",
"region:us"
] |
audio-classification
| 2023-09-18T14:31:32Z |
---
base_model: microsoft/wavlm-base
tags:
- audio-classification
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: wavlm-base_3
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# wavlm-base_3
This model is a fine-tuned version of [microsoft/wavlm-base](https://huggingface.co/microsoft/wavlm-base) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.6534
- Accuracy: 0.8974
## 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: 2
- seed: 0
- gradient_accumulation_steps: 4
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 10.0
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 0.2236 | 1.24 | 100 | 12.8495 | 0.4467 |
| 0.0514 | 2.48 | 200 | 16.3078 | 0.2677 |
| 0.0 | 3.72 | 300 | 17.5651 | 0.2597 |
| 0.3252 | 4.95 | 400 | 15.0382 | 0.1912 |
| 1.0577 | 6.19 | 500 | 0.6534 | 0.8974 |
| 0.6973 | 7.43 | 600 | 0.7352 | 0.1026 |
| 0.6939 | 8.67 | 700 | 0.6210 | 0.8974 |
| 0.6944 | 9.91 | 800 | 0.7129 | 0.1026 |
### Framework versions
- Transformers 4.34.0.dev0
- Pytorch 2.0.0.post302
- Datasets 2.14.5
- Tokenizers 0.13.3
|
darxkies/bart-large-cnn-samsum-ChatGPT_v3
|
darxkies
| 2023-09-21T17:47:31Z | 10 | 1 |
transformers
|
[
"transformers",
"rust",
"bart",
"text2text-generation",
"summarization",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
summarization
| 2023-09-21T15:44:26Z |
---
pipeline_tag: summarization
---
Original model: [Qiliang/bart-large-cnn-samsum-ChatGPT_v3](https://https://huggingface.co/Qiliang/bart-large-cnn-samsum-ChatGPT_v3)
Added files for [rust-bert](https://github.com/guillaume-be/rust-bert)
|
darxkies/bge-base-en-v1.5
|
darxkies
| 2023-09-21T17:47:07Z | 2 | 0 |
transformers
|
[
"transformers",
"rust",
"bert",
"feature-extraction",
"sentence-similarity",
"endpoints_compatible",
"region:us"
] |
sentence-similarity
| 2023-09-20T21:36:50Z |
---
pipeline_tag: sentence-similarity
---
Original model: [BAAI/bge-base-en-v1.5](https://huggingface.co/BAAI/bge-base-en-v1.5)
Added files for [rust-bert](https://github.com/guillaume-be/rust-bert)
|
benedikt-schaber/q-Taxi-v3
|
benedikt-schaber
| 2023-09-21T17:35:46Z | 0 | 0 | null |
[
"Taxi-v3",
"q-learning",
"reinforcement-learning",
"custom-implementation",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-09-21T17:35:45Z |
---
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="benedikt-schaber/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"])
```
|
poteminr/llama2-nerel-bio
|
poteminr
| 2023-09-21T17:33:53Z | 4 | 0 |
peft
|
[
"peft",
"region:us"
] | null | 2023-08-13T12:12:36Z |
---
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
|
CyberHarem/senzaki_ema_idolmastercinderellagirls
|
CyberHarem
| 2023-09-21T17:22:10Z | 0 | 0 | null |
[
"art",
"text-to-image",
"dataset:CyberHarem/senzaki_ema_idolmastercinderellagirls",
"license:mit",
"region:us"
] |
text-to-image
| 2023-09-21T17:13:47Z |
---
license: mit
datasets:
- CyberHarem/senzaki_ema_idolmastercinderellagirls
pipeline_tag: text-to-image
tags:
- art
---
# Lora of senzaki_ema_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 3400, you need to download `3400/senzaki_ema_idolmastercinderellagirls.pt` as the embedding and `3400/senzaki_ema_idolmastercinderellagirls.safetensors` for loading Lora. By using both files together, you can generate images for the desired characters.
**The best step we recommend is 3400**, with the score of 0.999. The trigger words are:
1. `senzaki_ema_idolmastercinderellagirls`
2. `short_hair, jewelry, blonde_hair, very_short_hair, earrings, smile, red_eyes, open_mouth`
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 | 0.962 | [Download](5100/senzaki_ema_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 | 0.993 | [Download](4760/senzaki_ema_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 | 0.998 | [Download](4420/senzaki_ema_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 | 0.996 | [Download](4080/senzaki_ema_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 | 0.962 | [Download](3740/senzaki_ema_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** | **0.999** | [**Download**](3400/senzaki_ema_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 | 0.978 | [Download](3060/senzaki_ema_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 | 0.994 | [Download](2720/senzaki_ema_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 | 0.996 | [Download](2380/senzaki_ema_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 | 0.994 | [Download](2040/senzaki_ema_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 | 0.992 | [Download](1700/senzaki_ema_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 | 0.997 | [Download](1360/senzaki_ema_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 | 0.983 | [Download](1020/senzaki_ema_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 | 0.992 | [Download](680/senzaki_ema_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 | 0.847 | [Download](340/senzaki_ema_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) |  |  |
|
steveice/videomae-large-finetuned-kinetics-finetuned-videomae-large-kitchen
|
steveice
| 2023-09-21T17:13:55Z | 8 | 0 |
transformers
|
[
"transformers",
"pytorch",
"videomae",
"video-classification",
"generated_from_trainer",
"base_model:MCG-NJU/videomae-large-finetuned-kinetics",
"base_model:finetune:MCG-NJU/videomae-large-finetuned-kinetics",
"license:cc-by-nc-4.0",
"endpoints_compatible",
"region:us"
] |
video-classification
| 2023-09-20T21:16:12Z |
---
license: cc-by-nc-4.0
base_model: MCG-NJU/videomae-large-finetuned-kinetics
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: videomae-large-finetuned-kinetics-finetuned-videomae-large-kitchen
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. -->
# videomae-large-finetuned-kinetics-finetuned-videomae-large-kitchen
This model is a fine-tuned version of [MCG-NJU/videomae-large-finetuned-kinetics](https://huggingface.co/MCG-NJU/videomae-large-finetuned-kinetics) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.6309
- Accuracy: 0.8900
## 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: 2
- eval_batch_size: 2
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- training_steps: 11100
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:-----:|:---------------:|:--------:|
| 3.5158 | 0.02 | 222 | 3.6067 | 0.0588 |
| 2.8571 | 1.02 | 444 | 3.1445 | 0.3014 |
| 1.8854 | 2.02 | 666 | 2.3644 | 0.4607 |
| 1.5533 | 3.02 | 888 | 1.7967 | 0.5621 |
| 1.3935 | 4.02 | 1110 | 1.3755 | 0.6502 |
| 1.1722 | 5.02 | 1332 | 1.2232 | 0.7109 |
| 0.2896 | 6.02 | 1554 | 1.2859 | 0.6256 |
| 0.3166 | 7.02 | 1776 | 1.2910 | 0.6720 |
| 0.6902 | 8.02 | 1998 | 1.2702 | 0.6995 |
| 0.4193 | 9.02 | 2220 | 1.2087 | 0.7137 |
| 0.1889 | 10.02 | 2442 | 1.0500 | 0.7611 |
| 0.4502 | 11.02 | 2664 | 1.1647 | 0.7118 |
| 0.7703 | 12.02 | 2886 | 1.1037 | 0.7242 |
| 0.0957 | 13.02 | 3108 | 1.0967 | 0.7706 |
| 0.3202 | 14.02 | 3330 | 1.0479 | 0.7545 |
| 0.3634 | 15.02 | 3552 | 1.0714 | 0.8057 |
| 0.3883 | 16.02 | 3774 | 1.2323 | 0.7498 |
| 0.0322 | 17.02 | 3996 | 1.0504 | 0.7848 |
| 0.5108 | 18.02 | 4218 | 1.1356 | 0.7915 |
| 0.309 | 19.02 | 4440 | 1.1409 | 0.7592 |
| 0.56 | 20.02 | 4662 | 1.0828 | 0.7915 |
| 0.3675 | 21.02 | 4884 | 0.9154 | 0.8123 |
| 0.0076 | 22.02 | 5106 | 1.0974 | 0.8133 |
| 0.0451 | 23.02 | 5328 | 1.0361 | 0.8152 |
| 0.2558 | 24.02 | 5550 | 0.7830 | 0.8237 |
| 0.0125 | 25.02 | 5772 | 0.8728 | 0.8171 |
| 0.4184 | 26.02 | 5994 | 0.8413 | 0.8265 |
| 0.2566 | 27.02 | 6216 | 1.0644 | 0.8009 |
| 0.1257 | 28.02 | 6438 | 0.8641 | 0.8265 |
| 0.1326 | 29.02 | 6660 | 0.8444 | 0.8417 |
| 0.0436 | 30.02 | 6882 | 0.8615 | 0.8322 |
| 0.0408 | 31.02 | 7104 | 0.8075 | 0.8332 |
| 0.0316 | 32.02 | 7326 | 0.8699 | 0.8341 |
| 0.2235 | 33.02 | 7548 | 0.8151 | 0.8455 |
| 0.0079 | 34.02 | 7770 | 0.8099 | 0.8550 |
| 0.001 | 35.02 | 7992 | 0.8640 | 0.8370 |
| 0.0007 | 36.02 | 8214 | 0.7146 | 0.8483 |
| 0.464 | 37.02 | 8436 | 0.7917 | 0.8464 |
| 0.0005 | 38.02 | 8658 | 0.7239 | 0.8531 |
| 0.0004 | 39.02 | 8880 | 0.7702 | 0.8701 |
| 0.1705 | 40.02 | 9102 | 0.7543 | 0.8521 |
| 0.0039 | 41.02 | 9324 | 0.7456 | 0.8673 |
| 0.0168 | 42.02 | 9546 | 0.7255 | 0.8730 |
| 0.2615 | 43.02 | 9768 | 0.7453 | 0.8758 |
| 0.0004 | 44.02 | 9990 | 0.6824 | 0.8806 |
| 0.236 | 45.02 | 10212 | 0.6624 | 0.8825 |
| 0.0007 | 46.02 | 10434 | 0.6727 | 0.8815 |
| 0.0004 | 47.02 | 10656 | 0.6478 | 0.8863 |
| 0.268 | 48.02 | 10878 | 0.6309 | 0.8900 |
| 0.0025 | 49.02 | 11100 | 0.6284 | 0.8900 |
### Framework versions
- Transformers 4.33.2
- Pytorch 1.12.1+cu113
- Datasets 2.14.5
- Tokenizers 0.13.3
|
annahaz/xlm-roberta-base-misogyny-sexism-tweets
|
annahaz
| 2023-09-21T17:11:00Z | 104 | 0 |
transformers
|
[
"transformers",
"pytorch",
"xlm-roberta",
"text-classification",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2022-08-19T17:14:54Z |
This model was an experiment BUT NOT THE FINAL MODEL.
The final model was ***annahaz/xlm-roberta-base-misogyny-sexism-indomain-mix-bal*** (https://huggingface.co/annahaz/xlm-roberta-base-misogyny-sexism-indomain-mix-bal)
Please consider using/trying that model instead.
This model was an experiment for the following paper BUT THIS MODEL IS NOT THE FINAL MODEL:
```
@InProceedings{10.1007/978-3-031-43129-6_9,
author="Chang, Rong-Ching
and May, Jonathan
and Lerman, Kristina",
editor="Thomson, Robert
and Al-khateeb, Samer
and Burger, Annetta
and Park, Patrick
and A. Pyke, Aryn",
title="Feedback Loops and Complex Dynamics of Harmful Speech in Online Discussions",
booktitle="Social, Cultural, and Behavioral Modeling",
year="2023",
publisher="Springer Nature Switzerland",
address="Cham",
pages="85--94",
abstract="Harmful and toxic speech contribute to an unwelcoming online environment that suppresses participation and conversation. Efforts have focused on detecting and mitigating harmful speech; however, the mechanisms by which toxicity degrades online discussions are not well understood. This paper makes two contributions. First, to comprehensively model harmful comments, we introduce a multilingual misogyny and sexist speech detection model (https://huggingface.co/annahaz/xlm-roberta-base-misogyny-sexism-indomain-mix-bal). Second, we model the complex dynamics of online discussions as feedback loops in which harmful comments lead to negative emotions which prompt even more harmful comments. To quantify the feedback loops, we use a combination of mutual Granger causality and regression to analyze discussions on two political forums on Reddit: the moderated political forum r/Politics and the moderated neutral political forum r/NeutralPolitics. Our results suggest that harmful comments and negative emotions create self-reinforcing feedback loops in forums. Contrarily, moderation with neutral discussion appears to tip interactions into self-extinguishing feedback loops that reduce harmful speech and negative emotions. Our study sheds more light on the complex dynamics of harmful speech and the role of moderation and neutral discussion in mitigating these dynamics.",
isbn="978-3-031-43129-6"
}
```
---
license: mit
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
- precision
- recall
model-index:
- name: xlm-roberta-base-misogyny-sexism-tweets
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-misogyny-sexism-tweets
This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.5009
- Accuracy: 0.796
- F1: 0.8132
- Precision: 0.75
- Recall: 0.888
- Mae: 0.204
- Tn: 352
- Fp: 148
- Fn: 56
- Tp: 444
## 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: 4
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall | Mae | Tn | Fp | Fn | Tp |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|:-----:|:---:|:---:|:--:|:---:|
| 0.4947 | 1.0 | 1646 | 0.4683 | 0.765 | 0.7866 | 0.7205 | 0.866 | 0.235 | 332 | 168 | 67 | 433 |
| 0.4285 | 2.0 | 3292 | 0.4514 | 0.779 | 0.8004 | 0.7298 | 0.886 | 0.221 | 336 | 164 | 57 | 443 |
| 0.3721 | 3.0 | 4938 | 0.4430 | 0.781 | 0.8060 | 0.7234 | 0.91 | 0.219 | 326 | 174 | 45 | 455 |
| 0.3127 | 4.0 | 6584 | 0.5009 | 0.796 | 0.8132 | 0.75 | 0.888 | 0.204 | 352 | 148 | 56 | 444 |
### Framework versions
- Transformers 4.20.1
- Pytorch 1.12.0+cu102
- Datasets 2.3.2
- Tokenizers 0.12.1
|
calculater/looking-up
|
calculater
| 2023-09-21T17:03:38Z | 0 | 4 | null |
[
"text-to-image",
"license:creativeml-openrail-m",
"region:us"
] |
text-to-image
| 2023-09-21T15:55:59Z |
---
pipeline_tag: text-to-image
license: creativeml-openrail-m
---
[looking-up](https://huggingface.co/hhpoo/looking-up/blob/main/looking-up.safetensors)
視線を上げるloraです。ファイルをwebuiのlora指定フォルダ内に入れてご使用ください。
トリガータグ等は指定しておらず、適用するだけで画面上方を見上げるはずです。
weightをマイナスにすることで下を見るようにもできるかもしれません。
|
LarryAIDraw/lappland_arknights
|
LarryAIDraw
| 2023-09-21T16:56:54Z | 0 | 0 | null |
[
"license:creativeml-openrail-m",
"region:us"
] | null | 2023-09-20T16:49:40Z |
---
license: creativeml-openrail-m
---
https://civitai.com/models/130880?modelVersionId=152857
|
vinayaksodar/dqn-SpaceInvadersNoFrameskip-v4
|
vinayaksodar
| 2023-09-21T16:55:40Z | 0 | 0 |
stable-baselines3
|
[
"stable-baselines3",
"SpaceInvadersNoFrameskip-v4",
"deep-reinforcement-learning",
"reinforcement-learning",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-09-21T15:29:58Z |
---
library_name: stable-baselines3
tags:
- SpaceInvadersNoFrameskip-v4
- deep-reinforcement-learning
- reinforcement-learning
- stable-baselines3
model-index:
- name: DQN
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: SpaceInvadersNoFrameskip-v4
type: SpaceInvadersNoFrameskip-v4
metrics:
- type: mean_reward
value: 303.00 +/- 219.25
name: mean_reward
verified: false
---
# **DQN** Agent playing **SpaceInvadersNoFrameskip-v4**
This is a trained model of a **DQN** agent playing **SpaceInvadersNoFrameskip-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 dqn --env SpaceInvadersNoFrameskip-v4 -orga vinayaksodar -f logs/
python -m rl_zoo3.enjoy --algo dqn --env SpaceInvadersNoFrameskip-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 dqn --env SpaceInvadersNoFrameskip-v4 -orga vinayaksodar -f logs/
python -m rl_zoo3.enjoy --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/
```
## Training (with the RL Zoo)
```
python -m rl_zoo3.train --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/
# Upload the model and generate video (when possible)
python -m rl_zoo3.push_to_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/ -orga vinayaksodar
```
## Hyperparameters
```python
OrderedDict([('batch_size', 128),
('buffer_size', 10000),
('env_wrapper',
['stable_baselines3.common.atari_wrappers.AtariWrapper']),
('exploration_final_eps', 0.01),
('exploration_fraction', 0.1),
('frame_stack', 4),
('gradient_steps', 1),
('learning_rate', 0.0001),
('learning_starts', 100000),
('n_timesteps', 1000000.0),
('optimize_memory_usage', False),
('policy', 'CnnPolicy'),
('target_update_interval', 1000),
('train_freq', 4),
('normalize', False)])
```
# Environment Arguments
```python
{'render_mode': 'rgb_array'}
```
|
ShivamMangale/XLM-Roberta-base-allhiweakdap_5th_iteration_d5_d4_d3_d2_d1_d0
|
ShivamMangale
| 2023-09-21T16:55:00Z | 106 | 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
| 2023-09-21T15:33:26Z |
---
license: mit
base_model: xlm-roberta-base
tags:
- generated_from_trainer
datasets:
- squad
model-index:
- name: XLM-Roberta-base-allhiweakdap_5th_iteration_d5_d4_d3_d2_d1_d0
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-allhiweakdap_5th_iteration_d5_d4_d3_d2_d1_d0
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: 8
### Training results
### Framework versions
- Transformers 4.33.2
- Pytorch 2.0.1+cu117
- Datasets 2.14.5
- Tokenizers 0.13.3
|
jtlowell/cozy_fantasy_xl
|
jtlowell
| 2023-09-21T16:43:51Z | 3 | 1 |
diffusers
|
[
"diffusers",
"stable-diffusion-xl",
"stable-diffusion-xl-diffusers",
"text-to-image",
"lora",
"dataset:jtlowell/cozy_interiors_2",
"base_model:stabilityai/stable-diffusion-xl-base-1.0",
"base_model:adapter:stabilityai/stable-diffusion-xl-base-1.0",
"region:us"
] |
text-to-image
| 2023-09-21T15:51:17Z |
---
base_model: stabilityai/stable-diffusion-xl-base-1.0
instance_prompt: cozy_int
tags:
- stable-diffusion-xl
- stable-diffusion-xl-diffusers
- text-to-image
- diffusers
- lora
inference: true
datasets:
- jtlowell/cozy_interiors_2
---
# LoRA DreamBooth - jtlowell/cozy_fantasy_xl
These are LoRA adaption weights for stabilityai/stable-diffusion-xl-base-1.0.
The weights were trained on the concept prompt:
`cozy_int`
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_fantasy_xl')
pipe.to("cuda")
prompt = "A majestic cozy_int jumping from a big stone at night"
image = pipe(prompt=prompt, num_inference_steps=50).images[0]
```
|
SHENMU007/neunit_BASE_V13.5.10
|
SHENMU007
| 2023-09-21T16:41:56Z | 76 | 0 |
transformers
|
[
"transformers",
"pytorch",
"speecht5",
"text-to-audio",
"1.1.0",
"generated_from_trainer",
"zh",
"dataset:facebook/voxpopuli",
"base_model:microsoft/speecht5_tts",
"base_model:finetune:microsoft/speecht5_tts",
"license:mit",
"endpoints_compatible",
"region:us"
] |
text-to-audio
| 2023-09-21T15:22:09Z |
---
language:
- zh
license: mit
base_model: microsoft/speecht5_tts
tags:
- 1.1.0
- generated_from_trainer
datasets:
- facebook/voxpopuli
model-index:
- name: SpeechT5 TTS Dutch neunit
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 TTS Dutch neunit
This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on the 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: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- 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
### Training results
### Framework versions
- Transformers 4.33.1
- Pytorch 2.0.1+cu117
- Datasets 2.14.5
- Tokenizers 0.13.3
|
TheBlokeAI/jackfram_llama-68m-GPTQ
|
TheBlokeAI
| 2023-09-21T16:33:08Z | 91 | 0 |
transformers
|
[
"transformers",
"safetensors",
"llama",
"text-generation",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"4-bit",
"gptq",
"region:us"
] |
text-generation
| 2023-09-21T16:30:27Z |
A 4-bit, 128g, act_order=True GPTQ quantisation of JackFram/llama-68m, a 68 million parameter Llama1 model; created on request for software testing.
Not for normal usage!
|
Rishs/DangerousV2
|
Rishs
| 2023-09-21T16:28:03Z | 0 | 0 | null |
[
"michaeljackson",
"en",
"region:us"
] | null | 2023-09-21T16:26:28Z |
---
language:
- en
tags:
- michaeljackson
---
|
ShivamMangale/XLM-Roberta-base-allhiweakdap_5th_iteration_d5_d4_d3_d2_d1
|
ShivamMangale
| 2023-09-21T16:23:11Z | 133 | 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
| 2023-09-21T15:19:39Z |
---
license: mit
base_model: xlm-roberta-base
tags:
- generated_from_trainer
datasets:
- squad
model-index:
- name: XLM-Roberta-base-allhiweakdap_5th_iteration_d5_d4_d3_d2_d1
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-allhiweakdap_5th_iteration_d5_d4_d3_d2_d1
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: 8
### Training results
### Framework versions
- Transformers 4.33.2
- Pytorch 2.0.1+cu117
- Datasets 2.14.5
- Tokenizers 0.13.3
|
Panchovix/Marcoroni-70B-v1-safetensors
|
Panchovix
| 2023-09-21T16:20:13Z | 5 | 0 |
transformers
|
[
"transformers",
"safetensors",
"llama",
"text-generation",
"license:llama2",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2023-09-21T13:30:48Z |
---
license: llama2
---
Marcoroni-70B-v1 (https://huggingface.co/AIDC-ai-business/Marcoroni-70B-v1) conversion to .safetensors. Can be used directly with transformers or be used to quant with exllamav2.
|
huygdng/whisper_small_tw12
|
huygdng
| 2023-09-21T16:09:13Z | 75 | 0 |
transformers
|
[
"transformers",
"pytorch",
"whisper",
"automatic-speech-recognition",
"generated_from_trainer",
"dataset:common_voice_13_0",
"base_model:openai/whisper-small",
"base_model:finetune:openai/whisper-small",
"license:apache-2.0",
"model-index",
"endpoints_compatible",
"region:us"
] |
automatic-speech-recognition
| 2023-09-21T16:08:20Z |
---
license: apache-2.0
base_model: openai/whisper-small
tags:
- generated_from_trainer
datasets:
- common_voice_13_0
metrics:
- wer
model-index:
- name: whisper_small_tw12
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: common_voice_13_0
type: common_voice_13_0
config: tw
split: train+test
args: tw
metrics:
- name: Wer
type: wer
value: 1.103734439834025
---
<!-- 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. -->
# whisper_small_tw12
This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the common_voice_13_0 dataset.
It achieves the following results on the evaluation set:
- Loss: 3.3399
- Wer: 1.1037
## 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: 6.25e-06
- 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
- lr_scheduler_warmup_steps: 200
- training_steps: 500
### Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|:-------------:|:-----:|:----:|:---------------:|:------:|
| 3.0649 | 6.25 | 100 | 3.2733 | 1.5726 |
| 0.9932 | 12.5 | 200 | 2.9873 | 1.9378 |
| 0.0521 | 18.75 | 300 | 3.0893 | 1.1203 |
| 0.0045 | 25.0 | 400 | 3.2862 | 1.1245 |
| 0.0025 | 31.25 | 500 | 3.3399 | 1.1037 |
### Framework versions
- Transformers 4.34.0.dev0
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.14.0
|
Keenan5755/ppo-LunarLander-v2
|
Keenan5755
| 2023-09-21T16:04:48Z | 0 | 0 |
stable-baselines3
|
[
"stable-baselines3",
"LunarLander-v2",
"deep-reinforcement-learning",
"reinforcement-learning",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-09-21T16:04:28Z |
---
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: 261.74 +/- 21.02
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
...
```
|
starkiee/stark
|
starkiee
| 2023-09-21T15:55:36Z | 0 | 0 | null |
[
"license:creativeml-openrail-m",
"region:us"
] | null | 2023-09-21T15:55:36Z |
---
license: creativeml-openrail-m
---
|
salesforce/blipdiffusion-controlnet
|
salesforce
| 2023-09-21T15:55:24Z | 85 | 2 |
diffusers
|
[
"diffusers",
"en",
"arxiv:2305.14720",
"license:apache-2.0",
"diffusers:BlipDiffusionControlNetPipeline",
"region:us"
] | null | 2023-09-21T15:55:24Z |
---
license: apache-2.0
language:
- en
library_name: diffusers
---
# BLIP-Diffusion: Pre-trained Subject Representation for Controllable Text-to-Image Generation and Editing
<!-- Provide a quick summary of what the model is/does. -->
Model card for BLIP-Diffusion, a text to image Diffusion model which enables zero-shot subject-driven generation and control-guided zero-shot generation.
The abstract from the paper is:
*Subject-driven text-to-image generation models create novel renditions of an input subject based on text prompts. Existing models suffer from lengthy fine-tuning and difficulties preserving the subject fidelity. To overcome these limitations, we introduce BLIP-Diffusion, a new subject-driven image generation model that supports multimodal control which consumes inputs of subject images and text prompts. Unlike other subject-driven generation models, BLIP-Diffusion introduces a new multimodal encoder which is pre-trained to provide subject representation. We first pre-train the multimodal encoder following BLIP-2 to produce visual representation aligned with the text. Then we design a subject representation learning task which enables a diffusion model to leverage such visual representation and generates new subject renditions. Compared with previous methods such as DreamBooth, our model enables zero-shot subject-driven generation, and efficient fine-tuning for customized subject with up to 20x speedup. We also demonstrate that BLIP-Diffusion can be flexibly combined with existing techniques such as ControlNet and prompt-to-prompt to enable novel subject-driven generation and editing applications.*
The model is created by Dongxu Li, Junnan Li, Steven C.H. Hoi.
### Model Sources
<!-- Provide the basic links for the model. -->
- **Original Repository:** https://github.com/salesforce/LAVIS/tree/main
- **Project Page:** https://dxli94.github.io/BLIP-Diffusion-website/
## Uses
### Zero-Shot Subject Driven Generation
```python
from diffusers.pipelines import BlipDiffusionPipeline
from diffusers.utils import load_image
import torch
blip_diffusion_pipe = BlipDiffusionPipeline.from_pretrained(
"Salesforce/blipdiffusion", torch_dtype=torch.float16
).to("cuda")
cond_subject = "dog"
tgt_subject = "dog"
text_prompt_input = "swimming underwater"
cond_image = load_image(
"https://huggingface.co/datasets/ayushtues/blipdiffusion_images/resolve/main/dog.jpg"
)
iter_seed = 88888
guidance_scale = 7.5
num_inference_steps = 25
negative_prompt = "over-exposure, under-exposure, saturated, duplicate, out of frame, lowres, cropped, worst quality, low quality, jpeg artifacts, morbid, mutilated, out of frame, ugly, bad anatomy, bad proportions, deformed, blurry, duplicate"
output = blip_diffusion_pipe(
text_prompt_input,
cond_image,
cond_subject,
tgt_subject,
guidance_scale=guidance_scale,
num_inference_steps=num_inference_steps,
neg_prompt=negative_prompt,
height=512,
width=512,
).images
output[0].save("image.png")
```
Input Image : <img src="https://huggingface.co/datasets/ayushtues/blipdiffusion_images/resolve/main/dog.jpg" style="width:500px;"/>
Generatred Image : <img src="https://huggingface.co/datasets/ayushtues/blipdiffusion_images/resolve/main/dog_underwater.png" style="width:500px;"/>
### Controlled subject-driven generation
```python
from diffusers.pipelines import BlipDiffusionControlNetPipeline
from diffusers.utils import load_image
from controlnet_aux import CannyDetector
blip_diffusion_pipe = BlipDiffusionControlNetPipeline.from_pretrained(
"Salesforce/blipdiffusion-controlnet", torch_dtype=torch.float16
).to("cuda")
style_subject = "flower" # subject that defines the style
tgt_subject = "teapot" # subject to generate.
text_prompt = "on a marble table"
cldm_cond_image = load_image(
"https://huggingface.co/datasets/ayushtues/blipdiffusion_images/resolve/main/kettle.jpg"
).resize((512, 512))
canny = CannyDetector()
cldm_cond_image = canny(cldm_cond_image, 30, 70, output_type="pil")
style_image = load_image(
"https://huggingface.co/datasets/ayushtues/blipdiffusion_images/resolve/main/flower.jpg"
)
guidance_scale = 7.5
num_inference_steps = 50
negative_prompt = "over-exposure, under-exposure, saturated, duplicate, out of frame, lowres, cropped, worst quality, low quality, jpeg artifacts, morbid, mutilated, out of frame, ugly, bad anatomy, bad proportions, deformed, blurry, duplicate"
output = blip_diffusion_pipe(
text_prompt,
style_image,
cldm_cond_image,
style_subject,
tgt_subject,
guidance_scale=guidance_scale,
num_inference_steps=num_inference_steps,
neg_prompt=negative_prompt,
height=512,
width=512,
).images
output[0].save("image.png")
```
Input Style Image : <img src="https://huggingface.co/datasets/ayushtues/blipdiffusion_images/resolve/main/flower.jpg" style="width:500px;"/>
Canny Edge Input : <img src="https://huggingface.co/datasets/ayushtues/blipdiffusion_images/resolve/main/kettle.jpg" style="width:500px;"/>
Generated Image : <img src="https://huggingface.co/datasets/ayushtues/blipdiffusion_images/resolve/main/canny_generated.png" style="width:500px;"/>
### Controlled subject-driven generation Scribble
```python
from diffusers.pipelines import BlipDiffusionControlNetPipeline
from diffusers.utils import load_image
from controlnet_aux import HEDdetector
blip_diffusion_pipe = BlipDiffusionControlNetPipeline.from_pretrained(
"Salesforce/blipdiffusion-controlnet"
)
controlnet = ControlNetModel.from_pretrained("lllyasviel/sd-controlnet-scribble")
blip_diffusion_pipe.controlnet = controlnet
blip_diffusion_pipe.to("cuda")
style_subject = "flower" # subject that defines the style
tgt_subject = "bag" # subject to generate.
text_prompt = "on a table"
cldm_cond_image = load_image(
"https://huggingface.co/lllyasviel/sd-controlnet-scribble/resolve/main/images/bag.png"
).resize((512, 512))
hed = HEDdetector.from_pretrained("lllyasviel/Annotators")
cldm_cond_image = hed(cldm_cond_image)
style_image = load_image(
"https://huggingface.co/datasets/ayushtues/blipdiffusion_images/resolve/main/flower.jpg"
)
guidance_scale = 7.5
num_inference_steps = 50
negative_prompt = "over-exposure, under-exposure, saturated, duplicate, out of frame, lowres, cropped, worst quality, low quality, jpeg artifacts, morbid, mutilated, out of frame, ugly, bad anatomy, bad proportions, deformed, blurry, duplicate"
output = blip_diffusion_pipe(
text_prompt,
style_image,
cldm_cond_image,
style_subject,
tgt_subject,
guidance_scale=guidance_scale,
num_inference_steps=num_inference_steps,
neg_prompt=negative_prompt,
height=512,
width=512,
).images
output[0].save("image.png")
```
Input Style Image : <img src="https://huggingface.co/datasets/ayushtues/blipdiffusion_images/resolve/main/flower.jpg" style="width:500px;"/>
Scribble Input : <img src="https://huggingface.co/datasets/ayushtues/blipdiffusion_images/resolve/main/scribble.png" style="width:500px;"/>
Generated Image : <img src="https://huggingface.co/datasets/ayushtues/blipdiffusion_images/resolve/main/scribble_output.png" style="width:500px;"/>
## Model Architecture
Blip-Diffusion learns a **pre-trained subject representation**. uch representation aligns with text embeddings and in the meantime also encodes the subject appearance. This allows efficient fine-tuning of the model for high-fidelity subject-driven applications, such as text-to-image generation, editing and style transfer.
To this end, they design a two-stage pre-training strategy to learn generic subject representation. In the first pre-training stage, they perform multimodal representation learning, which enforces BLIP-2 to produce text-aligned visual features based on the input image. In the second pre-training stage, they design a subject representation learning task, called prompted context generation, where the diffusion model learns to generate novel subject renditions based on the input visual features.
To achieve this, they curate pairs of input-target images with the same subject appearing in different contexts. Specifically, they synthesize input images by composing the subject with a random background. During pre-training, they feed the synthetic input image and the subject class label through BLIP-2 to obtain the multimodal embeddings as subject representation. The subject representation is then combined with a text prompt to guide the generation of the target image.
The architecture is also compatible to integrate with established techniques built on top of the diffusion model, such as ControlNet.
They attach the U-Net of the pre-trained ControlNet to that of BLIP-Diffusion via residuals. In this way, the model takes into account the input structure condition, such as edge maps and depth maps, in addition to the subject cues. Since the model inherits the architecture of the original latent diffusion model, they observe satisfying generations using off-the-shelf integration with pre-trained ControlNet without further training.
<img src="https://huggingface.co/datasets/ayushtues/blipdiffusion_images/resolve/main/arch_controlnet.png" style="width:50%;"/>
## Citation
**BibTeX:**
If you find this repository useful in your research, please cite:
```
@misc{li2023blipdiffusion,
title={BLIP-Diffusion: Pre-trained Subject Representation for Controllable Text-to-Image Generation and Editing},
author={Dongxu Li and Junnan Li and Steven C. H. Hoi},
year={2023},
eprint={2305.14720},
archivePrefix={arXiv},
primaryClass={cs.CV}
}
```
|
salesforce/blipdiffusion
|
salesforce
| 2023-09-21T15:55:12Z | 322 | 13 |
diffusers
|
[
"diffusers",
"safetensors",
"en",
"arxiv:2305.14720",
"license:apache-2.0",
"diffusers:BlipDiffusionPipeline",
"region:us"
] | null | 2023-09-21T15:55:12Z |
---
license: apache-2.0
language:
- en
library_name: diffusers
---
# BLIP-Diffusion: Pre-trained Subject Representation for Controllable Text-to-Image Generation and Editing
<!-- Provide a quick summary of what the model is/does. -->
Model card for BLIP-Diffusion, a text to image Diffusion model which enables zero-shot subject-driven generation and control-guided zero-shot generation.
The abstract from the paper is:
*Subject-driven text-to-image generation models create novel renditions of an input subject based on text prompts. Existing models suffer from lengthy fine-tuning and difficulties preserving the subject fidelity. To overcome these limitations, we introduce BLIP-Diffusion, a new subject-driven image generation model that supports multimodal control which consumes inputs of subject images and text prompts. Unlike other subject-driven generation models, BLIP-Diffusion introduces a new multimodal encoder which is pre-trained to provide subject representation. We first pre-train the multimodal encoder following BLIP-2 to produce visual representation aligned with the text. Then we design a subject representation learning task which enables a diffusion model to leverage such visual representation and generates new subject renditions. Compared with previous methods such as DreamBooth, our model enables zero-shot subject-driven generation, and efficient fine-tuning for customized subject with up to 20x speedup. We also demonstrate that BLIP-Diffusion can be flexibly combined with existing techniques such as ControlNet and prompt-to-prompt to enable novel subject-driven generation and editing applications.*
The model is created by Dongxu Li, Junnan Li, Steven C.H. Hoi.
### Model Sources
<!-- Provide the basic links for the model. -->
- **Original Repository:** https://github.com/salesforce/LAVIS/tree/main
- **Project Page:** https://dxli94.github.io/BLIP-Diffusion-website/
## Uses
### Zero-Shot Subject Driven Generation
```python
from diffusers.pipelines import BlipDiffusionPipeline
from diffusers.utils import load_image
import torch
blip_diffusion_pipe = BlipDiffusionPipeline.from_pretrained(
"Salesforce/blipdiffusion", torch_dtype=torch.float16
).to("cuda")
cond_subject = "dog"
tgt_subject = "dog"
text_prompt_input = "swimming underwater"
cond_image = load_image(
"https://huggingface.co/datasets/ayushtues/blipdiffusion_images/resolve/main/dog.jpg"
)
iter_seed = 88888
guidance_scale = 7.5
num_inference_steps = 25
negative_prompt = "over-exposure, under-exposure, saturated, duplicate, out of frame, lowres, cropped, worst quality, low quality, jpeg artifacts, morbid, mutilated, out of frame, ugly, bad anatomy, bad proportions, deformed, blurry, duplicate"
output = blip_diffusion_pipe(
text_prompt_input,
cond_image,
cond_subject,
tgt_subject,
guidance_scale=guidance_scale,
num_inference_steps=num_inference_steps,
neg_prompt=negative_prompt,
height=512,
width=512,
).images
output[0].save("image.png")
```
Input Image : <img src="https://huggingface.co/datasets/ayushtues/blipdiffusion_images/resolve/main/dog.jpg" style="width:500px;"/>
Generatred Image : <img src="https://huggingface.co/datasets/ayushtues/blipdiffusion_images/resolve/main/dog_underwater.png" style="width:500px;"/>
### Controlled subject-driven generation
```python
from diffusers.pipelines import BlipDiffusionControlNetPipeline
from diffusers.utils import load_image
from controlnet_aux import CannyDetector
blip_diffusion_pipe = BlipDiffusionControlNetPipeline.from_pretrained(
"Salesforce/blipdiffusion-controlnet", torch_dtype=torch.float16
).to("cuda")
style_subject = "flower" # subject that defines the style
tgt_subject = "teapot" # subject to generate.
text_prompt = "on a marble table"
cldm_cond_image = load_image(
"https://huggingface.co/datasets/ayushtues/blipdiffusion_images/resolve/main/kettle.jpg"
).resize((512, 512))
canny = CannyDetector()
cldm_cond_image = canny(cldm_cond_image, 30, 70, output_type="pil")
style_image = load_image(
"https://huggingface.co/datasets/ayushtues/blipdiffusion_images/resolve/main/flower.jpg"
)
guidance_scale = 7.5
num_inference_steps = 50
negative_prompt = "over-exposure, under-exposure, saturated, duplicate, out of frame, lowres, cropped, worst quality, low quality, jpeg artifacts, morbid, mutilated, out of frame, ugly, bad anatomy, bad proportions, deformed, blurry, duplicate"
output = blip_diffusion_pipe(
text_prompt,
style_image,
cldm_cond_image,
style_subject,
tgt_subject,
guidance_scale=guidance_scale,
num_inference_steps=num_inference_steps,
neg_prompt=negative_prompt,
height=512,
width=512,
).images
output[0].save("image.png")
```
Input Style Image : <img src="https://huggingface.co/datasets/ayushtues/blipdiffusion_images/resolve/main/flower.jpg" style="width:500px;"/>
Canny Edge Input : <img src="https://huggingface.co/datasets/ayushtues/blipdiffusion_images/resolve/main/kettle.jpg" style="width:500px;"/>
Generated Image : <img src="https://huggingface.co/datasets/ayushtues/blipdiffusion_images/resolve/main/canny_generated.png" style="width:500px;"/>
### Controlled subject-driven generation Scribble
```python
from diffusers.pipelines import BlipDiffusionControlNetPipeline
from diffusers.utils import load_image
from controlnet_aux import HEDdetector
blip_diffusion_pipe = BlipDiffusionControlNetPipeline.from_pretrained(
"Salesforce/blipdiffusion-controlnet"
)
controlnet = ControlNetModel.from_pretrained("lllyasviel/sd-controlnet-scribble")
blip_diffusion_pipe.controlnet = controlnet
blip_diffusion_pipe.to("cuda")
style_subject = "flower" # subject that defines the style
tgt_subject = "bag" # subject to generate.
text_prompt = "on a table"
cldm_cond_image = load_image(
"https://huggingface.co/lllyasviel/sd-controlnet-scribble/resolve/main/images/bag.png"
).resize((512, 512))
hed = HEDdetector.from_pretrained("lllyasviel/Annotators")
cldm_cond_image = hed(cldm_cond_image)
style_image = load_image(
"https://huggingface.co/datasets/ayushtues/blipdiffusion_images/resolve/main/flower.jpg"
)
guidance_scale = 7.5
num_inference_steps = 50
negative_prompt = "over-exposure, under-exposure, saturated, duplicate, out of frame, lowres, cropped, worst quality, low quality, jpeg artifacts, morbid, mutilated, out of frame, ugly, bad anatomy, bad proportions, deformed, blurry, duplicate"
output = blip_diffusion_pipe(
text_prompt,
style_image,
cldm_cond_image,
style_subject,
tgt_subject,
guidance_scale=guidance_scale,
num_inference_steps=num_inference_steps,
neg_prompt=negative_prompt,
height=512,
width=512,
).images
output[0].save("image.png")
```
Input Style Image : <img src="https://huggingface.co/datasets/ayushtues/blipdiffusion_images/resolve/main/flower.jpg" style="width:500px;"/>
Scribble Input : <img src="https://huggingface.co/datasets/ayushtues/blipdiffusion_images/resolve/main/scribble.png" style="width:500px;"/>
Generated Image : <img src="https://huggingface.co/datasets/ayushtues/blipdiffusion_images/resolve/main/scribble_output.png" style="width:500px;"/>
## Model Architecture
Blip-Diffusion learns a **pre-trained subject representation**. uch representation aligns with text embeddings and in the meantime also encodes the subject appearance. This allows efficient fine-tuning of the model for high-fidelity subject-driven applications, such as text-to-image generation, editing and style transfer.
To this end, they design a two-stage pre-training strategy to learn generic subject representation. In the first pre-training stage, they perform multimodal representation learning, which enforces BLIP-2 to produce text-aligned visual features based on the input image. In the second pre-training stage, they design a subject representation learning task, called prompted context generation, where the diffusion model learns to generate novel subject renditions based on the input visual features.
To achieve this, they curate pairs of input-target images with the same subject appearing in different contexts. Specifically, they synthesize input images by composing the subject with a random background. During pre-training, they feed the synthetic input image and the subject class label through BLIP-2 to obtain the multimodal embeddings as subject representation. The subject representation is then combined with a text prompt to guide the generation of the target image.
The architecture is also compatible to integrate with established techniques built on top of the diffusion model, such as ControlNet.
They attach the U-Net of the pre-trained ControlNet to that of BLIP-Diffusion via residuals. In this way, the model takes into account the input structure condition, such as edge maps and depth maps, in addition to the subject cues. Since the model inherits the architecture of the original latent diffusion model, they observe satisfying generations using off-the-shelf integration with pre-trained ControlNet without further training.
<img src="https://huggingface.co/datasets/ayushtues/blipdiffusion_images/resolve/main/arch_controlnet.png" style="width:50%;"/>
## Citation
**BibTeX:**
If you find this repository useful in your research, please cite:
```
@misc{li2023blipdiffusion,
title={BLIP-Diffusion: Pre-trained Subject Representation for Controllable Text-to-Image Generation and Editing},
author={Dongxu Li and Junnan Li and Steven C. H. Hoi},
year={2023},
eprint={2305.14720},
archivePrefix={arXiv},
primaryClass={cs.CV}
}
```
|
JuanMa360/kitchen-style-classification
|
JuanMa360
| 2023-09-21T15:51:55Z | 213 | 1 |
transformers
|
[
"transformers",
"pytorch",
"vit",
"image-classification",
"huggingpics",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
image-classification
| 2023-09-21T15:51:51Z |
---
tags:
- image-classification
- pytorch
- huggingpics
metrics:
- accuracy
model-index:
- name: kitchen-style-classification
results:
- task:
name: Image Classification
type: image-classification
metrics:
- name: Accuracy
type: accuracy
value: 0.7284768223762512
---
# kitchen-style-classification
House & Apartaments Classification model🤗🖼️
## Example Images
#### kitchens-island
#### kitchens-l
#### kitchens-lineal
#### kitchens-u
|
vgarg/my-fw9-identification-model-e5_large_v1
|
vgarg
| 2023-09-21T15:49:53Z | 3 | 0 |
sentence-transformers
|
[
"sentence-transformers",
"pytorch",
"xlm-roberta",
"setfit",
"text-classification",
"arxiv:2209.11055",
"license:apache-2.0",
"region:us"
] |
text-classification
| 2023-09-21T15:48:35Z |
---
license: apache-2.0
tags:
- setfit
- sentence-transformers
- text-classification
pipeline_tag: text-classification
---
# vgarg/my-fw9-identification-model-e5_large_v1
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("vgarg/my-fw9-identification-model-e5_large_v1")
# 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}
}
```
|
CyberHarem/saitou_youko_idolmastercinderellagirls
|
CyberHarem
| 2023-09-21T15:46:45Z | 0 | 0 | null |
[
"art",
"text-to-image",
"dataset:CyberHarem/saitou_youko_idolmastercinderellagirls",
"license:mit",
"region:us"
] |
text-to-image
| 2023-09-21T15:35:19Z |
---
license: mit
datasets:
- CyberHarem/saitou_youko_idolmastercinderellagirls
pipeline_tag: text-to-image
tags:
- art
---
# Lora of saitou_youko_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/saitou_youko_idolmastercinderellagirls.pt` as the embedding and `5100/saitou_youko_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 1.000. The trigger words are:
1. `saitou_youko_idolmastercinderellagirls`
2. `short_hair, ahoge, brown_hair, smile, brown_eyes, open_mouth, red_eyes, 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 | bikini | bondage | free | maid | miko | nude | nude2 | suit | yukata |
|:---------|:----------|:----------------------------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------|:--------------------------------------------------|:-------------------------------------|:-------------------------------------|:-------------------------------------|:-----------------------------------------------|:------------------------------------------------|:-------------------------------------|:-----------------------------------------|
| **5100** | **1.000** | [**Download**](5100/saitou_youko_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 | 0.996 | [Download](4760/saitou_youko_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 | 0.993 | [Download](4420/saitou_youko_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 | 0.999 | [Download](4080/saitou_youko_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 | 0.997 | [Download](3740/saitou_youko_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 | 0.999 | [Download](3400/saitou_youko_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 | 0.999 | [Download](3060/saitou_youko_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 | 0.997 | [Download](2720/saitou_youko_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 | 0.997 | [Download](2380/saitou_youko_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 | 0.997 | [Download](2040/saitou_youko_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 | 0.960 | [Download](1700/saitou_youko_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 | 0.966 | [Download](1360/saitou_youko_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 | 0.870 | [Download](1020/saitou_youko_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 | 0.863 | [Download](680/saitou_youko_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 | 0.951 | [Download](340/saitou_youko_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) |  |  |
|
ShivamMangale/XLM-Roberta-base-allhiweakdap_5th_iteration_d5_d4
|
ShivamMangale
| 2023-09-21T15:44:38Z | 122 | 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
| 2023-09-21T14:53:27Z |
---
license: mit
base_model: xlm-roberta-base
tags:
- generated_from_trainer
datasets:
- squad
model-index:
- name: XLM-Roberta-base-allhiweakdap_5th_iteration_d5_d4
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-allhiweakdap_5th_iteration_d5_d4
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: 1.4580000000000001e-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: 8
### Training results
### Framework versions
- Transformers 4.33.2
- Pytorch 2.0.1+cu117
- Datasets 2.14.5
- Tokenizers 0.13.3
|
ryatora/distilbert-base-uncased-finetuned-emotion
|
ryatora
| 2023-09-21T15:36:40Z | 105 | 0 |
transformers
|
[
"transformers",
"pytorch",
"tensorboard",
"distilbert",
"text-classification",
"generated_from_trainer",
"dataset:emotion",
"license:apache-2.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2023-09-19T12:44:18Z |
---
license: apache-2.0
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
args: split
metrics:
- name: Accuracy
type: accuracy
value: 0.9225
- name: F1
type: f1
value: 0.9224787080842691
---
<!-- 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: 0.2185
- Accuracy: 0.9225
- F1: 0.9225
## 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 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
| 0.8423 | 1.0 | 250 | 0.3084 | 0.9065 | 0.9049 |
| 0.2493 | 2.0 | 500 | 0.2185 | 0.9225 | 0.9225 |
### Framework versions
- Transformers 4.16.2
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.14.0
|
ShivamMangale/XLM-Roberta-base-allhiweakdap_5th_iteration_d5
|
ShivamMangale
| 2023-09-21T15:35:52Z | 122 | 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
| 2023-09-21T14:45:26Z |
---
license: mit
base_model: xlm-roberta-base
tags:
- generated_from_trainer
datasets:
- squad
model-index:
- name: XLM-Roberta-base-allhiweakdap_5th_iteration_d5
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-allhiweakdap_5th_iteration_d5
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: 1.3122e-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: 8
### Training results
### Framework versions
- Transformers 4.33.2
- Pytorch 2.0.1+cu117
- Datasets 2.14.5
- Tokenizers 0.13.3
|
MarcosMunoz95/SpaceInvadersNoFrameskip
|
MarcosMunoz95
| 2023-09-21T15:25:11Z | 1 | 0 |
stable-baselines3
|
[
"stable-baselines3",
"SpaceInvadersNoFrameskip-v4",
"deep-reinforcement-learning",
"reinforcement-learning",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-09-21T15:24:37Z |
---
library_name: stable-baselines3
tags:
- SpaceInvadersNoFrameskip-v4
- deep-reinforcement-learning
- reinforcement-learning
- stable-baselines3
model-index:
- name: DQN
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: SpaceInvadersNoFrameskip-v4
type: SpaceInvadersNoFrameskip-v4
metrics:
- type: mean_reward
value: 670.00 +/- 96.93
name: mean_reward
verified: false
---
# **DQN** Agent playing **SpaceInvadersNoFrameskip-v4**
This is a trained model of a **DQN** agent playing **SpaceInvadersNoFrameskip-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 dqn --env SpaceInvadersNoFrameskip-v4 -orga MarcosMunoz95 -f logs/
python -m rl_zoo3.enjoy --algo dqn --env SpaceInvadersNoFrameskip-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 dqn --env SpaceInvadersNoFrameskip-v4 -orga MarcosMunoz95 -f logs/
python -m rl_zoo3.enjoy --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/
```
## Training (with the RL Zoo)
```
python -m rl_zoo3.train --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/
# Upload the model and generate video (when possible)
python -m rl_zoo3.push_to_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/ -orga MarcosMunoz95
```
## Hyperparameters
```python
OrderedDict([('batch_size', 32),
('buffer_size', 100000),
('env_wrapper',
['stable_baselines3.common.atari_wrappers.AtariWrapper']),
('exploration_final_eps', 0.01),
('exploration_fraction', 0.1),
('frame_stack', 4),
('gradient_steps', 1),
('learning_rate', 0.0001),
('learning_starts', 100000),
('n_timesteps', 1000000.0),
('optimize_memory_usage', False),
('policy', 'CnnPolicy'),
('target_update_interval', 1000),
('train_freq', 4),
('normalize', False)])
```
# Environment Arguments
```python
{'render_mode': 'rgb_array'}
```
|
ShivamMangale/XLM-Roberta-base-all_hi_weakdap_4th_iteration_d4_d3_d2_d1_d0
|
ShivamMangale
| 2023-09-21T15:24:22Z | 133 | 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
| 2023-09-21T14:52:40Z |
---
license: mit
base_model: xlm-roberta-base
tags:
- generated_from_trainer
datasets:
- squad
model-index:
- name: XLM-Roberta-base-all_hi_weakdap_4th_iteration_d4_d3_d2_d1_d0
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-all_hi_weakdap_4th_iteration_d4_d3_d2_d1_d0
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: 8
### Training results
### Framework versions
- Transformers 4.33.2
- Pytorch 2.0.1+cu117
- Datasets 2.14.5
- Tokenizers 0.13.3
|
Agisight/alpaca-tyv-rus
|
Agisight
| 2023-09-21T15:24:10Z | 1 | 0 |
peft
|
[
"peft",
"region:us"
] | null | 2023-09-20T20:43:18Z |
---
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
|
neksjgg/rav3nus
|
neksjgg
| 2023-09-21T15:22:16Z | 0 | 0 | null |
[
"streamer",
"twitch",
"ru",
"region:us"
] | null | 2023-09-21T15:15:09Z |
---
language:
- ru
tags:
- streamer
- twitch
---
|
SHENMU007/neunit_BASE_V13.5.9
|
SHENMU007
| 2023-09-21T15:06:49Z | 75 | 0 |
transformers
|
[
"transformers",
"pytorch",
"speecht5",
"text-to-audio",
"1.1.0",
"generated_from_trainer",
"zh",
"dataset:facebook/voxpopuli",
"base_model:microsoft/speecht5_tts",
"base_model:finetune:microsoft/speecht5_tts",
"license:mit",
"endpoints_compatible",
"region:us"
] |
text-to-audio
| 2023-09-12T10:35:54Z |
---
language:
- zh
license: mit
base_model: microsoft/speecht5_tts
tags:
- 1.1.0
- generated_from_trainer
datasets:
- facebook/voxpopuli
model-index:
- name: SpeechT5 TTS Dutch neunit
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 TTS Dutch neunit
This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on the 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: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- 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
### Training results
### Framework versions
- Transformers 4.33.1
- Pytorch 2.0.1+cu117
- Datasets 2.14.5
- Tokenizers 0.13.3
|
acalatrava/TinyLlama-1.1B-orca-gpt4
|
acalatrava
| 2023-09-21T15:05:27Z | 136 | 1 |
transformers
|
[
"transformers",
"pytorch",
"llama",
"text-generation",
"en",
"dataset:cerebras/SlimPajama-627B",
"dataset:bigcode/starcoderdata",
"dataset:sam-mosaic/orca-gpt4-chatml",
"license:apache-2.0",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2023-09-21T10:11:33Z |
---
license: apache-2.0
datasets:
- cerebras/SlimPajama-627B
- bigcode/starcoderdata
- sam-mosaic/orca-gpt4-chatml
language:
- en
---
<div align="center">
# TinyLlama-1.1B
Finetuned with ORCA-GPT4 (chatml format)
</div>
This is a fine-tuned version of [TinyLlama-1.1B-intermediate-step-240k-503b](https://huggingface.co/PY007/TinyLlama-1.1B-intermediate-step-240k-503b) using the [sam-mosaic/orca-gpt4-chatml](https://huggingface.co/datasets/sam-mosaic/orca-gpt4-chatml) dataset.
### Training
- **Method**: QLORA
- **Quantization**: fp16
- **Time**: 20h on a RTX 4090 (from runpod.io)
- **Cost**: About $15
- **Based on**: [https://colab.research.google.com/drive/1Zmaceu65d7w4Tcd-cfnZRb6k_Tcv2b8g](https://colab.research.google.com/drive/1Zmaceu65d7w4Tcd-cfnZRb6k_Tcv2b8g)
|
CyberHarem/hiiragi_shino_idolmastercinderellagirls
|
CyberHarem
| 2023-09-21T14:54:07Z | 0 | 0 | null |
[
"art",
"text-to-image",
"dataset:CyberHarem/hiiragi_shino_idolmastercinderellagirls",
"license:mit",
"region:us"
] |
text-to-image
| 2023-09-21T14:42:01Z |
---
license: mit
datasets:
- CyberHarem/hiiragi_shino_idolmastercinderellagirls
pipeline_tag: text-to-image
tags:
- art
---
# Lora of hiiragi_shino_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/hiiragi_shino_idolmastercinderellagirls.pt` as the embedding and `4760/hiiragi_shino_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 0.994. The trigger words are:
1. `hiiragi_shino_idolmastercinderellagirls`
2. `long_hair, black_hair, blush, brown_eyes, smile, jewelry, breasts, large_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 | bikini | bondage | free | maid | miko | nude | nude2 | suit | yukata |
|:---------|:----------|:-----------------------------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------|:--------------------------------------------------|:-----------------------------------------------|:-------------------------------------|:-------------------------------------|:-----------------------------------------------|:------------------------------------------------|:-------------------------------------|:-----------------------------------------|
| 5100 | 0.976 | [Download](5100/hiiragi_shino_idolmastercinderellagirls.zip) |  |  |  |  |  | [<NSFW, click to see>](5100/previews/bondage.png) | [<NSFW, click to see>](5100/previews/free.png) |  |  | [<NSFW, click to see>](5100/previews/nude.png) | [<NSFW, click to see>](5100/previews/nude2.png) |  |  |
| **4760** | **0.994** | [**Download**](4760/hiiragi_shino_idolmastercinderellagirls.zip) |  |  |  |  |  | [<NSFW, click to see>](4760/previews/bondage.png) | [<NSFW, click to see>](4760/previews/free.png) |  |  | [<NSFW, click to see>](4760/previews/nude.png) | [<NSFW, click to see>](4760/previews/nude2.png) |  |  |
| 4420 | 0.981 | [Download](4420/hiiragi_shino_idolmastercinderellagirls.zip) |  |  |  |  |  | [<NSFW, click to see>](4420/previews/bondage.png) | [<NSFW, click to see>](4420/previews/free.png) |  |  | [<NSFW, click to see>](4420/previews/nude.png) | [<NSFW, click to see>](4420/previews/nude2.png) |  |  |
| 4080 | 0.977 | [Download](4080/hiiragi_shino_idolmastercinderellagirls.zip) |  |  |  |  |  | [<NSFW, click to see>](4080/previews/bondage.png) | [<NSFW, click to see>](4080/previews/free.png) |  |  | [<NSFW, click to see>](4080/previews/nude.png) | [<NSFW, click to see>](4080/previews/nude2.png) |  |  |
| 3740 | 0.963 | [Download](3740/hiiragi_shino_idolmastercinderellagirls.zip) |  |  |  |  |  | [<NSFW, click to see>](3740/previews/bondage.png) | [<NSFW, click to see>](3740/previews/free.png) |  |  | [<NSFW, click to see>](3740/previews/nude.png) | [<NSFW, click to see>](3740/previews/nude2.png) |  |  |
| 3400 | 0.951 | [Download](3400/hiiragi_shino_idolmastercinderellagirls.zip) |  |  |  |  |  | [<NSFW, click to see>](3400/previews/bondage.png) | [<NSFW, click to see>](3400/previews/free.png) |  |  | [<NSFW, click to see>](3400/previews/nude.png) | [<NSFW, click to see>](3400/previews/nude2.png) |  |  |
| 3060 | 0.984 | [Download](3060/hiiragi_shino_idolmastercinderellagirls.zip) |  |  |  |  |  | [<NSFW, click to see>](3060/previews/bondage.png) | [<NSFW, click to see>](3060/previews/free.png) |  |  | [<NSFW, click to see>](3060/previews/nude.png) | [<NSFW, click to see>](3060/previews/nude2.png) |  |  |
| 2720 | 0.966 | [Download](2720/hiiragi_shino_idolmastercinderellagirls.zip) |  |  |  |  |  | [<NSFW, click to see>](2720/previews/bondage.png) | [<NSFW, click to see>](2720/previews/free.png) |  |  | [<NSFW, click to see>](2720/previews/nude.png) | [<NSFW, click to see>](2720/previews/nude2.png) |  |  |
| 2380 | 0.938 | [Download](2380/hiiragi_shino_idolmastercinderellagirls.zip) |  |  |  |  |  | [<NSFW, click to see>](2380/previews/bondage.png) | [<NSFW, click to see>](2380/previews/free.png) |  |  | [<NSFW, click to see>](2380/previews/nude.png) | [<NSFW, click to see>](2380/previews/nude2.png) |  |  |
| 2040 | 0.938 | [Download](2040/hiiragi_shino_idolmastercinderellagirls.zip) |  |  |  |  |  | [<NSFW, click to see>](2040/previews/bondage.png) | [<NSFW, click to see>](2040/previews/free.png) |  |  | [<NSFW, click to see>](2040/previews/nude.png) | [<NSFW, click to see>](2040/previews/nude2.png) |  |  |
| 1700 | 0.971 | [Download](1700/hiiragi_shino_idolmastercinderellagirls.zip) |  |  |  |  |  | [<NSFW, click to see>](1700/previews/bondage.png) | [<NSFW, click to see>](1700/previews/free.png) |  |  | [<NSFW, click to see>](1700/previews/nude.png) | [<NSFW, click to see>](1700/previews/nude2.png) |  |  |
| 1360 | 0.955 | [Download](1360/hiiragi_shino_idolmastercinderellagirls.zip) |  |  |  |  |  | [<NSFW, click to see>](1360/previews/bondage.png) | [<NSFW, click to see>](1360/previews/free.png) |  |  | [<NSFW, click to see>](1360/previews/nude.png) | [<NSFW, click to see>](1360/previews/nude2.png) |  |  |
| 1020 | 0.792 | [Download](1020/hiiragi_shino_idolmastercinderellagirls.zip) |  |  |  |  |  | [<NSFW, click to see>](1020/previews/bondage.png) | [<NSFW, click to see>](1020/previews/free.png) |  |  | [<NSFW, click to see>](1020/previews/nude.png) | [<NSFW, click to see>](1020/previews/nude2.png) |  |  |
| 680 | 0.937 | [Download](680/hiiragi_shino_idolmastercinderellagirls.zip) |  |  |  |  |  | [<NSFW, click to see>](680/previews/bondage.png) | [<NSFW, click to see>](680/previews/free.png) |  |  | [<NSFW, click to see>](680/previews/nude.png) | [<NSFW, click to see>](680/previews/nude2.png) |  |  |
| 340 | 0.867 | [Download](340/hiiragi_shino_idolmastercinderellagirls.zip) |  |  |  |  |  | [<NSFW, click to see>](340/previews/bondage.png) | [<NSFW, click to see>](340/previews/free.png) |  |  | [<NSFW, click to see>](340/previews/nude.png) | [<NSFW, click to see>](340/previews/nude2.png) |  |  |
|
ShivamMangale/XLM-Roberta-base-all_hi_weakdap_4th_iteration_d4_d3_d2_d1
|
ShivamMangale
| 2023-09-21T14:52:39Z | 122 | 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
| 2023-09-21T14:34:47Z |
---
license: mit
base_model: xlm-roberta-base
tags:
- generated_from_trainer
datasets:
- squad
model-index:
- name: XLM-Roberta-base-all_hi_weakdap_4th_iteration_d4_d3_d2_d1
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-all_hi_weakdap_4th_iteration_d4_d3_d2_d1
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: 8
### Training results
### Framework versions
- Transformers 4.33.2
- Pytorch 2.0.1+cu117
- Datasets 2.14.5
- Tokenizers 0.13.3
|
mann-e/mann-e_5.4
|
mann-e
| 2023-09-21T14:52:30Z | 3 | 0 |
diffusers
|
[
"diffusers",
"text-to-image",
"region:us"
] |
text-to-image
| 2023-09-21T12:47:14Z |
---
library_name: diffusers
pipeline_tag: text-to-image
---
# Mann-E 5.4
This repository represents what is the main brain of [Mann-E](https://manne.ir) artificial intelligence platform.
## Features
1. _LoRa support_. In previous versions, most of LoRa models weren't working perfectly with the model.
2. _More coherent results_. Compared to the old versions, this version has more "midjourney" feel to its outputs.
3. _New License_. Unlike old versions this one isn't licensed undet MIT, we decided to go with our own license.
## Samples
<span align="center">
<img src="https://huggingface.co/mann-e/mann-e_5.4/resolve/main/grid-1.png" width=512px />
<br/>
<img src="https://huggingface.co/mann-e/mann-e_5.4/resolve/main/grid-2.png" width=512px />
<br/>
<img src="https://huggingface.co/mann-e/mann-e_5.4/resolve/main/grid-3.png" width=512px />
<br/>
<img src="https://huggingface.co/mann-e/mann-e_5.4/resolve/main/grid-4.png" width=512px />
<br/>
<img src="https://huggingface.co/mann-e/mann-e_5.4/resolve/main/grid-5.png" width=512px />
</span>
## License
This software and associated checkpoints are provided by Mann-E for educational and non-commercial use only. By accessing or using this software and checkpoints, you agree to the following terms and conditions:
1. Access and Use:
- You are granted the right to access and use the source code and checkpoints for educational and non-commercial purposes.
2. Modification and Distribution:
- You may modify and distribute the source code and checkpoints solely for educational and non-commercial purposes, provided that you retain this license notice.
3. Commercial Use:
- Commercial use of this software and checkpoints is strictly prohibited without the explicit written consent of the Copyright Holder.
4. Fine-tuning of Checkpoints:
- You may not fine-tune or modify the provided checkpoints without obtaining the express written consent of the Copyright Holder.
5. No Warranty:
- This software and checkpoints are provided "as is" without any warranty. The Copyright Holder shall not be liable for any damages or liabilities arising out of the use or inability to use the software and checkpoints.
6. Termination:
- This license is effective until terminated by the Copyright Holder. Your rights under this license will terminate automatically without notice from the Copyright Holder if you fail to comply with any term or condition of this license.
If you do not agree to these terms and conditions or do not have the legal authority to bind yourself, you may not use, modify, or distribute this software and checkpoints.
For inquiries regarding commercial use or fine-tuning of checkpoints, please contact Mann-E.
|
anjakuzev/13b_200
|
anjakuzev
| 2023-09-21T14:50:40Z | 1 | 0 |
peft
|
[
"peft",
"region:us"
] | null | 2023-09-21T14:50:37Z |
---
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 0.4.0
|
yunosuken/results
|
yunosuken
| 2023-09-21T14:50:34Z | 103 | 0 |
transformers
|
[
"transformers",
"pytorch",
"bert",
"text-classification",
"generated_from_trainer",
"base_model:tohoku-nlp/bert-large-japanese-v2",
"base_model:finetune:tohoku-nlp/bert-large-japanese-v2",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2023-09-13T14:15:12Z |
---
license: apache-2.0
base_model: cl-tohoku/bert-large-japanese-v2
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
model-index:
- name: bert-large-japanease-v2-gpt4-relevance-learned
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-large-japanease-v2-gpt4-relevance-learned
This model is a fine-tuned version of [cl-tohoku/bert-large-japanese-v2](https://huggingface.co/cl-tohoku/bert-large-japanese-v2) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 3.2693
- Accuracy: 0.885
- F1: 0.8788
## 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 | Accuracy | F1 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
| 3.3692 | 1.0 | 563 | 3.2122 | 0.872 | 0.8560 |
| 3.0963 | 2.0 | 1126 | 3.1045 | 0.866 | 0.8625 |
| 2.8698 | 3.0 | 1689 | 3.1410 | 0.882 | 0.8755 |
| 2.6212 | 4.0 | 2252 | 3.2119 | 0.876 | 0.8702 |
| 2.407 | 5.0 | 2815 | 3.2693 | 0.885 | 0.8788 |
### Framework versions
- Transformers 4.33.2
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3
|
nickypro/tinyllama-42M-fp32
|
nickypro
| 2023-09-21T14:50:34Z | 150 | 1 |
transformers
|
[
"transformers",
"pytorch",
"llama",
"text-generation",
"license:mit",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2023-09-16T17:25:17Z |
---
license: mit
---
This is the float32 42M parameter Llama 2 architecture model trained on the TinyStories dataset.
These are converted from
[karpathy/tinyllamas](https://huggingface.co/karpathy/tinyllamas).
See the [llama2.c](https://github.com/karpathy/llama2.c) project for more details.
|
nickypro/tinyllama-42M
|
nickypro
| 2023-09-21T14:49:31Z | 184 | 1 |
transformers
|
[
"transformers",
"pytorch",
"llama",
"text-generation",
"license:mit",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2023-09-16T13:33:58Z |
---
license: mit
---
This is the 42M parameter Llama 2 architecture model trained on the TinyStories dataset.
These are converted from
[karpathy/tinyllamas](https://huggingface.co/karpathy/tinyllamas).
See the [llama2.c](https://github.com/karpathy/llama2.c) project for more details.
|
nickypro/tinyllama-110M
|
nickypro
| 2023-09-21T14:49:10Z | 818 | 4 |
transformers
|
[
"transformers",
"pytorch",
"llama",
"text-generation",
"license:mit",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2023-09-16T13:37:27Z |
---
license: mit
---
This is the 110M parameter Llama 2 architecture model trained on the TinyStories dataset.
These are converted from
[karpathy/tinyllamas](https://huggingface.co/karpathy/tinyllamas).
See the [llama2.c](https://github.com/karpathy/llama2.c) project for more details.
|
yanyanstar/virus-ds
|
yanyanstar
| 2023-09-21T14:49:09Z | 131 | 0 |
transformers
|
[
"transformers",
"pytorch",
"gpt2",
"text-generation",
"generated_from_trainer",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2023-09-21T14:15:17Z |
---
tags:
- generated_from_trainer
model-index:
- name: virus-ds
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. -->
# virus-ds
This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.7950
## 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: 32
- eval_batch_size: 32
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 256
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 100
- num_epochs: 100
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 1.2776 | 44.44 | 200 | 1.2465 |
| 0.9432 | 88.89 | 400 | 0.7950 |
### Framework versions
- Transformers 4.33.2
- Pytorch 2.0.0+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3
|
ayushtues/blipdiffusion-controlnet
|
ayushtues
| 2023-09-21T14:44:41Z | 2 | 0 |
diffusers
|
[
"diffusers",
"en",
"arxiv:2305.14720",
"license:apache-2.0",
"diffusers:BlipDiffusionControlNetPipeline",
"region:us"
] | null | 2023-08-30T12:09:09Z |
---
license: apache-2.0
language:
- en
library_name: diffusers
---
# BLIP-Diffusion: Pre-trained Subject Representation for Controllable Text-to-Image Generation and Editing
<!-- Provide a quick summary of what the model is/does. -->
Model card for BLIP-Diffusion, a text to image Diffusion model which enables zero-shot subject-driven generation and control-guided zero-shot generation.
The abstract from the paper is:
*Subject-driven text-to-image generation models create novel renditions of an input subject based on text prompts. Existing models suffer from lengthy fine-tuning and difficulties preserving the subject fidelity. To overcome these limitations, we introduce BLIP-Diffusion, a new subject-driven image generation model that supports multimodal control which consumes inputs of subject images and text prompts. Unlike other subject-driven generation models, BLIP-Diffusion introduces a new multimodal encoder which is pre-trained to provide subject representation. We first pre-train the multimodal encoder following BLIP-2 to produce visual representation aligned with the text. Then we design a subject representation learning task which enables a diffusion model to leverage such visual representation and generates new subject renditions. Compared with previous methods such as DreamBooth, our model enables zero-shot subject-driven generation, and efficient fine-tuning for customized subject with up to 20x speedup. We also demonstrate that BLIP-Diffusion can be flexibly combined with existing techniques such as ControlNet and prompt-to-prompt to enable novel subject-driven generation and editing applications.*
The model is created by Dongxu Li, Junnan Li, Steven C.H. Hoi.
### Model Sources
<!-- Provide the basic links for the model. -->
- **Original Repository:** https://github.com/salesforce/LAVIS/tree/main
- **Project Page:** https://dxli94.github.io/BLIP-Diffusion-website/
## Uses
### Zero-Shot Subject Driven Generation
```python
from diffusers.pipelines import BlipDiffusionPipeline
from diffusers.utils import load_image
import torch
blip_diffusion_pipe = BlipDiffusionPipeline.from_pretrained(
"Salesforce/blipdiffusion", torch_dtype=torch.float16
).to("cuda")
cond_subject = "dog"
tgt_subject = "dog"
text_prompt_input = "swimming underwater"
cond_image = load_image(
"https://huggingface.co/datasets/ayushtues/blipdiffusion_images/resolve/main/dog.jpg"
)
iter_seed = 88888
guidance_scale = 7.5
num_inference_steps = 25
negative_prompt = "over-exposure, under-exposure, saturated, duplicate, out of frame, lowres, cropped, worst quality, low quality, jpeg artifacts, morbid, mutilated, out of frame, ugly, bad anatomy, bad proportions, deformed, blurry, duplicate"
output = blip_diffusion_pipe(
text_prompt_input,
cond_image,
cond_subject,
tgt_subject,
guidance_scale=guidance_scale,
num_inference_steps=num_inference_steps,
neg_prompt=negative_prompt,
height=512,
width=512,
).images
output[0].save("image.png")
```
Input Image : <img src="https://huggingface.co/datasets/ayushtues/blipdiffusion_images/resolve/main/dog.jpg" style="width:500px;"/>
Generatred Image : <img src="https://huggingface.co/datasets/ayushtues/blipdiffusion_images/resolve/main/dog_underwater.png" style="width:500px;"/>
### Controlled subject-driven generation
```python
from diffusers.pipelines import BlipDiffusionControlNetPipeline
from diffusers.utils import load_image
from controlnet_aux import CannyDetector
blip_diffusion_pipe = BlipDiffusionControlNetPipeline.from_pretrained(
"Salesforce/blipdiffusion-controlnet", torch_dtype=torch.float16
).to("cuda")
style_subject = "flower" # subject that defines the style
tgt_subject = "teapot" # subject to generate.
text_prompt = "on a marble table"
cldm_cond_image = load_image(
"https://huggingface.co/datasets/ayushtues/blipdiffusion_images/resolve/main/kettle.jpg"
).resize((512, 512))
canny = CannyDetector()
cldm_cond_image = canny(cldm_cond_image, 30, 70, output_type="pil")
style_image = load_image(
"https://huggingface.co/datasets/ayushtues/blipdiffusion_images/resolve/main/flower.jpg"
)
guidance_scale = 7.5
num_inference_steps = 50
negative_prompt = "over-exposure, under-exposure, saturated, duplicate, out of frame, lowres, cropped, worst quality, low quality, jpeg artifacts, morbid, mutilated, out of frame, ugly, bad anatomy, bad proportions, deformed, blurry, duplicate"
output = blip_diffusion_pipe(
text_prompt,
style_image,
cldm_cond_image,
style_subject,
tgt_subject,
guidance_scale=guidance_scale,
num_inference_steps=num_inference_steps,
neg_prompt=negative_prompt,
height=512,
width=512,
).images
output[0].save("image.png")
```
Input Style Image : <img src="https://huggingface.co/datasets/ayushtues/blipdiffusion_images/resolve/main/flower.jpg" style="width:500px;"/>
Canny Edge Input : <img src="https://huggingface.co/datasets/ayushtues/blipdiffusion_images/resolve/main/kettle.jpg" style="width:500px;"/>
Generated Image : <img src="https://huggingface.co/datasets/ayushtues/blipdiffusion_images/resolve/main/canny_generated.png" style="width:500px;"/>
### Controlled subject-driven generation Scribble
```python
from diffusers.pipelines import BlipDiffusionControlNetPipeline
from diffusers.utils import load_image
from controlnet_aux import HEDdetector
blip_diffusion_pipe = BlipDiffusionControlNetPipeline.from_pretrained(
"Salesforce/blipdiffusion-controlnet"
)
controlnet = ControlNetModel.from_pretrained("lllyasviel/sd-controlnet-scribble")
blip_diffusion_pipe.controlnet = controlnet
blip_diffusion_pipe.to("cuda")
style_subject = "flower" # subject that defines the style
tgt_subject = "bag" # subject to generate.
text_prompt = "on a table"
cldm_cond_image = load_image(
"https://huggingface.co/lllyasviel/sd-controlnet-scribble/resolve/main/images/bag.png"
).resize((512, 512))
hed = HEDdetector.from_pretrained("lllyasviel/Annotators")
cldm_cond_image = hed(cldm_cond_image)
style_image = load_image(
"https://huggingface.co/datasets/ayushtues/blipdiffusion_images/resolve/main/flower.jpg"
)
guidance_scale = 7.5
num_inference_steps = 50
negative_prompt = "over-exposure, under-exposure, saturated, duplicate, out of frame, lowres, cropped, worst quality, low quality, jpeg artifacts, morbid, mutilated, out of frame, ugly, bad anatomy, bad proportions, deformed, blurry, duplicate"
output = blip_diffusion_pipe(
text_prompt,
style_image,
cldm_cond_image,
style_subject,
tgt_subject,
guidance_scale=guidance_scale,
num_inference_steps=num_inference_steps,
neg_prompt=negative_prompt,
height=512,
width=512,
).images
output[0].save("image.png")
```
Input Style Image : <img src="https://huggingface.co/datasets/ayushtues/blipdiffusion_images/resolve/main/flower.jpg" style="width:500px;"/>
Scribble Input : <img src="https://huggingface.co/datasets/ayushtues/blipdiffusion_images/resolve/main/scribble.png" style="width:500px;"/>
Generated Image : <img src="https://huggingface.co/datasets/ayushtues/blipdiffusion_images/resolve/main/scribble_output.png" style="width:500px;"/>
## Model Architecture
Blip-Diffusion learns a **pre-trained subject representation**. uch representation aligns with text embeddings and in the meantime also encodes the subject appearance. This allows efficient fine-tuning of the model for high-fidelity subject-driven applications, such as text-to-image generation, editing and style transfer.
To this end, they design a two-stage pre-training strategy to learn generic subject representation. In the first pre-training stage, they perform multimodal representation learning, which enforces BLIP-2 to produce text-aligned visual features based on the input image. In the second pre-training stage, they design a subject representation learning task, called prompted context generation, where the diffusion model learns to generate novel subject renditions based on the input visual features.
To achieve this, they curate pairs of input-target images with the same subject appearing in different contexts. Specifically, they synthesize input images by composing the subject with a random background. During pre-training, they feed the synthetic input image and the subject class label through BLIP-2 to obtain the multimodal embeddings as subject representation. The subject representation is then combined with a text prompt to guide the generation of the target image.
The architecture is also compatible to integrate with established techniques built on top of the diffusion model, such as ControlNet.
They attach the U-Net of the pre-trained ControlNet to that of BLIP-Diffusion via residuals. In this way, the model takes into account the input structure condition, such as edge maps and depth maps, in addition to the subject cues. Since the model inherits the architecture of the original latent diffusion model, they observe satisfying generations using off-the-shelf integration with pre-trained ControlNet without further training.
<img src="https://huggingface.co/datasets/ayushtues/blipdiffusion_images/resolve/main/arch_controlnet.png" style="width:50%;"/>
## Citation
**BibTeX:**
If you find this repository useful in your research, please cite:
```
@misc{li2023blipdiffusion,
title={BLIP-Diffusion: Pre-trained Subject Representation for Controllable Text-to-Image Generation and Editing},
author={Dongxu Li and Junnan Li and Steven C. H. Hoi},
year={2023},
eprint={2305.14720},
archivePrefix={arXiv},
primaryClass={cs.CV}
}
```
|
ayushtues/blipdiffusion
|
ayushtues
| 2023-09-21T14:44:10Z | 7 | 0 |
diffusers
|
[
"diffusers",
"safetensors",
"en",
"arxiv:2305.14720",
"license:apache-2.0",
"diffusers:BlipDiffusionPipeline",
"region:us"
] | null | 2023-08-07T05:45:01Z |
---
license: apache-2.0
language:
- en
library_name: diffusers
---
# BLIP-Diffusion: Pre-trained Subject Representation for Controllable Text-to-Image Generation and Editing
<!-- Provide a quick summary of what the model is/does. -->
Model card for BLIP-Diffusion, a text to image Diffusion model which enables zero-shot subject-driven generation and control-guided zero-shot generation.
The abstract from the paper is:
*Subject-driven text-to-image generation models create novel renditions of an input subject based on text prompts. Existing models suffer from lengthy fine-tuning and difficulties preserving the subject fidelity. To overcome these limitations, we introduce BLIP-Diffusion, a new subject-driven image generation model that supports multimodal control which consumes inputs of subject images and text prompts. Unlike other subject-driven generation models, BLIP-Diffusion introduces a new multimodal encoder which is pre-trained to provide subject representation. We first pre-train the multimodal encoder following BLIP-2 to produce visual representation aligned with the text. Then we design a subject representation learning task which enables a diffusion model to leverage such visual representation and generates new subject renditions. Compared with previous methods such as DreamBooth, our model enables zero-shot subject-driven generation, and efficient fine-tuning for customized subject with up to 20x speedup. We also demonstrate that BLIP-Diffusion can be flexibly combined with existing techniques such as ControlNet and prompt-to-prompt to enable novel subject-driven generation and editing applications.*
The model is created by Dongxu Li, Junnan Li, Steven C.H. Hoi.
### Model Sources
<!-- Provide the basic links for the model. -->
- **Original Repository:** https://github.com/salesforce/LAVIS/tree/main
- **Project Page:** https://dxli94.github.io/BLIP-Diffusion-website/
## Uses
### Zero-Shot Subject Driven Generation
```python
from diffusers.pipelines import BlipDiffusionPipeline
from diffusers.utils import load_image
import torch
blip_diffusion_pipe = BlipDiffusionPipeline.from_pretrained(
"Salesforce/blipdiffusion", torch_dtype=torch.float16
).to("cuda")
cond_subject = "dog"
tgt_subject = "dog"
text_prompt_input = "swimming underwater"
cond_image = load_image(
"https://huggingface.co/datasets/ayushtues/blipdiffusion_images/resolve/main/dog.jpg"
)
iter_seed = 88888
guidance_scale = 7.5
num_inference_steps = 25
negative_prompt = "over-exposure, under-exposure, saturated, duplicate, out of frame, lowres, cropped, worst quality, low quality, jpeg artifacts, morbid, mutilated, out of frame, ugly, bad anatomy, bad proportions, deformed, blurry, duplicate"
output = blip_diffusion_pipe(
text_prompt_input,
cond_image,
cond_subject,
tgt_subject,
guidance_scale=guidance_scale,
num_inference_steps=num_inference_steps,
neg_prompt=negative_prompt,
height=512,
width=512,
).images
output[0].save("image.png")
```
Input Image : <img src="https://huggingface.co/datasets/ayushtues/blipdiffusion_images/resolve/main/dog.jpg" style="width:500px;"/>
Generatred Image : <img src="https://huggingface.co/datasets/ayushtues/blipdiffusion_images/resolve/main/dog_underwater.png" style="width:500px;"/>
### Controlled subject-driven generation
```python
from diffusers.pipelines import BlipDiffusionControlNetPipeline
from diffusers.utils import load_image
from controlnet_aux import CannyDetector
blip_diffusion_pipe = BlipDiffusionControlNetPipeline.from_pretrained(
"Salesforce/blipdiffusion-controlnet", torch_dtype=torch.float16
).to("cuda")
style_subject = "flower" # subject that defines the style
tgt_subject = "teapot" # subject to generate.
text_prompt = "on a marble table"
cldm_cond_image = load_image(
"https://huggingface.co/datasets/ayushtues/blipdiffusion_images/resolve/main/kettle.jpg"
).resize((512, 512))
canny = CannyDetector()
cldm_cond_image = canny(cldm_cond_image, 30, 70, output_type="pil")
style_image = load_image(
"https://huggingface.co/datasets/ayushtues/blipdiffusion_images/resolve/main/flower.jpg"
)
guidance_scale = 7.5
num_inference_steps = 50
negative_prompt = "over-exposure, under-exposure, saturated, duplicate, out of frame, lowres, cropped, worst quality, low quality, jpeg artifacts, morbid, mutilated, out of frame, ugly, bad anatomy, bad proportions, deformed, blurry, duplicate"
output = blip_diffusion_pipe(
text_prompt,
style_image,
cldm_cond_image,
style_subject,
tgt_subject,
guidance_scale=guidance_scale,
num_inference_steps=num_inference_steps,
neg_prompt=negative_prompt,
height=512,
width=512,
).images
output[0].save("image.png")
```
Input Style Image : <img src="https://huggingface.co/datasets/ayushtues/blipdiffusion_images/resolve/main/flower.jpg" style="width:500px;"/>
Canny Edge Input : <img src="https://huggingface.co/datasets/ayushtues/blipdiffusion_images/resolve/main/kettle.jpg" style="width:500px;"/>
Generated Image : <img src="https://huggingface.co/datasets/ayushtues/blipdiffusion_images/resolve/main/canny_generated.png" style="width:500px;"/>
### Controlled subject-driven generation Scribble
```python
from diffusers.pipelines import BlipDiffusionControlNetPipeline
from diffusers.utils import load_image
from controlnet_aux import HEDdetector
blip_diffusion_pipe = BlipDiffusionControlNetPipeline.from_pretrained(
"Salesforce/blipdiffusion-controlnet"
)
controlnet = ControlNetModel.from_pretrained("lllyasviel/sd-controlnet-scribble")
blip_diffusion_pipe.controlnet = controlnet
blip_diffusion_pipe.to("cuda")
style_subject = "flower" # subject that defines the style
tgt_subject = "bag" # subject to generate.
text_prompt = "on a table"
cldm_cond_image = load_image(
"https://huggingface.co/lllyasviel/sd-controlnet-scribble/resolve/main/images/bag.png"
).resize((512, 512))
hed = HEDdetector.from_pretrained("lllyasviel/Annotators")
cldm_cond_image = hed(cldm_cond_image)
style_image = load_image(
"https://huggingface.co/datasets/ayushtues/blipdiffusion_images/resolve/main/flower.jpg"
)
guidance_scale = 7.5
num_inference_steps = 50
negative_prompt = "over-exposure, under-exposure, saturated, duplicate, out of frame, lowres, cropped, worst quality, low quality, jpeg artifacts, morbid, mutilated, out of frame, ugly, bad anatomy, bad proportions, deformed, blurry, duplicate"
output = blip_diffusion_pipe(
text_prompt,
style_image,
cldm_cond_image,
style_subject,
tgt_subject,
guidance_scale=guidance_scale,
num_inference_steps=num_inference_steps,
neg_prompt=negative_prompt,
height=512,
width=512,
).images
output[0].save("image.png")
```
Input Style Image : <img src="https://huggingface.co/datasets/ayushtues/blipdiffusion_images/resolve/main/flower.jpg" style="width:500px;"/>
Scribble Input : <img src="https://huggingface.co/datasets/ayushtues/blipdiffusion_images/resolve/main/scribble.png" style="width:500px;"/>
Generated Image : <img src="https://huggingface.co/datasets/ayushtues/blipdiffusion_images/resolve/main/scribble_output.png" style="width:500px;"/>
## Model Architecture
Blip-Diffusion learns a **pre-trained subject representation**. uch representation aligns with text embeddings and in the meantime also encodes the subject appearance. This allows efficient fine-tuning of the model for high-fidelity subject-driven applications, such as text-to-image generation, editing and style transfer.
To this end, they design a two-stage pre-training strategy to learn generic subject representation. In the first pre-training stage, they perform multimodal representation learning, which enforces BLIP-2 to produce text-aligned visual features based on the input image. In the second pre-training stage, they design a subject representation learning task, called prompted context generation, where the diffusion model learns to generate novel subject renditions based on the input visual features.
To achieve this, they curate pairs of input-target images with the same subject appearing in different contexts. Specifically, they synthesize input images by composing the subject with a random background. During pre-training, they feed the synthetic input image and the subject class label through BLIP-2 to obtain the multimodal embeddings as subject representation. The subject representation is then combined with a text prompt to guide the generation of the target image.
The architecture is also compatible to integrate with established techniques built on top of the diffusion model, such as ControlNet.
They attach the U-Net of the pre-trained ControlNet to that of BLIP-Diffusion via residuals. In this way, the model takes into account the input structure condition, such as edge maps and depth maps, in addition to the subject cues. Since the model inherits the architecture of the original latent diffusion model, they observe satisfying generations using off-the-shelf integration with pre-trained ControlNet without further training.
<img src="https://huggingface.co/datasets/ayushtues/blipdiffusion_images/resolve/main/arch_controlnet.png" style="width:50%;"/>
## Citation
**BibTeX:**
If you find this repository useful in your research, please cite:
```
@misc{li2023blipdiffusion,
title={BLIP-Diffusion: Pre-trained Subject Representation for Controllable Text-to-Image Generation and Editing},
author={Dongxu Li and Junnan Li and Steven C. H. Hoi},
year={2023},
eprint={2305.14720},
archivePrefix={arXiv},
primaryClass={cs.CV}
}
```
|
ShivamMangale/XLM-Roberta-base-all_hi_weakdap_4th_iteration_d4_d3_d2_d1_d0-hq
|
ShivamMangale
| 2023-09-21T14:42:50Z | 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
| 2023-09-21T14:20:18Z |
---
license: mit
base_model: xlm-roberta-base
tags:
- generated_from_trainer
datasets:
- squad
model-index:
- name: XLM-Roberta-base-all_hi_weakdap_4th_iteration_d4_d3_d2_d1_d0-hq
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-all_hi_weakdap_4th_iteration_d4_d3_d2_d1_d0-hq
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: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 8
### Training results
### Framework versions
- Transformers 4.33.2
- Pytorch 2.0.1+cu117
- Datasets 2.14.5
- Tokenizers 0.13.3
|
newronai/clma2-13b-Chat-Adapter-NasdaqBalanced-3epoch
|
newronai
| 2023-09-21T14:41:07Z | 0 | 0 |
peft
|
[
"peft",
"region:us"
] | null | 2023-09-21T14:41:00Z |
---
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
|
optimaxbangladesh/optimaxbangladesh
|
optimaxbangladesh
| 2023-09-21T14:37:29Z | 0 | 0 | null |
[
"region:us"
] | null | 2023-09-21T14:36:56Z |
Optimax প্রাকৃতিক উপাদান ব্যবহার করে তৈরি করা হয়েছে যা চোখের সামগ্রিক স্বাস্থ্যের উন্নতিতে উপকারী বলে প্রমাণিত হয়েছে।
Optimax এখন কেন!! আরও তথ্যের জন্য নীচের লিঙ্কে ক্লিক করুন এবং এখনই 50% ছাড় পান!! তারাতারি কর !!
আরও পড়ুন: https://www.nutritioncrawler.com/OptiBang
https://sites.google.com/view/optimaxbangladesh/home
➢ পণ্যের নাম — Optimax
➢ এর জন্য ব্যবহৃত: চোখের স্বাস্থ্য
➢ প্রধান সুবিধা - চোখের দৃষ্টিশক্তি উন্নত করুন
➢ রচনা — প্রাকৃতিক জৈব যৌগ
➢ পার্শ্ব-প্রতিক্রিয়া—NA
➢ চূড়ান্ত রেটিং: — 4.7
➢ প্রাপ্যতা — অনলাইন
➢অফার এবং ডিসকাউন্ট; আজ সংরক্ষণ করুন! বিশেষ অফার কিনতে এখনই কেনাকাটা করুন!!!
Optimax কি?
যারা পরিচিত নন তাদের জন্য, Optimax হল একটি দৃষ্টি-উন্নতিকারী খাদ্যতালিকাগত সম্পূরক যা প্রতিবন্ধী দৃষ্টির 3টি প্রধান কারণ মোকাবেলা করে একজন ব্যক্তির দৃষ্টিশক্তি বাড়াতে সাহায্য করার দাবির জন্য ইন্টারনেটের চারপাশে ভাসছে। প্রাথমিক কারণ হল কিছু বিষাক্ত পদার্থের সংস্পর্শে যা চোখের মারাত্মক ক্ষতি করতে পারে।
Optimax এখন কেন!! আরও তথ্যের জন্য নীচের লিঙ্কে ক্লিক করুন এবং এখনই 50% ছাড় পান!! তারাতারি কর !!
আরও পড়ুন: https://www.nutritioncrawler.com/OptiBang
https://sites.google.com/view/optimaxbangladesh/home
Optimax Optimax বড়ি Optimax ক্যাপসুল Optimax ট্যাবলেট Optimax দাম Optimax পর্যালোচনা Optimax উপাদান Optimax সুবিধা Optimax ক্ষতিকর দিক Optimax ক্যাপসুলের দাম Optimax ক্যাপসুল পর্যালোচনা Optimax গঠন Optimax অভিযোগ Optimax কোথায় কিনতে হবে Optimax ব্যবহারবিধি Optimax খরচ Optimax কাজ করে Optimax ফোরাম Optimax মূল Optimax ফার্মেসি
|
LarryAIDraw/takina_inoue_v1
|
LarryAIDraw
| 2023-09-21T14:35:35Z | 0 | 0 | null |
[
"license:creativeml-openrail-m",
"region:us"
] | null | 2023-09-21T13:33:54Z |
---
license: creativeml-openrail-m
---
https://civitai.com/models/148903/takina-inoue-or-lycoris-recoil-5-outfits
|
akenzc/newRepo
|
akenzc
| 2023-09-21T14:28:57Z | 0 | 0 | null |
[
"a",
"arxiv:1910.09700",
"region:us"
] | null | 2023-09-11T06:41:03Z |
---
tags:
- a
arxiv:
- aaa
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
This modelcard aims to be a base template for new models. It has been generated using [this raw template](https://github.com/huggingface/huggingface_hub/blob/main/src/huggingface_hub/templates/modelcard_template.md?plain=1).
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
- **Developed by:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Data Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Data Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
|
ShivamMangale/XLM-Roberta-base-all_hi_weakdap_4th_iteration_d4_d3_d2_d1-hq
|
ShivamMangale
| 2023-09-21T14:20:17Z | 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
| 2023-09-21T14:06:26Z |
---
license: mit
base_model: xlm-roberta-base
tags:
- generated_from_trainer
datasets:
- squad
model-index:
- name: XLM-Roberta-base-all_hi_weakdap_4th_iteration_d4_d3_d2_d1-hq
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-all_hi_weakdap_4th_iteration_d4_d3_d2_d1-hq
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: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 8
### Training results
### Framework versions
- Transformers 4.33.2
- Pytorch 2.0.1+cu117
- Datasets 2.14.5
- Tokenizers 0.13.3
|
jmgb0127/bloom-lotr
|
jmgb0127
| 2023-09-21T13:56:28Z | 1 | 0 |
peft
|
[
"peft",
"base_model:bigscience/bloom-3b",
"base_model:adapter:bigscience/bloom-3b",
"region:us"
] | null | 2023-08-28T00:11:48Z |
---
library_name: peft
base_model: bigscience/bloom-3b
---
## Training procedure
The following `bitsandbytes` quantization config was used during training:
- 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 0.4.0
|
swastikhurana/q-Taxi-v1
|
swastikhurana
| 2023-09-21T13:54:37Z | 0 | 0 | null |
[
"Taxi-v3",
"q-learning",
"reinforcement-learning",
"custom-implementation",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-09-21T13:54:35Z |
---
tags:
- Taxi-v3
- q-learning
- reinforcement-learning
- custom-implementation
model-index:
- name: q-Taxi-v1
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: Taxi-v3
type: Taxi-v3
metrics:
- type: mean_reward
value: 7.50 +/- 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="swastikhurana/q-Taxi-v1", 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"])
```
|
Coroseven/TEST
|
Coroseven
| 2023-09-21T13:49:30Z | 0 | 0 | null |
[
"region:us"
] | null | 2023-09-07T14:18:20Z |
TEST 2 este un model combinat intre Primary model (A) - V3.0 Nordrin_little（诺德琳little）; Secondary model (B) - aamAnyloraAnimeMixAnime_v1 ; Tertiary model (C) - aingdiffusion_v92 la Multiplier (M) - 0.5 Weighted sum
TEST 3 este un model combinat intre Primary model (A) - aamAnyloraAnimeMixAnime_v1 ; Secondary model (B) - V3.0 Nordrin_little（诺德琳little）; la Multiplier (M) - 0.5 Weighted sum
TEST 5 este un model combinat intre Primary model (A) - aamAnyloraAnimeMixAnime_v1 ; Secondary model (B) - V3.0 Nordrin_little（诺德琳little）; Tertiary model (C) - aingdiffusion_v92 la Multiplier (M) - 0.3 Weighted sum
TEST 6 este un model combinat intre Primary model (A) - aamAnyloraAnimeMixAnime_v1 ; Secondary model (B) - BlueAilandMix (blueailandmix_v11) ; la Multiplier (M) - 0.4 Weighted sum
TEST 12 este un model combinat intre Primary model (A) - aamAnyloraAnimeMixAnime_v1 ; Secondary model (B) - Sudachi (sudachi_v1.0) ; la Multiplier (M) - 0.5 Weighted sum
TEST 13 este un model combinat intre Primary model (A) - TEST 12 ; Secondary model (B) - AingDiffusion (AingDiffusion_v9.2) ; la Multiplier (M) - 0.4 Weighted sum
|
ShivamMangale/XLM-Roberta-base-all_hi_weakdap_4th_iteration_d4-hq
|
ShivamMangale
| 2023-09-21T13:48:23Z | 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
| 2023-09-21T13:40:12Z |
---
license: mit
base_model: xlm-roberta-base
tags:
- generated_from_trainer
datasets:
- squad
model-index:
- name: XLM-Roberta-base-all_hi_weakdap_4th_iteration_d4-hq
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-all_hi_weakdap_4th_iteration_d4-hq
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: 1.4580000000000001e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 8
### Training results
### Framework versions
- Transformers 4.33.2
- Pytorch 2.0.1+cu117
- Datasets 2.14.5
- Tokenizers 0.13.3
|
nichonifroa/bert-finetuned-squad
|
nichonifroa
| 2023-09-21T13:47:34Z | 122 | 0 |
transformers
|
[
"transformers",
"pytorch",
"bert",
"question-answering",
"generated_from_trainer",
"dataset:squad",
"base_model:nichonifroa/bert-finetuned-squad",
"base_model:finetune:nichonifroa/bert-finetuned-squad",
"endpoints_compatible",
"region:us"
] |
question-answering
| 2023-09-21T10:04:51Z |
---
base_model: nichonifroa/bert-finetuned-squad
tags:
- generated_from_trainer
datasets:
- squad
model-index:
- name: bert-finetuned-squad
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-squad
This model is a fine-tuned version of [nichonifroa/bert-finetuned-squad](https://huggingface.co/nichonifroa/bert-finetuned-squad) 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: 3
### Framework versions
- Transformers 4.33.2
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3
|
firshme/llama2-lora7b-trans_chinese_alpaca_data
|
firshme
| 2023-09-21T13:45:19Z | 0 | 2 | null |
[
"arxiv:2106.09685",
"region:us"
] | null | 2023-07-28T14:38:06Z |
# 🦙🌲🤏 Alpaca-LoRA
- 🤗 **Try the pretrained model out [here](https://huggingface.co/spaces/tloen/alpaca-lora), courtesy of a GPU grant from Huggingface!**
- Users have created a Discord server for discussion and support [here](https://discord.gg/prbq284xX5)
- 4/14: Chansung Park's GPT4-Alpaca adapters: https://github.com/tloen/alpaca-lora/issues/340
This repository contains code for reproducing the [Stanford Alpaca](https://github.com/tatsu-lab/stanford_alpaca) results using [low-rank adaptation (LoRA)](https://arxiv.org/pdf/2106.09685.pdf).
We provide an Instruct model of similar quality to `text-davinci-003` that can run [on a Raspberry Pi](https://twitter.com/miolini/status/1634982361757790209) (for research),
and the code is easily extended to the `13b`, `30b`, and `65b` models.
In addition to the training code, which runs within hours on a single RTX 4090,
we publish a script for downloading and inference on the foundation model and LoRA,
as well as the resulting [LoRA weights themselves](https://huggingface.co/tloen/alpaca-lora-7b/tree/main).
To fine-tune cheaply and efficiently, we use Hugging Face's [PEFT](https://github.com/huggingface/peft)
as well as Tim Dettmers' [bitsandbytes](https://github.com/TimDettmers/bitsandbytes).
Without hyperparameter tuning, the LoRA model produces outputs comparable to the Stanford Alpaca model. (Please see the outputs included below.) Further tuning might be able to achieve better performance; I invite interested users to give it a try and report their results.
### Local Setup
1. Install dependencies
```bash
pip install -r requirements.txt
```
1. If bitsandbytes doesn't work, [install it from source.](https://github.com/TimDettmers/bitsandbytes/blob/main/compile_from_source.md) Windows users can follow [these instructions](https://github.com/tloen/alpaca-lora/issues/17).
### Training (`finetune.py`)
This file contains a straightforward application of PEFT to the LLaMA model,
as well as some code related to prompt construction and tokenization.
PRs adapting this code to support larger models are always welcome.
Example usage:
```bash
python finetune.py \
--base_model 'decapoda-research/llama-7b-hf' \
--data_path 'yahma/alpaca-cleaned' \
--output_dir './lora-alpaca'
```
We can also tweak our hyperparameters:
```bash
python finetune.py \
--base_model 'decapoda-research/llama-7b-hf' \
--data_path 'yahma/alpaca-cleaned' \
--output_dir './lora-alpaca' \
--batch_size 128 \
--micro_batch_size 4 \
--num_epochs 3 \
--learning_rate 1e-4 \
--cutoff_len 512 \
--val_set_size 2000 \
--lora_r 8 \
--lora_alpha 16 \
--lora_dropout 0.05 \
--lora_target_modules '[q_proj,v_proj]' \
--train_on_inputs \
--group_by_length
```
### Inference (`generate.py`)
This file reads the foundation model from the Hugging Face model hub and the LoRA weights from `tloen/alpaca-lora-7b`, and runs a Gradio interface for inference on a specified input. Users should treat this as example code for the use of the model, and modify it as needed.
Example usage:
```bash
python generate.py \
--load_8bit \
--base_model 'decapoda-research/llama-7b-hf' \
--lora_weights 'tloen/alpaca-lora-7b'
```
### Official weights
The most recent "official" Alpaca-LoRA adapter available at [`tloen/alpaca-lora-7b`](https://huggingface.co/tloen/alpaca-lora-7b) was trained on March 26 with the following command:
```bash
python finetune.py \
--base_model='decapoda-research/llama-7b-hf' \
--num_epochs=10 \
--cutoff_len=512 \
--group_by_length \
--output_dir='./lora-alpaca' \
--lora_target_modules='[q_proj,k_proj,v_proj,o_proj]' \
--lora_r=16 \
--micro_batch_size=8
```
### Checkpoint export (`export_*_checkpoint.py`)
These files contain scripts that merge the LoRA weights back into the base model
for export to Hugging Face format and to PyTorch `state_dicts`.
They should help users
who want to run inference in projects like [llama.cpp](https://github.com/ggerganov/llama.cpp)
or [alpaca.cpp](https://github.com/antimatter15/alpaca.cpp).
### Docker Setup & Inference
1. Build the container image:
```bash
docker build -t alpaca-lora .
```
2. Run the container (you can also use `finetune.py` and all of its parameters as shown above for training):
```bash
docker run --gpus=all --shm-size 64g -p 7860:7860 -v ${HOME}/.cache:/root/.cache --rm alpaca-lora generate.py \
--load_8bit \
--base_model 'decapoda-research/llama-7b-hf' \
--lora_weights 'tloen/alpaca-lora-7b'
```
3. Open `https://localhost:7860` in the browser
### Docker Compose Setup & Inference
1. (optional) Change desired model and weights under `environment` in the `docker-compose.yml`
2. Build and run the container
```bash
docker-compose up -d --build
```
3. Open `https://localhost:7860` in the browser
4. See logs:
```bash
docker-compose logs -f
```
5. Clean everything up:
```bash
docker-compose down --volumes --rmi all
```
### Notes
- We can likely improve our model performance significantly if we had a better dataset. Consider supporting the [LAION Open Assistant](https://open-assistant.io/) effort to produce a high-quality dataset for supervised fine-tuning (or bugging them to release their data).
- We're continually fixing bugs and conducting training runs, and the weights on the Hugging Face Hub are being updated accordingly. In particular, those facing issues with response lengths should make sure that they have the latest version of the weights and code.
- Users with multiple GPUs should take a look [here](https://github.com/tloen/alpaca-lora/issues/8#issuecomment-1477490259).
- We include the Stanford Alpaca dataset, which was made available under the ODC Attribution License.
### Resources
- [alpaca.cpp](https://github.com/antimatter15/alpaca.cpp), a native client for running Alpaca models on the CPU
- [Alpaca-LoRA-Serve](https://github.com/deep-diver/Alpaca-LoRA-Serve), a ChatGPT-style interface for Alpaca models
- [AlpacaDataCleaned](https://github.com/gururise/AlpacaDataCleaned), a project to improve the quality of the Alpaca dataset
- [GPT-4 Alpaca Data](https://github.com/Instruction-Tuning-with-GPT-4/GPT-4-LLM) a project to port synthetic data creation to GPT-4
- [dolly-15k-instruction-alpaca-format](https://huggingface.co/datasets/c-s-ale/dolly-15k-instruction-alpaca-format), an Alpaca-compatible version of [Databricks' Dolly 15k human-generated instruct dataset](https://github.com/databrickslabs/dolly/tree/master/data) (see [blog](https://www.databricks.com/blog/2023/04/12/dolly-first-open-commercially-viable-instruction-tuned-llm))
- [Alpaca-LoRA MT](https://github.com/juletx/alpaca-lora-mt), a project to finetune models with [machine-translated Alpaca data](https://huggingface.co/datasets/HiTZ/alpaca_mt) in 6 Iberian languages: Portuguese, Spanish, Catalan, Basque, Galician and Asturian.
- Various adapter weights (download at own risk):
- 7B:
- 3️⃣ <https://huggingface.co/tloen/alpaca-lora-7b>
- 3️⃣ <https://huggingface.co/samwit/alpaca7B-lora>
- **4️⃣ <https://huggingface.co/chansung/gpt4-alpaca-lora-7b>**
- 🚀 <https://huggingface.co/nomic-ai/gpt4all-lora>
- 🇧🇷 <https://huggingface.co/22h/cabrita-lora-v0-1>
- 🇨🇳 <https://huggingface.co/qychen/luotuo-lora-7b-0.1>
- 🇨🇳 <https://huggingface.co/ziqingyang/chinese-alpaca-lora-7b>
- 🇯🇵 <https://huggingface.co/kunishou/Japanese-Alapaca-LoRA-7b-v0>
- 🇫🇷 <https://huggingface.co/bofenghuang/vigogne-lora-7b>
- 🇹🇭 <https://huggingface.co/Thaweewat/thai-buffala-lora-7b-v0-1>
- 🇩🇪 <https://huggingface.co/thisserand/alpaca_lora_german>
- 🇵🇱 <https://huggingface.co/mmosiolek/polpaca-lora-7b>
- 🇵🇱 <https://huggingface.co/chrisociepa/alpaca-lora-7b-pl>
- 🇮🇹 <https://huggingface.co/teelinsan/camoscio-7b-llama>
- 🇷🇺 <https://huggingface.co/IlyaGusev/llama_7b_ru_turbo_alpaca_lora>
- 🇺🇦 <https://huggingface.co/robinhad/ualpaca-7b-llama>
- 🇮🇹 <https://huggingface.co/mchl-labs/stambecco-7b-plus>
- 🇪🇸 <https://huggingface.co/plncmm/guanaco-lora-7b>
- 🇬🇧 🇪🇸 🇵🇹 <https://huggingface.co/HiTZ/alpaca-lora-7b-en-pt-es-ca-eu-gl-at>
- 13B:
- 3️⃣ <https://huggingface.co/Angainor/alpaca-lora-13b>
- 3️⃣ <https://huggingface.co/chansung/alpaca-lora-13b>
- 3️⃣ <https://huggingface.co/mattreid/alpaca-lora-13b>
- 3️⃣ <https://huggingface.co/samwit/alpaca13B-lora>
- **4️⃣ <https://huggingface.co/chansung/gpt4-alpaca-lora-13b>**
- 🇯🇵 <https://huggingface.co/kunishou/Japanese-Alapaca-LoRA-13b-v0>
- 🇰🇷 <https://huggingface.co/chansung/koalpaca-lora-13b>
- 🇨🇳 <https://huggingface.co/facat/alpaca-lora-cn-13b>
- 🇨🇳 <https://huggingface.co/ziqingyang/chinese-alpaca-lora-13b>
- 🇪🇸 <https://huggingface.co/plncmm/guanaco-lora-13b>
- 🇮🇹 <https://huggingface.co/mchl-labs/stambecco-13b-plus>
- 🇬🇧 🇪🇸 🇵🇹 <https://huggingface.co/HiTZ/alpaca-lora-13b-en-pt-es-ca-eu-gl-at>
- 30B:
- 3️⃣ <https://huggingface.co/baseten/alpaca-30b>
- 3️⃣ <https://huggingface.co/chansung/alpaca-lora-30b>
- **4️⃣ <https://huggingface.co/chansung/gpt4-alpaca-lora-30b>**
- 🇯🇵 <https://huggingface.co/kunishou/Japanese-Alapaca-LoRA-30b-v0>
- 🇬🇧 🇪🇸 🇵🇹 <https://huggingface.co/HiTZ/alpaca-lora-30b-en-pt-es-ca-eu-gl-at>
- 65B
- <https://huggingface.co/chansung/alpaca-lora-65b>
- 🇬🇧 🇪🇸 🇵🇹 <https://huggingface.co/HiTZ/alpaca-lora-65b-en-pt-es-ca>
- [alpaca-native](https://huggingface.co/chavinlo/alpaca-native), a replication using the original Alpaca code
- [llama.onnx](https://github.com/tpoisonooo/llama.onnx), a project to inference alpaca with onnx format
### Example outputs
**Instruction**: Tell me about alpacas.
**Alpaca-LoRA**: Alpacas are members of the camelid family and are native to the Andes Mountains of South America. They are known for their soft, luxurious fleece, which is used to make clothing, blankets, and other items. Alpacas are herbivores and graze on grasses and other plants. They are social animals and live in herds of up to 20 individuals.
**Stanford Alpaca**: Alpacas are small, fluffy animals related to camels and llamas. They are native to Peru and Bolivia, and were first domesticated around 5,000 years ago. They are kept mainly for their fine, soft fleece, which is used to make knitwear and other garments. Alpacas are herd animals and live in small family groups, led by an older male. They are highly social animals and can form strong bonds with their owners.
**text-davinci-003**: Alpacas are a domesticated species of South American camelid, similar to llamas. They are native to the Andes Mountains in South America and are kept as livestock for their soft, luxurious wool. Alpacas are social animals and live in herds of up to 20 individuals. They are typically kept in small herds of two to five animals, and are relatively easy to care for. Alpacas are herbivores and feed on grass, hay, and other vegetation. They are also known for their gentle and friendly nature, making them popular as pets.
---
**Instruction**: Tell me about the president of Mexico in 2019.
**Alpaca-LoRA**: The president of Mexico in 2019 was Andrés Manuel López Obrador, who took office on December 1, 2018. He is a member of the National Regeneration Movement (MORENA) political party and is the first left-wing president of Mexico since 1946. He is known for his anti-corruption and anti-neoliberal policies, as well as his commitment to improving the living conditions of the Mexican people.
**Stanford Alpaca**: In 2019, Andres Manuel Lopez Obrador was sworn in as President of Mexico. He is the country’s 58th president and the first from the left-wing Morena party. He was elected in 2018 on a promise to combat corruption and reduce poverty and has faced criticism for his handling of the economy, crime and the country’s relationship with the United States. He is also known for his ambitious social welfare programs and has been praised for raising the minimum wage and providing aid to low-income families. He is seen as a champion of democracy and human rights in Mexico.
**text-davinci-003**: The president of Mexico in 2019 is Andrés Manuel López Obrador, commonly known as AMLO. He is a Mexican politician who has been the President of Mexico since December 1, 2018. He is a member of the National Regeneration Movement (MORENA) party and previously served as the Head of Government of Mexico City from 2000 to 2005. He is a left-wing populist and has promised to reduce corruption and inequality in Mexico. He has also promised to increase public spending on social programs and infrastructure projects.
---
**Instruction**: Tell me about the king of France in 2019.
**Alpaca-LoRA**: The King of France in 2019 is Emmanuel Macron, who was elected in May 2017. He is the youngest president in the history of the Fifth Republic and the first president to be born after World War II. He is also the first president to have never held elected office before.
**Stanford Alpaca**: In 2019, the King of France was Emmanuel Macron. He was sworn in as President of France on May 14, 2017, and has been leading the country ever since. He is a member of the centrist La République En Marche! Party. He is known for his reformist agenda and has faced a number of protests from both the right and left of the political spectrum. He is the youngest French president in history.
**text-davinci-003**: The King of France is a largely symbolic role, as France is a republic. The current President of France is Emmanuel Macron, who was elected in 2017.
---
**Instruction**: List all Canadian provinces in alphabetical order.
**Alpaca-LoRA**: Alberta, British Columbia, Manitoba, New Brunswick, Newfoundland and Labrador, Nova Scotia, Ontario, Prince Edward Island, Quebec, Saskatchewan
**Stanford Alpaca**: Alberta, British Columbia, Manitoba, New Brunswick, Newfoundland and Labrador, Nova Scotia, Ontario, Prince Edward Island, Quebec, Saskatchewan, Northwest Territories, Nunavut, Yukon.
**text-davinci-003**:
1. Alberta
2. British Columbia
3. Manitoba
4. New Brunswick
5. Newfoundland and Labrador
6. Northwest Territories
7. Nova Scotia
8. Nunavut
9. Ontario
10. Prince Edward Island
11. Quebec
12. Saskatchewan
13. Yukon
---
**Instruction**: Write a Python program that prints the first 10 Fibonacci numbers.
**Alpaca-LoRA**:
```python
def fibonacci(n):
if n == 0:
return 0
elif n == 1:
return 1
else:
return fibonacci(n-1) + fibonacci(n-2)
print(fibonacci(10))
```
**Stanford Alpaca**:
```python
numbers = [0, 1]
for i in range(2, 11):
numbers.append(numbers[i-2] + numbers[i-1])
print(numbers)
# Output: [0, 1, 1, 2, 3, 5, 8, 13, 21, 34]
```
**text-davinci-003**:
```python
# Fibonacci numbers are the numbers in the following integer sequence, called the Fibonacci sequence, and characterized by the fact that every number after the first two is the sum of the two preceding ones.
# Fibonacci sequence: 0, 1, 1, 2, 3, 5, 8, 13, 21, 34, ...
# Program:
# Initialize the first two numbers of the Fibonacci sequence
a = 0
b = 1
# Print the first 10 numbers of the Fibonacci sequence
print(a)
print(b)
for i in range(2,10):
c = a + b
a = b
b = c
print(c)
```
---
**Instruction**: Write a program that prints the numbers from 1 to 100. But for multiples of three print 'Fizz' instead of the number and for the multiples of five print 'Buzz'. For numbers which are multiples of both three and five print 'FizzBuzz'.
**Alpaca-LoRA**:
```python
for i in range(1, 101):
if i % 3 == 0 and i % 5 == 0:
print("FizzBuzz")
elif i % 3 == 0:
print("Fizz")
elif i % 5 == 0:
print("Buzz")
else:
print(i)
```
**Stanford Alpaca**:
```python
for i in range(1, 101):
if i % 3 == 0 and i % 5 == 0:
print('FizzBuzz')
elif i % 3 == 0:
print('Fizz')
elif i % 5 == 0:
print('Buzz')
else:
print(i)
```
**text-davinci-003**:
```javascript
for (let i = 1; i <= 100; i++) {
if (i % 3 === 0 && i % 5 === 0) {
console.log("FizzBuzz");
} else if (i % 3 === 0) {
console.log("Fizz");
} else if (i % 5 === 0) {
console.log("Buzz");
} else {
console.log(i);
}
}
```
---
**Instruction**: Tell me five words that rhyme with 'shock'.
**Alpaca-LoRA**: Flock, lock, rock, stock, and sock.
**Stanford Alpaca**: Five words that rhyme with shock are: rock, pop, shock, cook, and snock.
**text-davinci-003**:
1. Block
2. Lock
3. Dock
4. Clock
5. Rock
---
**Instruction**: Translate the sentence 'I have no mouth but I must scream' into Spanish.
**Alpaca-LoRA**: No tengo boca pero tengo que gritar.
**Stanford Alpaca**: No tengo boca, pero debo gritar.
**text-davinci-003**: No tengo boca pero debo gritar.
|
fsuarez/autotrain-logo-identifier-90194144191
|
fsuarez
| 2023-09-21T13:38:51Z | 184 | 0 |
transformers
|
[
"transformers",
"pytorch",
"safetensors",
"swin",
"image-classification",
"autotrain",
"vision",
"dataset:fsuarez/autotrain-data-logo-identifier",
"co2_eq_emissions",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
image-classification
| 2023-09-19T14:59:47Z |
---
tags:
- autotrain
- vision
- image-classification
datasets:
- fsuarez/autotrain-data-logo-identifier
widget:
- src: https://huggingface.co/datasets/mishig/sample_images/resolve/main/tiger.jpg
example_title: Tiger
- src: https://huggingface.co/datasets/mishig/sample_images/resolve/main/teapot.jpg
example_title: Teapot
- src: https://huggingface.co/datasets/mishig/sample_images/resolve/main/palace.jpg
example_title: Palace
co2_eq_emissions:
emissions: 0.060824697813101125
---
# 📒 logo-identifier-model
This model has been trained on a dataset called "LogoIdentifier" for multi-class classification of logos from 57 renowned brands and companies. These brands encompass a wide spectrum of industries and recognition, ranging from global giants like Coca-Cola, Coleman, Google, IBM, Nike, Pepsi, and many others. Each brand is thoughtfully organized into its designated subfolder, housing a comprehensive set of logo images for precise and accurate classification. Whether you're identifying iconic logos or exploring the branding diversity of these 57 famous names, this model is your go-to solution for logo recognition and classification.
# 🧪 Dataset Content
- The dataset includes logos from various brands and companies.
- The dataset is organized into subfolders, each corresponding to a specific brand or company.
- It contains a wide range of brand logos, including Acer, Acura, Adidas, Samsung, Lenovo, McDonald's, Java, and many more.
- Each brand or company in the dataset is associated with a numerical value, likely representing the number of images available for that brand.
The model has been trained to recognize and classify logos into their respective brand categories based on the images provided in the dataset.
| Company | Quantity of images |
| ----------------- | ------------------ |
| Acer | 67 |
| Acura | 74 |
| Addidas | 90 |
| Ades | 36 |
| Adio | 63 |
| Cadillac | 69 |
| CalvinKlein | 65 |
| Canon | 59 |
| Cocacola | 40 |
| CocaColaZero | 91 |
| Coleman | 57 |
| Converse | 60 |
| CornFlakes | 62 |
| DominossPizza | 99 |
| Excel | 88 |
| Gillette | 86 |
| GMC | 75 |
| Google | 93 |
| HardRockCafe | 93 |
| HBO | 103 |
| Heineken | 84 |
| HewlettPackard | 81 |
| Hp | 87 |
| Huawei | 84 |
| Hyundai | 84 |
| IBM | 84 |
| Java | 62 |
| KFC | 84 |
| Kia | 76 |
| Kingston | 79 |
| Lenovo | 82 |
| LG | 95 |
| Lipton | 94 |
| Mattel | 77 |
| McDonalds | 98 |
| MercedesBenz | 94 |
| Motorola | 86 |
| Nestle | 94 |
| Nickelodeon | 74 |
| Nike | 50 |
| Pennzoil | 82 |
| Pepsi | 93 |
| Peugeot | 60 |
| Porsche | 71 |
| Samsung | 96 |
| SchneiderElectric | 42 |
| Shell | 58 |
To use this model for brand logo identification, you can make use of the Hugging Face Transformers library and load the model using its model ID (90194144191). You can then input an image of a brand logo, and the model should be able to predict the brand it belongs to based on its training.
# 🤗 Model Trained Using AutoTrain
- Problem type: Multi-class Classification
- Model ID: 90194144191
- CO2 Emissions (in grams): 0.0608
## 📐 Validation Metrics
- Loss: 0.300
- Accuracy: 0.924
- Macro F1: 0.924
- Micro F1: 0.924
- Weighted F1: 0.922
- Macro Precision: 0.930
- Micro Precision: 0.924
- Weighted Precision: 0.928
- Macro Recall: 0.924
- Micro Recall: 0.924
- Weighted Recall: 0.924
|
ShivamMangale/XLM-Roberta-base-all_hi_weakdap_3rd_iteration_d3_d2_d1_d0-hq
|
ShivamMangale
| 2023-09-21T13:37:37Z | 106 | 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
| 2023-09-21T13:15:08Z |
---
license: mit
base_model: xlm-roberta-base
tags:
- generated_from_trainer
datasets:
- squad
model-index:
- name: XLM-Roberta-base-all_hi_weakdap_3rd_iteration_d3_d2_d1_d0-hq
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-all_hi_weakdap_3rd_iteration_d3_d2_d1_d0-hq
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: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 8
### Training results
### Framework versions
- Transformers 4.33.2
- Pytorch 2.0.1+cu117
- Datasets 2.14.5
- Tokenizers 0.13.3
|
LarryAIDraw/Char_Honkai_Raiden_Mei_adult
|
LarryAIDraw
| 2023-09-21T13:36:19Z | 0 | 0 | null |
[
"license:creativeml-openrail-m",
"region:us"
] | null | 2023-09-21T13:34:19Z |
---
license: creativeml-openrail-m
---
|
srushtibhavsar/squad_bloom_3b
|
srushtibhavsar
| 2023-09-21T13:29:25Z | 1 | 0 |
peft
|
[
"peft",
"region:us"
] | null | 2023-09-21T13:29:23Z |
---
library_name: peft
---
## Training procedure
### Framework versions
- PEFT 0.6.0.dev0
|
ShivamMangale/XLM-Roberta-base-all_hi_weakdap_3rd_iteration_d3_d2_d1-hq
|
ShivamMangale
| 2023-09-21T13:15:08Z | 106 | 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
| 2023-09-21T13:01:22Z |
---
license: mit
base_model: xlm-roberta-base
tags:
- generated_from_trainer
datasets:
- squad
model-index:
- name: XLM-Roberta-base-all_hi_weakdap_3rd_iteration_d3_d2_d1-hq
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-all_hi_weakdap_3rd_iteration_d3_d2_d1-hq
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: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 8
### Training results
### Framework versions
- Transformers 4.33.2
- Pytorch 2.0.1+cu117
- Datasets 2.14.5
- Tokenizers 0.13.3
|
zongxiao/my_awesome_mind_model
|
zongxiao
| 2023-09-21T13:13:42Z | 160 | 0 |
transformers
|
[
"transformers",
"pytorch",
"wav2vec2",
"audio-classification",
"generated_from_trainer",
"dataset:minds14",
"base_model:facebook/wav2vec2-base",
"base_model:finetune:facebook/wav2vec2-base",
"license:apache-2.0",
"model-index",
"endpoints_compatible",
"region:us"
] |
audio-classification
| 2023-09-21T12:39:50Z |
---
license: apache-2.0
base_model: facebook/wav2vec2-base
tags:
- generated_from_trainer
datasets:
- minds14
metrics:
- accuracy
model-index:
- name: my_awesome_mind_model
results:
- task:
name: Audio Classification
type: audio-classification
dataset:
name: minds14
type: minds14
config: en-US
split: train
args: en-US
metrics:
- name: Accuracy
type: accuracy
value: 0.08849557522123894
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# my_awesome_mind_model
This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the minds14 dataset.
It achieves the following results on the evaluation set:
- Loss: 2.6486
- Accuracy: 0.0885
## 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: 32
- eval_batch_size: 32
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 128
- 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 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| No log | 0.8 | 3 | 2.6442 | 0.0885 |
| No log | 1.87 | 7 | 2.6508 | 0.0531 |
| 2.636 | 2.93 | 11 | 2.6523 | 0.0177 |
| 2.636 | 4.0 | 15 | 2.6495 | 0.0619 |
| 2.636 | 4.8 | 18 | 2.6468 | 0.0973 |
| 2.6205 | 5.87 | 22 | 2.6510 | 0.0796 |
| 2.6205 | 6.93 | 26 | 2.6484 | 0.0796 |
| 2.6154 | 8.0 | 30 | 2.6486 | 0.0885 |
### Framework versions
- Transformers 4.34.0.dev0
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.14.0
|
CyberHarem/nishikawa_honami_idolmastercinderellagirls
|
CyberHarem
| 2023-09-21T13:13:40Z | 0 | 0 | null |
[
"art",
"text-to-image",
"dataset:CyberHarem/nishikawa_honami_idolmastercinderellagirls",
"license:mit",
"region:us"
] |
text-to-image
| 2023-09-21T13:02:46Z |
---
license: mit
datasets:
- CyberHarem/nishikawa_honami_idolmastercinderellagirls
pipeline_tag: text-to-image
tags:
- art
---
# Lora of nishikawa_honami_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/nishikawa_honami_idolmastercinderellagirls.pt` as the embedding and `4080/nishikawa_honami_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 0.919. The trigger words are:
1. `nishikawa_honami_idolmastercinderellagirls`
2. `long_hair, brown_hair, green_eyes, earrings, jewelry, smile, 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 | 0.903 | [Download](5100/nishikawa_honami_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 | 0.895 | [Download](4760/nishikawa_honami_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 | 0.912 | [Download](4420/nishikawa_honami_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** | **0.919** | [**Download**](4080/nishikawa_honami_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 | 0.831 | [Download](3740/nishikawa_honami_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 | 0.872 | [Download](3400/nishikawa_honami_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 | 0.882 | [Download](3060/nishikawa_honami_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 | 0.909 | [Download](2720/nishikawa_honami_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 | 0.857 | [Download](2380/nishikawa_honami_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 | 0.893 | [Download](2040/nishikawa_honami_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 | 0.874 | [Download](1700/nishikawa_honami_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 | 0.860 | [Download](1360/nishikawa_honami_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 | 0.877 | [Download](1020/nishikawa_honami_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 | 0.753 | [Download](680/nishikawa_honami_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 | 0.579 | [Download](340/nishikawa_honami_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) |  |  |
|
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.