modelId
stringlengths 4
81
| tags
list | pipeline_tag
stringclasses 17
values | config
dict | downloads
int64 0
59.7M
| first_commit
timestamp[ns, tz=UTC] | card
stringlengths 51
438k
|
|---|---|---|---|---|---|---|
Crives/distilbert-base-uncased-finetuned-emotion
|
[
"pytorch",
"tensorboard",
"distilbert",
"text-classification",
"dataset:emotion",
"transformers",
"generated_from_trainer",
"license:apache-2.0",
"model-index"
] |
text-classification
|
{
"architectures": [
"DistilBertForSequenceClassification"
],
"model_type": "distilbert",
"task_specific_params": {
"conversational": {
"max_length": null
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
}
| 31
| null |
Access to model ArneJacob/RemiBot is restricted and you are not in the authorized list. Visit https://huggingface.co/ArneJacob/RemiBot to ask for access.
|
CrypticT1tan/DialoGPT-medium-harrypotter
|
[] | null |
{
"architectures": null,
"model_type": null,
"task_specific_params": {
"conversational": {
"max_length": null
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
}
| 0
| null |
---
license: mit
tags:
- generated_from_trainer
model-index:
- name: donut_finetuned_chart
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# donut_finetuned_chart
This model is a fine-tuned version of [naver-clova-ix/donut-base](https://huggingface.co/naver-clova-ix/donut-base) on an chart images dataset.
It achieves the following results on the evaluation set:
- Loss: 0.4957
- Cer: 0.2318
## 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: 2.3e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 3
- total_train_batch_size: 24
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 4
- mixed_precision_training: Native AMP
### Training results
| Training Loss | Epoch | Step | Validation Loss | Cer |
|:-------------:|:-----:|:----:|:---------------:|:------:|
| 3.4943 | 1.0 | 166 | 0.6634 | 0.2341 |
| 0.475 | 2.0 | 333 | 0.5370 | 0.2320 |
| 0.3009 | 3.0 | 500 | 0.5051 | 0.2318 |
| 0.2611 | 3.98 | 664 | 0.4957 | 0.2318 |
### Framework versions
- Transformers 4.28.1
- Pytorch 2.0.0+cu118
- Datasets 2.11.0
- Tokenizers 0.13.3
|
Cryptikdw/DialoGPT-small-rick
|
[
"pytorch",
"gpt2",
"text-generation",
"transformers",
"conversational"
] |
conversational
|
{
"architectures": [
"GPT2LMHeadModel"
],
"model_type": "gpt2",
"task_specific_params": {
"conversational": {
"max_length": 1000
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
}
| 7
| null |
Access to model darkblack/meksarah is restricted and you are not in the authorized list. Visit https://huggingface.co/darkblack/meksarah to ask for access.
|
Cthyllax/DialoGPT-medium-PaladinDanse
|
[
"pytorch",
"gpt2",
"text-generation",
"transformers",
"conversational"
] |
conversational
|
{
"architectures": [
"GPT2LMHeadModel"
],
"model_type": "gpt2",
"task_specific_params": {
"conversational": {
"max_length": 1000
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
}
| 10
| null |
---
library_name: sample-factory
tags:
- deep-reinforcement-learning
- reinforcement-learning
- sample-factory
model-index:
- name: APPO
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: doom_health_gathering_supreme
type: doom_health_gathering_supreme
metrics:
- type: mean_reward
value: 12.86 +/- 5.93
name: mean_reward
verified: false
---
A(n) **APPO** model trained on the **doom_health_gathering_supreme** environment.
This model was trained using Sample-Factory 2.0: https://github.com/alex-petrenko/sample-factory.
Documentation for how to use Sample-Factory can be found at https://www.samplefactory.dev/
## Downloading the model
After installing Sample-Factory, download the model with:
```
python -m sample_factory.huggingface.load_from_hub -r abarekatain/rl_course_vizdoom_health_gathering_supreme
```
## Using the model
To run the model after download, use the `enjoy` script corresponding to this environment:
```
python -m .usr.local.lib.python3.9.dist-packages.ipykernel_launcher --algo=APPO --env=doom_health_gathering_supreme --train_dir=./train_dir --experiment=rl_course_vizdoom_health_gathering_supreme
```
You can also upload models to the Hugging Face Hub using the same script with the `--push_to_hub` flag.
See https://www.samplefactory.dev/10-huggingface/huggingface/ for more details
## Training with this model
To continue training with this model, use the `train` script corresponding to this environment:
```
python -m .usr.local.lib.python3.9.dist-packages.ipykernel_launcher --algo=APPO --env=doom_health_gathering_supreme --train_dir=./train_dir --experiment=rl_course_vizdoom_health_gathering_supreme --restart_behavior=resume --train_for_env_steps=10000000000
```
Note, you may have to adjust `--train_for_env_steps` to a suitably high number as the experiment will resume at the number of steps it concluded at.
|
Culmenus/XLMR-ENIS-finetuned-ner
|
[
"pytorch",
"tensorboard",
"xlm-roberta",
"token-classification",
"dataset:mim_gold_ner",
"transformers",
"generated_from_trainer",
"license:agpl-3.0",
"model-index",
"autotrain_compatible"
] |
token-classification
|
{
"architectures": [
"XLMRobertaForTokenClassification"
],
"model_type": "xlm-roberta",
"task_specific_params": {
"conversational": {
"max_length": null
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
}
| 6
| null |
---
library_name: stable-baselines3
tags:
- PandaPickAndPlaceDense-v2
- deep-reinforcement-learning
- reinforcement-learning
- stable-baselines3
model-index:
- name: PPO
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: PandaPickAndPlaceDense-v2
type: PandaPickAndPlaceDense-v2
metrics:
- type: mean_reward
value: -8.33 +/- 4.94
name: mean_reward
verified: false
---
# **PPO** Agent playing **PandaPickAndPlaceDense-v2**
This is a trained model of a **PPO** agent playing **PandaPickAndPlaceDense-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
...
```
|
Culmenus/checkpoint-168500-finetuned-de-to-is_nr2
|
[] | null |
{
"architectures": null,
"model_type": null,
"task_specific_params": {
"conversational": {
"max_length": null
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
}
| 0
| null |
---
license: mit
tags:
- pytorch
- diffusers
- unconditional-image-generation
- diffusion-models-class
---
# Example Fine-Tuned Model for Unit 2 of the [Diffusion Models Class 🧨](https://github.com/huggingface/diffusion-models-class)
Describe your model here
## Usage
```python
from diffusers import DDPMPipeline
pipeline = DDPMPipeline.from_pretrained('ntrant7/ddpm-celebahq-finetuned-butterflies-2epochs')
image = pipeline().images[0]
image
```
|
Culmenus/opus-mt-de-is-finetuned-de-to-is
|
[
"pytorch",
"marian",
"text2text-generation",
"transformers",
"autotrain_compatible"
] |
text2text-generation
|
{
"architectures": [
"MarianMTModel"
],
"model_type": "marian",
"task_specific_params": {
"conversational": {
"max_length": null
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
}
| 1
| null |
---
language: en
thumbnail: https://github.com/borisdayma/huggingtweets/blob/master/img/logo.png?raw=true
tags:
- huggingtweets
widget:
- text: "My dream is"
---
<div class="inline-flex flex-col" style="line-height: 1.5;">
<div class="flex">
<div
style="display:inherit; margin-left: 4px; margin-right: 4px; width: 92px; height:92px; border-radius: 50%; background-size: cover; background-image: url('https://pbs.twimg.com/profile_images/1594272914542567424/U-LvhH5a_400x400.jpg')">
</div>
<div
style="display:none; margin-left: 4px; margin-right: 4px; width: 92px; height:92px; border-radius: 50%; background-size: cover; background-image: url('')">
</div>
<div
style="display:none; margin-left: 4px; margin-right: 4px; width: 92px; height:92px; border-radius: 50%; background-size: cover; background-image: url('')">
</div>
</div>
<div style="text-align: center; margin-top: 3px; font-size: 16px; font-weight: 800">🤖 AI BOT 🤖</div>
<div style="text-align: center; font-size: 16px; font-weight: 800">@ubik@fedi.turbofish.cc</div>
<div style="text-align: center; font-size: 14px;">@pferreir</div>
</div>
I was made with [huggingtweets](https://github.com/borisdayma/huggingtweets).
Create your own bot based on your favorite user with [the demo](https://colab.research.google.com/github/borisdayma/huggingtweets/blob/master/huggingtweets-demo.ipynb)!
## How does it work?
The model uses the following pipeline.
To understand how the model was developed, check the [W&B report](https://wandb.ai/wandb/huggingtweets/reports/HuggingTweets-Train-a-Model-to-Generate-Tweets--VmlldzoxMTY5MjI).
## Training data
The model was trained on tweets from @ubik@fedi.turbofish.cc.
| Data | @ubik@fedi.turbofish.cc |
| --- | --- |
| Tweets downloaded | 3167 |
| Retweets | 796 |
| Short tweets | 479 |
| Tweets kept | 1892 |
[Explore the data](https://wandb.ai/wandb/huggingtweets/runs/d99e3gv0/artifacts), which is tracked with [W&B artifacts](https://docs.wandb.com/artifacts) at every step of the pipeline.
## Training procedure
The model is based on a pre-trained [GPT-2](https://huggingface.co/gpt2) which is fine-tuned on @pferreir's tweets.
Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/wandb/huggingtweets/runs/5mfsxmic) for full transparency and reproducibility.
At the end of training, [the final model](https://wandb.ai/wandb/huggingtweets/runs/5mfsxmic/artifacts) is logged and versioned.
## How to use
You can use this model directly with a pipeline for text generation:
```python
from transformers import pipeline
generator = pipeline('text-generation',
model='huggingtweets/pferreir')
generator("My dream is", num_return_sequences=5)
```
## Limitations and bias
The model suffers from [the same limitations and bias as GPT-2](https://huggingface.co/gpt2#limitations-and-bias).
In addition, the data present in the user's tweets further affects the text generated by the model.
## About
*Built by Boris Dayma*
[](https://twitter.com/intent/follow?screen_name=borisdayma)
For more details, visit the project repository.
[](https://github.com/borisdayma/huggingtweets)
|
Culmenus/opus-mt-de-is-finetuned-de-to-is_35g65cc
|
[] | null |
{
"architectures": null,
"model_type": null,
"task_specific_params": {
"conversational": {
"max_length": null
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
}
| 0
| null |
---
library_name: sample-factory
tags:
- deep-reinforcement-learning
- reinforcement-learning
- sample-factory
model-index:
- name: APPO
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: doom_health_gathering_supreme
type: doom_health_gathering_supreme
metrics:
- type: mean_reward
value: 13.04 +/- 4.37
name: mean_reward
verified: false
---
A(n) **APPO** model trained on the **doom_health_gathering_supreme** environment.
This model was trained using Sample-Factory 2.0: https://github.com/alex-petrenko/sample-factory.
Documentation for how to use Sample-Factory can be found at https://www.samplefactory.dev/
## Downloading the model
After installing Sample-Factory, download the model with:
```
python -m sample_factory.huggingface.load_from_hub -r dvesely/rl_course_vizdoom_health_gathering_supreme
```
## Using the model
To run the model after download, use the `enjoy` script corresponding to this environment:
```
python -m .usr.local.lib.python3.9.dist-packages.ipykernel_launcher --algo=APPO --env=doom_health_gathering_supreme --train_dir=./train_dir --experiment=rl_course_vizdoom_health_gathering_supreme
```
You can also upload models to the Hugging Face Hub using the same script with the `--push_to_hub` flag.
See https://www.samplefactory.dev/10-huggingface/huggingface/ for more details
## Training with this model
To continue training with this model, use the `train` script corresponding to this environment:
```
python -m .usr.local.lib.python3.9.dist-packages.ipykernel_launcher --algo=APPO --env=doom_health_gathering_supreme --train_dir=./train_dir --experiment=rl_course_vizdoom_health_gathering_supreme --restart_behavior=resume --train_for_env_steps=10000000000
```
Note, you may have to adjust `--train_for_env_steps` to a suitably high number as the experiment will resume at the number of steps it concluded at.
|
Culmenus/opus-mt-de-is-finetuned-de-to-is_35g65cc_2
|
[] | null |
{
"architectures": null,
"model_type": null,
"task_specific_params": {
"conversational": {
"max_length": null
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
}
| 0
| null |
---
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: 0.924
- name: F1
type: f1
value: 0.9239280493153317
---
<!-- 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: 0.2236
- Accuracy: 0.924
- F1: 0.9239
## 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 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
| 0.8552 | 1.0 | 250 | 0.3217 | 0.9045 | 0.9015 |
| 0.2578 | 2.0 | 500 | 0.2236 | 0.924 | 0.9239 |
### Framework versions
- Transformers 4.13.0
- Pytorch 2.0.0+cu118
- Datasets 2.8.0
- Tokenizers 0.10.3
|
Culmenus/opus-mt-de-is-finetuned-de-to-is_ancc
|
[] | null |
{
"architectures": null,
"model_type": null,
"task_specific_params": {
"conversational": {
"max_length": null
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
}
| 0
| null |
---
license: cc-by-nc-4.0
task_categories:
- text-to-video
language:
- en
tags:
- anime
---
This is a text2video model for diffusers, fine-tuned with a [modelscope](https://huggingface.co/damo-vilab/text-to-video-ms-1.7b) to have an anime-style appearance.
It was trained at 384x384 resolution.
It still generates unstable content often.
The usage is the same as with the original modelscope model.
example images are [here](https://imgur.com/a/sCwmKG1).
|
Culmenus/opus-mt-de-is-finetuned-de-to-is_nr2-finetuned-de-to-is_nr2
|
[] | null |
{
"architectures": null,
"model_type": null,
"task_specific_params": {
"conversational": {
"max_length": null
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
}
| 0
| null |
---
language:
- es
license: gpl-3.0
tags:
- generated_from_trainer
model-index:
- name: flisol-cba-martin-fierro
results: []
widget:
- text: "Aqui me pongo a cantar"
example_title: "Martin Fierro"
---
Hugging Face: IA Colaborativa
=============================
En este repositorio estará disponible el código y modelo que entrené para la
charla ["Hugging Face: IA Colaborativa"](https://eventol.flisol.org.ar/events/cordoba2023/activity/378/)
del [FLISoL de Córdoba](https://cordoba.flisol.org.ar), Argentina, de 2023.
Para inicializar el setup hace falta tener instalado y activado
[`git-lfs`](https://git-lfs.com/).
Pueden clonar el repositorio con:
$ git clone https://huggingface.co/crscardellino/flisol-cba-martin-fierro
Y luego crean el entorno e instalan los requerimientos.
$ python -m venv flisol-venv
$ source ./flisol-venv/bin/activate
(flisol-venv) $ pip install -r requirements.txt
El código está probado con Python 3.10, pero debería funcionar con Python >=
3.8. En los requerimientos está organizado para instalar
[PyTorch](https://pytorch.org/) v2.0.0 para cpu, pero pueden ajustarlo para
utilizar GPUs suponiendo que cumplan los requerimientos de CUDA.
## Model Specifications (Auto Generated)
This model is a fine-tuned version of
[DeepESP/gpt2-spanish](https://huggingface.co/DeepESP/gpt2-spanish) on the
`./data/martin-fierro_train.txt` dataset. It achieves the following results on
the evaluation set:
- Loss: 3.9067
## Model description
GPT-2 model finetuned on the poem ["El Gaucho Martin
Fierro"](https://es.wikipedia.org/wiki/El_Gaucho_Mart%C3%ADn_Fierro)
## Intended uses & limitations
This was trained for the talk ["Hugging Face: IA
Colaborativa"](https://eventol.flisol.org.ar/events/cordoba2023/activity/378/) @
[FLISoL de Córdoba](https://cordoba.flisol.org.ar), Argentina, 2023.
## Training and evaluation data
### 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: 10
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 4.3864 | 1.0 | 18 | 4.2025 |
| 3.948 | 2.0 | 36 | 4.0440 |
| 3.7962 | 3.0 | 54 | 3.9804 |
| 3.6105 | 4.0 | 72 | 3.9458 |
| 3.4444 | 5.0 | 90 | 3.9280 |
| 3.3855 | 6.0 | 108 | 3.9192 |
| 3.3142 | 7.0 | 126 | 3.9091 |
| 3.2192 | 8.0 | 144 | 3.9074 |
| 3.1615 | 9.0 | 162 | 3.9070 |
| 3.1637 | 10.0 | 180 | 3.9067 |
### Framework versions
- Transformers 4.28.1
- Pytorch 2.0.0+cpu
- Datasets 2.11.0
- Tokenizers 0.13.3
|
D-Keqi/espnet_asr_train_asr_streaming_transformer_raw_en_bpe500_sp_valid.acc.ave
|
[] | null |
{
"architectures": null,
"model_type": null,
"task_specific_params": {
"conversational": {
"max_length": null
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
}
| 11
| null |
---
tags:
- text-classification
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: 143-textcat-406
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. -->
# 143-textcat-406
This model is a fine-tuned version of [dccuchile/distilbert-base-spanish-uncased](https://huggingface.co/dccuchile/distilbert-base-spanish-uncased) on the dataset.
It achieves the following results on the evaluation set:
- Loss: 0.1962
- Accuracy: 0.9615
## 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: 15
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| No log | 1.0 | 89 | 1.6407 | 0.6346 |
| No log | 2.0 | 178 | 0.7345 | 0.9103 |
| No log | 3.0 | 267 | 0.3733 | 0.9423 |
| No log | 4.0 | 356 | 0.2489 | 0.9487 |
| No log | 5.0 | 445 | 0.2087 | 0.9615 |
| 0.7031 | 6.0 | 534 | 0.2073 | 0.9551 |
| 0.7031 | 7.0 | 623 | 0.1969 | 0.9551 |
| 0.7031 | 8.0 | 712 | 0.2000 | 0.9615 |
| 0.7031 | 9.0 | 801 | 0.1974 | 0.9615 |
| 0.7031 | 10.0 | 890 | 0.1962 | 0.9615 |
| 0.7031 | 11.0 | 979 | 0.2024 | 0.9615 |
| 0.0172 | 12.0 | 1068 | 0.2027 | 0.9615 |
| 0.0172 | 13.0 | 1157 | 0.2045 | 0.9615 |
| 0.0172 | 14.0 | 1246 | 0.2044 | 0.9615 |
| 0.0172 | 15.0 | 1335 | 0.2047 | 0.9615 |
### Framework versions
- Transformers 4.28.1
- Pytorch 2.0.0+cu118
- Datasets 2.11.0
- Tokenizers 0.13.3
|
D3vil/DialoGPT-smaall-harrypotter
|
[] | null |
{
"architectures": null,
"model_type": null,
"task_specific_params": {
"conversational": {
"max_length": null
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
}
| 0
| null |
---
tags:
- CartPole-v1
- reinforce
- reinforcement-learning
- custom-implementation
- deep-rl-class
model-index:
- name: Reinforce-pole
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: CartPole-v1
type: CartPole-v1
metrics:
- type: mean_reward
value: 500.00 +/- 0.00
name: mean_reward
verified: false
---
# **Reinforce** Agent playing **CartPole-v1**
This is a trained model of a **Reinforce** agent playing **CartPole-v1** .
To learn to use this model and train yours check Unit 4 of the Deep Reinforcement Learning Course: https://huggingface.co/deep-rl-course/unit4/introduction
|
D3xter1922/distilbert-base-uncased-finetuned-cola
|
[] | null |
{
"architectures": null,
"model_type": null,
"task_specific_params": {
"conversational": {
"max_length": null
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
}
| 0
| null |
---
language: en
widget:
- text: "I love sky news,"
---
# The Lumber Model
## Training data
The model was trained on tweets from Lumber himself.
| Data | Lumber |
| --- | --- |
| Tweets downloaded | 1155 |
| Retweets | 4 |
| Short tweets | 87 |
| Tweets kept | 1064 |
|
DARKVIP3R/DialoGPT-medium-Anakin
|
[
"pytorch",
"gpt2",
"text-generation",
"transformers",
"conversational"
] |
conversational
|
{
"architectures": [
"GPT2LMHeadModel"
],
"model_type": "gpt2",
"task_specific_params": {
"conversational": {
"max_length": 1000
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
}
| 13
| null |
---
license: mit
duplicated_from: rikineko/RVC_Models
---
|
DCU-NLP/bert-base-irish-cased-v1
|
[
"pytorch",
"tf",
"bert",
"fill-mask",
"transformers",
"generated_from_keras_callback",
"autotrain_compatible"
] |
fill-mask
|
{
"architectures": [
"BertForMaskedLM"
],
"model_type": "bert",
"task_specific_params": {
"conversational": {
"max_length": null
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
}
| 1,244
| null |
---
language: en
tags:
- multivae
license: apache-2.0
---
### Downloading this model from the Hub
This model was trained with multivae. It can be downloaded or reloaded using the method `load_from_hf_hub`
```python
>>> from multivae.models import AutoModel
>>> model = AutoModel.load_from_hf_hub(hf_hub_path="your_hf_username/repo_name")
```
|
DCU-NLP/electra-base-irish-cased-discriminator-v1
|
[
"pytorch",
"electra",
"pretraining",
"ga",
"transformers",
"irish",
"license:apache-2.0"
] | null |
{
"architectures": [
"ElectraForPreTraining"
],
"model_type": "electra",
"task_specific_params": {
"conversational": {
"max_length": null
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
}
| 4
| null |
---
tags:
- text-classification
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: 149-textcat-407
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. -->
# 149-textcat-407
This model is a fine-tuned version of [dccuchile/distilbert-base-spanish-uncased](https://huggingface.co/dccuchile/distilbert-base-spanish-uncased) on the dataset.
It achieves the following results on the evaluation set:
- Loss: 0.0206
- Accuracy: 1.0
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| No log | 1.0 | 34 | 0.7989 | 0.7759 |
| No log | 2.0 | 68 | 0.3001 | 0.9828 |
| No log | 3.0 | 102 | 0.1187 | 0.9828 |
| No log | 4.0 | 136 | 0.0633 | 1.0 |
| No log | 5.0 | 170 | 0.0445 | 1.0 |
| No log | 6.0 | 204 | 0.0308 | 1.0 |
| No log | 7.0 | 238 | 0.0261 | 1.0 |
| No log | 8.0 | 272 | 0.0232 | 1.0 |
| No log | 9.0 | 306 | 0.0207 | 1.0 |
| No log | 10.0 | 340 | 0.0206 | 1.0 |
### Framework versions
- Transformers 4.28.1
- Pytorch 2.0.0+cu118
- Datasets 2.11.0
- Tokenizers 0.13.3
|
DHBaek/gpt2-stackoverflow-question-contents-generator
|
[
"pytorch",
"gpt2",
"text-generation",
"transformers"
] |
text-generation
|
{
"architectures": [
"GPT2LMHeadModel"
],
"model_type": "gpt2",
"task_specific_params": {
"conversational": {
"max_length": null
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": true,
"max_length": 50
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
}
| 14
| null |
---
tags:
- CartPole-v1
- reinforce
- reinforcement-learning
- custom-implementation
- deep-rl-class
model-index:
- name: Reinforce-cartpole-v1
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: CartPole-v1
type: CartPole-v1
metrics:
- type: mean_reward
value: 500.00 +/- 0.00
name: mean_reward
verified: false
---
# **Reinforce** Agent playing **CartPole-v1**
This is a trained model of a **Reinforce** agent playing **CartPole-v1** .
To learn to use this model and train yours check Unit 4 of the Deep Reinforcement Learning Course: https://huggingface.co/deep-rl-course/unit4/introduction
|
DHBaek/xlm-roberta-large-korquad-mask
|
[
"pytorch",
"xlm-roberta",
"question-answering",
"transformers",
"autotrain_compatible"
] |
question-answering
|
{
"architectures": [
"XLMRobertaForQuestionAnswering"
],
"model_type": "xlm-roberta",
"task_specific_params": {
"conversational": {
"max_length": null
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
}
| 9
| null |
---
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- wer
model-index:
- name: whisper-small-hi
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. -->
# whisper-small-hi
This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.0000
- Wer: 0.0
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 1e-05
- train_batch_size: 16
- eval_batch_size: 8
- 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: 1000
- mixed_precision_training: Native AMP
### Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|:-------------:|:------:|:----:|:---------------:|:---:|
| 0.0 | 333.33 | 1000 | 0.0000 | 0.0 |
### Framework versions
- Transformers 4.27.4
- Pytorch 2.0.0+cu118
- Datasets 2.11.0
- Tokenizers 0.13.3
|
DJSammy/bert-base-swedish-uncased_BotXO-ai
|
[
"pytorch",
"transformers"
] | null |
{
"architectures": null,
"model_type": null,
"task_specific_params": {
"conversational": {
"max_length": null
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
}
| 1
| null |
---
tags:
- text-classification
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: 153-textcat-408
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. -->
# 153-textcat-408
This model is a fine-tuned version of [dccuchile/distilbert-base-spanish-uncased](https://huggingface.co/dccuchile/distilbert-base-spanish-uncased) on the dataset.
It achieves the following results on the evaluation set:
- Loss: 1.1284
- Accuracy: 0.6429
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| No log | 1.0 | 16 | 1.9857 | 0.3571 |
| No log | 2.0 | 32 | 1.8249 | 0.4286 |
| No log | 3.0 | 48 | 1.6683 | 0.5714 |
| No log | 4.0 | 64 | 1.5192 | 0.6071 |
| No log | 5.0 | 80 | 1.3937 | 0.6429 |
| No log | 6.0 | 96 | 1.2969 | 0.6429 |
| No log | 7.0 | 112 | 1.2173 | 0.6429 |
| No log | 8.0 | 128 | 1.1746 | 0.6429 |
| No log | 9.0 | 144 | 1.1387 | 0.6429 |
| No log | 10.0 | 160 | 1.1284 | 0.6429 |
### Framework versions
- Transformers 4.28.1
- Pytorch 2.0.0+cu118
- Datasets 2.11.0
- Tokenizers 0.13.3
|
DSI/TweetBasedSA
|
[
"pytorch",
"bert",
"text-classification",
"transformers"
] |
text-classification
|
{
"architectures": [
"BertForSequenceClassification"
],
"model_type": "bert",
"task_specific_params": {
"conversational": {
"max_length": null
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
}
| 29
| null |
---
tags:
- text-classification
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: 156-textcat-411
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. -->
# 156-textcat-411
This model is a fine-tuned version of [dccuchile/distilbert-base-spanish-uncased](https://huggingface.co/dccuchile/distilbert-base-spanish-uncased) on the dataset.
It achieves the following results on the evaluation set:
- Loss: 0.1080
- Accuracy: 0.9756
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| No log | 1.0 | 47 | 0.8363 | 0.7683 |
| No log | 2.0 | 94 | 0.4315 | 0.9024 |
| No log | 3.0 | 141 | 0.2443 | 0.9756 |
| No log | 4.0 | 188 | 0.1584 | 0.9634 |
| No log | 5.0 | 235 | 0.1210 | 0.9756 |
| No log | 6.0 | 282 | 0.1080 | 0.9756 |
| No log | 7.0 | 329 | 0.1211 | 0.9756 |
| No log | 8.0 | 376 | 0.1157 | 0.9756 |
| No log | 9.0 | 423 | 0.1150 | 0.9756 |
| No log | 10.0 | 470 | 0.1148 | 0.9756 |
### Framework versions
- Transformers 4.28.1
- Pytorch 2.0.0+cu118
- Datasets 2.11.0
- Tokenizers 0.13.3
|
DTAI-KULeuven/robbertje-1-gb-bort
|
[
"pytorch",
"roberta",
"fill-mask",
"nl",
"dataset:oscar",
"dataset:oscar (NL)",
"dataset:dbrd",
"dataset:lassy-ud",
"dataset:europarl-mono",
"dataset:conll2002",
"arxiv:2101.05716",
"transformers",
"Dutch",
"Flemish",
"RoBERTa",
"RobBERT",
"RobBERTje",
"license:mit",
"autotrain_compatible"
] |
fill-mask
|
{
"architectures": [
"RobertaForMaskedLM"
],
"model_type": "roberta",
"task_specific_params": {
"conversational": {
"max_length": null
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
}
| 6
| null |
---
library_name: ml-agents
tags:
- SnowballTarget
- deep-reinforcement-learning
- reinforcement-learning
- ML-Agents-SnowballTarget
---
# **ppo** Agent playing **SnowballTarget**
This is a trained model of a **ppo** agent playing **SnowballTarget** using the [Unity ML-Agents Library](https://github.com/Unity-Technologies/ml-agents).
## Usage (with ML-Agents)
The Documentation: https://github.com/huggingface/ml-agents#get-started
We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub:
### Resume the training
```
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. Go to https://huggingface.co/spaces/unity/ML-Agents-SnowballTarget
2. Step 1: Find your model_id: ckauth/ppo-ML-Agents-SnowballTarget
3. Step 2: Select your *.nn /*.onnx file
4. Click on Watch the agent play 👀
|
alexandrainst/da-emotion-classification-base
|
[
"pytorch",
"tf",
"bert",
"text-classification",
"da",
"transformers",
"license:cc-by-sa-4.0"
] |
text-classification
|
{
"architectures": [
"BertForSequenceClassification"
],
"model_type": "bert",
"task_specific_params": {
"conversational": {
"max_length": null
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
}
| 837
| null |
---
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: swin-tiny-patch4-window7-224-bottom_cleaned_data-hpt
results:
- task:
name: Image Classification
type: image-classification
dataset:
name: imagefolder
type: imagefolder
config: default
split: train
args: default
metrics:
- name: Accuracy
type: accuracy
value: 0.9694041867954911
---
<!-- 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. -->
# swin-tiny-patch4-window7-224-bottom_cleaned_data-hpt
This model is a fine-tuned version of [microsoft/swin-tiny-patch4-window7-224](https://huggingface.co/microsoft/swin-tiny-patch4-window7-224) on the imagefolder dataset.
It achieves the following results on the evaluation set:
- Loss: 0.0701
- Accuracy: 0.9694
## 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
- gradient_accumulation_steps: 7
- total_train_batch_size: 56
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.01
- num_epochs: 10
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 0.4307 | 0.99 | 99 | 0.2332 | 0.9227 |
| 0.3425 | 2.0 | 199 | 0.1904 | 0.9404 |
| 0.29 | 3.0 | 299 | 0.1316 | 0.9388 |
| 0.2597 | 3.99 | 398 | 0.1158 | 0.9533 |
| 0.2638 | 4.99 | 498 | 0.0987 | 0.9614 |
| 0.209 | 6.0 | 598 | 0.0802 | 0.9710 |
| 0.1776 | 7.0 | 698 | 0.0838 | 0.9597 |
| 0.1776 | 7.99 | 797 | 0.0787 | 0.9694 |
| 0.1502 | 9.0 | 897 | 0.0797 | 0.9726 |
| 0.1402 | 9.93 | 990 | 0.0701 | 0.9694 |
### Framework versions
- Transformers 4.28.1
- Pytorch 2.0.0+cu118
- Datasets 2.11.0
- Tokenizers 0.13.3
|
alexandrainst/da-sentiment-base
|
[
"pytorch",
"tf",
"safetensors",
"bert",
"text-classification",
"da",
"arxiv:1910.09700",
"transformers",
"license:cc-by-sa-4.0"
] |
text-classification
|
{
"architectures": [
"BertForSequenceClassification"
],
"model_type": "bert",
"task_specific_params": {
"conversational": {
"max_length": null
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
}
| 1,432
| null |
---
license: cc-by-nc-4.0
language:
- zh
- en
pipeline_tag: text-to-image
tags:
- art
---
# Image Sharpener
Image Sharpener is a text embedding used to make the image generated by the stable diffusion model clearer.
## Model Details
### Model Description
- **Developed by:** Eugeoter
- **Model type:** text embedding for stable diffusion
- **License:** cc-by-nc-4.0
## Uses
### How to Use
1. Load the model on stable diffusion: For example, put the is_v1.pt file into the embeddings folder of stable diffusion.
2. Add a trigger word (namely the file name without the extension) in the negative prompt word: For example, enter 'is_v1' in the negative prompt word.
## Limitations
It will sharpen any blurred areas in the image. If it ruins your original style, stop using it.
Furthermore, I don't recommend adjusting its weight.
## Training Details
I trained textual inversion on 200 crappy and blurry images to teach it low resolution & blurry.
### Training Data
I generated 200 images using a stable diffusion model. Some build parameters are as follows:
1. Resolution: 256x256
2. Positive prompt: solo
3. Negative reminder times:
4. Sampler: eular_a
5. Number of sampling steps: 12
I stretched them to 512x512 resolution in my processing and tagged them with deepdanbooru with a threshold of 0.5.
|
Davlan/bert-base-multilingual-cased-finetuned-luo
|
[
"pytorch",
"bert",
"fill-mask",
"transformers",
"autotrain_compatible"
] |
fill-mask
|
{
"architectures": [
"BertForMaskedLM"
],
"model_type": "bert",
"task_specific_params": {
"conversational": {
"max_length": null
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
}
| 11
| null |
---
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- tweet_sentiment_multilingual
model-index:
- name: custom_sentiment_224u
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. -->
# custom_sentiment_224u
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the tweet_sentiment_multilingual 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: 12
- eval_batch_size: 12
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 75
### Training results
### Framework versions
- Transformers 4.26.1
- Pytorch 1.13.1+cu117
- Datasets 2.10.1
- Tokenizers 0.13.3
|
DeadBeast/emoBERTTamil
|
[
"pytorch",
"tensorboard",
"bert",
"text-classification",
"dataset:tamilmixsentiment",
"transformers",
"generated_from_trainer",
"license:apache-2.0"
] |
text-classification
|
{
"architectures": [
"BertForSequenceClassification"
],
"model_type": "bert",
"task_specific_params": {
"conversational": {
"max_length": null
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
}
| 35
| null |
---
tags:
- unity-ml-agents
- ml-agents
- deep-reinforcement-learning
- reinforcement-learning
- ML-Agents-SoccerTwos
library_name: ml-agents
---
# **poca** Agent playing **SoccerTwos**
This is a trained model of a **poca** agent playing **SoccerTwos** using the [Unity ML-Agents Library](https://github.com/Unity-Technologies/ml-agents).
## Usage (with ML-Agents)
The Documentation: https://github.com/huggingface/ml-agents#get-started
We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub:
### Resume the training
```
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. Go to https://huggingface.co/spaces/unity/ML-Agents-SoccerTwos
2. Step 1: Write your model_id: QYHcrossover/poca-test4
3. Step 2: Select your *.nn /*.onnx file
4. Click on Watch the agent play 👀
|
Declan/NPR_model_v1
|
[
"pytorch",
"bert",
"fill-mask",
"transformers",
"autotrain_compatible"
] |
fill-mask
|
{
"architectures": [
"BertForMaskedLM"
],
"model_type": "bert",
"task_specific_params": {
"conversational": {
"max_length": null
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
}
| 3
| 2023-04-17T17:06:40Z
|
---
library_name: ml-agents
tags:
- SnowballTarget
- deep-reinforcement-learning
- reinforcement-learning
- ML-Agents-SnowballTarget
---
# **ppo** Agent playing **SnowballTarget**
This is a trained model of a **ppo** agent playing **SnowballTarget** using the [Unity ML-Agents Library](https://github.com/Unity-Technologies/ml-agents).
## Usage (with ML-Agents)
The Documentation: https://github.com/huggingface/ml-agents#get-started
We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub:
### Resume the training
```
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. Go to https://huggingface.co/spaces/unity/ML-Agents-SnowballTarget
2. Step 1: Find your model_id: dylwil3/ppo-SnowballTarget2
3. Step 2: Select your *.nn /*.onnx file
4. Click on Watch the agent play 👀
|
Declan/NPR_model_v2
|
[
"pytorch",
"bert",
"fill-mask",
"transformers",
"autotrain_compatible"
] |
fill-mask
|
{
"architectures": [
"BertForMaskedLM"
],
"model_type": "bert",
"task_specific_params": {
"conversational": {
"max_length": null
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
}
| 7
| 2023-04-17T17:08:39Z
|
---
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="elhamagk/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"])
```
|
Declan/NewYorkTimes_model_v1
|
[] | null |
{
"architectures": null,
"model_type": null,
"task_specific_params": {
"conversational": {
"max_length": null
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
}
| 0
| null |
---
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- f1
model-index:
- name: distilbert-base-uncased_intent_classification
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. -->
# distilbert-base-uncased_intent_classification
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: 10.1998
- F1: 0.0560
## 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 | F1 |
|:-------------:|:-----:|:----:|:---------------:|:------:|
| No log | 1.0 | 312 | 7.5574 | 0.058 |
| 0.458 | 2.0 | 624 | 8.9497 | 0.0560 |
| 0.458 | 3.0 | 936 | 9.6656 | 0.0560 |
| 0.0848 | 4.0 | 1248 | 10.0615 | 0.058 |
| 0.0379 | 5.0 | 1560 | 10.1998 | 0.0560 |
### Framework versions
- Transformers 4.28.1
- Pytorch 2.0.0+cu118
- Datasets 2.11.0
- Tokenizers 0.13.3
|
Declan/NewYorkTimes_model_v2
|
[
"pytorch",
"bert",
"fill-mask",
"transformers",
"autotrain_compatible"
] |
fill-mask
|
{
"architectures": [
"BertForMaskedLM"
],
"model_type": "bert",
"task_specific_params": {
"conversational": {
"max_length": null
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
}
| 7
| null |
Access to model Andreas-w/brain-classification is restricted and you are not in the authorized list. Visit https://huggingface.co/Andreas-w/brain-classification to ask for access.
|
Declan/Reuters_model_v2
|
[
"pytorch",
"bert",
"fill-mask",
"transformers",
"autotrain_compatible"
] |
fill-mask
|
{
"architectures": [
"BertForMaskedLM"
],
"model_type": "bert",
"task_specific_params": {
"conversational": {
"max_length": null
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
}
| 5
| 2023-04-17T17:38:39Z
|
---
library_name: stable-baselines3
tags:
- AntBulletEnv-v0
- deep-reinforcement-learning
- reinforcement-learning
- stable-baselines3
model-index:
- name: A2C
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: AntBulletEnv-v0
type: AntBulletEnv-v0
metrics:
- type: mean_reward
value: 1547.80 +/- 42.88
name: mean_reward
verified: false
---
# **A2C** Agent playing **AntBulletEnv-v0**
This is a trained model of a **A2C** agent playing **AntBulletEnv-v0**
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
...
```
|
Declan/Reuters_model_v5
|
[
"pytorch",
"bert",
"fill-mask",
"transformers",
"autotrain_compatible"
] |
fill-mask
|
{
"architectures": [
"BertForMaskedLM"
],
"model_type": "bert",
"task_specific_params": {
"conversational": {
"max_length": null
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
}
| 3
| null |
---
tags:
- generated_from_trainer
model-index:
- name: workstation_whisper_small_distil_libri360_12_to_6_batch_8_epoch_100
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. -->
# workstation_whisper_small_distil_libri360_12_to_6_batch_8_epoch_100
This model is a fine-tuned version of [](https://huggingface.co/) on the None dataset.
It achieves the following results on the evaluation set:
- eval_loss: 7.0953
- eval_wer: 101.0579
- eval_runtime: 672.9494
- eval_samples_per_second: 8.033
- eval_steps_per_second: 8.033
- epoch: 17.98
- step: 900
## 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: 1
- seed: 42
- gradient_accumulation_steps: 512
- total_train_batch_size: 4096
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.2
- num_epochs: 100
- mixed_precision_training: Native AMP
### Framework versions
- Transformers 4.24.0
- Pytorch 1.12.1
- Datasets 2.7.1
- Tokenizers 0.11.0
|
Declan/Reuters_model_v6
|
[
"pytorch",
"bert",
"fill-mask",
"transformers",
"autotrain_compatible"
] |
fill-mask
|
{
"architectures": [
"BertForMaskedLM"
],
"model_type": "bert",
"task_specific_params": {
"conversational": {
"max_length": null
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
}
| 7
| null |
---
library_name: stable-baselines3
tags:
- LunarLander-v2
- deep-reinforcement-learning
- reinforcement-learning
- stable-baselines3
model-index:
- name: A2C
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: LunarLander-v2
type: LunarLander-v2
metrics:
- type: mean_reward
value: -133.83 +/- 27.14
name: mean_reward
verified: false
---
# **A2C** Agent playing **LunarLander-v2**
This is a trained model of a **A2C** 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
...
```
|
Declan/Reuters_model_v8
|
[
"pytorch",
"bert",
"fill-mask",
"transformers",
"autotrain_compatible"
] |
fill-mask
|
{
"architectures": [
"BertForMaskedLM"
],
"model_type": "bert",
"task_specific_params": {
"conversational": {
"max_length": null
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
}
| 3
| null |
Access to model Ejiji/stable-finetuned is restricted and you are not in the authorized list. Visit https://huggingface.co/Ejiji/stable-finetuned to ask for access.
|
Declan/WallStreetJournal_model_v3
|
[
"pytorch",
"bert",
"fill-mask",
"transformers",
"autotrain_compatible"
] |
fill-mask
|
{
"architectures": [
"BertForMaskedLM"
],
"model_type": "bert",
"task_specific_params": {
"conversational": {
"max_length": null
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
}
| 3
| null |
---
license: creativeml-openrail-m
tags:
- text-to-image
- stable-diffusion
---
### CXR-Fine-Tuning---trained-on-ChestX-ray14-dataset-with-bounding-boxes-(only-1k-images-as-of-now) Dreambooth model trained by DanishH 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:
|
DeepPavlov/distilrubert-tiny-cased-conversational-v1
|
[
"pytorch",
"distilbert",
"ru",
"arxiv:2205.02340",
"transformers"
] | null |
{
"architectures": null,
"model_type": "distilbert",
"task_specific_params": {
"conversational": {
"max_length": null
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
}
| 9,141
| null |
---
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: 230.75 +/- 80.95
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
...
```
|
DeltaHub/adapter_t5-3b_cola
|
[
"pytorch",
"transformers"
] | null |
{
"architectures": null,
"model_type": null,
"task_specific_params": {
"conversational": {
"max_length": null
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
}
| 3
| null |
---
license: apache-2.0
tags:
- generated_from_trainer
model-index:
- name: flan-t5-large-extraction-all-dm_2000-ep1-nonstop
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. -->
# flan-t5-large-extraction-all-dm_2000-ep1-nonstop
This model is a fine-tuned version of [google/flan-t5-large](https://huggingface.co/google/flan-t5-large) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 1.7533
- Hint Hit Num: 2.5596
- Hint Precision: 0.4547
- Num: 5.6376
- Gen Len: 18.9593
## 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: 12
- eval_batch_size: 96
- seed: 1799
- 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 | Hint Hit Num | Hint Precision | Num | Gen Len |
|:-------------:|:-----:|:----:|:---------------:|:------------:|:--------------:|:------:|:-------:|
| 2.4984 | 0.6 | 100 | 1.7721 | 2.5428 | 0.4477 | 5.6636 | 18.9525 |
### Framework versions
- Transformers 4.18.0
- Pytorch 1.10.0+cu111
- Datasets 2.5.1
- Tokenizers 0.12.1
|
DemangeJeremy/4-sentiments-with-flaubert
|
[
"pytorch",
"flaubert",
"text-classification",
"fr",
"transformers",
"sentiments",
"french",
"flaubert-large"
] |
text-classification
|
{
"architectures": [
"FlaubertForSequenceClassification"
],
"model_type": "flaubert",
"task_specific_params": {
"conversational": {
"max_length": null
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
}
| 226
| 2023-04-17T18:50:07Z
|
---
library_name: sample-factory
tags:
- deep-reinforcement-learning
- reinforcement-learning
- sample-factory
model-index:
- name: APPO
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: doom_health_gathering_supreme
type: doom_health_gathering_supreme
metrics:
- type: mean_reward
value: 7.39 +/- 4.33
name: mean_reward
verified: false
---
A(n) **APPO** model trained on the **doom_health_gathering_supreme** environment.
This model was trained using Sample-Factory 2.0: https://github.com/alex-petrenko/sample-factory.
Documentation for how to use Sample-Factory can be found at https://www.samplefactory.dev/
## Downloading the model
After installing Sample-Factory, download the model with:
```
python -m sample_factory.huggingface.load_from_hub -r jcramirezpr/rl_course_vizdoom_health_gathering_supreme
```
## Using the model
To run the model after download, use the `enjoy` script corresponding to this environment:
```
python -m .usr.local.lib.python3.9.dist-packages.ipykernel_launcher --algo=APPO --env=doom_health_gathering_supreme --train_dir=./train_dir --experiment=rl_course_vizdoom_health_gathering_supreme
```
You can also upload models to the Hugging Face Hub using the same script with the `--push_to_hub` flag.
See https://www.samplefactory.dev/10-huggingface/huggingface/ for more details
## Training with this model
To continue training with this model, use the `train` script corresponding to this environment:
```
python -m .usr.local.lib.python3.9.dist-packages.ipykernel_launcher --algo=APPO --env=doom_health_gathering_supreme --train_dir=./train_dir --experiment=rl_course_vizdoom_health_gathering_supreme --restart_behavior=resume --train_for_env_steps=10000000000
```
Note, you may have to adjust `--train_for_env_steps` to a suitably high number as the experiment will resume at the number of steps it concluded at.
|
Deniskin/essays_small_2000i
|
[] | null |
{
"architectures": null,
"model_type": null,
"task_specific_params": {
"conversational": {
"max_length": null
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
}
| 0
| null |
---
license: mit
language:
- de
tags:
- title generation
- headline-generation
- teaser generation
- keyword generation
- tweet generation
- news
inference: false
---
# snip-igel-500-v2
<!-- Provide a quick summary of what the model is/does. -->
snip-igel-500
Version 1.0 / 17 April 2023
An adapter for [IGEL](https://huggingface.co/philschmid/instruct-igel-001) to generate german news snippets with human written instructions.
For usage example see this [notebook](https://github.com/snipaid-nlg/igel-lora-finetune-news-snippets/blob/main/getting-started-with-igel-lora-finetuned.ipynb).
# Model Details
## Model Description
<!-- Provide a longer summary of what this model is. -->
Test generation capabilities here: [https://snipaid.tech](https://snipaid.tech)
SNIP-IGEL is a continued instruction-tuned LoRa-Adapter to generate titles, teasers, summaries, tweets, search engine result page and keyword snippets from news article text in german language. [IGEL](https://huggingface.co/philschmid/instruct-igel-001) is an instruction-tuned model on top of the pre-trained german version of BLOOM ([bloom-6b4-clp-german](https://huggingface.co/malteos/bloom-6b4-clp-german)). It was developed by fine-tuning with a machine translated instruction-dataset, aimed to explore the potential of the BLOOM architecture for language modeling tasks requiring instruction-based responses.
- **Developed by:** snipaid
- **Model type:** bloom
- **Language(s) (NLP):** de
- **License:** MIT
- **Finetuned from model:** [IGEL](https://huggingface.co/philschmid/instruct-igel-001)
# 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. -->
SNIP-IGEL is intended to be used for generating snippets for german news articles. It can be used by researchers, journalists, content creators and news agencies to automatically generate snippets for their articles in german language.
# Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
Several common deficiencies can be observed, including hallucination, toxicity and stereotypes.
# 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. -->
SNIP-IGEL has been fine-tuned on [instruct-snippet-mlsum-v2](https://huggingface.co/datasets/snipaid/instruct-snippet-mlsum-v2). MLSUM is a dataset containing a german subset with text, title and teaser for news articles from the newspaper "Süddeutsche Zeitung". The dataset has been augmented with snippet data generated using a composite prompt which involves generating a SERP, keywords and a tweet for the news articles using a student-teacher-approach. Also see [snippet-mlsum-500-v2](https://huggingface.co/datasets/snipaid/snippet-mlsum-500-v2) for the dataset without instructions and our [blogpost](https://snipaid-nlg.github.io/2023/04/13/SNIP-IGEL.html) for more information about the construction of the dataset.
# Environmental Impact
Carbon emissions were estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact/#compute) presented in Lacoste et al. (2019).
Hardware Type: RTX 4090
Hours used: 1h 51min 48s
Cloud Provider: Vast.ai
Compute Region: United States
Carbon Emitted: ~0.31 kg of CO2e
|
Deniskin/gpt3_medium
|
[
"pytorch",
"gpt2",
"text-generation",
"transformers",
"has_space"
] |
text-generation
|
{
"architectures": [
"GPT2LMHeadModel"
],
"model_type": "gpt2",
"task_specific_params": {
"conversational": {
"max_length": null
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
}
| 52
| null |
---
library_name: transformers
pipeline_tag: text-generation
---
Quant of https://huggingface.co/TheBloke/vicuna-13B-1.1-HF
There's already one located at https://huggingface.co/TheBloke/vicuna-13B-1.1-GPTQ-4bit-128g, but neither version they uploaded works with certain older versions of GPTQ-for-LLaMA (such as 0cc4m's fork that is used with their fork of KoboldAI).
This was quantized with 0cc4m's fork of GPTQ-for-LLaMA.
```python llama.py ./vicuna-13B-1.1-HF c4 --wbits 4 --true-sequential --groupsize 128 --save_safetensors 4bit-128g.safetensors```
|
Devrim/prism-default
|
[
"license:mit"
] | null |
{
"architectures": null,
"model_type": null,
"task_specific_params": {
"conversational": {
"max_length": null
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
}
| 0
| 2023-04-17T19:36:40Z
|
---
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: distilbert-base-multilingual-cased-ft-jd
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. -->
# distilbert-base-multilingual-cased-ft-jd
This model is a fine-tuned version of [distilbert-base-multilingual-cased](https://huggingface.co/distilbert-base-multilingual-cased) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.4255
- Accuracy: 0.8855
## 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 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 0.451 | 1.0 | 464 | 0.3695 | 0.8661 |
| 0.3076 | 2.0 | 928 | 0.3406 | 0.8942 |
| 0.2363 | 3.0 | 1392 | 0.3779 | 0.8866 |
| 0.1919 | 4.0 | 1856 | 0.4218 | 0.8844 |
| 0.1619 | 5.0 | 2320 | 0.4255 | 0.8855 |
### Framework versions
- Transformers 4.11.3
- Pytorch 1.13.0
- Datasets 1.16.1
- Tokenizers 0.10.3
|
Dhritam/Zova-bot
|
[] | null |
{
"architectures": null,
"model_type": null,
"task_specific_params": {
"conversational": {
"max_length": null
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
}
| 0
| null |
---
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://github.com/huggingface/ml-agents#get-started
We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub:
### Resume the training
```
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. Go to https://huggingface.co/spaces/unity/ML-Agents-Huggy
2. Step 1: Find your model_id: Nebukadn9zar/ppo-Huggy
3. Step 2: Select your *.nn /*.onnx file
4. Click on Watch the agent play 👀
|
Dhruva/Interstellar
|
[] | null |
{
"architectures": null,
"model_type": null,
"task_specific_params": {
"conversational": {
"max_length": null
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
}
| 0
| null |
---
library_name: ml-agents
tags:
- SnowballTarget
- deep-reinforcement-learning
- reinforcement-learning
- ML-Agents-SnowballTarget
---
# **ppo** Agent playing **SnowballTarget**
This is a trained model of a **ppo** agent playing **SnowballTarget** using the [Unity ML-Agents Library](https://github.com/Unity-Technologies/ml-agents).
## Usage (with ML-Agents)
The Documentation: https://github.com/huggingface/ml-agents#get-started
We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub:
### Resume the training
```
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. Go to https://huggingface.co/spaces/unity/ML-Agents-SnowballTarget
2. Step 1: Find your model_id: redfungus/ppo-SnowballTarget
3. Step 2: Select your *.nn /*.onnx file
4. Click on Watch the agent play 👀
|
Dibyaranjan/nl_image_search
|
[] | null |
{
"architectures": null,
"model_type": null,
"task_specific_params": {
"conversational": {
"max_length": null
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
}
| 0
| null |
---
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: 410.00 +/- 198.05
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 thackerhelik -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 thackerhelik -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 thackerhelik
```
## Hyperparameters
```python
OrderedDict([('batch_size', 32),
('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', 10000),
('n_timesteps', 1000000.0),
('optimize_memory_usage', False),
('policy', 'CnnPolicy'),
('target_update_interval', 1000),
('train_freq', 4),
('normalize', False)])
```
|
DiegoAlysson/opus-mt-en-ro-finetuned-en-to-ro
|
[
"pytorch",
"tensorboard",
"marian",
"text2text-generation",
"dataset:wmt16",
"transformers",
"generated_from_trainer",
"license:apache-2.0",
"model-index",
"autotrain_compatible"
] |
text2text-generation
|
{
"architectures": [
"MarianMTModel"
],
"model_type": "marian",
"task_specific_params": {
"conversational": {
"max_length": null
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
}
| 1
| null |
---
license: creativeml-openrail-m
tags:
- text-to-image
- stable-diffusion
---
### ic Dreambooth model trained by fblues 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:
|
DiegoBalam12/institute_classification
|
[] | null |
{
"architectures": null,
"model_type": null,
"task_specific_params": {
"conversational": {
"max_length": null
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
}
| 0
| null |
---
tags:
- Taxi-v3
- q-learning
- reinforcement-learning
- custom-implementation
model-index:
- name: taxiDriver
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: Taxi-v3
type: Taxi-v3
metrics:
- type: mean_reward
value: 7.52 +/- 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="elhamagk/taxiDriver", 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"])
```
|
Digakive/Hsgshs
|
[] | null |
{
"architectures": null,
"model_type": null,
"task_specific_params": {
"conversational": {
"max_length": null
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
}
| 0
| null |
---
license: cc-by-3.0
---
This model has been designed by zubair
|
Dilmk2/DialoGPT-small-harrypotter
|
[
"pytorch",
"gpt2",
"text-generation",
"transformers",
"conversational"
] |
conversational
|
{
"architectures": [
"GPT2LMHeadModel"
],
"model_type": "gpt2",
"task_specific_params": {
"conversational": {
"max_length": 1000
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
}
| 13
| null |
---
library_name: stable-baselines3
tags:
- PandaReachDense-v2
- deep-reinforcement-learning
- reinforcement-learning
- stable-baselines3
model-index:
- name: A2C
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: PandaReachDense-v2
type: PandaReachDense-v2
metrics:
- type: mean_reward
value: -2.02 +/- 0.63
name: mean_reward
verified: false
---
# **A2C** Agent playing **PandaReachDense-v2**
This is a trained model of a **A2C** agent playing **PandaReachDense-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
...
```
|
Dmitriiserg/Pxd
|
[] | null |
{
"architectures": null,
"model_type": null,
"task_specific_params": {
"conversational": {
"max_length": null
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
}
| 0
| null |
---
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- accuracy
- precision
- recall
model-index:
- name: distilbert-base-uncased-PINA-dfnew-insyaallah
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. -->
# distilbert-base-uncased-PINA-dfnew-insyaallah
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: 0.2680
- Accuracy: 0.9431
- Precision: 0.8480
- Recall: 0.8258
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall |
|:-------------:|:-----:|:-----:|:---------------:|:--------:|:---------:|:------:|
| 1.1591 | 1.0 | 1436 | 0.4581 | 0.8945 | 0.7871 | 0.7185 |
| 0.3058 | 2.0 | 2872 | 0.2901 | 0.9349 | 0.8307 | 0.8157 |
| 0.1623 | 3.0 | 4308 | 0.2680 | 0.9431 | 0.8480 | 0.8258 |
| 0.0936 | 4.0 | 5744 | 0.2942 | 0.9474 | 0.8758 | 0.8415 |
| 0.0562 | 5.0 | 7180 | 0.2681 | 0.9535 | 0.8730 | 0.8527 |
| 0.034 | 6.0 | 8616 | 0.3010 | 0.9504 | 0.8761 | 0.8474 |
| 0.0193 | 7.0 | 10052 | 0.2971 | 0.9532 | 0.8643 | 0.8507 |
| 0.0115 | 8.0 | 11488 | 0.3139 | 0.9519 | 0.8640 | 0.8489 |
| 0.0078 | 9.0 | 12924 | 0.3056 | 0.9551 | 0.8649 | 0.8529 |
| 0.0056 | 10.0 | 14360 | 0.3062 | 0.9549 | 0.8636 | 0.8531 |
### Framework versions
- Transformers 4.28.1
- Pytorch 2.0.0+cu118
- Datasets 2.11.0
- Tokenizers 0.13.3
|
DongHyoungLee/kogpt2-base-v2-finetuned-kogpt2_nsmc_single_sentence_classification
|
[] | null |
{
"architectures": null,
"model_type": null,
"task_specific_params": {
"conversational": {
"max_length": null
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
}
| 0
| null |
---
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="alderucci/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"])
```
|
Donghyun/L2_BERT
|
[] | null |
{
"architectures": null,
"model_type": null,
"task_specific_params": {
"conversational": {
"max_length": null
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
}
| 0
| null |
---
tags:
- CartPole-v1
- reinforce
- reinforcement-learning
- custom-implementation
- deep-rl-class
model-index:
- name: Reinforce-CartPole-v1
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: CartPole-v1
type: CartPole-v1
metrics:
- type: mean_reward
value: 500.00 +/- 0.00
name: mean_reward
verified: false
---
# **Reinforce** Agent playing **CartPole-v1**
This is a trained model of a **Reinforce** agent playing **CartPole-v1** .
To learn to use this model and train yours check Unit 4 of the Deep Reinforcement Learning Course: https://huggingface.co/deep-rl-course/unit4/introduction
|
Dongmin/testmodel
|
[
"pytorch",
"t5",
"text2text-generation",
"transformers",
"autotrain_compatible"
] |
text2text-generation
|
{
"architectures": [
"T5ForConditionalGeneration"
],
"model_type": "t5",
"task_specific_params": {
"conversational": {
"max_length": null
},
"summarization": {
"early_stopping": true,
"length_penalty": 2,
"max_length": 200,
"min_length": 30,
"no_repeat_ngram_size": 3,
"num_beams": 4,
"prefix": "summarize: "
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": true,
"max_length": 300,
"num_beams": 4,
"prefix": "translate English to German: "
},
"translation_en_to_fr": {
"early_stopping": true,
"max_length": 300,
"num_beams": 4,
"prefix": "translate English to French: "
},
"translation_en_to_ro": {
"early_stopping": true,
"max_length": 300,
"num_beams": 4,
"prefix": "translate English to Romanian: "
}
}
}
| 11
| null |
---
tags:
- Taxi-v3
- q-learning
- reinforcement-learning
- custom-implementation
model-index:
- name: experimental
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: Taxi-v3
type: Taxi-v3
metrics:
- type: mean_reward
value: 7.50 +/- 2.72
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="alderucci/experimental", 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"])
```
|
Waynehillsdev/Wayne_NLP_mT5
|
[
"pytorch",
"tensorboard",
"mt5",
"text2text-generation",
"dataset:cnn_dailymail",
"transformers",
"generated_from_trainer",
"autotrain_compatible"
] |
text2text-generation
|
{
"architectures": [
"MT5ForConditionalGeneration"
],
"model_type": "mt5",
"task_specific_params": {
"conversational": {
"max_length": null
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
}
| 11
| null |
---
library_name: ml-agents
tags:
- Pyramids
- deep-reinforcement-learning
- reinforcement-learning
- ML-Agents-Pyramids
---
# **ppo** Agent playing **Pyramids**
This is a trained model of a **ppo** agent playing **Pyramids** using the [Unity ML-Agents Library](https://github.com/Unity-Technologies/ml-agents).
## Usage (with ML-Agents)
The Documentation: https://github.com/huggingface/ml-agents#get-started
We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub:
### Resume the training
```
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. Go to https://huggingface.co/spaces/unity/ML-Agents-Pyramids
2. Step 1: Find your model_id: dylwil3/ppo-Pyramids
3. Step 2: Select your *.nn /*.onnx file
4. Click on Watch the agent play 👀
|
Doogie/Waynehills-KE-T5-doogie
|
[] | null |
{
"architectures": null,
"model_type": null,
"task_specific_params": {
"conversational": {
"max_length": null
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
}
| 0
| null |
---
library_name: ml-agents
tags:
- Pyramids
- deep-reinforcement-learning
- reinforcement-learning
- ML-Agents-Pyramids
---
# **ppo** Agent playing **Pyramids**
This is a trained model of a **ppo** agent playing **Pyramids** using the [Unity ML-Agents Library](https://github.com/Unity-Technologies/ml-agents).
## Usage (with ML-Agents)
The Documentation: https://github.com/huggingface/ml-agents#get-started
We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub:
### Resume the training
```
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. Go to https://huggingface.co/spaces/unity/ML-Agents-Pyramids
2. Step 1: Find your model_id: bjarlestam/PyramidsRND
3. Step 2: Select your *.nn /*.onnx file
4. Click on Watch the agent play 👀
|
Waynehillsdev/Waynehills-STT-doogie-server
|
[
"pytorch",
"tensorboard",
"wav2vec2",
"automatic-speech-recognition",
"transformers",
"generated_from_trainer",
"license:apache-2.0"
] |
automatic-speech-recognition
|
{
"architectures": [
"Wav2Vec2ForCTC"
],
"model_type": "wav2vec2",
"task_specific_params": {
"conversational": {
"max_length": null
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
}
| 61
| null |
---
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- audiofolder
metrics:
- accuracy
- f1
- recall
- precision
model-index:
- name: wav2vec2-base-Speech_Emotion_Recognition
results: []
language:
- en
pipeline_tag: audio-classification
---
# wav2vec2-base-Speech_Emotion_Recognition
This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the audiofolder dataset.
It achieves the following results on the evaluation set:
- Loss: 0.7264
- Accuracy: 0.7539
- Weighted f1: 0.7514
- Micro f1: 0.7539
- Macro f1: 0.7529
- Weighted recall: 0.7539
- Micro recall: 0.7539
- Macro recall: 0.7577
- Weighted precision: 0.7565
- Micro precision: 0.7539
- Macro precision: 0.7558
## Model description
This model predicts the emotion of the person speaking in the audio sample.
For more information on how it was created, check out the following link: https://github.com/DunnBC22/Vision_Audio_and_Multimodal_Projects/tree/main/Audio-Projects/Emotion%20Detection/Speech%20Emotion%20Detection
## Intended uses & limitations
This model is intended to demonstrate my ability to solve a complex problem using technology.
## Training and evaluation data
Dataset Source: https://www.kaggle.com/datasets/dmitrybabko/speech-emotion-recognition-en
## 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 | Weighted f1 | Micro f1 | Macro f1 | Weighted recall | Micro recall | Macro recall | Weighted precision | Micro precision | Macro precision |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:-----------:|:--------:|:--------:|:---------------:|:------------:|:------------:|:------------------:|:---------------:|:---------------:|
| 1.5581 | 0.98 | 43 | 1.4046 | 0.4653 | 0.4080 | 0.4653 | 0.4174 | 0.4653 | 0.4653 | 0.4793 | 0.5008 | 0.4653 | 0.4974 |
| 1.5581 | 1.98 | 86 | 1.1566 | 0.5997 | 0.5836 | 0.5997 | 0.5871 | 0.5997 | 0.5997 | 0.6093 | 0.6248 | 0.5997 | 0.6209 |
| 1.5581 | 2.98 | 129 | 0.9733 | 0.6883 | 0.6845 | 0.6883 | 0.6860 | 0.6883 | 0.6883 | 0.6923 | 0.7012 | 0.6883 | 0.7009 |
| 1.5581 | 3.98 | 172 | 0.8313 | 0.7399 | 0.7392 | 0.7399 | 0.7409 | 0.7399 | 0.7399 | 0.7417 | 0.7415 | 0.7399 | 0.7432 |
| 1.5581 | 4.98 | 215 | 0.8708 | 0.7028 | 0.6963 | 0.7028 | 0.6970 | 0.7028 | 0.7028 | 0.7081 | 0.7148 | 0.7028 | 0.7114 |
| 1.5581 | 5.98 | 258 | 0.7969 | 0.7297 | 0.7267 | 0.7297 | 0.7277 | 0.7297 | 0.7297 | 0.7333 | 0.7393 | 0.7297 | 0.7382 |
| 1.5581 | 6.98 | 301 | 0.7349 | 0.7603 | 0.7613 | 0.7603 | 0.7631 | 0.7603 | 0.7603 | 0.7635 | 0.7699 | 0.7603 | 0.7702 |
| 1.5581 | 7.98 | 344 | 0.7714 | 0.7469 | 0.7444 | 0.7469 | 0.7456 | 0.7469 | 0.7469 | 0.7485 | 0.7554 | 0.7469 | 0.7563 |
| 1.5581 | 8.98 | 387 | 0.7183 | 0.7630 | 0.7615 | 0.7630 | 0.7631 | 0.7630 | 0.7630 | 0.7652 | 0.7626 | 0.7630 | 0.7637 |
| 1.5581 | 9.98 | 430 | 0.7264 | 0.7539 | 0.7514 | 0.7539 | 0.7529 | 0.7539 | 0.7539 | 0.7577 | 0.7565 | 0.7539 | 0.7558 |
### Framework versions
- Transformers 4.26.1
- Pytorch 2.0.0+cu118
- Datasets 2.11.0
- Tokenizers 0.13.3
|
Waynehillsdev/Waynehills_summary_tensorflow
|
[
"tf",
"t5",
"text2text-generation",
"transformers",
"generated_from_keras_callback",
"autotrain_compatible"
] |
text2text-generation
|
{
"architectures": [
"T5ForConditionalGeneration"
],
"model_type": "t5",
"task_specific_params": {
"conversational": {
"max_length": null
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
}
| 5
| null |
---
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- imdb
metrics:
- accuracy
- f1
model-index:
- name: finetuning-sentiment-model-3000-samples
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: imdb
type: imdb
config: plain_text
split: test
args: plain_text
metrics:
- name: Accuracy
type: accuracy
value: 0.8333333333333334
- name: F1
type: f1
value: 0.8275862068965518
---
<!-- 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. -->
# finetuning-sentiment-model-3000-samples
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the imdb dataset.
It achieves the following results on the evaluation set:
- Loss: 0.5229
- Accuracy: 0.8333
- F1: 0.8276
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 2
### Training results
### Framework versions
- Transformers 4.28.1
- Pytorch 2.0.0+cu118
- Datasets 2.11.0
- Tokenizers 0.13.3
|
Doohae/q_encoder
|
[
"pytorch"
] | null |
{
"architectures": null,
"model_type": null,
"task_specific_params": {
"conversational": {
"max_length": null
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
}
| 3
| null |
---
tags:
- Pixelcopter-PLE-v0
- reinforce
- reinforcement-learning
- custom-implementation
- deep-rl-class
model-index:
- name: Reinforce-Pixelcopter-PLE-v0
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: Pixelcopter-PLE-v0
type: Pixelcopter-PLE-v0
metrics:
- type: mean_reward
value: 10.60 +/- 13.48
name: mean_reward
verified: false
---
# **Reinforce** Agent playing **Pixelcopter-PLE-v0**
This is a trained model of a **Reinforce** agent playing **Pixelcopter-PLE-v0** .
To learn to use this model and train yours check Unit 4 of the Deep Reinforcement Learning Course: https://huggingface.co/deep-rl-course/unit4/introduction
|
DoyyingFace/bert-asian-hate-tweets-asian-unclean-warmup-100
|
[
"pytorch",
"bert",
"text-classification",
"transformers"
] |
text-classification
|
{
"architectures": [
"BertForSequenceClassification"
],
"model_type": "bert",
"task_specific_params": {
"conversational": {
"max_length": null
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
}
| 28
| null |
---
license: creativeml-openrail-m
---
https://civitai.com/models/43409/hoshino-ai-or-or-oshi-no-ko-or
|
DoyyingFace/bert-asian-hate-tweets-asian-unclean-warmup-25
|
[
"pytorch",
"bert",
"text-classification",
"transformers"
] |
text-classification
|
{
"architectures": [
"BertForSequenceClassification"
],
"model_type": "bert",
"task_specific_params": {
"conversational": {
"max_length": null
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
}
| 30
| null |
---
license: creativeml-openrail-m
---
https://civitai.com/models/43520/jin-bora-counter-side
|
DoyyingFace/bert-asian-hate-tweets-asian-unclean-warmup-50
|
[
"pytorch",
"bert",
"text-classification",
"transformers"
] |
text-classification
|
{
"architectures": [
"BertForSequenceClassification"
],
"model_type": "bert",
"task_specific_params": {
"conversational": {
"max_length": null
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
}
| 28
| null |
---
license: creativeml-openrail-m
---
https://civitai.com/models/43400/shinju-inui-or-my-dress-up-darling
|
DoyyingFace/bert-asian-hate-tweets-asian-unclean-warmup-75
|
[
"pytorch",
"bert",
"text-classification",
"transformers"
] |
text-classification
|
{
"architectures": [
"BertForSequenceClassification"
],
"model_type": "bert",
"task_specific_params": {
"conversational": {
"max_length": null
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
}
| 37
| null |
---
license: creativeml-openrail-m
---
https://civitai.com/models/16849/rangiku-matsumoto-bleach
|
DoyyingFace/bert-asian-hate-tweets-asian-unclean-with-clean-valid
|
[
"pytorch",
"bert",
"text-classification",
"transformers"
] |
text-classification
|
{
"architectures": [
"BertForSequenceClassification"
],
"model_type": "bert",
"task_specific_params": {
"conversational": {
"max_length": null
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
}
| 33
| null |
---
license: creativeml-openrail-m
---
https://civitai.com/models/43773/asahina-mikuru-suzumiya-haruhi-series
|
DoyyingFace/bert-asian-hate-tweets-asonam-clean
|
[
"pytorch",
"bert",
"text-classification",
"transformers"
] |
text-classification
|
{
"architectures": [
"BertForSequenceClassification"
],
"model_type": "bert",
"task_specific_params": {
"conversational": {
"max_length": null
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
}
| 27
| null |
---
license: creativeml-openrail-m
---
https://civitai.com/models/43800/ais-wallenstein-or-danmachi
|
DoyyingFace/bert-asian-hate-tweets-asonam-unclean
|
[
"pytorch",
"bert",
"text-classification",
"transformers"
] |
text-classification
|
{
"architectures": [
"BertForSequenceClassification"
],
"model_type": "bert",
"task_specific_params": {
"conversational": {
"max_length": null
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
}
| 30
| null |
---
license: creativeml-openrail-m
---
https://civitai.com/models/43754/ishizu-ishtar-or-yu-gi-oh
|
DoyyingFace/bert-asian-hate-tweets-concat-clean-with-unclean-valid
|
[
"pytorch",
"bert",
"text-classification",
"transformers"
] |
text-classification
|
{
"architectures": [
"BertForSequenceClassification"
],
"model_type": "bert",
"task_specific_params": {
"conversational": {
"max_length": null
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
}
| 25
| 2023-04-17T21:24:56Z
|
---
library_name: sample-factory
tags:
- deep-reinforcement-learning
- reinforcement-learning
- sample-factory
model-index:
- name: APPO
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: doom_health_gathering_supreme
type: doom_health_gathering_supreme
metrics:
- type: mean_reward
value: 9.87 +/- 4.46
name: mean_reward
verified: false
---
A(n) **APPO** model trained on the **doom_health_gathering_supreme** environment.
This model was trained using Sample-Factory 2.0: https://github.com/alex-petrenko/sample-factory.
Documentation for how to use Sample-Factory can be found at https://www.samplefactory.dev/
## Downloading the model
After installing Sample-Factory, download the model with:
```
python -m sample_factory.huggingface.load_from_hub -r Emperor/rl_course_vizdoom_health_gathering_supreme
```
## Using the model
To run the model after download, use the `enjoy` script corresponding to this environment:
```
python -m .usr.local.lib.python3.9.dist-packages.ipykernel_launcher --algo=APPO --env=doom_health_gathering_supreme --train_dir=./train_dir --experiment=rl_course_vizdoom_health_gathering_supreme
```
You can also upload models to the Hugging Face Hub using the same script with the `--push_to_hub` flag.
See https://www.samplefactory.dev/10-huggingface/huggingface/ for more details
## Training with this model
To continue training with this model, use the `train` script corresponding to this environment:
```
python -m .usr.local.lib.python3.9.dist-packages.ipykernel_launcher --algo=APPO --env=doom_health_gathering_supreme --train_dir=./train_dir --experiment=rl_course_vizdoom_health_gathering_supreme --restart_behavior=resume --train_for_env_steps=10000000000
```
Note, you may have to adjust `--train_for_env_steps` to a suitably high number as the experiment will resume at the number of steps it concluded at.
|
DoyyingFace/bert-asian-hate-tweets-concat-clean
|
[
"pytorch",
"bert",
"text-classification",
"transformers"
] |
text-classification
|
{
"architectures": [
"BertForSequenceClassification"
],
"model_type": "bert",
"task_specific_params": {
"conversational": {
"max_length": null
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
}
| 25
| 2023-04-17T21:25:26Z
|
---
tags:
- autotrain
- text-classification
language:
- unk
widget:
- text: "I love AutoTrain 🤗"
datasets:
- Muhsabrys/autotrain-data-xlmroberta-iuexist
co2_eq_emissions:
emissions: 1.1811615672607385
---
# Model Trained Using AutoTrain
- Problem type: Multi-class Classification
- Model ID: 50302120401
- CO2 Emissions (in grams): 1.1812
## Validation Metrics
- Loss: 0.637
- Accuracy: 0.772
- Macro F1: 0.541
- Micro F1: 0.772
- Weighted F1: 0.731
- Macro Precision: 0.514
- Micro Precision: 0.772
- Weighted Precision: 0.694
- Macro Recall: 0.571
- Micro Recall: 0.772
- Weighted Recall: 0.772
## Usage
You can use cURL to access this model:
```
$ curl -X POST -H "Authorization: Bearer YOUR_API_KEY" -H "Content-Type: application/json" -d '{"inputs": "I love AutoTrain"}' https://api-inference.huggingface.co/models/Muhsabrys/autotrain-xlmroberta-iuexist-50302120401
```
Or Python API:
```
from transformers import AutoModelForSequenceClassification, AutoTokenizer
model = AutoModelForSequenceClassification.from_pretrained("Muhsabrys/autotrain-xlmroberta-iuexist-50302120401", use_auth_token=True)
tokenizer = AutoTokenizer.from_pretrained("Muhsabrys/autotrain-xlmroberta-iuexist-50302120401", use_auth_token=True)
inputs = tokenizer("I love AutoTrain", return_tensors="pt")
outputs = model(**inputs)
```
|
albert-base-v1
|
[
"pytorch",
"tf",
"safetensors",
"albert",
"fill-mask",
"en",
"dataset:bookcorpus",
"dataset:wikipedia",
"arxiv:1909.11942",
"transformers",
"exbert",
"license:apache-2.0",
"autotrain_compatible",
"has_space"
] |
fill-mask
|
{
"architectures": [
"AlbertForMaskedLM"
],
"model_type": "albert",
"task_specific_params": {
"conversational": {
"max_length": null
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
}
| 38,156
| 2023-04-17T21:35:03Z
|
---
datasets:
- IlyaGusev/ru_turbo_alpaca
- IlyaGusev/ru_turbo_saiga
- IlyaGusev/oasst1_ru_main_branch
- IlyaGusev/ru_sharegpt_cleaned
language:
- ru
pipeline_tag: conversational
license: cc-by-4.0
---
# Saiga 30B, Russian LLaMA-based chatbot
Based on [LLaMA 30B](https://huggingface.co/huggyllama/llama-30b).
* This is an adapter-only version.
Colab: [link](https://colab.research.google.com/drive/1zvF0I52NJ7ngAk_zWzEA_QOYOMCdITZN?usp=sharing)
llama.cpp version: [link](https://huggingface.co/IlyaGusev/saiga_30b_lora_llamacpp/)
Training code: [link](https://github.com/IlyaGusev/rulm/tree/master/self_instruct)
```python
from peft import PeftModel, PeftConfig
from transformers import AutoModelForCausalLM, AutoTokenizer, GenerationConfig
MODEL_NAME = "IlyaGusev/saiga_30b_lora"
DEFAULT_MESSAGE_TEMPLATE = "<s>{role}\n{content}</s>\n"
DEFAULT_SYSTEM_PROMPT = "Ты — Сайга, русскоязычный автоматический ассистент. Ты разговариваешь с людьми и помогаешь им."
class Conversation:
def __init__(
self,
message_template=DEFAULT_MESSAGE_TEMPLATE,
system_prompt=DEFAULT_SYSTEM_PROMPT,
start_token_id=1,
bot_token_id=9225
):
self.message_template = message_template
self.start_token_id = start_token_id
self.bot_token_id = bot_token_id
self.messages = [{
"role": "system",
"content": system_prompt
}]
def get_start_token_id(self):
return self.start_token_id
def get_bot_token_id(self):
return self.bot_token_id
def add_user_message(self, message):
self.messages.append({
"role": "user",
"content": message
})
def add_bot_message(self, message):
self.messages.append({
"role": "bot",
"content": message
})
def get_prompt(self, tokenizer):
final_text = ""
for message in self.messages:
message_text = self.message_template.format(**message)
final_text += message_text
final_text += tokenizer.decode([self.start_token_id, self.bot_token_id])
return final_text.strip()
def generate(model, tokenizer, prompt, generation_config):
data = tokenizer(prompt, return_tensors="pt")
data = {k: v.to(model.device) for k, v in data.items()}
output_ids = model.generate(
**data,
generation_config=generation_config
)[0]
output_ids = output_ids[len(data["input_ids"][0]):]
output = tokenizer.decode(output_ids, skip_special_tokens=True)
return output.strip()
config = PeftConfig.from_pretrained(MODEL_NAME)
model = AutoModelForCausalLM.from_pretrained(
config.base_model_name_or_path,
load_in_8bit=True,
torch_dtype=torch.float16,
device_map="auto"
)
model = PeftModel.from_pretrained(
model,
MODEL_NAME,
torch_dtype=torch.float16
)
model.eval()
tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME)
generation_config = GenerationConfig.from_pretrained(MODEL_NAME)
print(generation_config)
inputs = ["Почему трава зеленая?", "Сочини длинный рассказ, обязательно упоминая следующие объекты. Дано: Таня, мяч"]
for inp in inputs:
conversation = Conversation()
conversation.add_user_message(inp)
prompt = conversation.get_prompt(tokenizer)
output = generate(model, tokenizer, prompt, generation_config)
print(inp)
print(output)
print()
print("==============================")
print()
```
Examples:
```
User: Почему трава зеленая?
Saiga: Трава зеленая потому, что она содержит хлорофилл - пигмент, который отвечает за зеленый цвет листьев растений. Хлорофилл используется для фотосинтеза - процесса преобразования света в энергию, необходимую для роста и развития растения. Кроме того, зеленый цвет является наиболее распространенным цветом среди всех растительных видов на Земле, поэтому большинство трав имеют зеленый цвет.
```
```
User: Сочини длинный рассказ, обязательно упоминая следующие объекты. Дано: Таня, мяч
Saiga: Однажды летом, когда все дети уже вышли из школы и начали проводить время на улице, Таня решила поиграть в футбол со своими друзьями. Она взяла свой любимый мяч и отправилась к парку, где они обычно играют.
Когда она пришла туда, ее друзья уже были готовы к игре. Они разделились на две команды и начали играть. Таня была очень энергичной и активной, она бежала по полю, прыгала и ловила мяч.
Но однажды, когда она пыталась заблокировать удар соперника, мяч ударился ей прямо в лицо. Она упала на землю и не могла двигаться. Ее друзья сразу же подобрали ее и провели медицинскую помощь.
Так как Тане было больно, они решили не продолжать игру и вернуться домой. Но Таня не хотела пропустить возможность играть в футбол, поэтому она решила найти другой способ.
Она купила себе новый мяч и начала тренироваться дома. Она старалась делать упражнения каждый день, чтобы улучшить свою технику и скорость. Вскоре она стала лучшей футболисткой в своей команде.
Ее друзья были поражены ее умением играть в футбол и часто приглашали ее на матчи. Таня была очень горда своей новой профессией и никогда не переставала тренироваться.
В конце концов, благодаря своим усилиям, она стала настоящей звездой футбола и даже получила предложение от известного клуба. Она приняла его и начала играть на профессиональном уровне.
Таким образом, мяч стал для Тани не только игрушкой, но и источником ее успеха и счастья.
```
```
User: Реши уравнение 4x + 5 = 21
Saiga: Для решения этого уравнения нужно найти значение переменной x. Для этого нужно вычесть из левой части уравнения 5, чтобы получить 4x = 16. Далее, делим обе стороны на 4, чтобы получить x = 4. Таким образом, x равно 4.
```
```
User: Заполни пропуски в предложении. Дано: Я пытался ____ от маньяка, но он меня настиг
Saiga: Я пытался убежать от маньяка, но он меня настиг.
```
v1:
- revision 8573592257aa6476e8179f09a922aff513592886
- wandb [link](https://wandb.ai/ilyagusev/rulm_self_instruct/runs/x2c19kfk)
- 4 datasets: ru_turbo_alpaca, ru_turbo_saiga, ru_sharegpt_cleaned, oasst1_ru_main_branch
- Datasets merging script: [create_chat_set.py](https://github.com/IlyaGusev/rulm/blob/ef58f3d82d6e7b3784d42167ff69188d3766ab61/self_instruct/src/data_processing/create_chat_set.py)
- Loss: 0.817
- Context length: 2000
- Conversational template: `"<s>{role}\n{content}</s>"`
- Possible roles: `["system", "user", "bot"]`
- System prompt: `"Ты — Сайга, русскоязычный автоматический ассистент. Ты разговариваешь с людьми и помогаешь им."`
|
albert-xlarge-v2
|
[
"pytorch",
"tf",
"albert",
"fill-mask",
"en",
"dataset:bookcorpus",
"dataset:wikipedia",
"arxiv:1909.11942",
"transformers",
"license:apache-2.0",
"autotrain_compatible",
"has_space"
] |
fill-mask
|
{
"architectures": [
"AlbertForMaskedLM"
],
"model_type": "albert",
"task_specific_params": {
"conversational": {
"max_length": null
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
}
| 2,973
| 2023-04-17T21:44:34Z
|
---
license: openrail
---
This is a textual inversion trained on black and white rough sketches, designed to be used
as a negative embedding with Stable Diffusion 1.5 models. It generally improves the quality
of non-sketches.
|
bert-base-cased-finetuned-mrpc
|
[
"pytorch",
"tf",
"jax",
"bert",
"fill-mask",
"transformers",
"autotrain_compatible",
"has_space"
] |
fill-mask
|
{
"architectures": [
"BertForMaskedLM"
],
"model_type": "bert",
"task_specific_params": {
"conversational": {
"max_length": null
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
}
| 11,644
| 2023-04-17T21:49:47Z
|
---
license: other
language:
- en
pipeline_tag: text2text-generation
tags:
- alpaca
- llama
- chat
- gpt4
---
This is the HF format merged model for [chansung's gpt4-alpaca-lora-13b](https://huggingface.co/chansung/gpt4-alpaca-lora-13b).
# Original model card
This repository comes with LoRA checkpoint to make LLaMA into a chatbot like language model. The checkpoint is the output of instruction following fine-tuning process with the following settings on 8xA100(40G) DGX system.
- Training script: borrowed from the official [Alpaca-LoRA](https://github.com/tloen/alpaca-lora) implementation
- Training script:
```shell
python finetune.py \
--base_model='decapoda-research/llama-30b-hf' \
--data_path='alpaca_data_gpt4.json' \
--num_epochs=10 \
--cutoff_len=512 \
--group_by_length \
--output_dir='./gpt4-alpaca-lora-30b' \
--lora_target_modules='[q_proj,k_proj,v_proj,o_proj]' \
--lora_r=16 \
--batch_size=... \
--micro_batch_size=...
```
You can find how the training went from W&B report [here](https://wandb.ai/chansung18/gpt4_alpaca_lora/runs/w3syd157?workspace=user-chansung18).
|
bert-base-cased
|
[
"pytorch",
"tf",
"jax",
"safetensors",
"bert",
"fill-mask",
"en",
"dataset:bookcorpus",
"dataset:wikipedia",
"arxiv:1810.04805",
"transformers",
"exbert",
"license:apache-2.0",
"autotrain_compatible",
"has_space"
] |
fill-mask
|
{
"architectures": [
"BertForMaskedLM"
],
"model_type": "bert",
"task_specific_params": {
"conversational": {
"max_length": null
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
}
| 8,621,271
| null |
---
tags:
- image-classification
- pytorch
- huggingpics
metrics:
- accuracy
model-index:
- name: GenderNew_v002
results:
- task:
name: Image Classification
type: image-classification
metrics:
- name: Accuracy
type: accuracy
value: 0.9855228066444397
---
# GenderNew_v002
Autogenerated by HuggingPics🤗🖼️
Create your own image classifier for **anything** by running [the demo on Google Colab](https://colab.research.google.com/github/nateraw/huggingpics/blob/main/HuggingPics.ipynb).
Report any issues with the demo at the [github repo](https://github.com/nateraw/huggingpics).
## Example Images
#### man
#### woman
|
bert-base-german-dbmdz-uncased
|
[
"pytorch",
"jax",
"safetensors",
"bert",
"fill-mask",
"de",
"transformers",
"license:mit",
"autotrain_compatible",
"has_space"
] |
fill-mask
|
{
"architectures": [
"BertForMaskedLM"
],
"model_type": "bert",
"task_specific_params": {
"conversational": {
"max_length": null
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
}
| 68,305
| null |
---
license: openrail
---
This is a Stable Diffusion 1.5 textual inversion embedding, \<neg-anime\>, trained using InvokeAI on a set of low quality generated sketches and pathological outputs from an animated model (https://civitai.com/models/35893/526mix-animated). Its use in a negative prompt helps push that model and others toward a more "realistic" style, sometimes. This was inspired by and heavily patterned after another embedding found here: https://huggingface.co/JPPhoto/neg-sketch-2
|
bert-large-uncased-whole-word-masking-finetuned-squad
|
[
"pytorch",
"tf",
"jax",
"safetensors",
"bert",
"question-answering",
"en",
"dataset:bookcorpus",
"dataset:wikipedia",
"arxiv:1810.04805",
"transformers",
"license:apache-2.0",
"autotrain_compatible",
"has_space"
] |
question-answering
|
{
"architectures": [
"BertForQuestionAnswering"
],
"model_type": "bert",
"task_specific_params": {
"conversational": {
"max_length": null
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
}
| 480,510
| 2023-04-17T22:13:51Z
|
---
license: apache-2.0
datasets:
- tatsu-lab/alpaca
---
## Flan-UL2-Alpaca
Model weights are from epoch 0.
This [Github repository](https://github.com/ConiferLabsWA/flan-ul2-alpaca) contains code for leveraging the [Stanford Alpaca](https://github.com/tatsu-lab/stanford_alpaca) synthetic dataset to fine tune the [Flan-UL2](https://huggingface.co/google/flan-ul2) model, leveraging recent advances in instruction tuning. The Flan UL2 model has been shown to outperform Flan-T5 XXL on a number of metrics and has a 4x improvement in receptive field (2048 vs 512).
### Resource Considerations
A goal of this project was to produce this model with a limited budget demonstrating the ability train a robust LLM using systems available to even small businesses and individuals. This had the added benefit of personally saving me money as well :). To achieve this a server was rented on [vultr.com](vultr.com) with the following pricing/specs:
- Pricing: $1.302/hour
- OS: Ubuntu 22.10 x64
- 6 vCPUs
- 60 GB CPU RAM
- 40 GB GPU RAM (1/2 x A100)
To dramatically reduce memory footprint and compute requirements [Low Rank Adaption(LoRA)](https://huggingface.co/docs/diffusers/training/lora) was used as opposed to finetuning the entire network. Additionally, the Flan-UL2 model was loaded and trained in 8 bit mode, also greatly reducing memory requirements. Finally, a batch size of 1 was used with 8 gradient accumulation steps. Here is a list of training parameters used:
- Epochs: 2
- Learning Rate: 1e-5
- Batch Size: 1
- Gradient Accumulation Steps: 8
- 8 Bit Mode: Yes
### Usage
```
from transformers import AutoModelForSeq2SeqLM, AutoTokenizer
from peft import PeftModel, PeftConfig
prompt = "Write a story about an alpaca that went to the zoo."
peft_model_id = 'coniferlabs/flan-ul2-alpaca-lora'
config = PeftConfig.from_pretrained(peft_model_id)
model = AutoModelForSeq2SeqLM.from_pretrained(config.base_model_name_or_path, device_map="auto", load_in_8bit=True)
model = PeftModel.from_pretrained(model, peft_model_id, device_map={'': 0})
tokenizer = AutoTokenizer.from_pretrained(config.base_model_name_or_path)
model.eval()
tokenized_text = tokenizer.encode(prompt, return_tensors="pt").to("cuda")
outputs = model.generate(input_ids=tokenized_text, parameters={"min_length": 10, "max_length": 250})
tokenizer.batch_decode(outputs, skip_special_tokens=True)
###
```
### Flan-UL2 Training Results
| Epoch | Train Loss | Eval Loss |
|-------|------------|------------|
| 1 | 12102.7285 | 2048.0518 |
| 2 | 9318.9199 | 2033.5337 |
Loss Trendline: y = -1.1302001815753724e-05x + 0.73000991550589
|
bert-large-uncased-whole-word-masking
|
[
"pytorch",
"tf",
"jax",
"safetensors",
"bert",
"fill-mask",
"en",
"dataset:bookcorpus",
"dataset:wikipedia",
"arxiv:1810.04805",
"transformers",
"license:apache-2.0",
"autotrain_compatible",
"has_space"
] |
fill-mask
|
{
"architectures": [
"BertForMaskedLM"
],
"model_type": "bert",
"task_specific_params": {
"conversational": {
"max_length": null
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
}
| 76,685
| null |
---
license: apache-2.0
datasets:
- databricks/dolly-15k
---
## Flan-UL2-Dolly - Building a commercially viable LLM
Model weights are outputs from epoch 1.
This [Github repository](https://github.com/ConiferLabsWA/flan-ul2-dolly) contains code for leveraging the [Dolly 15K](https://github.com/databrickslabs/dolly/tree/master/data) dataset [released by Databricks](https://github.com/databrickslabs/dolly/tree/master/data) to fine tune the [Flan-UL2](https://huggingface.co/google/flan-ul2) model, leveraging recent advances in instruction tuning. Flan-UL2 has been shown to outperform Flan-T5 XXL on a number of metrics and has a 4x improvement in receptive field (2048 vs 512 tokens). Additionally, both the Flan-UL2 model and the Dolly 15K dataset have the significant advantage of a commercially viable license.
### Resource Considerations
A goal of this project was to produce this model with a limited budget demonstrating the ability train a robust, commercially viable LLM using systems available to even small businesses and individuals. This had the added benefit of personally saving me money as well :). To achieve this a server was rented on [vultr.com](vultr.com) with the following pricing/specs:
- Pricing: $1.302/hour
- OS: Ubuntu 22.10 x64
- 6 vCPUs
- 60 GB CPU RAM
- 40 GB GPU RAM (1/2 x A100)
To dramatically reduce memory footprint and compute requirements [Low Rank Adaption(LoRA)](https://huggingface.co/docs/diffusers/training/lora) was used as opposed to finetuning the entire network. Additionally, the Flan-UL2 model was loaded and trained in 8 bit mode, also greatly reducing memory requirements. Finally, a batch size of 1 was used with 8 gradient accumulation steps. Here is a list of training parameters used:
- Epochs: 3
- Learning Rate: 1e-4
- Batch Size: 1
- Gradient Accumulation Steps: 8
- 8 Bit Mode: Yes
### Why?
Rapid recent advancements in the natural language processing (NLP) space have been extraordinary. Large Language Models (LLMs) like Meta's LLaMA are getting a lot of attention with their remarkable generative abilities however, many people are looking at the implications of these projects and looking for ways to leverage the technology in a commercial setting. Unfortunately, many LLMs (ie LLaMA, Vicuna) are limited by their licensing, restricting opportunities for usage within businesses and products.
To address this issue, the entirely open-source [Flan-UL2 model](https://huggingface.co/google/flan-ul2), built by Google on the [Flan-T5](https://arxiv.org/abs/2210.11416) encoder-decoder framework, is an excellent alternative to LLMs with more restrictive licensing. Flan-UL2 is accessible for commercial applications and fine-tuned on academic NLP tasks, providing exceptional performance in comparison to models of similar size across various benchmarks. Additionally, with a receptive field of 2048 token is suitable for a number of LLM tasks including [Retrieval Augmented Generation (RAG)](https://arxiv.org/abs/2005.11401).
Additionally, the use of the Dolly 15K dataset has the advantage of being a fully open source, human generated dataset with permissive licensing for commercial applications. This is in contract to synthetic datasets (ie Alpaca) generated using ChatGPT API's which are limited by OpenAI's Terms of Service and do not have the natural variation and depth of human generated content.
### Usage
```
from transformers import AutoModelForSeq2SeqLM, AutoTokenizer
from peft import PeftModel, PeftConfig
prompt = "Write a story about an lamb named Dolly that went to the zoo."
peft_model_id = 'coniferlabs/flan-ul2-dolly-lora'
config = PeftConfig.from_pretrained(peft_model_id)
model = AutoModelForSeq2SeqLM.from_pretrained(config.base_model_name_or_path, device_map="auto", load_in_8bit=True)
model = PeftModel.from_pretrained(model, peft_model_id, device_map={'': 0})
tokenizer = AutoTokenizer.from_pretrained(config.base_model_name_or_path)
model.eval()
tokenized_text = tokenizer.encode(prompt, return_tensors="pt").to("cuda")
outputs = model.generate(input_ids=tokenized_text, parameters={"min_length": 10, "max_length": 250})
tokenizer.batch_decode(outputs, skip_special_tokens=True)
###
```
### Training Results
| Epoch | Train Loss | Eval Loss |
|-------|------------|------------|
| 1 | 6456.1367 | 852.3842 |
| 2 | 3738.73442 | 835.1929 |
| 3 | 3719.4336 | 834.9722 |
Loss Trendline: y = -1.1981345834547134e-05x + 0.6018711605440453
|
bert-large-uncased
|
[
"pytorch",
"tf",
"jax",
"safetensors",
"bert",
"fill-mask",
"en",
"dataset:bookcorpus",
"dataset:wikipedia",
"arxiv:1810.04805",
"transformers",
"license:apache-2.0",
"autotrain_compatible",
"has_space"
] |
fill-mask
|
{
"architectures": [
"BertForMaskedLM"
],
"model_type": "bert",
"task_specific_params": {
"conversational": {
"max_length": null
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
}
| 1,058,496
| 2023-04-17T22:14:52Z
|
---
language:
- en
license:
- cc-by-sa-4.0
tags:
- causal-lm
---
# StableLM-Base-Alpha
## Model Description
`StableLM-Base-Alpha` is a suite of 3B and 7B parameter decoder-only language models pre-trained on a diverse collection of English and Code datasets with a sequence length of 4096 to push beyond the context window limitations of existing open-source language models.
## Usage
Get started generating text with `StableLM-Base-Alpha` by using the following code snippet:
```python
from transformers import AutoModelForCausalLM, AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained("StabilityAI/stablelm-base-alpha-3b")
model = AutoModelForCausalLM.from_pretrained("StabilityAI/stablelm-base-alpha-3b")
model.half().cuda()
inputs = tokenizer("What's your mood today?", return_tensors="pt").to("cuda")
tokens = model.generate(
**inputs,
max_new_tokens=64,
temperature=0.7,
do_sample=True,
)
print(tokenizer.decode(tokens[0], skip_special_tokens=True))
```
## Model Details
* **Developed by**: [Stability AI](https://stability.ai/)
* **Model type**: StableLM-Base-Alpha models are auto-regressive language models based on the NeoX transformer architecture.
* **Language(s)**: English
* **Library**: [GPT-NeoX](https://github.com/EleutherAI/gpt-neox)
* **License**: Base model checkpoints (StableLM-Base-Alpha) are licensed under the Creative Commons license (CC BY-SA-4.0). Under the license, you must give credit to Stability AI, provide a link to the license, and indicate if changes were made. You may do so in any reasonable manner, but not in any way that suggests the Stability AI endorses you or your use.
* **Contact**: For questions and comments about the model, please email `lm@stability.ai`
## Training
| Parameters | Hidden Size | Layers | Heads | Sequence Length |
|------------|-------------|--------|-------|-----------------|
| 3B | 4096 | 16 | 32 | 4096 |
| 7B | 6144 | 16 | 48 | 4096 |
### Training Dataset
`StableLM-Base-Alpha` is pre-trained on a new experimental dataset built atop [The Pile](https://huggingface.co/datasets/EleutherAI/the_pile) and is threes times larger at approximately 1.5T tokens.
### Training Procedure
Models are pre-trained on the aforementioned dataset in mixed-precision (FP16), optimized with Adam, and trained using the NeoX tokenizer with a vocabulary size of 50,257. We outline the complete hyperparameters choices in the project's [GitHub repository](https://github.com/Stability-AI/StableLM/blob/main/configs/stablelm-base-alpha-3b.yaml).
## Use and Limitations
### Intended Use
These models are intended to be used by all individuals as foundational models for application-specific fine-tuning without strict limitations on commercial use.
### Limitations and bias
The pre-training dataset may contain offensive or inappropriate content even after applying data cleansing filters which can be reflected in generated text. We recommend users exercise reasonable caution when using these models in production systems. Do not use the models for any applications that may cause harm or distress to individuals or groups.
## Citations
```bibtext
@software{gpt-neox-library,
title = {{GPT-NeoX: Large Scale Autoregressive Language Modeling in PyTorch}},
author = {Andonian, Alex and Anthony, Quentin and Biderman, Stella and Black, Sid and Gali, Preetham and Gao, Leo and Hallahan, Eric and Levy-Kramer, Josh and Leahy, Connor and Nestler, Lucas and Parker, Kip and Pieler, Michael and Purohit, Shivanshu and Songz, Tri and Phil, Wang and Weinbach, Samuel},
url = {https://www.github.com/eleutherai/gpt-neox},
doi = {10.5281/zenodo.5879544},
month = {8},
year = {2021},
version = {0.0.1},
}
```
|
camembert-base
|
[
"pytorch",
"tf",
"safetensors",
"camembert",
"fill-mask",
"fr",
"dataset:oscar",
"arxiv:1911.03894",
"transformers",
"license:mit",
"autotrain_compatible",
"has_space"
] |
fill-mask
|
{
"architectures": [
"CamembertForMaskedLM"
],
"model_type": "camembert",
"task_specific_params": {
"conversational": {
"max_length": null
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
}
| 1,440,898
| null |
---
library_name: sample-factory
tags:
- deep-reinforcement-learning
- reinforcement-learning
- sample-factory
model-index:
- name: APPO
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: doom_health_gathering_supreme
type: doom_health_gathering_supreme
metrics:
- type: mean_reward
value: 11.01 +/- 4.52
name: mean_reward
verified: false
---
A(n) **APPO** model trained on the **doom_health_gathering_supreme** environment.
This model was trained using Sample-Factory 2.0: https://github.com/alex-petrenko/sample-factory.
Documentation for how to use Sample-Factory can be found at https://www.samplefactory.dev/
## Downloading the model
After installing Sample-Factory, download the model with:
```
python -m sample_factory.huggingface.load_from_hub -r redfungus/rl_course_vizdoom_health_gathering_supreme
```
## Using the model
To run the model after download, use the `enjoy` script corresponding to this environment:
```
python -m .usr.local.lib.python3.9.dist-packages.ipykernel_launcher --algo=APPO --env=doom_health_gathering_supreme --train_dir=./train_dir --experiment=rl_course_vizdoom_health_gathering_supreme
```
You can also upload models to the Hugging Face Hub using the same script with the `--push_to_hub` flag.
See https://www.samplefactory.dev/10-huggingface/huggingface/ for more details
## Training with this model
To continue training with this model, use the `train` script corresponding to this environment:
```
python -m .usr.local.lib.python3.9.dist-packages.ipykernel_launcher --algo=APPO --env=doom_health_gathering_supreme --train_dir=./train_dir --experiment=rl_course_vizdoom_health_gathering_supreme --restart_behavior=resume --train_for_env_steps=10000000000
```
Note, you may have to adjust `--train_for_env_steps` to a suitably high number as the experiment will resume at the number of steps it concluded at.
|
distilbert-base-cased-distilled-squad
|
[
"pytorch",
"tf",
"rust",
"safetensors",
"openvino",
"distilbert",
"question-answering",
"en",
"dataset:squad",
"arxiv:1910.01108",
"arxiv:1910.09700",
"transformers",
"license:apache-2.0",
"model-index",
"autotrain_compatible",
"has_space"
] |
question-answering
|
{
"architectures": [
"DistilBertForQuestionAnswering"
],
"model_type": "distilbert",
"task_specific_params": {
"conversational": {
"max_length": null
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
}
| 257,745
| null |
---
pipeline_tag: sentence-similarity
tags:
- sentence-transformers
- feature-extraction
- sentence-similarity
- transformers
---
# msmarco-bert-base-dot-v5
This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 768 dimensional dense vector space and was designed for **semantic search**. It has been trained on 500K (query, answer) pairs from the [MS MARCO dataset](https://github.com/microsoft/MSMARCO-Passage-Ranking/). For an introduction to semantic search, have a look at: [SBERT.net - Semantic Search](https://www.sbert.net/examples/applications/semantic-search/README.html)
## Usage (Sentence-Transformers)
Using this model becomes easy when you have [sentence-transformers](https://www.SBERT.net) installed:
```
pip install -U sentence-transformers
```
Then you can use the model like this:
```python
from sentence_transformers import SentenceTransformer, util
query = "How many people live in London?"
docs = ["Around 9 Million people live in London", "London is known for its financial district"]
#Load the model
model = SentenceTransformer('sentence-transformers/msmarco-bert-base-dot-v5')
#Encode query and documents
query_emb = model.encode(query)
doc_emb = model.encode(docs)
#Compute dot score between query and all document embeddings
scores = util.dot_score(query_emb, doc_emb)[0].cpu().tolist()
#Combine docs & scores
doc_score_pairs = list(zip(docs, scores))
#Sort by decreasing score
doc_score_pairs = sorted(doc_score_pairs, key=lambda x: x[1], reverse=True)
#Output passages & scores
print("Query:", query)
for doc, score in doc_score_pairs:
print(score, doc)
```
## Usage (HuggingFace Transformers)
Without [sentence-transformers](https://www.SBERT.net), you can use the model like this: First, you pass your input through the transformer model, then you have to apply the correct pooling-operation on-top of the contextualized word embeddings.
```python
from transformers import AutoTokenizer, AutoModel
import torch
#Mean Pooling - Take attention mask into account for correct averaging
def mean_pooling(model_output, attention_mask):
token_embeddings = model_output.last_hidden_state
input_mask_expanded = attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float()
return torch.sum(token_embeddings * input_mask_expanded, 1) / torch.clamp(input_mask_expanded.sum(1), min=1e-9)
#Encode text
def encode(texts):
# Tokenize sentences
encoded_input = tokenizer(texts, padding=True, truncation=True, return_tensors='pt')
# Compute token embeddings
with torch.no_grad():
model_output = model(**encoded_input, return_dict=True)
# Perform pooling
embeddings = mean_pooling(model_output, encoded_input['attention_mask'])
return embeddings
# Sentences we want sentence embeddings for
query = "How many people live in London?"
docs = ["Around 9 Million people live in London", "London is known for its financial district"]
# Load model from HuggingFace Hub
tokenizer = AutoTokenizer.from_pretrained("sentence-transformers/msmarco-bert-base-dot-v5")
model = AutoModel.from_pretrained("sentence-transformers/msmarco-bert-base-dot-v5")
#Encode query and docs
query_emb = encode(query)
doc_emb = encode(docs)
#Compute dot score between query and all document embeddings
scores = torch.mm(query_emb, doc_emb.transpose(0, 1))[0].cpu().tolist()
#Combine docs & scores
doc_score_pairs = list(zip(docs, scores))
#Sort by decreasing score
doc_score_pairs = sorted(doc_score_pairs, key=lambda x: x[1], reverse=True)
#Output passages & scores
print("Query:", query)
for doc, score in doc_score_pairs:
print(score, doc)
```
## Technical Details
In the following some technical details how this model must be used:
| Setting | Value |
| --- | :---: |
| Dimensions | 768 |
| Max Sequence Length | 512 |
| Produces normalized embeddings | No |
| Pooling-Method | Mean pooling |
| Suitable score functions | dot-product (e.g. `util.dot_score`) |
## Evaluation Results
<!--- Describe how your model was evaluated -->
For an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: [https://seb.sbert.net](https://seb.sbert.net?model_name=msmarco-bert-base-base-dot-v5)
## Training
See `train_script.py` in this repository for the used training script.
The model was trained with the parameters:
**DataLoader**:
`torch.utils.data.dataloader.DataLoader` of length 7858 with parameters:
```
{'batch_size': 64, 'sampler': 'torch.utils.data.sampler.RandomSampler', 'batch_sampler': 'torch.utils.data.sampler.BatchSampler'}
```
**Loss**:
`sentence_transformers.losses.MarginMSELoss.MarginMSELoss`
Parameters of the fit()-Method:
```
{
"callback": null,
"epochs": 30,
"evaluation_steps": 0,
"evaluator": "NoneType",
"max_grad_norm": 1,
"optimizer_class": "<class 'transformers.optimization.AdamW'>",
"optimizer_params": {
"lr": 1e-05
},
"scheduler": "WarmupLinear",
"steps_per_epoch": null,
"warmup_steps": 10000,
"weight_decay": 0.01
}
```
## Full Model Architecture
```
SentenceTransformer(
(0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: bert-base-uncased
(1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False})
)
```
## Citing & Authors
This model was trained by [sentence-transformers](https://www.sbert.net/).
If you find this model helpful, feel free to cite our publication [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://arxiv.org/abs/1908.10084):
```bibtex
@inproceedings{reimers-2019-sentence-bert,
title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
author = "Reimers, Nils and Gurevych, Iryna",
booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
month = "11",
year = "2019",
publisher = "Association for Computational Linguistics",
url = "http://arxiv.org/abs/1908.10084",
}
```
|
distilbert-base-german-cased
|
[
"pytorch",
"safetensors",
"distilbert",
"fill-mask",
"de",
"transformers",
"license:apache-2.0",
"autotrain_compatible",
"has_space"
] |
fill-mask
|
{
"architectures": [
"DistilBertForMaskedLM"
],
"model_type": "distilbert",
"task_specific_params": {
"conversational": {
"max_length": null
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
}
| 43,667
| null |
---
license: openrail
datasets:
- tatsu-lab/alpaca
language:
- es
metrics:
- cer
library_name: asteroid
tags:
- art
---
# 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]
|
distilbert-base-uncased-distilled-squad
|
[
"pytorch",
"tf",
"tflite",
"coreml",
"safetensors",
"distilbert",
"question-answering",
"en",
"dataset:squad",
"arxiv:1910.01108",
"arxiv:1910.09700",
"transformers",
"license:apache-2.0",
"autotrain_compatible",
"has_space"
] |
question-answering
|
{
"architectures": [
"DistilBertForQuestionAnswering"
],
"model_type": "distilbert",
"task_specific_params": {
"conversational": {
"max_length": null
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
}
| 100,097
| null |
---
license: other
language:
- en
pipeline_tag: text2text-generation
tags:
- alpaca
- llama
- chat
- gpt4
inference: false
---
This is a 4bit 128g GPTQ of [chansung's gpt4-alpaca-lora-13b](https://huggingface.co/chansung/gpt4-alpaca-lora-13b).
## How to easily download and use this model in text-generation-webui
Open the text-generation-webui UI as normal.
1. Click the **Model tab**.
2. Under **Download custom model or LoRA**, enter `TheBloke/gpt4-alpaca-lora-13B-GPTQ-4bit-128g`.
3. Click **Download**.
4. Wait until it says it's finished downloading.
5. Click the **Refresh** icon next to **Model** in the top left.
6. In the **Model drop-down**: choose the model you just downloaded,`gpt4-alpaca-lora-13B-GPTQ-4bit-128g`.
7. If you see an error in the bottom right, ignore it - it's temporary.
8. Check that the `GPTQ parameters` are correct on the right: `Bits = 4`, `Groupsize = 128`, `model_type = Llama`
9. Click **Save settings for this model** in the top right.
10. Click **Reload the Model** in the top right.
11. Once it says it's loaded, click the **Text Generation tab** and enter a prompt!
Command to create was:
```
CUDA_VISIBLE_DEVICES=0 python3 llama.py /content/gpt4-alpaca-lora-13B-HF c4 --wbits 4 --true-sequential --act-order --groupsize 128 --save_safetensors /content/gpt4-alpaca-lora-13B-GPTQ-4bit-128g.safetensors
```
Command to clone the latest Triton GPTQ-for-LLaMa repo for inference using `llama_inference.py`, or in `text-generation-webui`:
```
# Clone text-generation-webui, if you don't already have it
git clone https://github.com/oobabooga/text-generation-webui
# Make a repositories directory
mkdir -p text-generation-webui/repositories
cd text-generation-webui/repositories
# Clone the latest GPTQ-for-LLaMa code inside text-generation-webui
git clone https://github.com/qwopqwop200/GPTQ-for-LLaMa
```
There is also a `no-act-order.safetensors` file which will work with oobabooga's fork of GPTQ-for-LLaMa; it does not require the latest GPTQ code.
# Original model card is below
This repository comes with LoRA checkpoint to make LLaMA into a chatbot like language model. The checkpoint is the output of instruction following fine-tuning process with the following settings on 8xA100(40G) DGX system.
- Training script: borrowed from the official [Alpaca-LoRA](https://github.com/tloen/alpaca-lora) implementation
- Training script:
```shell
python finetune.py \
--base_model='decapoda-research/llama-30b-hf' \
--data_path='alpaca_data_gpt4.json' \
--num_epochs=10 \
--cutoff_len=512 \
--group_by_length \
--output_dir='./gpt4-alpaca-lora-30b' \
--lora_target_modules='[q_proj,k_proj,v_proj,o_proj]' \
--lora_r=16 \
--batch_size=... \
--micro_batch_size=...
```
You can find how the training went from W&B report [here](https://wandb.ai/chansung18/gpt4_alpaca_lora/runs/w3syd157?workspace=user-chansung18).
|
1503277708/namo
|
[] | null |
{
"architectures": null,
"model_type": null,
"task_specific_params": {
"conversational": {
"max_length": null
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
}
| 0
| null |
---
tags:
- generated_from_trainer
model-index:
- name: raw_disaster_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. -->
# raw_disaster_tweets
This model is a fine-tuned version of [cardiffnlp/twitter-roberta-base-sentiment](https://huggingface.co/cardiffnlp/twitter-roberta-base-sentiment) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.4184
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-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: 5
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 0.7201 | 0.12 | 12 | 0.7164 |
| 0.7234 | 0.25 | 24 | 0.7148 |
| 0.7128 | 0.38 | 36 | 0.7121 |
| 0.7122 | 0.5 | 48 | 0.7086 |
| 0.7074 | 0.62 | 60 | 0.7042 |
| 0.699 | 0.75 | 72 | 0.6990 |
| 0.6989 | 0.88 | 84 | 0.6934 |
| 0.6904 | 1.0 | 96 | 0.6871 |
| 0.6884 | 1.12 | 108 | 0.6801 |
| 0.6793 | 1.25 | 120 | 0.6723 |
| 0.6746 | 1.38 | 132 | 0.6638 |
| 0.6635 | 1.5 | 144 | 0.6539 |
| 0.647 | 1.62 | 156 | 0.6426 |
| 0.6418 | 1.75 | 168 | 0.6293 |
| 0.6287 | 1.88 | 180 | 0.6140 |
| 0.5938 | 2.0 | 192 | 0.5959 |
| 0.5869 | 2.12 | 204 | 0.5768 |
| 0.5718 | 2.25 | 216 | 0.5586 |
| 0.5638 | 2.38 | 228 | 0.5413 |
| 0.5265 | 2.5 | 240 | 0.5259 |
| 0.5165 | 2.62 | 252 | 0.5111 |
| 0.4966 | 2.75 | 264 | 0.4987 |
| 0.5072 | 2.88 | 276 | 0.4886 |
| 0.456 | 3.0 | 288 | 0.4827 |
| 0.458 | 3.12 | 300 | 0.4704 |
| 0.434 | 3.25 | 312 | 0.4647 |
| 0.421 | 3.38 | 324 | 0.4604 |
| 0.4679 | 3.5 | 336 | 0.4546 |
| 0.4463 | 3.62 | 348 | 0.4498 |
| 0.4288 | 3.75 | 360 | 0.4500 |
| 0.4261 | 3.88 | 372 | 0.4406 |
| 0.4314 | 4.0 | 384 | 0.4420 |
| 0.3848 | 4.12 | 396 | 0.4349 |
| 0.4145 | 4.25 | 408 | 0.4354 |
| 0.4151 | 4.38 | 420 | 0.4277 |
| 0.4034 | 4.5 | 432 | 0.4273 |
| 0.3933 | 4.62 | 444 | 0.4295 |
| 0.4171 | 4.75 | 456 | 0.4216 |
| 0.3926 | 4.88 | 468 | 0.4179 |
| 0.3739 | 5.0 | 480 | 0.4184 |
### Framework versions
- Transformers 4.28.1
- Pytorch 1.13.0
- Datasets 2.1.0
- Tokenizers 0.13.2
|
842458199/model_name
|
[] | null |
{
"architectures": null,
"model_type": null,
"task_specific_params": {
"conversational": {
"max_length": null
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
}
| 0
| 2023-04-18T01:45:29Z
|
---
pipeline_tag: sentence-similarity
tags:
- sentence-transformers
- feature-extraction
- sentence-similarity
- transformers
---
# hlyu/basemodel_2layer_1_11
This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 768 dimensional dense vector space and can be used for tasks like clustering or semantic search.
<!--- Describe your model here -->
## Usage (Sentence-Transformers)
Using this model becomes easy when you have [sentence-transformers](https://www.SBERT.net) installed:
```
pip install -U sentence-transformers
```
Then you can use the model like this:
```python
from sentence_transformers import SentenceTransformer
sentences = ["This is an example sentence", "Each sentence is converted"]
model = SentenceTransformer('hlyu/basemodel_2layer_1_11')
embeddings = model.encode(sentences)
print(embeddings)
```
## Usage (HuggingFace Transformers)
Without [sentence-transformers](https://www.SBERT.net), you can use the model like this: First, you pass your input through the transformer model, then you have to apply the right pooling-operation on-top of the contextualized word embeddings.
```python
from transformers import AutoTokenizer, AutoModel
import torch
#Mean Pooling - Take attention mask into account for correct averaging
def mean_pooling(model_output, attention_mask):
token_embeddings = model_output[0] #First element of model_output contains all token embeddings
input_mask_expanded = attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float()
return torch.sum(token_embeddings * input_mask_expanded, 1) / torch.clamp(input_mask_expanded.sum(1), min=1e-9)
# Sentences we want sentence embeddings for
sentences = ['This is an example sentence', 'Each sentence is converted']
# Load model from HuggingFace Hub
tokenizer = AutoTokenizer.from_pretrained('hlyu/basemodel_2layer_1_11')
model = AutoModel.from_pretrained('hlyu/basemodel_2layer_1_11')
# Tokenize sentences
encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt')
# Compute token embeddings
with torch.no_grad():
model_output = model(**encoded_input)
# Perform pooling. In this case, mean pooling.
sentence_embeddings = mean_pooling(model_output, encoded_input['attention_mask'])
print("Sentence embeddings:")
print(sentence_embeddings)
```
## Evaluation Results
<!--- Describe how your model was evaluated -->
For an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: [https://seb.sbert.net](https://seb.sbert.net?model_name=hlyu/basemodel_2layer_1_11)
## Training
The model was trained with the parameters:
**DataLoader**:
`torch.utils.data.dataloader.DataLoader` of length 5055 with parameters:
```
{'batch_size': 128, 'sampler': 'torch.utils.data.sampler.RandomSampler', 'batch_sampler': 'torch.utils.data.sampler.BatchSampler'}
```
**Loss**:
`sentence_transformers.losses.MSELoss.MSELoss`
Parameters of the fit()-Method:
```
{
"epochs": 1,
"evaluation_steps": 2000,
"evaluator": "sentence_transformers.evaluation.SequentialEvaluator.SequentialEvaluator",
"max_grad_norm": 1,
"optimizer_class": "<class 'torch.optim.adamw.AdamW'>",
"optimizer_params": {
"eps": 1e-06,
"lr": 0.0001
},
"scheduler": "WarmupLinear",
"steps_per_epoch": null,
"warmup_steps": 1000,
"weight_decay": 0.01
}
```
## Full Model Architecture
```
SentenceTransformer(
(0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: BertModel
(1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False})
)
```
## Citing & Authors
<!--- Describe where people can find more information -->
|
AbhinavSaiTheGreat/DialoGPT-small-harrypotter
|
[
"pytorch",
"gpt2",
"text-generation",
"transformers",
"conversational"
] |
conversational
|
{
"architectures": [
"GPT2LMHeadModel"
],
"model_type": "gpt2",
"task_specific_params": {
"conversational": {
"max_length": 1000
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
}
| 10
| 2023-04-18T08:20:16Z
|
---
tags:
- generated_from_trainer
datasets:
- audiofolder
metrics:
- wer
model-index:
- name: wav2vec2-300m-kik-t22-1k-ft
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: audiofolder
type: audiofolder
config: default
split: train
args: default
metrics:
- name: Wer
type: wer
value: 0.058442974485716365
---
<!-- 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. -->
# wav2vec2-300m-kik-t22-1k-ft
This model is a fine-tuned version of [mutisya/wav2vec2-300m-kik-t22-1k](https://huggingface.co/mutisya/wav2vec2-300m-kik-t22-1k) on the audiofolder dataset.
It achieves the following results on the evaluation set:
- Loss: 0.0710
- Wer: 0.0584
## 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: 4
- eval_batch_size: 4
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 5000
- num_epochs: 20
- mixed_precision_training: Native AMP
### Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|:-------------:|:-----:|:-----:|:---------------:|:------:|
| 5.3356 | 0.2 | 400 | 2.8887 | 1.0 |
| 2.2627 | 0.39 | 800 | 0.8369 | 0.9304 |
| 0.7404 | 0.59 | 1200 | 0.4181 | 0.6309 |
| 0.4978 | 0.79 | 1600 | 0.2758 | 0.4067 |
| 0.395 | 0.98 | 2000 | 0.2290 | 0.3405 |
| 0.3139 | 1.18 | 2400 | 0.1787 | 0.2675 |
| 0.294 | 1.38 | 2800 | 0.1590 | 0.2443 |
| 0.2669 | 1.57 | 3200 | 0.1522 | 0.2270 |
| 0.2606 | 1.77 | 3600 | 0.1351 | 0.2047 |
| 0.2402 | 1.97 | 4000 | 0.1269 | 0.1986 |
| 0.2289 | 2.16 | 4400 | 0.1245 | 0.1903 |
| 0.215 | 2.36 | 4800 | 0.1140 | 0.1846 |
| 0.2238 | 2.56 | 5200 | 0.1176 | 0.1831 |
| 0.2039 | 2.75 | 5600 | 0.1070 | 0.1574 |
| 0.2028 | 2.95 | 6000 | 0.1049 | 0.1555 |
| 0.1839 | 3.14 | 6400 | 0.1030 | 0.1488 |
| 0.1728 | 3.34 | 6800 | 0.1088 | 0.1491 |
| 0.1767 | 3.54 | 7200 | 0.1032 | 0.1505 |
| 0.1712 | 3.73 | 7600 | 0.0924 | 0.1390 |
| 0.1799 | 3.93 | 8000 | 0.0934 | 0.1369 |
| 0.1557 | 4.13 | 8400 | 0.0992 | 0.1355 |
| 0.1526 | 4.32 | 8800 | 0.1042 | 0.1427 |
| 0.1495 | 4.52 | 9200 | 0.0918 | 0.1333 |
| 0.1435 | 4.72 | 9600 | 0.0896 | 0.1204 |
| 0.154 | 4.91 | 10000 | 0.0851 | 0.1154 |
| 0.1378 | 5.11 | 10400 | 0.0879 | 0.1167 |
| 0.1426 | 5.31 | 10800 | 0.0820 | 0.1110 |
| 0.1306 | 5.5 | 11200 | 0.0801 | 0.1074 |
| 0.1277 | 5.7 | 11600 | 0.0772 | 0.1012 |
| 0.1272 | 5.9 | 12000 | 0.0783 | 0.1034 |
| 0.1215 | 6.09 | 12400 | 0.0777 | 0.0994 |
| 0.1155 | 6.29 | 12800 | 0.0762 | 0.0983 |
| 0.1294 | 6.49 | 13200 | 0.0711 | 0.0968 |
| 0.1169 | 6.68 | 13600 | 0.0768 | 0.0935 |
| 0.1121 | 6.88 | 14000 | 0.0804 | 0.1026 |
| 0.1052 | 7.08 | 14400 | 0.0784 | 0.0986 |
| 0.1061 | 7.27 | 14800 | 0.0744 | 0.0922 |
| 0.1029 | 7.47 | 15200 | 0.0774 | 0.0968 |
| 0.1121 | 7.67 | 15600 | 0.0789 | 0.0976 |
| 0.1038 | 7.86 | 16000 | 0.0783 | 0.0999 |
| 0.1025 | 8.06 | 16400 | 0.0710 | 0.0882 |
| 0.1033 | 8.26 | 16800 | 0.0742 | 0.0906 |
| 0.0942 | 8.45 | 17200 | 0.0708 | 0.0866 |
| 0.0908 | 8.65 | 17600 | 0.0742 | 0.0909 |
| 0.0932 | 8.85 | 18000 | 0.0722 | 0.0863 |
| 0.0858 | 9.04 | 18400 | 0.0710 | 0.0826 |
| 0.0867 | 9.24 | 18800 | 0.0669 | 0.0825 |
| 0.0837 | 9.43 | 19200 | 0.0678 | 0.0837 |
| 0.095 | 9.63 | 19600 | 0.0698 | 0.0852 |
| 0.0801 | 9.83 | 20000 | 0.0709 | 0.0844 |
| 0.0883 | 10.02 | 20400 | 0.0668 | 0.0834 |
| 0.0758 | 10.22 | 20800 | 0.0740 | 0.0805 |
| 0.0765 | 10.42 | 21200 | 0.0695 | 0.0778 |
| 0.0802 | 10.61 | 21600 | 0.0722 | 0.0810 |
| 0.0809 | 10.81 | 22000 | 0.0705 | 0.0770 |
| 0.0755 | 11.01 | 22400 | 0.0729 | 0.0779 |
| 0.0702 | 11.2 | 22800 | 0.0721 | 0.0765 |
| 0.0744 | 11.4 | 23200 | 0.0732 | 0.0789 |
| 0.0731 | 11.6 | 23600 | 0.0717 | 0.0768 |
| 0.0712 | 11.79 | 24000 | 0.0704 | 0.0792 |
| 0.0684 | 11.99 | 24400 | 0.0682 | 0.0764 |
| 0.0643 | 12.19 | 24800 | 0.0721 | 0.0736 |
| 0.0654 | 12.38 | 25200 | 0.0677 | 0.0703 |
| 0.0656 | 12.58 | 25600 | 0.0695 | 0.0715 |
| 0.0666 | 12.78 | 26000 | 0.0691 | 0.0743 |
| 0.0616 | 12.97 | 26400 | 0.0698 | 0.0755 |
| 0.0614 | 13.17 | 26800 | 0.0657 | 0.0685 |
| 0.0582 | 13.37 | 27200 | 0.0672 | 0.0691 |
| 0.0614 | 13.56 | 27600 | 0.0673 | 0.0680 |
| 0.0585 | 13.76 | 28000 | 0.0699 | 0.0709 |
| 0.06 | 13.96 | 28400 | 0.0706 | 0.0669 |
| 0.0544 | 14.15 | 28800 | 0.0724 | 0.0680 |
| 0.0554 | 14.35 | 29200 | 0.0657 | 0.0686 |
| 0.0507 | 14.55 | 29600 | 0.0692 | 0.0672 |
| 0.0561 | 14.74 | 30000 | 0.0695 | 0.0675 |
| 0.0539 | 14.94 | 30400 | 0.0730 | 0.0704 |
| 0.0538 | 15.14 | 30800 | 0.0709 | 0.0692 |
| 0.0522 | 15.33 | 31200 | 0.0688 | 0.0668 |
| 0.0508 | 15.53 | 31600 | 0.0699 | 0.0643 |
| 0.0498 | 15.72 | 32000 | 0.0705 | 0.0652 |
| 0.0447 | 15.92 | 32400 | 0.0728 | 0.0630 |
| 0.046 | 16.12 | 32800 | 0.0735 | 0.0648 |
| 0.0458 | 16.31 | 33200 | 0.0699 | 0.0604 |
| 0.0423 | 16.51 | 33600 | 0.0712 | 0.0639 |
| 0.0454 | 16.71 | 34000 | 0.0739 | 0.0637 |
| 0.0438 | 16.9 | 34400 | 0.0719 | 0.0629 |
| 0.0429 | 17.1 | 34800 | 0.0706 | 0.0605 |
| 0.0396 | 17.3 | 35200 | 0.0744 | 0.0594 |
| 0.0412 | 17.49 | 35600 | 0.0719 | 0.0624 |
| 0.0425 | 17.69 | 36000 | 0.0746 | 0.0613 |
| 0.0385 | 17.89 | 36400 | 0.0728 | 0.0616 |
| 0.039 | 18.08 | 36800 | 0.0731 | 0.0611 |
| 0.0418 | 18.28 | 37200 | 0.0704 | 0.0609 |
| 0.0386 | 18.48 | 37600 | 0.0696 | 0.0597 |
| 0.0349 | 18.67 | 38000 | 0.0704 | 0.0590 |
| 0.0334 | 18.87 | 38400 | 0.0719 | 0.0591 |
| 0.0369 | 19.07 | 38800 | 0.0697 | 0.0598 |
| 0.0377 | 19.26 | 39200 | 0.0708 | 0.0589 |
| 0.0342 | 19.46 | 39600 | 0.0705 | 0.0598 |
| 0.0351 | 19.66 | 40000 | 0.0708 | 0.0587 |
| 0.0346 | 19.85 | 40400 | 0.0711 | 0.0582 |
### Framework versions
- Transformers 4.28.1
- Pytorch 2.0.0+cu117
- Datasets 2.11.0
- Tokenizers 0.13.3
|
AdapterHub/bert-base-uncased-pf-fce_error_detection
|
[
"bert",
"en",
"dataset:fce_error_detection",
"arxiv:2104.08247",
"adapter-transformers",
"token-classification",
"adapterhub:ged/fce"
] |
token-classification
|
{
"architectures": null,
"model_type": "bert",
"task_specific_params": {
"conversational": {
"max_length": null
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
}
| 68
| null |
---
tags:
- CartPole-v1
- reinforce
- reinforcement-learning
- custom-implementation
- deep-rl-class
model-index:
- name: CartPole_unit4-videotest
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: CartPole-v1
type: CartPole-v1
metrics:
- type: mean_reward
value: 349.50 +/- 221.47
name: mean_reward
verified: false
---
# **Reinforce** Agent playing **CartPole-v1**
This is a trained model of a **Reinforce** agent playing **CartPole-v1** .
To learn to use this model and train yours check Unit 4 of the Deep Reinforcement Learning Course: https://huggingface.co/deep-rl-course/unit4/introduction
|
AdapterHub/roberta-base-pf-conll2000
|
[
"roberta",
"en",
"dataset:conll2000",
"arxiv:2104.08247",
"adapter-transformers",
"token-classification",
"adapterhub:chunk/conll2000"
] |
token-classification
|
{
"architectures": null,
"model_type": "roberta",
"task_specific_params": {
"conversational": {
"max_length": null
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
}
| 3
| null |
---
license: apache-2.0
tags:
- generated_from_trainer
- polyglot-ko
- gpt-neox
- KoAlpaca
model-index:
- name: KoAlpaca-Polyglot-12.8B
results: []
language:
- ko
datasets:
- KoAlpaca-v1.1b
pipeline_tag: text-generation
---
# KoAlpaca-Polyglot-12.8B (v1.1b)
This model is a fine-tuned version of [EleutherAI/polyglot-ko-12.8b](https://huggingface.co/EleutherAI/polyglot-ko-12.8b) on a KoAlpaca Dataset v1.1b
Detail Codes are available at [KoAlpaca Github Repository](https://github.com/Beomi/KoAlpaca)
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 1
- seed: 42
- distributed_type: multi-GPU (A100 80G)
- num_devices: 4
- gradient_accumulation_steps: 64
- total_train_batch_size: 256
- total_eval_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 2.0
### Framework versions
- Transformers 4.28.1
- Pytorch 2.0.0+cu117
- Datasets 2.11.0
- Tokenizers 0.13.3
|
AdapterHub/roberta-base-pf-fce_error_detection
|
[
"roberta",
"en",
"dataset:fce_error_detection",
"arxiv:2104.08247",
"adapter-transformers",
"token-classification",
"adapterhub:ged/fce"
] |
token-classification
|
{
"architectures": null,
"model_type": "roberta",
"task_specific_params": {
"conversational": {
"max_length": null
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
}
| 30
| 2023-04-18T08:02:28Z
|
---
license: creativeml-openrail-m
tags:
- stable-diffusion
---
random mixed anime models
<img src="https://huggingface.co/sleepotimer/Model_A/resolve/main/example1.png" width="768px">
<img src="https://huggingface.co/sleepotimer/Model_A/resolve/main/example2.png" width="768px">
<img src="https://huggingface.co/sleepotimer/Model_A/resolve/main/example3.png" width="768px">
|
AdapterHub/roberta-base-pf-scitail
|
[
"roberta",
"en",
"dataset:scitail",
"arxiv:2104.08247",
"adapter-transformers",
"text-classification",
"adapterhub:nli/scitail"
] |
text-classification
|
{
"architectures": null,
"model_type": "roberta",
"task_specific_params": {
"conversational": {
"max_length": null
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
}
| 1
| null |
---
datasets:
- yahma/alpaca_cleaned
- lksy/ru_instruct_gpt4
language:
- ru
pipeline_tag: text2text-generation
inference: false
---
Based on [LLaMA 13B](https://huggingface.co/yahma/llama-13b-hf).
Trained on 4 LoRA modules.
Parameters:
```
{
"base_model_name_or_path": "./llama-30b-hf",
"bias": "none",
"enable_lora": null,
"fan_in_fan_out": false,
"inference_mode": true,
"lora_alpha": 16,
"lora_dropout": 0.05,
"merge_weights": false,
"modules_to_save": null,
"peft_type": "LORA",
"r": 16,
"target_modules": [
"q_proj",
"v_proj",
"k_proj",
"o_proj"
],
"task_type": "CAUSAL_LM"
}
```
Cutoff length set to 512
```
Prompt template:
{
"description": "A shorter template to experiment with.",
"prompt_input": "### Задание:\n{instruction}\n\n### Вход:\n{input}\n\n### Ответ:\n",
"prompt_no_input": "### Задание:\n{instruction}\n\n### Ответ:\n",
"response_split": "### Ответ:"
}
```
[WandB report](https://wandb.ai/lksy/huggingface/runs/oj1ezptd)
Epochs: 4
Loss: 0.853
|
AdapterHub/roberta-base-pf-ud_pos
|
[
"roberta",
"en",
"dataset:universal_dependencies",
"arxiv:2104.08247",
"adapter-transformers",
"token-classification",
"adapterhub:pos/ud_ewt"
] |
token-classification
|
{
"architectures": null,
"model_type": "roberta",
"task_specific_params": {
"conversational": {
"max_length": null
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
}
| 8
| null |
---
license: apache-2.0
tags:
- generated_from_keras_callback
model-index:
- name: NiallRooney/my_awesome_eli5_clm-model
results: []
---
<!-- This model card has been generated automatically according to the information Keras had access to. You should
probably proofread and complete it, then remove this comment. -->
# NiallRooney/my_awesome_eli5_clm-model
This model is a fine-tuned version of [distilgpt2](https://huggingface.co/distilgpt2) on an unknown dataset.
It achieves the following results on the evaluation set:
- Train Loss: 3.5982
- Validation Loss: 3.7245
- Epoch: 2
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- optimizer: {'name': 'AdamWeightDecay', 'learning_rate': 2e-05, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False, 'weight_decay_rate': 0.01}
- training_precision: float32
### Training results
| Train Loss | Validation Loss | Epoch |
|:----------:|:---------------:|:-----:|
| 3.6789 | 3.7295 | 0 |
| 3.6362 | 3.7240 | 1 |
| 3.5982 | 3.7245 | 2 |
### Framework versions
- Transformers 4.28.1
- TensorFlow 2.12.0
- Datasets 2.11.0
- Tokenizers 0.13.3
|
AdapterHub/roberta-base-pf-wic
|
[
"roberta",
"en",
"arxiv:2104.08247",
"adapter-transformers",
"text-classification",
"adapterhub:wordsence/wic"
] |
text-classification
|
{
"architectures": null,
"model_type": "roberta",
"task_specific_params": {
"conversational": {
"max_length": null
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
}
| 0
| null |
# CLIP+MLP Aesthetic Score Predictor
Train, use and visualize an aesthetic score predictor ( how much people like on average an image ) based on a simple neural net that takes CLIP embeddings as inputs.
Link to the AVA training data ( already prepared) :
https://drive.google.com/drive/folders/186XiniJup5Rt9FXsHiAGWhgWz-nmCK_r?usp=sharing
Visualizations of all images from LAION 5B (english subset with 2.37B images) in 40 buckets with the model sac+logos+ava1-l14-linearMSE.pth:
http://captions.christoph-schuhmann.de/aesthetic_viz_laion_sac+logos+ava1-l14-linearMSE-en-2.37B.html
|
Adielcane/Adielcane
|
[] | null |
{
"architectures": null,
"model_type": null,
"task_specific_params": {
"conversational": {
"max_length": null
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
}
| 0
| null |
Models for https://github.com/denniswittich/JointAppearanceAdaptation
---
license: mit
---
|
AethiQs-Max/aethiqs-base_bertje-data_rotterdam-epochs_30-epoch_30
|
[
"pytorch",
"bert",
"fill-mask",
"transformers",
"autotrain_compatible"
] |
fill-mask
|
{
"architectures": [
"BertForMaskedLM"
],
"model_type": "bert",
"task_specific_params": {
"conversational": {
"max_length": null
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
}
| 8
| null |
---
license: cc-by-nc-4.0
tags:
- text-classification
datasets:
- NYTK/HuCOLA
language:
- hu
widget:
- text: >-
Két szoba híján tele volt a szálloda.
---
# Hungarian Linguistic Acceptability with Finetuned PULI BERT-Large Model
For further details, see [our demo site](https://juniper.nytud.hu/demo/nlp).
## Limitations
- max_seq_length = 128
## Citation
If you use this model, please cite the following paper:
```
@inproceedings {yang-puli,
title = {Jönnek a nagyok! BERT-Large, GPT-2 és GPT-3 nyelvmodellek magyar nyelvre},
booktitle = {XIX. Magyar Számítógépes Nyelvészeti Konferencia (MSZNY 2023)},
year = {2023},
publisher = {Szegedi Tudományegyetem, Informatikai Intézet},
address = {Szeged, Hungary},
author = {Yang, Zijian Győző and Dodé, Réka and Ferenczi, Gergő and Héja, Enikő and Jelencsik-Mátyus, Kinga and Kőrös, Ádám and Laki, László János and Ligeti-Nagy, Noémi and Vadász, Noémi and Váradi, Tamás},
pages = {247--262}
}
```
|
AidenGO/KDXF_Bert4MaskedLM
|
[
"pytorch",
"bert",
"fill-mask",
"transformers",
"autotrain_compatible"
] |
fill-mask
|
{
"architectures": [
"BertForMaskedLM"
],
"model_type": "bert",
"task_specific_params": {
"conversational": {
"max_length": null
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
}
| 5
| null |
---
tags:
- autotrain
- tabular
- regression
- tabular-regression
datasets:
- vyver7952/autotrain-data-foreign-exchange-idr-usd
co2_eq_emissions:
emissions: 0.12129817373109428
---
# Model Trained Using AutoTrain
- Problem type: Single Column Regression
- Model ID: 50442120508
- CO2 Emissions (in grams): 0.1213
## Validation Metrics
- Loss: 0.611
- R2: 1.000
- MSE: 0.374
- MAE: 0.466
- RMSLE: 0.000
## Usage
```python
import json
import joblib
import pandas as pd
model = joblib.load('model.joblib')
config = json.load(open('config.json'))
features = config['features']
# data = pd.read_csv("data.csv")
data = data[features]
data.columns = ["feat_" + str(col) for col in data.columns]
predictions = model.predict(data) # or model.predict_proba(data)
```
|
AigizK/wav2vec2-large-xls-r-300m-bashkir-cv7_no_lm
|
[] | null |
{
"architectures": null,
"model_type": null,
"task_specific_params": {
"conversational": {
"max_length": null
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
}
| 0
| null |
---
tags:
- autotrain
- tabular
- regression
- tabular-regression
datasets:
- vyver7952/autotrain-data-foreign-exchange-idr-usd
co2_eq_emissions:
emissions: 0.1187798673649329
---
# Model Trained Using AutoTrain
- Problem type: Single Column Regression
- Model ID: 50442120509
- CO2 Emissions (in grams): 0.1188
## Validation Metrics
- Loss: 13.859
- R2: 0.999
- MSE: 192.085
- MAE: 13.842
- RMSLE: 0.001
## Usage
```python
import json
import joblib
import pandas as pd
model = joblib.load('model.joblib')
config = json.load(open('config.json'))
features = config['features']
# data = pd.read_csv("data.csv")
data = data[features]
data.columns = ["feat_" + str(col) for col in data.columns]
predictions = model.predict(data) # or model.predict_proba(data)
```
|
AigizK/wav2vec2-large-xls-r-300m-bashkir-cv7_opt
|
[
"pytorch",
"wav2vec2",
"automatic-speech-recognition",
"ba",
"dataset:mozilla-foundation/common_voice_7_0",
"transformers",
"generated_from_trainer",
"hf-asr-leaderboard",
"mozilla-foundation/common_voice_7_0",
"robust-speech-event",
"license:apache-2.0",
"model-index",
"has_space"
] |
automatic-speech-recognition
|
{
"architectures": [
"Wav2Vec2ForCTC"
],
"model_type": "wav2vec2",
"task_specific_params": {
"conversational": {
"max_length": null
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
}
| 64
| null |
---
license: mit
tags:
- generated_from_trainer
model-index:
- name: gpt2-kl_1_04_hscnspecial-hs_cn
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# gpt2-kl_1_04_hscnspecial-hs_cn
This model is a fine-tuned version of [gpt2-medium](https://huggingface.co/gpt2-medium) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.5848
## 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: 4
- seed: 21
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 3.0
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 73.7379 | 0.02 | 10 | 69.5698 |
| 46.2931 | 0.04 | 20 | 32.9010 |
| 13.6754 | 0.06 | 30 | 10.6422 |
| 6.462 | 0.08 | 40 | 4.5318 |
| 2.8639 | 0.1 | 50 | 2.0239 |
| 1.5179 | 0.12 | 60 | 1.0382 |
| 1.2111 | 0.14 | 70 | 0.9591 |
| 1.1308 | 0.16 | 80 | 0.7130 |
| 0.965 | 0.18 | 90 | 0.6553 |
| 0.9107 | 0.2 | 100 | 0.6113 |
| 0.8141 | 0.22 | 110 | 0.5902 |
| 0.7915 | 0.24 | 120 | 0.5813 |
| 0.8184 | 0.26 | 130 | 0.5831 |
| 0.7759 | 0.28 | 140 | 0.5860 |
| 0.7813 | 0.3 | 150 | 0.5848 |
### Framework versions
- Transformers 4.28.0
- Pytorch 1.11.0+cu113
- Datasets 2.11.0
- Tokenizers 0.12.1
|
AimB/konlpy_berttokenizer_helsinki
|
[] | null |
{
"architectures": null,
"model_type": null,
"task_specific_params": {
"conversational": {
"max_length": null
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
}
| 0
| null |
---
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://github.com/huggingface/ml-agents#get-started
We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub:
### Resume the training
```
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. Go to https://huggingface.co/spaces/unity/ML-Agents-Huggy
2. Step 1: Find your model_id: danieliser/ppo-Huggy
3. Step 2: Select your *.nn /*.onnx file
4. Click on Watch the agent play 👀
|
Ajteks/Chatbot
|
[] | null |
{
"architectures": null,
"model_type": null,
"task_specific_params": {
"conversational": {
"max_length": null
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
}
| 0
| null |
Access to model AndreZheng/distilbert-base-uncased-finetuned-emotion is restricted and you are not in the authorized list. Visit https://huggingface.co/AndreZheng/distilbert-base-uncased-finetuned-emotion to ask for access.
|
Akash7897/distilbert-base-uncased-finetuned-sst2
|
[
"pytorch",
"tensorboard",
"distilbert",
"text-classification",
"dataset:glue",
"transformers",
"generated_from_trainer",
"license:apache-2.0",
"model-index"
] |
text-classification
|
{
"architectures": [
"DistilBertForSequenceClassification"
],
"model_type": "distilbert",
"task_specific_params": {
"conversational": {
"max_length": null
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
}
| 31
| null |
---
tags:
- autotrain
- vision
- image-classification
datasets:
- losergi/autotrain-data-meleg_car_parts
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: 0.008134552496204995
---
# Model Trained Using AutoTrain
- Problem type: Binary Classification
- Model ID: 47031120543
- CO2 Emissions (in grams): 0.0081
## Validation Metrics
- Loss: 0.044
- Accuracy: 1.000
- Precision: 1.000
- Recall: 1.000
- AUC: 1.000
- F1: 1.000
|
Akashamba/distilbert-base-uncased-finetuned-ner
|
[] | null |
{
"architectures": null,
"model_type": null,
"task_specific_params": {
"conversational": {
"max_length": null
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
}
| 0
| null |
---
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="cha00/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"])
```
|
Akashpb13/Galician_xlsr
|
[
"pytorch",
"wav2vec2",
"automatic-speech-recognition",
"gl",
"dataset:mozilla-foundation/common_voice_8_0",
"transformers",
"mozilla-foundation/common_voice_8_0",
"generated_from_trainer",
"robust-speech-event",
"model_for_talk",
"hf-asr-leaderboard",
"license:apache-2.0",
"model-index"
] |
automatic-speech-recognition
|
{
"architectures": [
"Wav2Vec2ForCTC"
],
"model_type": "wav2vec2",
"task_specific_params": {
"conversational": {
"max_length": null
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
}
| 7
| null |
---
tags:
- LunarLander-v2
- ppo
- deep-reinforcement-learning
- reinforcement-learning
- custom-implementation
- deep-rl-course
model-index:
- name: PPO
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: LunarLander-v2
type: LunarLander-v2
metrics:
- type: mean_reward
value: -152.92 +/- 91.80
name: mean_reward
verified: false
---
# PPO Agent Playing LunarLander-v2
This is a trained model of a PPO agent playing LunarLander-v2.
# Hyperparameters
```python
{'exp_name': 'ppo'
'seed': 1
'torch_deterministic': True
'cuda': True
'track': False
'wandb_project_name': 'cleanRL'
'wandb_entity': None
'capture_video': False
'env_id': 'LunarLander-v2'
'total_timesteps': 50000
'learning_rate': 0.00025
'num_envs': 4
'num_steps': 128
'anneal_lr': True
'gae': True
'gamma': 0.99
'gae_lambda': 0.95
'num_minibatches': 4
'update_epochs': 4
'norm_adv': True
'clip_coef': 0.2
'clip_vloss': True
'ent_coef': 0.01
'vf_coef': 0.5
'max_grad_norm': 0.5
'target_kl': None
'repo_id': 'Nasree/ppo-CartPole-v1'
'batch_size': 512
'minibatch_size': 128}
```
|
Akashpb13/Hausa_xlsr
|
[
"pytorch",
"wav2vec2",
"automatic-speech-recognition",
"ha",
"dataset:mozilla-foundation/common_voice_8_0",
"transformers",
"generated_from_trainer",
"hf-asr-leaderboard",
"model_for_talk",
"mozilla-foundation/common_voice_8_0",
"robust-speech-event",
"license:apache-2.0",
"model-index",
"has_space"
] |
automatic-speech-recognition
|
{
"architectures": [
"Wav2Vec2ForCTC"
],
"model_type": "wav2vec2",
"task_specific_params": {
"conversational": {
"max_length": null
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
}
| 31
| null |
---
tags:
- Taxi-v3
- q-learning
- reinforcement-learning
- custom-implementation
model-index:
- name: taxi
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: Taxi-v3
type: Taxi-v3
metrics:
- type: mean_reward
value: 7.52 +/- 2.75
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="cha00/taxi", 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"])
```
|
Akashpb13/xlsr_kurmanji_kurdish
|
[
"pytorch",
"safetensors",
"wav2vec2",
"automatic-speech-recognition",
"kmr",
"ku",
"dataset:mozilla-foundation/common_voice_8_0",
"transformers",
"mozilla-foundation/common_voice_8_0",
"generated_from_trainer",
"robust-speech-event",
"model_for_talk",
"hf-asr-leaderboard",
"license:apache-2.0",
"model-index"
] |
automatic-speech-recognition
|
{
"architectures": [
"Wav2Vec2ForCTC"
],
"model_type": "wav2vec2",
"task_specific_params": {
"conversational": {
"max_length": null
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
}
| 10
| null |
---
license: mit
tags:
- generated_from_trainer
model-index:
- name: gpt2-kl_1_05_hscnspecial-hs_cn
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# gpt2-kl_1_05_hscnspecial-hs_cn
This model is a fine-tuned version of [gpt2-medium](https://huggingface.co/gpt2-medium) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.5776
## 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: 4
- seed: 21
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 3.0
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 73.8761 | 0.02 | 10 | 69.5761 |
| 46.4656 | 0.04 | 20 | 32.9595 |
| 13.7865 | 0.06 | 30 | 10.6413 |
| 6.1955 | 0.08 | 40 | 4.4713 |
| 3.2865 | 0.1 | 50 | 1.9343 |
| 1.7057 | 0.12 | 60 | 1.0630 |
| 1.4395 | 0.14 | 70 | 0.8938 |
| 1.3446 | 0.16 | 80 | 0.7473 |
| 1.0525 | 0.18 | 90 | 0.6359 |
| 1.0155 | 0.2 | 100 | 0.6422 |
| 0.9368 | 0.22 | 110 | 0.6149 |
| 0.909 | 0.24 | 120 | 0.5954 |
| 0.9592 | 0.26 | 130 | 0.5766 |
| 0.8922 | 0.28 | 140 | 0.5787 |
| 0.9056 | 0.3 | 150 | 0.5820 |
| 0.8984 | 0.32 | 160 | 0.5776 |
### Framework versions
- Transformers 4.28.0
- Pytorch 1.11.0+cu113
- Datasets 2.11.0
- Tokenizers 0.12.1
|
Akashpb13/xlsr_maltese_wav2vec2
|
[
"pytorch",
"jax",
"wav2vec2",
"automatic-speech-recognition",
"mt",
"dataset:common_voice",
"transformers",
"audio",
"speech",
"xlsr-fine-tuning-week",
"license:apache-2.0",
"model-index"
] |
automatic-speech-recognition
|
{
"architectures": [
"Wav2Vec2ForCTC"
],
"model_type": "wav2vec2",
"task_specific_params": {
"conversational": {
"max_length": null
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
}
| 8
| null |
---
license: mit
tags:
- generated_from_trainer
model-index:
- name: gpt2-kl_1_06_hscnspecial-hs_cn
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# gpt2-kl_1_06_hscnspecial-hs_cn
This model is a fine-tuned version of [gpt2-medium](https://huggingface.co/gpt2-medium) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.5629
## 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: 4
- seed: 21
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 3.0
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 74.052 | 0.02 | 10 | 69.5755 |
| 46.65 | 0.04 | 20 | 32.9625 |
| 13.934 | 0.06 | 30 | 10.6496 |
| 7.3279 | 0.08 | 40 | 4.6536 |
| 3.3304 | 0.1 | 50 | 2.0489 |
| 1.8218 | 0.12 | 60 | 1.0747 |
| 1.5128 | 0.14 | 70 | 0.9476 |
| 1.3618 | 0.16 | 80 | 0.7425 |
| 1.266 | 0.18 | 90 | 0.6568 |
| 1.2051 | 0.2 | 100 | 0.6164 |
| 1.0429 | 0.22 | 110 | 0.6028 |
| 1.0656 | 0.24 | 120 | 0.5926 |
| 1.1331 | 0.26 | 130 | 0.5911 |
| 1.0681 | 0.28 | 140 | 0.5848 |
| 1.0687 | 0.3 | 150 | 0.5777 |
| 1.0282 | 0.32 | 160 | 0.5811 |
| 0.9522 | 0.34 | 170 | 0.5803 |
| 1.114 | 0.36 | 180 | 0.5679 |
| 1.1167 | 0.38 | 190 | 0.5643 |
| 1.0369 | 0.4 | 200 | 0.5615 |
| 1.1708 | 0.42 | 210 | 0.5631 |
| 1.1546 | 0.44 | 220 | 0.5574 |
| 0.951 | 0.46 | 230 | 0.5649 |
| 1.0367 | 0.48 | 240 | 0.5596 |
| 1.0206 | 0.5 | 250 | 0.5629 |
### Framework versions
- Transformers 4.28.0
- Pytorch 1.11.0+cu113
- Datasets 2.11.0
- Tokenizers 0.12.1
|
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.