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
|
|---|---|---|---|---|---|---|
AdapterHub/roberta-base-pf-multirc
|
[
"roberta",
"en",
"arxiv:2104.08247",
"adapter-transformers",
"text-classification",
"adapterhub:rc/multirc"
] |
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
}
}
}
| 2
| null |
---
license: apache-2.0
datasets:
- mmosiolek/pl_alpaca_data_cleaned
language:
- pl
tags:
- alpaca
- llama
- self-instruct
- casual language model
- llm
- gpt
- chat-gpt
---
# Polpaca: The Alpaca Speaks Polish
The blogpost: https://medium.com/@mmosiolek/can-alpacas-learn-languages-df48a03b6d8
[LLaMA](https://ai.facebook.com/blog/large-language-model-llama-meta-ai/) is a state-of-the-art, foundational, open-source large language model designed to help engineers and researchers advance their work in NLP.
For example, Stanford researchers have fine-tuned [LLaMA](https://ai.facebook.com/blog/large-language-model-llama-meta-ai/) to construct an alternative to the famous ChatGPT - a model called [Alpaca](https://crfm.stanford.edu/2023/03/13/alpaca.html).
Unfortunately, [LLaMA](https://ai.facebook.com/blog/large-language-model-llama-meta-ai/) was trained on a dataset consisting mainly of English texts, with only 4.5% of the data relating to other languages.
In addition, the [Alpaca](https://crfm.stanford.edu/2023/03/13/alpaca.html) instruction training dataset consists only of examples of English instructions.
So [Alpaca](https://crfm.stanford.edu/2023/03/13/alpaca.html) simply doesn't work for the other languages.
This repo makes [Alpaca-Lora-7B](https://huggingface.co/tloen/alpaca-lora-7b) speak Polish.
### Usage
```python
from transformers import LlamaTokenizer, LlamaForCausalLM
from peft import PeftModel
import bitsandbytes as bnb
base = "decapoda-research/llama-7b-hf"
finetuned = "mmosiolek/polpaca-lora-7b"
tokenizer = LlamaTokenizer.from_pretrained(base)
tokenizer.pad_token_id = 0
tokenizer.padding_side = "left"
model = LlamaForCausalLM.from_pretrained(base)
model = PeftModel.from_pretrained(model, finetuned).to("cuda")
```
For output generation use the following code. Feel free to adjust the parameters according to your needs.
```python
from transformers import GenerationConfig
config = GenerationConfig(
temperature=0.1,
top_p=0.5,
top_k=40,
num_beams=4,
max_new_tokens=128,
repetition_penalty=1.2
)
def run(instruction, model, tokenizer):
encodings = tokenizer(instruction, padding=True, return_tensors="pt").to('cuda')
generated_ids = model.generate(
**encodings,
generation_config=GENERATION_CONFIG,
)
decoded = tokenizer.batch_decode(generated_ids)
del encodings, generated_ids
torch.cuda.empty_cache()
return decoded[0].split("\n")[-1]
```
### Example input/output
instruction:
```
Wymyśl kilka zapytań w google na temat kodowania.
```
output
```
Jaki jest najpopularniejszy język programowania?
Jaki jest najbardziej powszechnie używany język programowania?
Jaki jest najnowszy język programowania?
Jaki jest najbardziej efektywny język programowania?
```
---
instruction
```
Zrób listę pożądanych umiejętności inżynierów oprogramowania, którą możesz dodać do LinkedIn.
```
output
```
Pożądane umiejętności dla inżyniera oprogramowania obejmują:
- Programowanie w językach takich jak Java, C++, C#, Python, JavaScript i HTML
- Wnioskowanie logiczne
- Rozwiązywanie problemów
- Inżynieria oprogramowania
- Uczenie maszynowe
- Przetwarzanie języka naturalnego (NLP)
- Systemy zarządzania bazami danych (DBMS)
- Architektura
```
---
instruction
```
W odniesieniu do danego scenariusza pogody podaj kilka wskazówek, jak dostosować do niego plany podróży.
```
input
```
nagłą zmianę temperatury
```
output
```
Kilka wskazówek dotyczących dostosowania planów podróży w przypadku nagłej zmiany temperatury obejmują:
1. Upewnij się, że masz odpowiednie ubrania i akcesoria, takie jak krem przeciwsłoneczny, kapelusze i okulary przeciwsłoneczne.
2. Upewnij się, że masz wystarczającą ilość płynów, takich jak woda i napoje gazowane.
```
|
Adinda/Adinda
|
[
"license:artistic-2.0"
] | 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:
- 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: -0.24 +/- 0.12
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
...
```
|
Aimendo/Triage
|
[] | 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-4.0
tags:
- generated_from_trainer
datasets:
- qg_squadshifts
metrics:
- bleu
model-index:
- name: t5-small-squad-qg-a2c-spt
results:
- task:
name: Sequence-to-sequence Language Modeling
type: text2text-generation
dataset:
name: qg_squadshifts
type: qg_squadshifts
config: new_wiki
split: test
args: new_wiki
metrics:
- name: Bleu
type: bleu
value: 0.23693792340861347
---
<!-- 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. -->
# t5-small-squad-qg-a2c-spt
This model is a fine-tuned version of [lmqg/t5-small-squad-qg](https://huggingface.co/lmqg/t5-small-squad-qg) on the qg_squadshifts dataset.
It achieves the following results on the evaluation set:
- Loss: 3.4424
- Bleu: 0.2369
- Precisions: [0.5087032407189018, 0.27403783600926385, 0.18636099825885083, 0.1320389623167492]
- Brevity Penalty: 0.9790
- Length Ratio: 0.9793
- Translation Length: 42398
- Reference Length: 43296
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0001
- train_batch_size: 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: 10
- label_smoothing_factor: 0.15
### Training results
| Training Loss | Epoch | Step | Validation Loss | Bleu | Precisions | Brevity Penalty | Length Ratio | Translation Length | Reference Length |
|:-------------:|:-----:|:----:|:---------------:|:------:|:-----------------------------------------------------------------------------------:|:---------------:|:------------:|:------------------:|:----------------:|
| 3.646 | 1.0 | 42 | 3.4501 | 0.2324 | [0.5031057356491574, 0.26807773815061764, 0.18061915046796256, 0.12696709585121602] | 0.9853 | 0.9854 | 42663 | 43296 |
| 3.5951 | 2.0 | 84 | 3.4456 | 0.2328 | [0.5061518076850274, 0.27000913957435696, 0.1832138903455107, 0.12926178476134007] | 0.9759 | 0.9762 | 42264 | 43296 |
| 3.5572 | 3.0 | 126 | 3.4427 | 0.2355 | [0.505242954779515, 0.27049412978970455, 0.18334962341171734, 0.12953889087192133] | 0.9867 | 0.9868 | 42724 | 43296 |
| 3.5295 | 4.0 | 168 | 3.4411 | 0.2351 | [0.5057055646865461, 0.27130317702804174, 0.1838566316518527, 0.12948538278525568] | 0.9836 | 0.9837 | 42590 | 43296 |
| 3.4945 | 5.0 | 210 | 3.4418 | 0.2359 | [0.5068653913859875, 0.27228491562273527, 0.18446938010211442, 0.1297804417225878] | 0.9839 | 0.9840 | 42605 | 43296 |
| 3.4771 | 6.0 | 252 | 3.4432 | 0.2375 | [0.507522591245159, 0.2735272802567554, 0.18594051980269422, 0.13157208938693074] | 0.9839 | 0.9840 | 42605 | 43296 |
| 3.46 | 7.0 | 294 | 3.4431 | 0.2377 | [0.5092926294961487, 0.2746595987943041, 0.1869911632623497, 0.13212859294179272] | 0.9803 | 0.9805 | 42453 | 43296 |
| 3.4656 | 8.0 | 336 | 3.4413 | 0.2368 | [0.5082384555547698, 0.2738076663025953, 0.18616789908655937, 0.1317669419321012] | 0.9796 | 0.9798 | 42423 | 43296 |
| 3.443 | 9.0 | 378 | 3.4425 | 0.2373 | [0.5089378360532025, 0.27438532587485365, 0.18661869668658967, 0.13227530576778043] | 0.9792 | 0.9794 | 42404 | 43296 |
| 3.4455 | 10.0 | 420 | 3.4424 | 0.2369 | [0.5087032407189018, 0.27403783600926385, 0.18636099825885083, 0.1320389623167492] | 0.9790 | 0.9793 | 42398 | 43296 |
### Framework versions
- Transformers 4.27.4
- Pytorch 1.9.0
- Datasets 2.9.0
- Tokenizers 0.13.2
|
Aimendo/autonlp-triage-35248482
|
[
"pytorch",
"bert",
"text-classification",
"en",
"dataset:Aimendo/autonlp-data-triage",
"transformers",
"autonlp",
"co2_eq_emissions"
] |
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 |
---
tags:
- spacy
- token-classification
language:
- en
model-index:
- name: en_pipeline
results:
- task:
name: NER
type: token-classification
metrics:
- name: NER Precision
type: precision
value: 1.0
- name: NER Recall
type: recall
value: 1.0
- name: NER F Score
type: f_score
value: 1.0
---
| Feature | Description |
| --- | --- |
| **Name** | `en_pipeline` |
| **Version** | `0.0.0` |
| **spaCy** | `>=3.5.1,<3.6.0` |
| **Default Pipeline** | `transformer`, `ner` |
| **Components** | `transformer`, `ner` |
| **Vectors** | 0 keys, 0 unique vectors (0 dimensions) |
| **Sources** | n/a |
| **License** | n/a |
| **Author** | [n/a]() |
### Label Scheme
<details>
<summary>View label scheme (5 labels for 1 components)</summary>
| Component | Labels |
| --- | --- |
| **`ner`** | `avg rating`, `name`, `price`, `quantity`, `total rating` |
</details>
### Accuracy
| Type | Score |
| --- | --- |
| `ENTS_F` | 100.00 |
| `ENTS_P` | 100.00 |
| `ENTS_R` | 100.00 |
| `TRANSFORMER_LOSS` | 1.73 |
| `NER_LOSS` | 1.25 |
|
AkshatSurolia/ICD-10-Code-Prediction
|
[
"pytorch",
"bert",
"transformers",
"text-classification",
"license:apache-2.0",
"has_space"
] |
text-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
}
}
}
| 994
| null |
---
license: apache-2.0
language:
- tr
pipeline_tag: text-classification
widget:
- text: >-
Seni lanet olası, senin derdin ne ha?
example_title: Example Text
---
---
|
AkshayDev/BERT_Fine_Tuning
|
[] | 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:
- 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: -172.26 +/- 106.08
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': 'brand25/ppo-LunarLander-v2-cleanRL'
'batch_size': 512
'minibatch_size': 128}
```
|
AkshaySg/GrammarCorrection
|
[] | 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
| 2023-04-03T11:28:06Z
|
---
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: Westcott/poca-SoccerTwos
3. Step 2: Select your *.nn /*.onnx file
4. Click on Watch the agent play 👀
|
Aleksandar1932/distilgpt2-rock
|
[
"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
}
}
}
| 11
| 2023-04-03T12:06:17Z
|
---
license: apache-2.0
language:
- tr
pipeline_tag: text-classification
widget:
- text: >-
Seni lanet olası, senin derdin ne ha?
example_title: Example Text
---
---
|
Aleksandar1932/gpt2-country
|
[
"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
}
}
}
| 12
| 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: 10.02 +/- 3.78
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 brand25/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.
|
AlexaRyck/KEITH
|
[] | 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: creativeml-openrail-m
language:
- ja
pipeline_tag: text-to-image
tags:
- stable-diffusion
- stable-diffusion-diffusers
- text-to-image
library_name: diffusers
---
# HimawariMixV3とは
HimawariMixV3は様々なモデルをマージしたものになります！<br>
今回のV3は2.0の大規模改修モデルとなり更に背景に強くなりました<br>
---
# 特徴
HimawariMixは他のモデルと比較し彩度が高いmodelとなっていて背景を特に重視したAnimeModelになります<br>
SakuraMixとの違いはSakuraMixのほうが背景よりもキャラ重視になっておりSakuraMixのほうが扱いやすい感じます(個人的な印象)
---
# README
✅=Allowed<br>
❌=Not allowed<br>
❌ 本モデルを商用の画像生成サービスで利用する行為 <br>
Use of this model for commercial image generation services
❌ 本モデルや本モデルをマージしたモデルを販売する行為<br>
The act of selling this model or a model merged with this model
❌ 本モデルを使用し意図的に違法な出力をする行為 <br>
Intentionally using this model to produce illegal output
❌ 本モデルをマージしたモデルに異なる権限を与える行為 <br>
Have different permissions when sharing
❌ 本モデルをマージしたモデルを配布または本モデルを再配布した際に同じ使用制限を含め、CreativeML OpenRAIL-M のコピーをすべてのユーザーと共有しない行為 <br>
The act of not sharing a copy of CreativeML OpenRAIL-M with all users, including the same usage restrictions when distributing or redistributing a merged model of this model.
✅ 本モデルで生成した画像を商用利用する行為 <br>
Commercial use of images generated by this model
✅ 本モデルを使用したマージモデルを使用または再配布する行為 <br>
Use or redistribution of merged models using this model
✅ 本モデルのクレジット表記をせずに使用する行為 <br>
Use of this model without crediting the model
❌ 以下の説明に違反する行為 <br>
Violation of the following description
---
### 本モデルのおすすめ設定
Negative:
EasyNegative, bad-hands-5, (worst quality, low quality:1.4), text, grid view, nsfw, crumpled limbs, Bad Anatomy
---
### 出力例
---
### 連絡先
Twitter: min__san<br>
mail: natsusakiyomi@mail.ru
|
Alexander-Learn/bert-finetuned-ner-accelerate
|
[
"pytorch",
"bert",
"token-classification",
"transformers",
"autotrain_compatible"
] |
token-classification
|
{
"architectures": [
"BertForTokenClassification"
],
"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
}
}
}
| 4
| null |
---
license: mit
tags:
- pytorch
- diffusers
- unconditional-image-generation
- diffusion-models-class
---
# Model Card for Unit 1 of the [Diffusion Models Class 🧨](https://github.com/huggingface/diffusion-models-class)
This model is a diffusion model for unconditional image generation of cute 🦋.
## Usage
```python
from diffusers import DDPMPipeline
pipeline = DDPMPipeline.from_pretrained('Murray04/sd-class-butterflies-32')
image = pipeline().images[0]
image
```
|
Alexander-Learn/bert-finetuned-squad-accelerate
|
[] | 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: mlm-20230403-001-1
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. -->
# mlm-20230403-001-1
This model is a fine-tuned version of [indobenchmark/indobert-base-p1](https://huggingface.co/indobenchmark/indobert-base-p1) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.7205
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 20
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:-----:|:---------------:|
| 2.2253 | 1.0 | 913 | 1.6319 |
| 1.548 | 2.0 | 1826 | 1.3652 |
| 1.3394 | 3.0 | 2739 | 1.2166 |
| 1.2098 | 4.0 | 3652 | 1.1025 |
| 1.1165 | 5.0 | 4565 | 1.0387 |
| 1.0774 | 6.0 | 5478 | 0.9896 |
| 1.0021 | 7.0 | 6391 | 0.9372 |
| 0.9598 | 8.0 | 7304 | 0.9025 |
| 0.9144 | 9.0 | 8217 | 0.8720 |
| 0.8858 | 10.0 | 9130 | 0.8518 |
| 0.8561 | 11.0 | 10043 | 0.8142 |
| 0.8344 | 12.0 | 10956 | 0.8189 |
| 0.8102 | 13.0 | 11869 | 0.7833 |
| 0.7964 | 14.0 | 12782 | 0.7783 |
| 0.7834 | 15.0 | 13695 | 0.7577 |
| 0.7483 | 16.0 | 14608 | 0.7441 |
| 0.7437 | 17.0 | 15521 | 0.7408 |
| 0.7507 | 18.0 | 16434 | 0.7268 |
| 0.7382 | 19.0 | 17347 | 0.7223 |
| 0.7263 | 20.0 | 18260 | 0.7301 |
### Framework versions
- Transformers 4.27.4
- Pytorch 1.13.1+cu116
- Datasets 2.11.0
- Tokenizers 0.13.2
|
AlexeyIgnatov/albert-xlarge-v2-squad-v2
|
[] | 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
language:
- tr
pipeline_tag: text-classification
widget:
- text: >-
Seni lanet olası, senin derdin ne ha?
example_title: Example Text
---
---
|
AliPotter24/a
|
[] | 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="saberzl/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"])
```
|
Alireza1044/albert-base-v2-qnli
|
[
"pytorch",
"tensorboard",
"albert",
"text-classification",
"en",
"dataset:glue",
"transformers",
"generated_from_trainer",
"license:apache-2.0"
] |
text-classification
|
{
"architectures": [
"AlbertForSequenceClassification"
],
"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
}
}
}
| 41
| 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: -1.90 +/- 0.48
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
...
```
|
AllwynJ/HarryBoy
|
[
"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
}
}
}
| 12
| 2023-04-03T12:55:48Z
|
---
license: apache-2.0
language:
- tr
pipeline_tag: text-classification
widget:
- text: >-
Seni lanet olası, senin derdin ne ha?
example_title: Example Text
---
---
|
Allybaby21/Allysai
|
[] | 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 Izara/TextClassificationOnDiseases is restricted and you are not in the authorized list. Visit https://huggingface.co/Izara/TextClassificationOnDiseases to ask for access.
|
AnonymousSub/SR_rule_based_hier_quadruplet_epochs_1_shard_1
|
[
"pytorch",
"bert",
"feature-extraction",
"transformers"
] |
feature-extraction
|
{
"architectures": [
"BertModel"
],
"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
| 2023-04-03T15:23:40Z
|
---
tags:
- Taxi-v3
- q-learning
- reinforcement-learning
- custom-implementation
model-index:
- name: Taxi-v3
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: Taxi-v3
type: Taxi-v3
metrics:
- type: mean_reward
value: 7.54 +/- 2.74
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="sofre/Taxi-v3", filename="q-learning.pkl")
# Don't forget to check if you need to add additional attributes (is_slippery=False etc)
env = gym.make(model["env_id"])
```
|
AnonymousSub/SR_rule_based_roberta_hier_quadruplet_epochs_1_shard_1
|
[
"pytorch",
"roberta",
"feature-extraction",
"transformers"
] |
feature-extraction
|
{
"architectures": [
"RobertaModel"
],
"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
}
}
}
| 2
| 2023-04-03T15:28:25Z
|
---
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")
```
|
AnonymousSub/bert_hier_diff_equal_wts_epochs_1_shard_10
|
[
"pytorch",
"bert",
"feature-extraction",
"transformers"
] |
feature-extraction
|
{
"architectures": [
"BertModel"
],
"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
| null |
---
license: mit
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
model-index:
- name: XLMR_HASOC
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. -->
# XLMR_HASOC
This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 1.3081
- Accuracy: 0.6667
- F1: 0.6845
## 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: 2
- eval_batch_size: 2
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-05
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 3
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
| 0.7501 | 1.0 | 2100 | 0.7108 | 0.6756 | 0.7065 |
| 0.8911 | 2.0 | 4200 | 0.8944 | 0.6739 | 0.7022 |
| 0.9043 | 3.0 | 6300 | 1.3081 | 0.6667 | 0.6845 |
### Framework versions
- Transformers 4.27.4
- Pytorch 1.13.1+cu116
- Datasets 2.11.0
- Tokenizers 0.13.2
|
AnonymousSub/bert_mean_diff_epochs_1_shard_1
|
[
"pytorch",
"bert",
"feature-extraction",
"transformers"
] |
feature-extraction
|
{
"architectures": [
"BertModel"
],
"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
}
}
}
| 6
| 2023-04-03T16:18:53Z
|
---
tags:
- Pixelcopter-PLE-v0
- reinforce
- reinforcement-learning
- custom-implementation
- deep-rl-class
model-index:
- name: HF_DRL_U4_pixelcopter_reinforcepg
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: Pixelcopter-PLE-v0
type: Pixelcopter-PLE-v0
metrics:
- type: mean_reward
value: 184.60 +/- 148.96
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
|
AnonymousSub/bert_mean_diff_epochs_1_shard_10
|
[
"pytorch",
"bert",
"feature-extraction",
"transformers"
] |
feature-extraction
|
{
"architectures": [
"BertModel"
],
"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
}
}
}
| 4
| null |
---
tags:
- CartPole-v1
- 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: CartPole-v1
type: CartPole-v1
metrics:
- type: mean_reward
value: 22.70 +/- 12.09
name: mean_reward
verified: false
---
# PPO Agent Playing CartPole-v1
This is a trained model of a PPO agent playing CartPole-v1.
# Hyperparameters
```python
{'exp_name': 'ppo'
'gym_id': 'CartPole-v1'
'learning_rate': 0.00025
'seed': 1
'total_timesteps': 25000
'torch_deterministic': True
'cuda': True
'track': False
'wandb_project_name': 'ppo-implementation-details'
'wandb_entity': None
'capture_video': False
'repo_id': 'Paperbag/ppo-CartPole-v1'
'env_id': 'CartPole-v1'
'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}
```
|
AnonymousSub/cline
|
[
"pytorch",
"roberta",
"transformers"
] | null |
{
"architectures": [
"LecbertForPreTraining"
],
"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
}
}
}
| 2
| 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: -112.66 +/- 36.33
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': 'Paperbag/LunarLander-v2'
'batch_size': 512
'minibatch_size': 128}
```
|
AnonymousSub/cline_emanuals
|
[
"pytorch",
"roberta",
"transformers"
] | null |
{
"architectures": [
"LecbertForPreTraining"
],
"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
| 2023-04-03T16:49:34Z
|
---
license: apache-2.0
tags:
- generated_from_keras_callback
model-index:
- name: HASAN55/bert-finetuned-squadddd
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. -->
# HASAN55/bert-finetuned-squadddd
This model is a fine-tuned version of [bert-base-cased](https://huggingface.co/bert-base-cased) on an unknown dataset.
It achieves the following results on the evaluation set:
- Train Loss: 0.6652
- Train End Logits Accuracy: 0.8086
- Train Start Logits Accuracy: 0.7691
- Validation Loss: 0.0
- Validation End Logits Accuracy: 0.0
- Validation Start Logits Accuracy: 0.0
- Epoch: 1
## 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': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 5e-05, 'decay_steps': 11090, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.01}
- training_precision: float32
### Training results
| Train Loss | Train End Logits Accuracy | Train Start Logits Accuracy | Validation Loss | Validation End Logits Accuracy | Validation Start Logits Accuracy | Epoch |
|:----------:|:-------------------------:|:---------------------------:|:---------------:|:------------------------------:|:--------------------------------:|:-----:|
| 1.2234 | 0.6746 | 0.6356 | 0.0 | 0.0 | 0.0 | 0 |
| 0.6652 | 0.8086 | 0.7691 | 0.0 | 0.0 | 0.0 | 1 |
### Framework versions
- Transformers 4.27.4
- TensorFlow 2.12.0
- Datasets 2.11.0
- Tokenizers 0.13.3
|
AnonymousSub/declutr-model-emanuals
|
[
"pytorch",
"roberta",
"fill-mask",
"transformers",
"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
}
}
}
| 4
| null |
---
license: apache-2.0
tags:
- generated_from_keras_callback
model-index:
- name: HASAN55/bert-finetuned-squuuad
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. -->
# HASAN55/bert-finetuned-squuuad
This model is a fine-tuned version of [bert-base-cased](https://huggingface.co/bert-base-cased) on an unknown dataset.
It achieves the following results on the evaluation set:
- Train Loss: 4.8790
- Train End Logits Accuracy: 0.1667
- Train Start Logits Accuracy: 0.2083
- Validation Loss: 0.0
- Validation End Logits Accuracy: 0.0
- Validation Start Logits Accuracy: 0.0
- Epoch: 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:
- optimizer: {'name': 'AdamWeightDecay', 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 18, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.01}
- training_precision: mixed_float16
### Training results
| Train Loss | Train End Logits Accuracy | Train Start Logits Accuracy | Validation Loss | Validation End Logits Accuracy | Validation Start Logits Accuracy | Epoch |
|:----------:|:-------------------------:|:---------------------------:|:---------------:|:------------------------------:|:--------------------------------:|:-----:|
| 4.8790 | 0.1667 | 0.2083 | 0.0 | 0.0 | 0.0 | 0 |
### Framework versions
- Transformers 4.27.4
- TensorFlow 2.12.0
- Datasets 2.11.0
- Tokenizers 0.13.2
|
AnonymousSub/dummy_2
|
[
"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
}
}
}
| 39
| 2023-04-03T17:07:45Z
|
---
license: apache-2.0
---
|
AnonymousSub/rule_based_bert_quadruplet_epochs_1_shard_1_squad2.0
|
[
"pytorch",
"bert",
"question-answering",
"transformers",
"autotrain_compatible"
] |
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
}
}
}
| 3
| 2023-04-03T17:39:52Z
|
---
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: -4.92 +/- 1.84
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
...
```
|
AnonymousSub/rule_based_bert_quadruplet_epochs_1_shard_1_wikiqa
|
[
"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
| 2023-04-03T17:41:07Z
|
---
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- conll2003
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: bert-finetuned-ner
results:
- task:
name: Token Classification
type: token-classification
dataset:
name: conll2003
type: conll2003
config: conll2003
split: validation
args: conll2003
metrics:
- name: Precision
type: precision
value: 0.935222001325381
- name: Recall
type: recall
value: 0.9500168293503871
- name: F1
type: f1
value: 0.9425613624979129
- name: Accuracy
type: accuracy
value: 0.9866074056631542
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# bert-finetuned-ner
This model is a fine-tuned version of [bert-base-cased](https://huggingface.co/bert-base-cased) on the conll2003 dataset.
It achieves the following results on the evaluation set:
- Loss: 0.0611
- Precision: 0.9352
- Recall: 0.9500
- F1: 0.9426
- Accuracy: 0.9866
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
### Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
| 0.0869 | 1.0 | 1756 | 0.0729 | 0.9084 | 0.9300 | 0.9191 | 0.9817 |
| 0.0351 | 2.0 | 3512 | 0.0626 | 0.9286 | 0.9458 | 0.9371 | 0.9854 |
| 0.0171 | 3.0 | 5268 | 0.0611 | 0.9352 | 0.9500 | 0.9426 | 0.9866 |
### Framework versions
- Transformers 4.27.4
- Pytorch 2.0.0+cu118
- Datasets 2.11.0
- Tokenizers 0.13.2
|
AnonymousSub/rule_based_bert_triplet_epochs_1_shard_1
|
[
"pytorch",
"bert",
"feature-extraction",
"transformers"
] |
feature-extraction
|
{
"architectures": [
"BertModel"
],
"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
| 2023-04-03T17:44:33Z
|
---
license: apache-2.0
tags:
- generated_from_trainer
model-index:
- name: distilgpt2-finetuned-brookstraining
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. -->
# distilgpt2-finetuned-brookstraining
This model is a fine-tuned version of [distilgpt2](https://huggingface.co/distilgpt2) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 3.6363
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 15
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| No log | 1.0 | 201 | 4.1881 |
| No log | 2.0 | 402 | 4.0630 |
| 4.3174 | 3.0 | 603 | 3.9803 |
| 4.3174 | 4.0 | 804 | 3.9193 |
| 4.0754 | 5.0 | 1005 | 3.8654 |
| 4.0754 | 6.0 | 1206 | 3.8216 |
| 4.0754 | 7.0 | 1407 | 3.7805 |
| 3.9638 | 8.0 | 1608 | 3.7475 |
| 3.9638 | 9.0 | 1809 | 3.7168 |
| 3.8825 | 10.0 | 2010 | 3.6928 |
| 3.8825 | 11.0 | 2211 | 3.6715 |
| 3.8825 | 12.0 | 2412 | 3.6567 |
| 3.8238 | 13.0 | 2613 | 3.6455 |
| 3.8238 | 14.0 | 2814 | 3.6389 |
| 3.7844 | 15.0 | 3015 | 3.6363 |
### Framework versions
- Transformers 4.27.4
- Pytorch 1.13.1
- Datasets 2.11.0
- Tokenizers 0.11.0
|
AnonymousSub/rule_based_bert_triplet_epochs_1_shard_10
|
[
"pytorch",
"bert",
"feature-extraction",
"transformers"
] |
feature-extraction
|
{
"architectures": [
"BertModel"
],
"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
}
}
}
| 4
| 2023-04-03T17:45:44Z
|
---
datasets:
- Izara/ClassificationOnDiseaseDataset
language:
- en
metrics:
- accuracy
library_name: sklearn
pipeline_tag: text-classification
---
|
AnonymousSub/rule_based_only_classfn_epochs_1_shard_1
|
[
"pytorch",
"bert",
"feature-extraction",
"transformers"
] |
feature-extraction
|
{
"architectures": [
"BertModel"
],
"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
}
}
}
| 4
| 2023-04-03T18:13:23Z
|
---
license: creativeml-openrail-m
---
https://civitai.com/models/28708/noelle-silva-or-black-clover
|
AnonymousSub/rule_based_roberta_bert_triplet_epochs_1_shard_10
|
[
"pytorch",
"roberta",
"feature-extraction",
"transformers"
] |
feature-extraction
|
{
"architectures": [
"RobertaModel"
],
"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
}
}
}
| 2
| 2023-04-03T18:30:48Z
|
---
license: creativeml-openrail-m
---
https://civitai.com/models/27577/volleyball-uniform
|
AnonymousSub/rule_based_roberta_hier_quadruplet_epochs_1_shard_1_wikiqa
|
[
"pytorch",
"roberta",
"text-classification",
"transformers"
] |
text-classification
|
{
"architectures": [
"RobertaForSequenceClassification"
],
"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
}
}
}
| 24
| null |
Access to model him1411/EDGAR-Tk-instruct-base-inst-tune is restricted and you are not in the authorized list. Visit https://huggingface.co/him1411/EDGAR-Tk-instruct-base-inst-tune to ask for access.
|
AnonymousSub/rule_based_roberta_hier_triplet_epochs_1_shard_1
|
[
"pytorch",
"roberta",
"feature-extraction",
"transformers"
] |
feature-extraction
|
{
"architectures": [
"RobertaModel"
],
"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
}
}
}
| 4
| 2023-04-03T18:42:19Z
|
---
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/1600568966660952065/5Pi8CRjx_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">Willow Hart</div>
<div style="text-align: center; font-size: 14px;">@whart31</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 Willow Hart.
| Data | Willow Hart |
| --- | --- |
| Tweets downloaded | 3207 |
| Retweets | 63 |
| Short tweets | 290 |
| Tweets kept | 2854 |
[Explore the data](https://wandb.ai/wandb/huggingtweets/runs/kfvmn3e7/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 @whart31's tweets.
Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/wandb/huggingtweets/runs/99156pb3) for full transparency and reproducibility.
At the end of training, [the final model](https://wandb.ai/wandb/huggingtweets/runs/99156pb3/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/whart31')
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)
|
AnonymousSub/rule_based_roberta_hier_triplet_epochs_1_shard_10
|
[
"pytorch",
"roberta",
"feature-extraction",
"transformers"
] |
feature-extraction
|
{
"architectures": [
"RobertaModel"
],
"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
| 2023-04-03T18:42:31Z
|
---
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: 611.50 +/- 169.72
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 romeromuerto -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 romeromuerto -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 romeromuerto
```
## Hyperparameters
```python
OrderedDict([('batch_size', 32),
('buffer_size', 100000),
('env_wrapper',
['stable_baselines3.common.atari_wrappers.AtariWrapper']),
('exploration_final_eps', 0.01),
('exploration_fraction', 0.1),
('frame_stack', 4),
('gradient_steps', 1),
('learning_rate', 0.0001),
('learning_starts', 100000),
('n_timesteps', 1000000),
('optimize_memory_usage', False),
('policy', 'CnnPolicy'),
('target_update_interval', 1000),
('train_freq', 4),
('normalize', False)])
```
|
AnonymousSub/rule_based_roberta_hier_triplet_epochs_1_shard_1_squad2.0
|
[
"pytorch",
"roberta",
"question-answering",
"transformers",
"autotrain_compatible"
] |
question-answering
|
{
"architectures": [
"RobertaForQuestionAnswering"
],
"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
}
}
}
| 4
| 2023-04-03T18:44:26Z
|
---
license: mit
tags:
- generated_from_trainer
model-index:
- name: gpt2-finetuned-brookstraining
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-finetuned-brookstraining
This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 4.3233
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 20
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| No log | 1.0 | 201 | 3.7473 |
| No log | 2.0 | 402 | 3.7192 |
| 3.9557 | 3.0 | 603 | 3.7303 |
| 3.9557 | 4.0 | 804 | 3.7354 |
| 3.4723 | 5.0 | 1005 | 3.7725 |
| 3.4723 | 6.0 | 1206 | 3.7934 |
| 3.4723 | 7.0 | 1407 | 3.8325 |
| 3.1092 | 8.0 | 1608 | 3.8907 |
| 3.1092 | 9.0 | 1809 | 3.9566 |
| 2.8224 | 10.0 | 2010 | 3.9908 |
| 2.8224 | 11.0 | 2211 | 4.0487 |
| 2.8224 | 12.0 | 2412 | 4.0744 |
| 2.5733 | 13.0 | 2613 | 4.1212 |
| 2.5733 | 14.0 | 2814 | 4.1872 |
| 2.3879 | 15.0 | 3015 | 4.2208 |
| 2.3879 | 16.0 | 3216 | 4.2358 |
| 2.3879 | 17.0 | 3417 | 4.2799 |
| 2.2721 | 18.0 | 3618 | 4.3077 |
| 2.2721 | 19.0 | 3819 | 4.3217 |
| 2.2043 | 20.0 | 4020 | 4.3233 |
### Framework versions
- Transformers 4.27.4
- Pytorch 1.13.1
- Datasets 2.11.0
- Tokenizers 0.11.0
|
AnonymousSub/rule_based_roberta_only_classfn_epochs_1_shard_1_squad2.0
|
[
"pytorch",
"roberta",
"question-answering",
"transformers",
"autotrain_compatible"
] |
question-answering
|
{
"architectures": [
"RobertaForQuestionAnswering"
],
"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
}
}
}
| 4
| 2023-04-03T18:53:31Z
|
---
tags:
- autotrain
- summarization
language:
- unk
widget:
- text: "I love AutoTrain 🤗"
datasets:
- Ybhav14/autotrain-data-chat-sum-dialogsum-samsum
co2_eq_emissions:
emissions: 3.0774487291128
---
# Model Trained Using AutoTrain
- Problem type: Summarization
- Model ID: 46317114985
- CO2 Emissions (in grams): 3.0774
## Validation Metrics
- Loss: 1.270
- Rouge1: 39.115
- Rouge2: 17.283
- RougeL: 30.158
- RougeLsum: 34.226
- Gen Len: 61.380
## Usage
You can use cURL to access this model:
```
$ curl -X POST -H "Authorization: Bearer YOUR_HUGGINGFACE_API_KEY" -H "Content-Type: application/json" -d '{"inputs": "I love AutoTrain"}' https://api-inference.huggingface.co/Ybhav14/autotrain-chat-sum-dialogsum-samsum-46317114985
```
|
AnonymousSub/rule_based_roberta_only_classfn_twostage_epochs_1_shard_1_squad2.0
|
[
"pytorch",
"roberta",
"question-answering",
"transformers",
"autotrain_compatible"
] |
question-answering
|
{
"architectures": [
"RobertaForQuestionAnswering"
],
"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
}
}
}
| 2
| 2023-04-03T18:58:51Z
|
---
language: hy
tags:
- exbert
- armenian
- mlm
- llm
license: mit
datasets:
- oscar
---
# Model Card for HyeBERT
Pre-trained language model trained on Armenian using a masked language training strategy. The architecture is based on [BERT](https://arxiv.org/abs/1810.04805) but trained exclusively for the Armenian language subset of OSCAR, a cleaned and de-duplicated subset of the common crawl dataset (hence, the `Hye` in HyeBERT).
Disclaimer: this model is not specifically trained for either the Western or Eastern dialect, though the data likely contain more examples of Eastern Armenian.
### Model Description
HyeBERT is shares the same architecture as BERT; it is a stacked transformer model trained on a large corpus of Armenian without any human annotations. However, it was trained using only the mask language task (replacing 15% of tokens with `[MASK]` and trying to predict them from the other tokens in the text) and not to predict the next sentence, making it more akin to [RoBERTa](https://arxiv.org/pdf/1907.11692.pdf). Unlike RoBERTa, however, it tokenizes using WordPiece rather than BPE.
## Inteded Uses
### Direct Use
As an MLM, this model can be used to predict word in a sentence or text generation, though generation would best be done with a model like GPT.
### Downstream Use [optional]
The ideal use of this model is fine-tuning on a specific classification task for Armenian.
## Bias, Risks, and Limitations
As mentioned earlier, this model is not trained exclusively on Western or Eastern Armenian which may lead to problems in its internal understanding of the language's syntax and lexicon. In addition, many of the training texts include content from other languages (mostly English and Russian) which may affect the performance of the model.
## How to Get Started with the Model
Use the code below to get started with the model.
{{ get_started_code | default("[More Information Needed]", true)}}
## Training Details
### Training Data
This model was trained on the Armenian subset of the [OSCAR](https://huggingface.co/datasets/oscar) corpus, which is a cleaned version of the common crawl. The training data consiset of roughly XXX document, with roughly YYY tokens in total. 2% of the total dataset was held out and using as validation.
### Training Procedure
The model was trained by masking 15% of tokens and predicting the identity of those masked tokens from the unmasked items in a training datum. The model was trained over 3 epochs and the identify of the masked token for a given text was reassigned for each epoch, i.e., the masks moved around each epoch.
#### Preprocessing
No major preprocessing. Texts of less than 5 character were removed and texts were limited to 512 tokens.
#### Training Hyperparameters
- Optimizer: AdamW
- Learning rate: `1e4`
- Num. attention head: 12
- Num. hidden layers: 6
- Vocab. size: 30,000
- Embedding size: 768
## Evaluation
At each epoch's completion, the loss was computed for a held out validation set, roughly 2% the size of the total data.
```
0 evaluating....
val_loss: 0.47787963975066194
1 evaluating....
val_loss: 0.47497553823474115
2 evaluating....
val_loss: 0.4765327044259816
```
## Model Card Authors [optional]
Adam King
## Model Card Contact
adam.king.phd@gmail.com
|
AnonymousSub/rule_based_roberta_twostagetriplet_hier_epochs_1_shard_10
|
[
"pytorch",
"roberta",
"feature-extraction",
"transformers"
] |
feature-extraction
|
{
"architectures": [
"RobertaModel"
],
"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 |
---
license: apache-2.0
tags:
- generated_from_trainer
model-index:
- name: t5-large-new-v1
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. -->
# t5-large-new-v1
This model is a fine-tuned version of [t5-large](https://huggingface.co/t5-large) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.1352
- Rouge2 Precision: 0.7349
- Rouge2 Recall: 0.0736
- Rouge2 Fmeasure: 0.1318
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 8
### Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge2 Precision | Rouge2 Recall | Rouge2 Fmeasure |
|:-------------:|:-----:|:-----:|:---------------:|:----------------:|:-------------:|:---------------:|
| 0.031 | 1.0 | 2000 | 0.1570 | 0.7141 | 0.0725 | 0.1298 |
| 0.022 | 2.0 | 4000 | 0.1339 | 0.7571 | 0.0751 | 0.1349 |
| 0.0191 | 3.0 | 6000 | 0.1333 | 0.76 | 0.077 | 0.138 |
| 0.0163 | 4.0 | 8000 | 0.1304 | 0.7413 | 0.0752 | 0.1343 |
| 0.0158 | 5.0 | 10000 | 0.1241 | 0.7372 | 0.0733 | 0.1311 |
| 0.0138 | 6.0 | 12000 | 0.1343 | 0.7486 | 0.0734 | 0.1317 |
| 0.0132 | 7.0 | 14000 | 0.1318 | 0.7232 | 0.0721 | 0.129 |
| 0.0122 | 8.0 | 16000 | 0.1352 | 0.7349 | 0.0736 | 0.1318 |
### Framework versions
- Transformers 4.27.3
- Pytorch 2.0.0+cu117
- Datasets 2.11.0
- Tokenizers 0.13.2
|
AnonymousSub/rule_based_twostagetriplet_epochs_1_shard_1
|
[
"pytorch",
"bert",
"feature-extraction",
"transformers"
] |
feature-extraction
|
{
"architectures": [
"BertModel"
],
"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
}
}
}
| 10
| null |
---
tags:
- llama
- vicuna
- text-generation-inference
---
**NOTE: Get the new version here: https://huggingface.co/eachadea/vicuna-13b-1.1**
|
AnonymousSub/rule_based_twostagetriplet_epochs_1_shard_1_wikiqa
|
[
"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 |
---
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: 272.89 +/- 14.24
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
...
```
|
AnonymousSub/rule_based_twostagetriplet_hier_epochs_1_shard_1
|
[
"pytorch",
"bert",
"feature-extraction",
"transformers"
] |
feature-extraction
|
{
"architectures": [
"BertModel"
],
"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 |
---
license: apache-2.0
---
# Debate-alpaca-lora
An English debate model by instruct-tuning LLaMA on [Kialo](https://www.kialo.com/) data.
We may ask the model to **support** or **oppose** a claim by the desconding order of impact.
**A quick start for inference**: <a href="https://colab.research.google.com/drive/1emuN4LcO4X2-BCoATbhawIZeGBr-d3Y-?usp=sharing" target="_parent"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"/></a> Some results are shown below:
```
Instruction: Support the following claim in descending order of impact.
Input: The impact of AI on the education will be positive.
Response: 1. AI will be able to help teachers with administrative tasks such as grading papers and keeping track of student progress.
2. AI can help teachers to keep track of students' progress and to make sure that they have understood the lesson.
3. AI will be able to help teachers to customize the lesson to their students' needs.
```
```
Instruction: Oppose the following claim in descending order of impact.
Input: The impact of AI on the education will be positive.
Response: 1. AI will replace teachers and thus reduce the number of jobs in this sector.
```
## Well-trained Model
| Model Name | Training Data and Setting |
| --- | :--- |
| [debate-alpaca-lora_7b_001](https://huggingface.co/YuxinJiang/debate-alpaca-lora_7b_001) | Trained on 21k kialo data, 10 epoch |
| [debate-alpaca-lora_7b_002](https://huggingface.co/YuxinJiang/debate-alpaca-lora_7b_002) | Trained on 52k alpaca data + 21k kialo data, 10 epoch |
## Data Collection
We collected 1,560 discussion threads before January 2020 of Kialo. Each discussion forms an argument tree as the following figure shows. Except the thesis, every claim in the argument tree either opposes or supports its parent claim. Moreover, each claim has impact votes assigned by the users of the platform. The impact votes evaluate how impactful a claim is.
We extract each argument with its supported children claims or opposed children claims to form a training example. The children claims are ranked by the descending order of impact. We delete children claims with votes less than 5 or average impact score less than 2. Finally, we obtain 20,998 [training data](https://github.com/YJiangcm/Debate-alpaca-lora/blob/master/kialo_debate.json) formuated as the following examples:
```
{
"instruction": "Support the following claim in descending order of impact.",
"input": "Pineapple belongs on pizza.",
"output": "1. From a culinary point of view, it's always a good thing to have another recipe to make.\n2. Even if pizza does not remain authentically Italian, that is fine, as many foods have been reinvented in foreign cultures and remained delicious e.g. sushi.\n3. Pineapple is a cost effective topping, adding sweetness to the recipe that few other ingredients could at that price point.\n4. Pineapples make pizza aesthetically pleasing.\n5. It's no coincidence that pineapple and pizza both start with pi.\n6. The taste is unusual, which is a good way of changing a routine.\n7. Pineapple enhances the pizza-indulging experience, making pizza bring a greater joy to and satisfaction from eating than ever before.\n8. Sweet pineapple and salty Canadian bacon or ham brings an [umami](https://www.realsimple.com/food-recipes/recipe-collections-favorites/what-umami) that is acceptable the world over.\n9. The pineapple cleanses the palate from having an overly fatty and savory taste.\n10. Assuming meat is also involved, the idea of combining meat and fruit is in [no way new](http://www.dartagnan.com/meat-and-fruit-recipes-and-combinations.html).\n11. If [pizza wurstel](http://pizzawuerstel.de/uber/) is ok, pineapple on pizza must be ok, too.\n12. It is a way for students to have a main course and desert in one meal, enabling more time for exstensive learning.\n13. Pineapple adds a texture and mouthfeel \\(in between crisp and juicy\\) that is missing from most pizzas. Textural variety makes for a more pleasing meal"
},
{
"instruction": "Oppose the following claim in descending order of impact.",
"input": "Pineapple belongs on pizza.",
"output": "1. Pineapple on pizza is an insult to the Italian origins of pizza.\n2. While pineapple is not an ideal pizza topping, it may be helped by being applied directly to the pizza surface by a qualified professional with the appropriate certifications in moisture removal procedures.\n3. You cannot eat Spongebob's house and be considered a good person at the same time.\n4. The sweetness of the pineapple is a bad fit for the general taste of the pizza.\n5. It's wrong in class terms. Pizza is proletarian food: good, cheap, and filling. Pineapples were a complete luxury when they first came to Europe, being displayed for [social status](https://www.foodbeast.com/news/til-people-used-to-rent-pineapples/) instead of eaten. This caused a divide, as the poor were deprived from eating it on pizza, while knowing the wealthy frivolously wasted it on decor. It's a class war on a plate, and that's exactly what it tastes like.\n6. Pineapple agriculture is [heavily polluting](http://www.ticotimes.net/2011/05/26/costa-rica-s-pineapple-boom-unhealthy-warn-experts), It destroys the lives of people in the tropics. Pizza is a large part of the demand for these pineapples.\n7. Torture is wrong. In today's day and age, we should have moved well beyond this kind of barbarism. It's cruel to a tropical fruit to be stuck on top of a pizza and be shoved into an oven.\n8. According to the [Oxford dictionary](https://en.oxforddictionaries.com/definition/pizza), pizza is \"a dish of Italian origin, consisting of a flat round base of dough baked with a topping of tomatoes and cheese, typically with added meat, fish, or vegetables\". Pineapple is a fruit.\n9. Eating pizza first and pineapple as dessert would make the whole meal experience better than together.\n10. Many people have spoken out publicly against pineapple pizza.\n11. Pineapple agriculture is bad for the environment.\n12. [Hawaiian pizza](https://en.wikipedia.org/wiki/Hawaiian_pizza) is a Canadian invention.\n13. Because of the incredible passion people have against putting pineapples on pizza, we ought not to combine the two, thus ending existing conflict and reducing the chance of future conflict, altogether leading towards world peace"
},
```
## Training
We train our model based on [Alpaca LoRA](https://github.com/tloen/alpaca-lora). It costs about 5 hours on 2 RTX 3090Ti.
```
WORLD_SIZE=2 CUDA_VISIBLE_DEVICES=0,1 torchrun --nproc_per_node=2 --master_port=1234 finetune.py \
--base_model='decapoda-research/llama-7b-hf' \
--resume_from_checkpoint 'alpaca-lora-7b' \
--num_epochs=10 \
--cutoff_len=256 \
--group_by_length \
--data_path 'kialo_debate.json' \
--output_dir './debate-alpaca-lora_7b_001' \
--lora_target_modules='[q_proj,k_proj,v_proj,o_proj]' \
--lora_r=16 \
--micro_batch_size=16
```
## Citation
Please cite the repo if you use the data or code in this repo.
```
@misc{debate-alpaca-lora,
author={Yuxin Jiang},
title = {An Instruction-following English debate model, LoRA tuning on LLaMA},
year = {2023},
publisher = {GitHub},
journal = {GitHub repository},
howpublished = {\url{https://github.com/YJiangcm/Debate-alpaca-lora}},
}
```
|
AnonymousSub/unsup-consert-base
|
[
"pytorch",
"bert",
"feature-extraction",
"transformers"
] |
feature-extraction
|
{
"architectures": [
"BertModel"
],
"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
}
}
}
| 6
| null |
---
library_name: stable-baselines3
tags:
- InvertedDoublePendulumBulletEnv-v0
- deep-reinforcement-learning
- reinforcement-learning
- stable-baselines3
model-index:
- name: A2C
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: InvertedDoublePendulumBulletEnv-v0
type: InvertedDoublePendulumBulletEnv-v0
metrics:
- type: mean_reward
value: 1129.72 +/- 346.09
name: mean_reward
verified: false
---
# **A2C** Agent playing **InvertedDoublePendulumBulletEnv-v0**
This is a trained model of a **A2C** agent playing **InvertedDoublePendulumBulletEnv-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
...
```
|
Anthos23/FS-distilroberta-fine-tuned
|
[
"pytorch",
"roberta",
"text-classification",
"transformers",
"has_space"
] |
text-classification
|
{
"architectures": [
"RobertaForSequenceClassification"
],
"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
}
}
}
| 33
| null |
---
license: mit
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: tmvar_5e-05
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. -->
# tmvar_5e-05
This model is a fine-tuned version of [microsoft/BiomedNLP-PubMedBERT-base-uncased-abstract-fulltext](https://huggingface.co/microsoft/BiomedNLP-PubMedBERT-base-uncased-abstract-fulltext) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.0165
- Precision: 0.8814
- Recall: 0.9243
- F1: 0.9024
- Accuracy: 0.9977
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- training_steps: 500
### Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
| 0.2905 | 1.47 | 25 | 0.0978 | 0.0 | 0.0 | 0.0 | 0.9843 |
| 0.0551 | 2.94 | 50 | 0.0382 | 0.3893 | 0.6270 | 0.4803 | 0.9887 |
| 0.0239 | 4.41 | 75 | 0.0192 | 0.5915 | 0.7514 | 0.6619 | 0.9947 |
| 0.0111 | 5.88 | 100 | 0.0153 | 0.8564 | 0.8703 | 0.8633 | 0.9964 |
| 0.0031 | 7.35 | 125 | 0.0126 | 0.8731 | 0.9297 | 0.9005 | 0.9975 |
| 0.002 | 8.82 | 150 | 0.0129 | 0.865 | 0.9351 | 0.8987 | 0.9978 |
| 0.0013 | 10.29 | 175 | 0.0163 | 0.8830 | 0.8973 | 0.8901 | 0.9968 |
| 0.0011 | 11.76 | 200 | 0.0171 | 0.9 | 0.9243 | 0.912 | 0.9970 |
| 0.001 | 13.24 | 225 | 0.0165 | 0.8808 | 0.9189 | 0.8995 | 0.9973 |
| 0.0008 | 14.71 | 250 | 0.0138 | 0.8923 | 0.9405 | 0.9158 | 0.9981 |
| 0.0007 | 16.18 | 275 | 0.0165 | 0.8763 | 0.9189 | 0.8971 | 0.9975 |
| 0.0005 | 17.65 | 300 | 0.0170 | 0.8854 | 0.9189 | 0.9019 | 0.9974 |
| 0.0005 | 19.12 | 325 | 0.0148 | 0.8731 | 0.9297 | 0.9005 | 0.9979 |
| 0.0005 | 20.59 | 350 | 0.0171 | 0.8848 | 0.9135 | 0.8989 | 0.9973 |
| 0.0005 | 22.06 | 375 | 0.0176 | 0.8848 | 0.9135 | 0.8989 | 0.9973 |
| 0.0005 | 23.53 | 400 | 0.0167 | 0.8860 | 0.9243 | 0.9048 | 0.9975 |
| 0.0004 | 25.0 | 425 | 0.0166 | 0.8860 | 0.9243 | 0.9048 | 0.9976 |
| 0.0004 | 26.47 | 450 | 0.0165 | 0.8814 | 0.9243 | 0.9024 | 0.9977 |
| 0.0004 | 27.94 | 475 | 0.0165 | 0.8814 | 0.9243 | 0.9024 | 0.9977 |
### Framework versions
- Transformers 4.27.4
- Pytorch 2.0.0+cu118
- Datasets 2.11.0
- Tokenizers 0.13.2
|
Anubhav23/IndianlegalBert
|
[] | 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:
- llama
- alpaca
- gpt4
- text-generation-inference
pipeline_tag: conversational
---
GPT4 x Alpaca-13b-native
---
- Converted and quantized by **ItsBradarr**
|
ArBert/roberta-base-finetuned-ner
|
[
"pytorch",
"tensorboard",
"roberta",
"token-classification",
"transformers",
"generated_from_trainer",
"license:mit",
"autotrain_compatible"
] |
token-classification
|
{
"architectures": [
"RobertaForTokenClassification"
],
"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
language:
- tr
pipeline_tag: text-classification
tags:
- code
---
Aşağılayıcı Söylem Tespit Modelimiz
İlk olarak yorumun OFFENSİVE ya da NOT OFFENSİVE olup olmadığını tespit eder.
Yorum OFFENSİVE olarak algılanmışsa alt kategorilerine göre 'INSULT', 'RACIST', 'SEXIST', 'PROFANITY'
olma durumlarına göre etiketleme yapar.
Yorum NOT OFFENSİVE olarak algılanmışsa 'OTHER' olarak etiketler.
end_to_end Model için
https://huggingface.co/spaces/TeamGZG/toxic-comment-classificationn/tree/main/end_to_end_model
tr-stop-words için
https://huggingface.co/spaces/TeamGZG/toxic-comment-classificationn/blob/main/tr-stop-words.txt
Eğitim Verileri için
https://huggingface.co/spaces/TeamGZG/toxic-comment-classificationn/blob/main/teknofest_train_final%20(1).csv
Test Edilebilir Space Alanı
https://huggingface.co/spaces/TeamGZG/toxic-comment-classificationn
|
Aracatto/Catto
|
[] | 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
| 2023-04-03T21:34:48Z
|
---
license: mit
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: tmvar_5e-05_ES2
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. -->
# tmvar_5e-05_ES2
This model is a fine-tuned version of [microsoft/BiomedNLP-PubMedBERT-base-uncased-abstract-fulltext](https://huggingface.co/microsoft/BiomedNLP-PubMedBERT-base-uncased-abstract-fulltext) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.0189
- Precision: 0.8469
- Recall: 0.8973
- F1: 0.8714
- Accuracy: 0.9971
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- training_steps: 1000
### Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
| 0.3852 | 1.47 | 25 | 0.1019 | 0.0 | 0.0 | 0.0 | 0.9843 |
| 0.0775 | 2.94 | 50 | 0.0398 | 0.2812 | 0.3892 | 0.3265 | 0.9863 |
| 0.0327 | 4.41 | 75 | 0.0243 | 0.4740 | 0.4919 | 0.4828 | 0.9910 |
| 0.02 | 5.88 | 100 | 0.0191 | 0.7656 | 0.7946 | 0.7798 | 0.9954 |
| 0.0084 | 7.35 | 125 | 0.0229 | 0.7766 | 0.7892 | 0.7828 | 0.9952 |
| 0.0045 | 8.82 | 150 | 0.0172 | 0.8351 | 0.8486 | 0.8418 | 0.9964 |
| 0.0023 | 10.29 | 175 | 0.0190 | 0.9148 | 0.8703 | 0.8920 | 0.9968 |
| 0.0015 | 11.76 | 200 | 0.0189 | 0.8469 | 0.8973 | 0.8714 | 0.9971 |
### Framework versions
- Transformers 4.27.4
- Pytorch 2.0.0+cu118
- Datasets 2.11.0
- Tokenizers 0.13.2
|
AragornII/DialoGPT-small-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
| 2023-04-03T21:36:59Z
|
---
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: -29.46 +/- 98.36
name: mean_reward
verified: false
---
# PPO Agent Playing LunarLander-v2
This is a trained model of a PPO agent playing LunarLander-v2.
# Hyperparameters
|
ArashEsk95/bert-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 |
---
license: mit
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: tmvar_0.0001_ES2
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. -->
# tmvar_0.0001_ES2
This model is a fine-tuned version of [microsoft/BiomedNLP-PubMedBERT-base-uncased-abstract-fulltext](https://huggingface.co/microsoft/BiomedNLP-PubMedBERT-base-uncased-abstract-fulltext) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.0187
- Precision: 0.8449
- Recall: 0.8541
- F1: 0.8495
- Accuracy: 0.9961
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0001
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- training_steps: 1000
### Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
| 0.2263 | 1.47 | 25 | 0.0788 | 0.0 | 0.0 | 0.0 | 0.9843 |
| 0.0492 | 2.94 | 50 | 0.0355 | 0.2576 | 0.3676 | 0.3029 | 0.9863 |
| 0.0258 | 4.41 | 75 | 0.0224 | 0.6 | 0.6811 | 0.6380 | 0.9933 |
| 0.013 | 5.88 | 100 | 0.0141 | 0.8267 | 0.9027 | 0.8630 | 0.9969 |
| 0.0031 | 7.35 | 125 | 0.0162 | 0.8218 | 0.8973 | 0.8579 | 0.9971 |
| 0.0028 | 8.82 | 150 | 0.0187 | 0.8449 | 0.8541 | 0.8495 | 0.9961 |
### Framework versions
- Transformers 4.27.4
- Pytorch 2.0.0+cu118
- Datasets 2.11.0
- Tokenizers 0.13.2
|
ArseniyBolotin/bert-multi-PAD-ner
|
[
"pytorch",
"jax",
"bert",
"token-classification",
"transformers",
"autotrain_compatible"
] |
token-classification
|
{
"architectures": [
"BertForTokenClassification"
],
"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
| 2023-04-03T23:16:48Z
|
---
license: other
---
This contains the weights for the LLaMA-7b model. This model is under a non-commercial license (see the LICENSE file).
You should only use this repository if you have been granted access to the model by filling out [this form](https://docs.google.com/forms/d/e/1FAIpQLSfqNECQnMkycAp2jP4Z9TFX0cGR4uf7b_fBxjY_OjhJILlKGA/viewform?usp=send_form) but either lost your copy of the weights or got some trouble converting them to the Transformers format.
|
Atiqah/Atiqah
|
[
"license:artistic-2.0"
] | 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 |
# Emotion Recognition on Gradio
This repo contains code to launch a [Gradio](https://github.com/gradio-app/gradio) interface for Emotion Recognition on [Gradio Hub](https://hub.gradio.app)
Please see the **original repo**: [omar178/Emotion-recognition](https://github.com/omar178/Emotion-recognition)
|
Augustvember/WokkaBot2
|
[] | 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 |
## Model Details
**Model name:** AskMe
**Model type:** GPT-based, fine-tuned on Arabic instruction-based dataset
**Base model:** aubmindlab/aragpt2-large
**Languages:** Arabic
**Author:** Research team at Naseej
## Introduction
AskMe is a GPT-based model, fine-tuned on an Arabic instruction-based dataset generated from ChatGPT. The research team at Naseej has fine-tuned this model using the aubmindlab/aragpt2-large model as the base. The model aims to provide a high-quality, context-aware language model that can assist users in generating human-like responses in Arabic, specifically when given instructions or prompts.
## Dataset
The dataset used for fine-tuning AskMe consists of Arabic instruction-based conversations generated from ChatGPT. The research team at Naseej has made sure to curate and clean the dataset for better model performance and to reduce any biases that might be present in the data.
## Fine-tuning
AskMe is fine-tuned using the aubmindlab/aragpt2-large model, which is specifically designed for Arabic language understanding and generation tasks. The research team at Naseej has carefully fine-tuned the model to improve its performance on instruction-based tasks, ensuring that the model is capable of generating accurate and contextually relevant responses.
## Demo
https://askme.naseej.ai
## Usage
AskMe can be used for a variety of tasks that involve understanding and responding to instructions or prompts in Arabic. This includes tasks such as:
- Question-answering
- Conversation modeling
- Summarization
- Translation
- Generating instructions
- Text completion
You can use the model with the Hugging Face Transformers library by loading it using the `from_pretrained` method:
```python
from transformers import AutoTokenizer
from arabert.aragpt2.grover.modeling_gpt2 import GPT2LMHeadModel
tokenizer = AutoTokenizer.from_pretrained("Naseej/AskMe-Large")
model = GPT2LMHeadModel.from_pretrained("Naseej/AskMe-Large")
```
## Limitations and Bias
Although AskMe has been fine-tuned on a curated dataset, it is still susceptible to biases present in the training data. This can result in the generation of biased or politically incorrect responses. Users should be cautious and critically evaluate the generated outputs.
Additionally, as a language model, AskMe may produce incorrect or nonsensical answers, especially when handling complex or ambiguous prompts. It is recommended to use the model as a tool to assist in decision-making and content generation rather than as a standalone solution.
## Feedback and Contributions
We welcome feedback and contributions to improve the AskMe model. If you have any issues, suggestions, or questions, please feel free to open an issue on our GitHub repository, or reach out to the research team at Naseej.
## License
AskMe is released under the [MIT License](https://opensource.org/licenses/MIT).
|
Augustvember/WokkaBot3
|
[
"conversational"
] |
conversational
|
{
"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: creativeml-openrail-m
---
# [https://civitai.com/models/22354/clearvae](https://civitai.com/models/22354/clearvae)
## This is just a mirror
|
Augustvember/WokkaBot6
|
[] | 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: other
---
This contains the weights for the LLaMA-30b model. This model is under a non-commercial license (see the LICENSE file).
You should only use this repository if you have been granted access to the model by filling out [this form](https://docs.google.com/forms/d/e/1FAIpQLSfqNECQnMkycAp2jP4Z9TFX0cGR4uf7b_fBxjY_OjhJILlKGA/viewform?usp=send_form) but either lost your copy of the weights or got some trouble converting them to the Transformers format.
|
Augustvember/WokkaBotF
|
[] | 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:
- image-classification
- pytorch
- huggingpics
metrics:
- accuracy
model-index:
- name: flower-classifier
results:
- task:
name: Image Classification
type: image-classification
metrics:
- name: Accuracy
type: accuracy
value: 0.9701492786407471
---
# flower-classifier
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
#### lily
#### orchids
#### roses
|
Ayah/GPT2-DBpedia
|
[
"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
}
}
}
| 6
| 2023-04-04T02:26:39Z
|
---
license: apache-2.0
---
This is a streaming Zipformer Transducer model trained on LibriSpeech and GigaSpeech.
Please see https://github.com/k2-fsa/icefall/pull/984 for more details.
|
Ayham/bert_distilgpt2_summarization_cnn_dailymail
|
[
"pytorch",
"tensorboard",
"encoder-decoder",
"text2text-generation",
"dataset:cnn_dailymail",
"transformers",
"generated_from_trainer",
"autotrain_compatible"
] |
text2text-generation
|
{
"architectures": [
"EncoderDecoderModel"
],
"model_type": "encoder-decoder",
"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:
- LunarLander-v2
- deep-reinforcement-learning
- reinforcement-learning
- stable-baselines3
model-index:
- name: POP
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: LunarLander-v2
type: LunarLander-v2
metrics:
- type: mean_reward
value: 254.57 +/- 16.50
name: mean_reward
verified: false
---
# **POP** Agent playing **LunarLander-v2**
This is a trained model of a **POP** 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
...
```
|
Ayham/bert_gpt2_summarization_cnndm_new
|
[
"pytorch",
"tensorboard",
"encoder-decoder",
"text2text-generation",
"dataset:cnn_dailymail",
"transformers",
"generated_from_trainer",
"autotrain_compatible"
] |
text2text-generation
|
{
"architectures": [
"EncoderDecoderModel"
],
"model_type": "encoder-decoder",
"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 |
---
pipeline_tag: sentence-similarity
tags:
- sentence-transformers
- feature-extraction
- sentence-similarity
- transformers
---
# {MODEL_NAME}
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('{MODEL_NAME}')
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('{MODEL_NAME}')
model = AutoModel.from_pretrained('{MODEL_NAME}')
# 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={MODEL_NAME})
## Training
The model was trained with the parameters:
**DataLoader**:
`torch.utils.data.dataloader.DataLoader` of length 5944 with parameters:
```
{'batch_size': 4, 'sampler': 'torch.utils.data.sampler.RandomSampler', 'batch_sampler': 'torch.utils.data.sampler.BatchSampler'}
```
**Loss**:
`sentence_transformers.losses.CosineSimilarityLoss.CosineSimilarityLoss`
Parameters of the fit()-Method:
```
{
"epochs": 10,
"evaluation_steps": 0,
"evaluator": "NoneType",
"max_grad_norm": 1,
"optimizer_class": "<class 'torch.optim.adamw.AdamW'>",
"optimizer_params": {
"lr": 2e-05
},
"scheduler": "WarmupLinear",
"steps_per_epoch": null,
"warmup_steps": 5944,
"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 -->
|
Ayham/roberta_roberta_summarization_cnn_dailymail
|
[
"pytorch",
"tensorboard",
"encoder-decoder",
"text2text-generation",
"dataset:cnn_dailymail",
"transformers",
"generated_from_trainer",
"autotrain_compatible"
] |
text2text-generation
|
{
"architectures": [
"EncoderDecoderModel"
],
"model_type": "encoder-decoder",
"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 |
---
library_name: paddlenlp
---
# linjieccc/tiny-random-uie-m
|
Ayham/robertagpt2_cnn
|
[
"pytorch",
"tensorboard",
"encoder-decoder",
"text2text-generation",
"transformers",
"generated_from_trainer",
"autotrain_compatible"
] |
text2text-generation
|
{
"architectures": [
"EncoderDecoderModel"
],
"model_type": "encoder-decoder",
"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 |
---
library_name: paddlenlp
---
# linjieccc/tiny-random-uie-x
|
Ayham/xlmroberta_gpt2_summarization_xsum
|
[
"pytorch",
"tensorboard",
"encoder-decoder",
"text2text-generation",
"dataset:xsum",
"transformers",
"generated_from_trainer",
"autotrain_compatible"
] |
text2text-generation
|
{
"architectures": [
"EncoderDecoderModel"
],
"model_type": "encoder-decoder",
"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: creativeml-openrail-m
tags:
- text-to-image
- stable-diffusion
---
### ssagirl Dreambooth model trained by Fred99774 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:
|
Ayham/xlnet_gpt_xsum
|
[
"pytorch",
"tensorboard",
"encoder-decoder",
"text2text-generation",
"transformers",
"generated_from_trainer",
"autotrain_compatible"
] |
text2text-generation
|
{
"architectures": [
"EncoderDecoderModel"
],
"model_type": "encoder-decoder",
"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
| 2023-04-04T04:08:06Z
|
---
tags:
- Pixelcopter-PLE-v0
- reinforce
- reinforcement-learning
- custom-implementation
- deep-rl-class
model-index:
- name: Reinforce-unit4_2
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: Pixelcopter-PLE-v0
type: Pixelcopter-PLE-v0
metrics:
- type: mean_reward
value: 43.60 +/- 23.80
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
|
Ayham/xlnet_roberta_new_summarization_cnn_dailymail
|
[] | 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
model-index:
- name: distilroberta-base-finetuned-wikitext2
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. -->
# distilroberta-base-finetuned-wikitext2
This model is a fine-tuned version of [distilroberta-base](https://huggingface.co/distilroberta-base) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 1.8493
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3.0
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 2.0852 | 1.0 | 2406 | 1.9234 |
| 1.992 | 2.0 | 4812 | 1.8828 |
| 1.9603 | 3.0 | 7218 | 1.8223 |
### Framework versions
- Transformers 4.27.4
- Pytorch 2.0.0+cu118
- Datasets 2.11.0
- Tokenizers 0.13.2
|
Ayham/xlnet_roberta_summarization_cnn_dailymail
|
[
"pytorch",
"tensorboard",
"encoder-decoder",
"text2text-generation",
"dataset:cnn_dailymail",
"transformers",
"generated_from_trainer",
"autotrain_compatible"
] |
text2text-generation
|
{
"architectures": [
"EncoderDecoderModel"
],
"model_type": "encoder-decoder",
"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 |
This is a clone of EleutherAI/gpt-j-6b. Only change is config.js - allow larger inputs to TextGeneration pipeline
|
Ayham/xlnetgpt2_xsum7
|
[
"pytorch",
"tensorboard",
"encoder-decoder",
"text2text-generation",
"transformers",
"generated_from_trainer",
"autotrain_compatible"
] |
text2text-generation
|
{
"architectures": [
"EncoderDecoderModel"
],
"model_type": "encoder-decoder",
"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: other
tags:
- generated_from_trainer
datasets:
- image_folder
metrics:
- accuracy
model-index:
- name: mobilenet_v2_1.0_224-plant-disease-identification
results:
- task:
name: Image Classification
type: image-classification
dataset:
name: New Plant Diseases Dataset
type: image_folder
config: default
split: train
args: default
metrics:
- name: Accuracy
type: accuracy
value: 0.9541
---
<!-- 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. -->
# mobilenet_v2_1.0_224-plant-disease-identification
This model is a fine-tuned version of [google/mobilenet_v2_1.0_224](https://huggingface.co/google/mobilenet_v2_1.0_224) on the [Kaggle version](https://www.kaggle.com/datasets/vipoooool/new-plant-diseases-dataset) of the [Plant Village dataset](https://github.com/spMohanty/PlantVillage-Dataset).
It achieves the following results on the evaluation set:
- Cross Entropy Loss: 0.15
- Accuracy: 0.9541
## Intended uses & limitations
For identifying common diseases in crops and assessing plant health. Not to be used as a replacement for an actual diagnosis from experts.
## Training and evaluation data
The plant village dataset consists of 38 classes of diseases in common crops (including healthy/normal crops).
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-5
- train_batch_size: 256
- eval_batch_size: 256
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.2
- num_epochs: 6
### Framework versions
- Transformers 4.27.3
- Pytorch 1.13.0
- Datasets 2.1.0
- Tokenizers 0.13.2
|
Aymene/opus-mt-en-ro-finetuned-en-to-ro
|
[] | 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
---
This model is a diffusion model for unconditional image generation of the universe trained for 1400 epochs.
## Usage
```python
from diffusers import DDPMPipeline
pipeline = DDPMPipeline.from_pretrained('ocariz/universe_1400')
image = pipeline().images[0]
image
```
|
Ayoola/wav2vec2-large-xlsr-turkish-demo-colab
|
[] | 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 Cletrason/mario-movie-toad-centered is restricted and you are not in the authorized list. Visit https://huggingface.co/Cletrason/mario-movie-toad-centered to ask for access.
|
AyushPJ/ai-club-inductions-21-nlp-distilBERT
|
[
"pytorch",
"distilbert",
"question-answering",
"transformers",
"generated_from_trainer",
"autotrain_compatible"
] |
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
}
}
}
| 8
| null |
---
tags:
- Pixelcopter-PLE-v0
- reinforce
- reinforcement-learning
- custom-implementation
- deep-rl-class
model-index:
- name: Reinforce-v2
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: Pixelcopter-PLE-v0
type: Pixelcopter-PLE-v0
metrics:
- type: mean_reward
value: 34.20 +/- 24.48
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
|
AyushPJ/ai-club-inductions-21-nlp-roBERTa
|
[
"pytorch",
"roberta",
"question-answering",
"transformers",
"generated_from_trainer",
"autotrain_compatible"
] |
question-answering
|
{
"architectures": [
"RobertaForQuestionAnswering"
],
"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 |
---
language:
- en
license: apache-2.0
---
# BERT multilingual base model (cased)
Pretrained model on the English dataset using a masked language modeling (MLM) objective.
It was introduced in [this paper](https://arxiv.org/abs/1810.04805) and first released in
[this repository](https://github.com/google-research/bert). This model is case sensitive: it makes a difference
between english and English.
## Model description
BERT is a transformers model pretrained on a large corpus of English data in a self-supervised fashion. This means
it was pretrained on the raw texts only, with no humans labelling them in any way (which is why it can use lots of
publicly available data) with an automatic process to generate inputs and labels from those texts. More precisely, it
was pretrained with two objectives:
- Masked language modeling (MLM): taking a sentence, the model randomly masks 15% of the words in the input then run
the entire masked sentence through the model and has to predict the masked words. This is different from traditional
recurrent neural networks (RNNs) that usually see the words one after the other, or from autoregressive models like
GPT which internally mask the future tokens. It allows the model to learn a bidirectional representation of the
sentence.
- Next sentence prediction (NSP): the models concatenates two masked sentences as inputs during pretraining. Sometimes
they correspond to sentences that were next to each other in the original text, sometimes not. The model then has to
predict if the two sentences were following each other or not.
The pretrained model has been finetuned for one specific language for one specific task.
### How to use
Here is how to use this model to get the features of a given text in PyTorch:
```python
from transformers import BertTokenizer, BertModel
model = BertModel.from_pretrained("mushfiqur11/<repo_name>")
```
|
AyushPJ/test-squad-trained-finetuned-squad
|
[
"pytorch",
"tensorboard",
"distilbert",
"question-answering",
"dataset:squad",
"transformers",
"generated_from_trainer",
"autotrain_compatible"
] |
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
}
}
}
| 8
| 2023-04-04T05:08:24Z
|
---
language:
- en
license: apache-2.0
---
# BERT multilingual base model (cased)
Pretrained model on the English dataset using a masked language modeling (MLM) objective.
It was introduced in [this paper](https://arxiv.org/abs/1810.04805) and first released in
[this repository](https://github.com/google-research/bert). This model is case sensitive: it makes a difference
between english and English.
## Model description
BERT is a transformers model pretrained on a large corpus of English data in a self-supervised fashion. This means
it was pretrained on the raw texts only, with no humans labelling them in any way (which is why it can use lots of
publicly available data) with an automatic process to generate inputs and labels from those texts. More precisely, it
was pretrained with two objectives:
- Masked language modeling (MLM): taking a sentence, the model randomly masks 15% of the words in the input then run
the entire masked sentence through the model and has to predict the masked words. This is different from traditional
recurrent neural networks (RNNs) that usually see the words one after the other, or from autoregressive models like
GPT which internally mask the future tokens. It allows the model to learn a bidirectional representation of the
sentence.
- Next sentence prediction (NSP): the models concatenates two masked sentences as inputs during pretraining. Sometimes
they correspond to sentences that were next to each other in the original text, sometimes not. The model then has to
predict if the two sentences were following each other or not.
The pretrained model has been finetuned for one specific language for one specific task.
### How to use
Here is how to use this model to get the features of a given text in PyTorch:
```python
from transformers import BertTokenizer, BertModel
model = BertModel.from_pretrained("mushfiqur11/<repo_name>")
```
|
Azaghast/DistilBART-SCP-ParaSummarization
|
[
"pytorch",
"bart",
"text2text-generation",
"transformers",
"autotrain_compatible"
] |
text2text-generation
|
{
"architectures": [
"BartForConditionalGeneration"
],
"model_type": "bart",
"task_specific_params": {
"conversational": {
"max_length": null
},
"summarization": {
"early_stopping": true,
"length_penalty": 2,
"max_length": 142,
"min_length": 56,
"no_repeat_ngram_size": 3,
"num_beams": 4,
"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 |
---
language:
- en
license: apache-2.0
---
# BERT multilingual base model (cased)
Pretrained model on the English dataset using a masked language modeling (MLM) objective.
It was introduced in [this paper](https://arxiv.org/abs/1810.04805) and first released in
[this repository](https://github.com/google-research/bert). This model is case sensitive: it makes a difference
between english and English.
## Model description
BERT is a transformers model pretrained on a large corpus of English data in a self-supervised fashion. This means
it was pretrained on the raw texts only, with no humans labelling them in any way (which is why it can use lots of
publicly available data) with an automatic process to generate inputs and labels from those texts. More precisely, it
was pretrained with two objectives:
- Masked language modeling (MLM): taking a sentence, the model randomly masks 15% of the words in the input then run
the entire masked sentence through the model and has to predict the masked words. This is different from traditional
recurrent neural networks (RNNs) that usually see the words one after the other, or from autoregressive models like
GPT which internally mask the future tokens. It allows the model to learn a bidirectional representation of the
sentence.
- Next sentence prediction (NSP): the models concatenates two masked sentences as inputs during pretraining. Sometimes
they correspond to sentences that were next to each other in the original text, sometimes not. The model then has to
predict if the two sentences were following each other or not.
The pretrained model has been finetuned for one specific language for one specific task.
### How to use
Here is how to use this model to get the features of a given text in PyTorch:
```python
from transformers import BertTokenizer, BertModel
model = BertModel.from_pretrained("mushfiqur11/<repo_name>")
```
|
Azaghast/DistilBERT-SCP-Class-Classification
|
[
"pytorch",
"distilbert",
"text-classification",
"transformers"
] |
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
}
}
}
| 42
| 2023-04-04T05:08:48Z
|
---
language:
- en
license: apache-2.0
---
# BERT multilingual base model (cased)
Pretrained model on the English dataset using a masked language modeling (MLM) objective.
It was introduced in [this paper](https://arxiv.org/abs/1810.04805) and first released in
[this repository](https://github.com/google-research/bert). This model is case sensitive: it makes a difference
between english and English.
## Model description
BERT is a transformers model pretrained on a large corpus of English data in a self-supervised fashion. This means
it was pretrained on the raw texts only, with no humans labelling them in any way (which is why it can use lots of
publicly available data) with an automatic process to generate inputs and labels from those texts. More precisely, it
was pretrained with two objectives:
- Masked language modeling (MLM): taking a sentence, the model randomly masks 15% of the words in the input then run
the entire masked sentence through the model and has to predict the masked words. This is different from traditional
recurrent neural networks (RNNs) that usually see the words one after the other, or from autoregressive models like
GPT which internally mask the future tokens. It allows the model to learn a bidirectional representation of the
sentence.
- Next sentence prediction (NSP): the models concatenates two masked sentences as inputs during pretraining. Sometimes
they correspond to sentences that were next to each other in the original text, sometimes not. The model then has to
predict if the two sentences were following each other or not.
The pretrained model has been finetuned for one specific language for one specific task.
### How to use
Here is how to use this model to get the features of a given text in PyTorch:
```python
from transformers import BertTokenizer, BertModel
model = BertModel.from_pretrained("mushfiqur11/<repo_name>")
```
|
Azaghast/GPT2-SCP-ContainmentProcedures
|
[
"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
}
}
}
| 5
| null |
---
language:
- en
license: apache-2.0
---
# BERT multilingual base model (cased)
Pretrained model on the English dataset using a masked language modeling (MLM) objective.
It was introduced in [this paper](https://arxiv.org/abs/1810.04805) and first released in
[this repository](https://github.com/google-research/bert). This model is case sensitive: it makes a difference
between english and English.
## Model description
BERT is a transformers model pretrained on a large corpus of English data in a self-supervised fashion. This means
it was pretrained on the raw texts only, with no humans labelling them in any way (which is why it can use lots of
publicly available data) with an automatic process to generate inputs and labels from those texts. More precisely, it
was pretrained with two objectives:
- Masked language modeling (MLM): taking a sentence, the model randomly masks 15% of the words in the input then run
the entire masked sentence through the model and has to predict the masked words. This is different from traditional
recurrent neural networks (RNNs) that usually see the words one after the other, or from autoregressive models like
GPT which internally mask the future tokens. It allows the model to learn a bidirectional representation of the
sentence.
- Next sentence prediction (NSP): the models concatenates two masked sentences as inputs during pretraining. Sometimes
they correspond to sentences that were next to each other in the original text, sometimes not. The model then has to
predict if the two sentences were following each other or not.
The pretrained model has been finetuned for one specific language for one specific task.
### How to use
Here is how to use this model to get the features of a given text in PyTorch:
```python
from transformers import BertTokenizer, BertModel
model = BertModel.from_pretrained("mushfiqur11/<repo_name>")
```
|
BSC-LT/roberta-base-bne-capitel-ner
|
[
"pytorch",
"roberta",
"token-classification",
"es",
"dataset:bne",
"dataset:capitel",
"arxiv:1907.11692",
"arxiv:2107.07253",
"transformers",
"national library of spain",
"spanish",
"bne",
"capitel",
"ner",
"license:apache-2.0",
"autotrain_compatible"
] |
token-classification
|
{
"architectures": [
"RobertaForTokenClassification"
],
"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
}
}
}
| 12
| 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: mark-e/poca-SoccerTwos
3. Step 2: Select your *.nn /*.onnx file
4. Click on Watch the agent play 👀
|
BatuhanYilmaz/distilbert-base-uncased-finetuned-squad-d5716d28
|
[
"pytorch",
"distilbert",
"fill-mask",
"en",
"dataset:squad",
"arxiv:1910.01108",
"transformers",
"question-answering",
"license:apache-2.0",
"autotrain_compatible"
] |
question-answering
|
{
"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
}
}
}
| 18
| null |
---
license: creativeml-openrail-m
tags:
- text-to-image
- stable-diffusion
---
### Toad-Mario-Movie- Dreambooth model trained by Cletrason 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:
|
BearThreat/distilbert-base-uncased-finetuned-cola
|
[
"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
}
}
}
| 30
| null |
---
language:
- en
- zh
- de
- fr
library_name: sentence-transformers
license: apache-2.0
---
# ZeroNLG
Without any labeled downstream pairs for training, ZeroNLG is an unified framework that deals with multiple natural language generation (NLG) tasks in a zero-shot manner, including image-to-text, video-to-text, and text-to-text generation tasks across English, Chinese, German, and French.
Pre-trained data: a machine-translated version of [CC3M](https://huggingface.co/datasets/conceptual_captions), including
- 1.1M English sentences
- 1.1M English-Chinese pairs
- 1.1M English-German pairs
- 1.1M English-French pairs
Paper: [ZeroNLG: Aligning and Autoencoding Domains for Zero-Shot Multimodal and Multilingual Natural Language Generation](https://arxiv.org/abs/2303.06458)
Authors: *Bang Yang\*, Fenglin Liu\*, Yuexian Zou, Xian Wu, Yaowei Wang, David A. Clifton*
## Quick Start
Please follow our [github repo](https://github.com/yangbang18/ZeroNLG) to prepare the environment at first.
```python
from zeronlg import ZeroNLG
# Automatically download the model from Huggingface Hub
# Note: this model is especially pre-trained for machine translation
model = ZeroNLG('zeronlg-4langs-mt')
# Translating English into Chinese
# Note: the multilingual encoder is langauge-agnostic, so the `lang` below means the langauge to be generated
output = model.forward_translate(texts='a girl and a boy are playing', lang='zh', num_beams=3)
# output = "一 个 女 孩 和 一 个 男 孩 一 起 玩"
```
## Zero-Shot Performance
### Machine translation
Model: [zeronlg-4langs-mt](https://huggingface.co/yangbang18/zeronlg-4langs-mt) only.
| En->Zh | En<-Zh | En->De | En<-De | En->Fr | En<-Fr | Zh->De | Zh<-De | Zh->Fr | Zh<-Fr | De->Fr | De<-Fr|
| :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: |
6.0|9.2|21.6|23.2|27.2|26.8|7.8|4.6|6.1|9.7|20.9|19.6
## Citation
```bibtex
@article{Yang2023ZeroNLG,
title={ZeroNLG: Aligning and Autoencoding Domains for Zero-Shot Multimodal and Multilingual Natural Language Generation},
author={Yang, Bang and Liu, Fenglin and Zou, Yuexian and Wu, Xian and Wang, Yaowei and Clifton, David A.},
journal={arXiv preprint arXiv:2303.06458}
year={2023}
}
```
|
BigDaddyNe1L/Hhaa
|
[] | 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:
- squad
model-index:
- name: my_awesome_qa_model
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# my_awesome_qa_model
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the squad dataset.
It achieves the following results on the evaluation set:
- Loss: 1.5710
## 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: 3
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| No log | 1.0 | 250 | 2.0992 |
| 2.6207 | 2.0 | 500 | 1.6513 |
| 2.6207 | 3.0 | 750 | 1.5710 |
### Framework versions
- Transformers 4.27.4
- Pytorch 1.13.1+cu116
- Datasets 2.11.0
- Tokenizers 0.13.2
|
BigSalmon/BestMask2
|
[
"pytorch",
"roberta",
"fill-mask",
"transformers",
"autotrain_compatible",
"has_space"
] |
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
}
}
}
| 10
| null |
---
pipeline_tag: sentence-similarity
tags:
- sentence-transformers
- feature-extraction
- sentence-similarity
- transformers
language:
- he
library_name: sentence-transformers
---
# imvladikon/sentence-transformers-alephbert[WIP]
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.
Current version is distillation of the [LaBSE](https://huggingface.co/sentence-transformers/LaBSE) model on private corpus.
## 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
from sentence_transformers.util import cos_sim
sentences = [
"הם היו שמחים לראות את האירוע שהתקיים.",
"לראות את האירוע שהתקיים היה מאוד משמח להם."
]
model = SentenceTransformer('imvladikon/sentence-transformers-alephbert')
embeddings = model.encode(sentences)
print(cos_sim(*tuple(embeddings)).item())
# 0.883316159248352
```
## 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
import torch
from torch import nn
from transformers import AutoTokenizer, AutoModel
#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 = [
"הם היו שמחים לראות את האירוע שהתקיים.",
"לראות את האירוע שהתקיים היה מאוד משמח להם."
]
# Load model from HuggingFace Hub
tokenizer = AutoTokenizer.from_pretrained('imvladikon/sentence-transformers-alephbert')
model = AutoModel.from_pretrained('imvladikon/sentence-transformers-alephbert')
# 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'])
cos_sim = nn.CosineSimilarity(dim=0, eps=1e-6)
print(cos_sim(sentence_embeddings[0], sentence_embeddings[1]).item())
```
## Evaluation Results
For an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: [https://seb.sbert.net](https://seb.sbert.net?model_name={MODEL_NAME})
## Training
The model was trained with the parameters:
**DataLoader**:
`torch.utils.data.dataloader.DataLoader` of length 44999 with parameters:
```
{'batch_size': 8, 'sampler': 'torch.utils.data.sampler.RandomSampler', 'batch_sampler': 'torch.utils.data.sampler.BatchSampler'}
```
**Loss**:
`sentence_transformers.losses.MultipleNegativesRankingLoss.MultipleNegativesRankingLoss` with parameters:
```
{'scale': 20.0, 'similarity_fct': 'cos_sim'}
```
Parameters of the fit()-Method:
```
{
"epochs": 10,
"evaluation_steps": 0,
"evaluator": "NoneType",
"max_grad_norm": 1,
"optimizer_class": "<class 'torch.optim.adamw.AdamW'>",
"optimizer_params": {
"lr": 2e-05
},
"scheduler": "WarmupLinear",
"steps_per_epoch": null,
"warmup_steps": 44999,
"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
```bibtex
@misc{seker2021alephberta,
title={AlephBERT:A Hebrew Large Pre-Trained Language Model to Start-off your Hebrew NLP Application With},
author={Amit Seker and Elron Bandel and Dan Bareket and Idan Brusilovsky and Refael Shaked Greenfeld and Reut Tsarfaty},
year={2021},
eprint={2104.04052},
archivePrefix={arXiv},
primaryClass={cs.CL}
}
```
```bibtex
@misc{reimers2019sentencebert,
title={Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks},
author={Nils Reimers and Iryna Gurevych},
year={2019},
eprint={1908.10084},
archivePrefix={arXiv},
primaryClass={cs.CL}
}
```
|
BigSalmon/FormalRobertaaa
|
[
"pytorch",
"roberta",
"fill-mask",
"transformers",
"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
}
}
}
| 12
| null |
---
pipeline_tag: text-to-image
---
# 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]
|
BigSalmon/GPT2HardandEasy
|
[
"pytorch",
"tensorboard",
"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
}
}
}
| 9
| null |
---
license: apache-2.0
---
# Cohere `multilingual-22-12` tokenizer
This is the tokenizer for the Cohere `multilingual-22-12` embedding model: [Cohere Multilingual Embeddings](https://docs.cohere.ai/docs/multilingual-language-models)
You can load it with the transformers library like this:
```python
from transformers import AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained("Cohere/multilingual-22-12")
text = "Hellö World, this is my input string!"
enc = tokenizer(text)
print("Encoded input:")
print(enc)
inv_vocab = {v: k for k, v in tokenizer.vocab.items()}
tokens = [inv_vocab[token_id] for token_id in enc['input_ids']]
print("Tokens:")
print(tokens)
number_of_tokens = len(enc['input_ids'])
print("Number of tokens:", number_of_tokens)
```
## Computing number of tokens
The following values can be used to approximate the number of tokens given the number input characters:
```
approx_number_of_tokens = len(input_text) / ratio
```
E.g. for English, `approx_number_of_tokens = len(input_text) / 4.8`.
| Language | Avg. characters per token |
| --- | :---: |
| ar | 3.6 |
| de | 4.6 |
| en | 4.8 |
| es | 4.6 |
| fr | 4.4 |
| hi | 3.8 |
| it | 4.5 |
| ja | 1.3 |
| ko | 2.0 |
| zh | 1.1 |
These values have been computed on the first 10,000 paragraphs from [Wikipedia](https://huggingface.co/datasets/Cohere/wikipedia-22-12). For other dataset, these values might change.
|
BigSalmon/MrLincoln13
|
[
"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
}
}
}
| 9
| null |
---
license: apache-2.0
tags:
- generated_from_trainer
model-index:
- name: gpt-j-t-q
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. -->
# gpt-j-t-q
This model is a fine-tuned version of [EleutherAI/gpt-j-6B](https://huggingface.co/EleutherAI/gpt-j-6B) on the None dataset.
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0002
- train_batch_size: 4
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 100
- training_steps: 100
- mixed_precision_training: Native AMP
### Training results
### Framework versions
- Transformers 4.27.4
- Pytorch 2.0.0+cu118
- Datasets 2.11.0
- Tokenizers 0.13.2
|
BigSalmon/MrLincoln14
|
[] | 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
| 2023-04-04T09:44:51Z
|
---
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: 705.00 +/- 174.43
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 DesignOrder -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 DesignOrder -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 DesignOrder
```
## Hyperparameters
```python
OrderedDict([('batch_size', 32),
('buffer_size', 100000),
('env_wrapper',
['stable_baselines3.common.atari_wrappers.AtariWrapper']),
('exploration_final_eps', 0.01),
('exploration_fraction', 0.1),
('frame_stack', 4),
('gradient_steps', 1),
('learning_rate', 0.0001),
('learning_starts', 100000),
('n_timesteps', 10000000.0),
('optimize_memory_usage', False),
('policy', 'CnnPolicy'),
('target_update_interval', 1000),
('train_freq', 4),
('normalize', False)])
```
|
BigSalmon/MrLincoln3
|
[
"pytorch",
"tensorboard",
"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
}
}
}
| 17
| 2023-04-04T09:48:05Z
|
---
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: 267.74 +/- 20.91
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
...
```
|
BigSalmon/NEO125InformalToFormalLincoln
|
[
"pytorch",
"gpt_neo",
"text-generation",
"transformers"
] |
text-generation
|
{
"architectures": [
"GPTNeoForCausalLM"
],
"model_type": "gpt_neo",
"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 |
---
pipeline_tag: sentence-similarity
tags:
- sentence-transformers
- feature-extraction
- sentence-similarity
- transformers
---
# {MODEL_NAME}
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('{MODEL_NAME}')
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('{MODEL_NAME}')
model = AutoModel.from_pretrained('{MODEL_NAME}')
# 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={MODEL_NAME})
## Training
The model was trained with the parameters:
**DataLoader**:
`torch.utils.data.dataloader.DataLoader` of length 5944 with parameters:
```
{'batch_size': 4, 'sampler': 'torch.utils.data.sampler.RandomSampler', 'batch_sampler': 'torch.utils.data.sampler.BatchSampler'}
```
**Loss**:
`sentence_transformers.losses.CosineSimilarityLoss.CosineSimilarityLoss`
Parameters of the fit()-Method:
```
{
"epochs": 10,
"evaluation_steps": 0,
"evaluator": "NoneType",
"max_grad_norm": 1,
"optimizer_class": "<class 'torch.optim.adamw.AdamW'>",
"optimizer_params": {
"lr": 2e-05
},
"scheduler": "WarmupLinear",
"steps_per_epoch": null,
"warmup_steps": 5944,
"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 -->
|
BigSalmon/ParaphraseParentheses2.0
|
[
"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
}
}
}
| 13
| null |
---
tags:
- Pixelcopter-PLE-v0
- reinforce
- reinforcement-learning
- custom-implementation
- deep-rl-class
model-index:
- name: Reinforce-pixelcopter
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: Pixelcopter-PLE-v0
type: Pixelcopter-PLE-v0
metrics:
- type: mean_reward
value: 30.10 +/- 12.61
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
|
BigSalmon/Points
|
[
"pytorch",
"tensorboard",
"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": 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
}
}
}
| 13
| null |
---
license: openrail
---
# 本仓库为备份仓库，模型来源于网络
# 命令下载格式：
git lfs clone https://huggingface.co/用户名/项目
(下载全部)
aria2c https://huggingface.co/用户名/项目/resolve/main/目录/文件名
(下载单个文件)
|
BigSalmon/Robertsy
|
[
"pytorch",
"roberta",
"fill-mask",
"transformers",
"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
}
}
}
| 4
| null |
---
# For reference on model card metadata, see the spec: https://github.com/huggingface/hub-docs/blob/main/modelcard.md?plain=1
# Doc / guide: https://huggingface.co/docs/hub/model-cards
{}
---
# AudioLDM
AudioLDM is a latent text-to-audio diffusion model capable of generating realistic audio samples given any text input. It is available in the 🧨 Diffusers library from v0.15.0 onwards.
# Model Details
AudioLDM was proposed in the paper [AudioLDM: Text-to-Audio Generation with Latent Diffusion Models](https://arxiv.org/abs/2301.12503) by Haohe Liu et al.
Inspired by [Stable Diffusion](https://huggingface.co/CompVis/stable-diffusion-v1-4), AudioLDM
is a text-to-audio _latent diffusion model (LDM)_ that learns continuous audio representations from [CLAP](https://huggingface.co/laion/clap-htsat-unfused)
latents. AudioLDM takes a text prompt as input and predicts the corresponding audio. It can generate text-conditional
sound effects, human speech and music.
# Checkpoint Details
This is the **small v2** version of the AudioLDM model, which is the same size as the original AudioLDM small checkpoint, but trained for more steps. The four AudioLDM checkpoints are summarised below:
**Table 1:** Summary of the AudioLDM checkpoints.
| Checkpoint | Training Steps | Audio conditioning | CLAP audio dim | UNet dim | Params |
|-----------------------------------------------------------------------|----------------|--------------------|----------------|----------|--------|
| [audioldm-s-full](https://huggingface.co/cvssp/audioldm) | 1.5M | No | 768 | 128 | 421M |
| [audioldm-s-full-v2](https://huggingface.co/cvssp/audioldm-s-full-v2) | > 1.5M | No | 768 | 128 | 421M |
| [audioldm-m-full](https://huggingface.co/cvssp/audioldm-m-full) | 1.5M | Yes | 1024 | 192 | 652M |
| [audioldm-l-full](https://huggingface.co/cvssp/audioldm-l-full) | 1.5M | No | 768 | 256 | 975M |
## Model Sources
- [**Original Repository**](https://github.com/haoheliu/AudioLDM)
- [**🧨 Diffusers Pipeline**](https://huggingface.co/docs/diffusers/api/pipelines/audioldm)
- [**Paper**](https://arxiv.org/abs/2301.12503)
- [**Demo**](https://huggingface.co/spaces/haoheliu/audioldm-text-to-audio-generation)
# Usage
First, install the required packages:
```
pip install --upgrade diffusers transformers
```
## Text-to-Audio
For text-to-audio generation, the [AudioLDMPipeline](https://huggingface.co/docs/diffusers/api/pipelines/audioldm) can be
used to load pre-trained weights and generate text-conditional audio outputs:
```python
from diffusers import AudioLDMPipeline
import torch
repo_id = "cvssp/audioldm-s-full-v2"
pipe = AudioLDMPipeline.from_pretrained(repo_id, torch_dtype=torch.float16)
pipe = pipe.to("cuda")
prompt = "Techno music with a strong, upbeat tempo and high melodic riffs"
audio = pipe(prompt, num_inference_steps=10, audio_length_in_s=5.0).audios[0]
```
The resulting audio output can be saved as a .wav file:
```python
import scipy
scipy.io.wavfile.write("techno.wav", rate=16000, data=audio)
```
Or displayed in a Jupyter Notebook / Google Colab:
```python
from IPython.display import Audio
Audio(audio, rate=16000)
```
<audio controls>
<source src="https://huggingface.co/datasets/sanchit-gandhi/audioldm-readme-samples/resolve/main/audioldm-s-full-v2-techno.wav" type="audio/wav">
Your browser does not support the audio element.
</audio>
## Tips
Prompts:
* Descriptive prompt inputs work best: you can use adjectives to describe the sound (e.g. "high quality" or "clear") and make the prompt context specific (e.g., "water stream in a forest" instead of "stream").
* It's best to use general terms like 'cat' or 'dog' instead of specific names or abstract objects that the model may not be familiar with.
Inference:
* The _quality_ of the predicted audio sample can be controlled by the `num_inference_steps` argument: higher steps give higher quality audio at the expense of slower inference.
* The _length_ of the predicted audio sample can be controlled by varying the `audio_length_in_s` argument.
# Citation
**BibTeX:**
```
@article{liu2023audioldm,
title={AudioLDM: Text-to-Audio Generation with Latent Diffusion Models},
author={Liu, Haohe and Chen, Zehua and Yuan, Yi and Mei, Xinhao and Liu, Xubo and Mandic, Danilo and Wang, Wenwu and Plumbley, Mark D},
journal={arXiv preprint arXiv:2301.12503},
year={2023}
}
```
|
BigSalmon/T5F
|
[
"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: "
}
}
}
| 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: parinzee/ppo-SnowballTarget
3. Step 2: Select your *.nn /*.onnx file
4. Click on Watch the agent play 👀
|
BigSalmon/prepositions
|
[
"pytorch",
"roberta",
"fill-mask",
"transformers",
"autotrain_compatible",
"has_space"
] |
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
}
}
}
| 7
| null |
---
pipeline_tag: text2text-generation
widget:
- text: Hellooooo
example_title: Ex 0
- text: believ
example_title: Ex 1
language:
- en
tags:
- spell
- spell correction
- spelling
- spelling correction
- english
- english spelling
---
# Model Card for Model ID
This is a model for word-based spell correction tasks. This model is generated by fine-tuning bart base model.
This model works best for ''WORD-BASED'' spell correction(`not so good with the sequence of words`).
## How to Get Started with the Model
```python
from transformers import AutoTokenizer, TFBartForConditionalGeneration
tokenizer = AutoTokenizer.from_pretrained("veghar/spell_correct_bart_base")
model = TFBartForConditionalGeneration.from_pretrained("veghar/spell_correct_bart_base")
text='believ'
text_tok=tokenizer(text,padding=True, return_tensors='tf')
input_ids = text_tok['input_ids']
outputs = model.generate(input_ids=input_ids, max_length=10,num_return_sequences=3)
corrected_sentences = tokenizer.batch_decode(outputs, skip_special_tokens=True)
print('Misspelled word:', text)
print('Corrected word:', corrected_sentences)
>>Misspelled word: believ
>>Corrected word: ['believe', 'belief', 'believer']
```
|
BigTooth/DialoGPT-Megumin
|
[
"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
}
}
}
| 16
| null |
---
license: mit
language:
- en
pipeline_tag: text-to-image
---
## NVJOBAim v1.0. This is a model for generating crosshair assets. For stable diffusion.
This is a trained model for stable diffusion capable of generating crosshair images for video games. She trained on a large crosshair image dataset, which allows her to create new unique crosshairs based on the training data.
The model allows you to create high-quality images with a high degree of accuracy and detail.
Game developers can use this model to create their own custom crosshairs, allowing them to create unique visuals in their games and improve the user experience.
With this model, developers can save time and effort that would otherwise be spent manually creating each crosshair.
### Stable Diffusion Parameters:
Sampling method - Euler a<br>
Sampling steps - 30-80<br>
Resolution - 768x768<br>
CFG Scale - 12-15<br>
Or<br>
Sampling method - DPM++ 2M Karras<br>
Sampling steps - 23-35<br>
Resolution - 768x768<br>
CFG Scale - 12-15<br>
For higher resolution use Hires. fix or upscale.
### Prompts examples:
• nvjobaim, crosshair, aim, crosshaired sight scope, in a circle, white background, intricate, complicated, black and white<br>
• nvjobaim, a crosshaired sight scope with a crosshaired sight, crosshair, aim, white background, intricate, complicated, black and white<br>
• nvjobaim, a crosshaired with circle with a circular, crosshair, aim, white background, intricate, complicated, black and white<br>
• nvjobaim, cross arrows, crosshair, aim, white background, intricate, complicated, black and white<br>
### Negative prompts examples:
boring, simple, easy
### 🖤 Donate: [paypal.me/nvjob](https://paypal.me/nvjob)
[nvjob.github.io/ai](https://nvjob.github.io/ai)
|
BigeS/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
}
}
}
| 10
| null |
---
license: apache-2.0
tags:
- generated_from_trainer
model-index:
- name: gpt-j-tweet-quset
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. -->
# gpt-j-tweet-quset
This model is a fine-tuned version of [EleutherAI/gpt-j-6B](https://huggingface.co/EleutherAI/gpt-j-6B) on the None dataset.
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0002
- train_batch_size: 16
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 100
- training_steps: 100
- mixed_precision_training: Native AMP
### Training results
### Framework versions
- Transformers 4.27.4
- Pytorch 2.0.0+cu118
- Datasets 2.11.0
- Tokenizers 0.13.2
|
Bilz/DialoGPT-small-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
- 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: CartPole-v1
type: CartPole-v1
metrics:
- type: mean_reward
value: 179.20 +/- 62.75
name: mean_reward
verified: false
---
# PPO Agent Playing CartPole-v1
This is a trained model of a PPO agent playing CartPole-v1.
# Hyperparameters
```python
{'exp_name': 'ppo_file'
'seed': 1
'torch_deterministic': True
'cuda': True
'track': False
'wandb_project_name': 'cleanRL'
'wandb_entity': None
'capture_video': False
'env_id': 'CartPole-v1'
'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': 'EvaOr/ppo-CartPole-UNDERSTANDED'
'batch_size': 512
'minibatch_size': 128}
```
|
Binbin/test
|
[] | 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: parinzee/ppo-pyramids
3. Step 2: Select your *.nn /*.onnx file
4. Click on Watch the agent play 👀
|
BinksSachary/ShaxxBot
|
[
"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
}
}
}
| 9
| null |
---
tags:
- autotrain
- text-classification
language:
- en
widget:
- text: "I love AutoTrain 🤗"
datasets:
- sefaozalpadl/autotrain-data-postnashville_antitrans_telegram
co2_eq_emissions:
emissions: 0.4434488215878769
---
# Model Trained Using AutoTrain
- Problem type: Multi-class Classification
- Model ID: 46622115298
- CO2 Emissions (in grams): 0.4434
## Validation Metrics
- Loss: 0.569
- Accuracy: 0.818
- Macro F1: 0.707
- Micro F1: 0.818
- Weighted F1: 0.807
- Macro Precision: 0.777
- Micro Precision: 0.818
- Weighted Precision: 0.814
- Macro Recall: 0.674
- Micro Recall: 0.818
- Weighted Recall: 0.818
## 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/sefaozalpadl/autotrain-postnashville_antitrans_telegram-46622115298
```
Or Python API:
```
from transformers import AutoModelForSequenceClassification, AutoTokenizer
model = AutoModelForSequenceClassification.from_pretrained("sefaozalpadl/autotrain-postnashville_antitrans_telegram-46622115298", use_auth_token=True)
tokenizer = AutoTokenizer.from_pretrained("sefaozalpadl/autotrain-postnashville_antitrans_telegram-46622115298", use_auth_token=True)
inputs = tokenizer("I love AutoTrain", return_tensors="pt")
outputs = model(**inputs)
```
|
Blabla/Pipipopo
|
[] | 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:
- 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: 897.89 +/- 69.21
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
...
```
|
Blackmist786/DialoGPt-small-transformers4
|
[
"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
}
}
}
| 4
| null |
# Experience 8.0
[Civitai](https://civitai.com/models/5952)
* Includes Noise Offset training
* Darker images
* Improved contrast
* Read more [here](https://www.crosslabs.org/blog/diffusion-with-offset-noise)
* Requires slightly different prompting than v7.0
* Best for cinematic/dramatic generations.
* Is capable of very high fidelity generations
## Capabilities
* NSFW Photography
* SFW Photography is also possible, see "Trigger Words" bellow.
* Photorealistic 3D renders
* human anatomy
* Stylized images
* Landscapes
* Concept Art
* Album Art
etc.. This is more of a general purpose model
## Trigger Words
I'm not aware of any trigger words that have drastic influence on the generation process.
However, tags such as:
`3d render`, `cartoon` | `nsfw`, `sfw`, `nudity`, and `erotica`
tend to add push the generation (to some degree) in one direction or another. For example, putting `sfw` in your prompt and `nsfw` in your negative prompt should push the generation to produce a SFW image.
|
Blaine-Mason/hackMIT-finetuned-sst2
|
[
"pytorch",
"tensorboard",
"bert",
"text-classification",
"dataset:glue",
"transformers",
"generated_from_trainer"
] |
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
}
}
}
| 36
| null |
---
license: bigscience-openrail-m
datasets:
- laion/Anh
library_name: transformers
pipeline_tag: text-generation
tags:
- pytorch
- casual-lm
- multilingual
- instruct
- bloomz
---
### Model description
This model is [`bloomz-7b1-mt`](https://huggingface.co/bigscience/bloomz-7b1-mt) model finetuned on instruct dataset `cross_lingual.jsonl` from [`laion/Anh`](https://huggingface.co/datasets/laion/Anh).
### How to use
anh-bloomz-7b1-mt-cross-lingual model can be loaded and used via the following code:
```python
import re
from transformers import AutoModelForCausalLM, AutoTokenizer
model_name = "laion/anh-bloomz-7b1-mt-cross-lingual"
model = AutoModelForCausalLM.from_pretrained(model_name)
tokenizer = AutoTokenizer.from_pretrained(model_name)
whitespace_tokens_map = {'\n': '<n>', ' ': '<w>'}
text = "User: Apakah kita akan bisa menyembuhkan penyakit kanker? Jawab dalam bahasa China.\n"
for k, v in whitespace_tokens_map.items():
text = text.replace(k, v)
inputs = tokenizer(text, return_tensors="pt")
tokens = model.generate(**inputs, max_new_tokens=200, do_sample=True, top_k=40, top_p=0.9, temperature=0.2,
repetition_penalty=1.2,num_return_sequences=1)
output = tokenizer.decode(tokens[0], skip_special_tokens=True)
for v in whitespace_tokens_map.values():
output = re.sub(rf"{v}\s+(\S+)", rf"{v}\1", output)
for k, v in whitespace_tokens_map.items():
output = output.replace(v, k)
```
|
Botjallu/DialoGPT-small-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
| 2023-04-04T11:10:20Z
|
---
license: apache-2.0
datasets:
- tatsu-lab/alpaca
---
## 🍮 🦙 Flan-Alpaca: Instruction Tuning from Humans and Machines
📣 **FLAN-T5** is also useful in text-to-audio generation. Find our work at [https://github.com/declare-lab/tango](https://github.com/declare-lab/tango) if you are interested.
Our [repository](https://github.com/declare-lab/flan-alpaca) contains code for extending the [Stanford Alpaca](https://github.com/tatsu-lab/stanford_alpaca)
synthetic instruction tuning to existing instruction-tuned models such as [Flan-T5](https://arxiv.org/abs/2210.11416).
We have a [live interactive demo](https://huggingface.co/spaces/joaogante/transformers_streaming) thanks to [Joao Gante](https://huggingface.co/joaogante)!
We are also benchmarking many instruction-tuned models at [declare-lab/flan-eval](https://github.com/declare-lab/flan-eval).
Our pretrained models are fully available on HuggingFace 🤗 :
| Model | Parameters | Instruction Data | Training GPUs |
|----------------------------------------------------------------------------------|------------|----------------------------------------------------------------------------------------------------------------------------------------------------|-----------------|
| [Flan-Alpaca-Base](https://huggingface.co/declare-lab/flan-alpaca-base) | 220M | [Flan](https://github.com/google-research/FLAN), [Alpaca](https://github.com/tatsu-lab/stanford_alpaca) | 1x A6000 |
| [Flan-Alpaca-Large](https://huggingface.co/declare-lab/flan-alpaca-large) | 770M | [Flan](https://github.com/google-research/FLAN), [Alpaca](https://github.com/tatsu-lab/stanford_alpaca) | 1x A6000 |
| [Flan-Alpaca-XL](https://huggingface.co/declare-lab/flan-alpaca-xl) | 3B | [Flan](https://github.com/google-research/FLAN), [Alpaca](https://github.com/tatsu-lab/stanford_alpaca) | 1x A6000 |
| [Flan-Alpaca-XXL](https://huggingface.co/declare-lab/flan-alpaca-xxl) | 11B | [Flan](https://github.com/google-research/FLAN), [Alpaca](https://github.com/tatsu-lab/stanford_alpaca) | 4x A6000 (FSDP) |
| [Flan-GPT4All-XL](https://huggingface.co/declare-lab/flan-gpt4all-xl) | 3B | [Flan](https://github.com/google-research/FLAN), [GPT4All](https://github.com/nomic-ai/gpt4all) | 1x A6000 |
| [Flan-ShareGPT-XL](https://huggingface.co/declare-lab/flan-sharegpt-xl) | 3B | [Flan](https://github.com/google-research/FLAN), [ShareGPT](https://github.com/domeccleston/sharegpt)/[Vicuna](https://github.com/lm-sys/FastChat) | 1x A6000 |
| [Flan-Alpaca-GPT4-XL*](https://huggingface.co/declare-lab/flan-alpaca-gpt4-xl) | 3B | [Flan](https://github.com/google-research/FLAN), [GPT4-Alpaca](https://github.com/Instruction-Tuning-with-GPT-4/GPT-4-LLM) | 1x A6000 |
*recommended for better performance
### Why?
[Alpaca](https://crfm.stanford.edu/2023/03/13/alpaca.html) represents an exciting new direction
to approximate the performance of large language models (LLMs) like ChatGPT cheaply and easily.
Concretely, they leverage an LLM such as GPT-3 to generate instructions as synthetic training data.
The synthetic data which covers more than 50k tasks can then be used to finetune a smaller model.
However, the original implementation is less accessible due to licensing constraints of the
underlying [LLaMA](https://ai.facebook.com/blog/large-language-model-llama-meta-ai/) model.
Furthermore, users have noted [potential noise](https://github.com/tloen/alpaca-lora/issues/65) in the synthetic
dataset. Hence, it may be better to explore a fully accessible model that is already trained on high-quality (but
less diverse) instructions such as [Flan-T5](https://arxiv.org/abs/2210.11416).
### Usage
```
from transformers import pipeline
prompt = "Write an email about an alpaca that likes flan"
model = pipeline(model="declare-lab/flan-alpaca-gpt4-xl")
model(prompt, max_length=128, do_sample=True)
# Dear AlpacaFriend,
# My name is Alpaca and I'm 10 years old.
# I'm excited to announce that I'm a big fan of flan!
# We like to eat it as a snack and I believe that it can help with our overall growth.
# I'd love to hear your feedback on this idea.
# Have a great day!
# Best, AL Paca
```
|
Branex/gpt-neo-2.7B
|
[] | 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
| 2023-04-04T11:12:15Z
|
---
library_name: stable-baselines3
tags:
- LunarLander-v2
- deep-reinforcement-learning
- reinforcement-learning
- stable-baselines3
model-index:
- name: PPO
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: LunarLander-v2
type: LunarLander-v2
metrics:
- type: mean_reward
value: 275.24 +/- 22.00
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
...
```
|
Brokette/projetCS
|
[
"pytorch",
"wav2vec2",
"automatic-speech-recognition",
"transformers"
] |
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
}
}
}
| 4
| 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: -3.73 +/- 113.17
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': 5000000
'learning_rate': 0.00025
'num_envs': 8
'num_steps': 258
'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': 'EvaOr/chp8-ppo-LunarLander-v2-UNDERSTANDED'
'batch_size': 2064
'minibatch_size': 516}
```
|
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.