Datasets:
librarian-bots
/
model_cards_with_metadata

Dataset card Data Studio Files
xet
Community
2
modelId
string
author
string
last_modified
timestamp[us, tz=UTC]
downloads
int64
likes
int64
library_name
string
tags
sequence
pipeline_tag
string
createdAt
timestamp[us, tz=UTC]
card
string
Word2vec/nlpl_220
Word2vec
2023-07-06T07:30:44Z
0
0
null
[ "word2vec", "rus", "dataset:Russian_National_Corpus", "license:cc-by-4.0", "region:us" ]
null
2023-07-05T08:01:16Z
--- language: rus license: cc-by-4.0 tags: - word2vec datasets: Russian_National_Corpus --- ## Information A word2vec model trained by Andrey Kutuzov ([email protected]) on a vocabulary of size 249333 corresponding to 270000000 tokens from the dataset `Russian_National_Corpus`. The model is trained with the following properties: lemmatization and postag with the algorith Gensim Continuous Bag-of-Words with window of 10 and dimension of 300. ## How to use? ``` from gensim.models import KeyedVectors from huggingface_hub import hf_hub_download model = KeyedVectors.load_word2vec_format(hf_hub_download(repo_id="Word2vec/nlpl_220", filename="model.bin"), binary=True, unicode_errors="ignore") ``` ## Citation Fares, Murhaf; Kutuzov, Andrei; Oepen, Stephan & Velldal, Erik (2017). Word vectors, reuse, and replicability: Towards a community repository of large-text resources, In Jörg Tiedemann (ed.), Proceedings of the 21st Nordic Conference on Computational Linguistics, NoDaLiDa, 22-24 May 2017. Linköping University Electronic Press. ISBN 978-91-7685-601-7 This archive is part of the NLPL Word Vectors Repository (http://vectors.nlpl.eu/repository/), version 2.0, published on Friday, December 27, 2019. Please see the file 'meta.json' in this archive and the overall repository metadata file http://vectors.nlpl.eu/repository/20.json for additional information. The life-time identifier for this model is: http://vectors.nlpl.eu/repository/20/220.zip
NTQAI/pedestrian_gender_recognition
NTQAI
2023-07-06T07:29:58Z
45,879
15
transformers
[ "transformers", "pytorch", "onnx", "safetensors", "beit", "image-classification", "vision", "generated_from_trainer", "license:apache-2.0", "model-index", "autotrain_compatible", "endpoints_compatible", "region:us" ]
image-classification
2023-01-06T04:37:51Z
--- license: apache-2.0 tags: - image-classification - vision - generated_from_trainer metrics: - accuracy model-index: - name: outputs results: - task: name: Image Classification type: image-classification metrics: - name: Accuracy type: accuracy value: 0.9107332624867163 --- <!-- 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. --> # outputs This model is a fine-tuned version of [microsoft/beit-base-patch16-224-pt22k-ft22k](https://huggingface.co/microsoft/beit-base-patch16-224-pt22k-ft22k) on the [PETA dataset](http://mmlab.ie.cuhk.edu.hk/projects/PETA_files/Pedestrian%20Attribute%20Recognition%20At%20Far%20Distance.pdf) dataset. It achieves the following results on the evaluation set: - Loss: 0.2170 - Accuracy: 0.9107 ## Model description More information needed #### How to use You can use this model with Transformers *pipeline* . ```python from transformers import pipeline gender_classifier = pipeline(model="NTQAI/pedestrian_gender_recognition") image_path = "abc.jpg" results = gender_classifier(image_path) print(results) ``` ## 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: 1337 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 5.0 ### Training results | Training Loss | Epoch | Step | Validation Loss | Accuracy | |:-------------:|:-----:|:-----:|:---------------:|:--------:| | 0.5193 | 1.0 | 2000 | 0.3346 | 0.8533 | | 0.337 | 2.0 | 4000 | 0.2892 | 0.8778 | | 0.3771 | 3.0 | 6000 | 0.2493 | 0.8969 | | 0.3819 | 4.0 | 8000 | 0.2275 | 0.9100 | | 0.3581 | 5.0 | 10000 | 0.2170 | 0.9107 | ### Framework versions - Transformers 4.24.0.dev0 - Pytorch 1.12.1+cu113 - Datasets 2.6.1 - Tokenizers 0.13.1 ### Contact information For personal communication related to this project, please contact Nha Nguyen Van ([email protected]).
Word2vec/nlpl_206
Word2vec
2023-07-06T07:29:52Z
0
0
null
[ "word2vec", "pol", "dataset:Polish_CommonCrawl_Dump_of_December_2019", "license:cc-by-4.0", "region:us" ]
null
2023-07-05T08:09:12Z
--- language: pol license: cc-by-4.0 tags: - word2vec datasets: Polish_CommonCrawl_Dump_of_December_2019 --- ## Information A word2vec model trained by Krzysztof Wolk ([email protected]) on a vocabulary of size 4885806 corresponding to 32565035188 tokens from the dataset `Polish_CommonCrawl_Dump_of_December_2019`. The model is trained with the following properties: no lemmatization and postag with the algorith fastText Skipgram with window of 5 and dimension of 100. ## How to use? ``` from gensim.models import KeyedVectors from huggingface_hub import hf_hub_download model = KeyedVectors.load_word2vec_format(hf_hub_download(repo_id="Word2vec/nlpl_206", filename="model.bin"), binary=True, unicode_errors="ignore") ``` ## Citation Fares, Murhaf; Kutuzov, Andrei; Oepen, Stephan & Velldal, Erik (2017). Word vectors, reuse, and replicability: Towards a community repository of large-text resources, In Jörg Tiedemann (ed.), Proceedings of the 21st Nordic Conference on Computational Linguistics, NoDaLiDa, 22-24 May 2017. Linköping University Electronic Press. ISBN 978-91-7685-601-7 This archive is part of the NLPL Word Vectors Repository (http://vectors.nlpl.eu/repository/), version 2.0, published on Friday, December 27, 2019. Please see the file 'meta.json' in this archive and the overall repository metadata file http://vectors.nlpl.eu/repository/20.json for additional information. The life-time identifier for this model is: http://vectors.nlpl.eu/repository/20/206.zip
NTQAI/pedestrian_age_recognition
NTQAI
2023-07-06T07:28:59Z
110,387
3
transformers
[ "transformers", "pytorch", "safetensors", "beit", "image-classification", "vision", "generated_from_trainer", "license:apache-2.0", "model-index", "autotrain_compatible", "endpoints_compatible", "region:us" ]
image-classification
2023-01-09T03:36:33Z
--- license: apache-2.0 tags: - image-classification - vision - generated_from_trainer metrics: - accuracy model-index: - name: pedestrian_age_recognition_local results: - task: name: Image Classification type: image-classification dataset: name: imagefolder type: imagefolder config: default split: train args: default metrics: - name: Accuracy type: accuracy value: 0.8073394495412844 --- <!-- 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. --> # pedestrian_age_recognition_local This model is a fine-tuned version of [microsoft/beit-base-patch16-224-pt22k-ft22k](https://huggingface.co/microsoft/beit-base-patch16-224-pt22k-ft22k) on the imagefolder dataset. It achieves the following results on the evaluation set: - Loss: 0.5004 - Accuracy: 0.8073 ## 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: 1337 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 10.0 ### Training results | Training Loss | Epoch | Step | Validation Loss | Accuracy | |:-------------:|:-----:|:-----:|:---------------:|:--------:| | 0.8849 | 1.0 | 2008 | 0.7939 | 0.6807 | | 0.9836 | 2.0 | 4016 | 0.6694 | 0.7336 | | 0.8128 | 3.0 | 6024 | 0.5768 | 0.7668 | | 0.7611 | 4.0 | 8032 | 0.5541 | 0.7833 | | 0.6441 | 5.0 | 10040 | 0.5473 | 0.7773 | | 0.5696 | 6.0 | 12048 | 0.5187 | 0.7971 | | 0.6925 | 7.0 | 14056 | 0.5082 | 0.8038 | | 0.5711 | 8.0 | 16064 | 0.5092 | 0.8098 | | 0.7741 | 9.0 | 18072 | 0.5026 | 0.8020 | | 0.5269 | 10.0 | 20080 | 0.5004 | 0.8073 | ### Framework versions - Transformers 4.24.0.dev0 - Pytorch 1.12.1+cu113 - Datasets 2.6.1 - Tokenizers 0.13.1 ### Contact information For personal communication related to this project, please contact Nha Nguyen Van ([email protected]).
Word2vec/nlpl_184
Word2vec
2023-07-06T07:28:01Z
0
0
null
[ "word2vec", "rus", "dataset:Russian_News", "license:cc-by-4.0", "region:us" ]
null
2023-07-05T07:55:10Z
--- language: rus license: cc-by-4.0 tags: - word2vec datasets: Russian_News --- ## Information A word2vec model trained by Andrey Kutuzov ([email protected]) on a vocabulary of size 249318 corresponding to 2550000000 tokens from the dataset `Russian_News`. The model is trained with the following properties: lemmatization and postag with the algorith Gensim Continuous Skipgram with window of 5 and dimension of 300. ## How to use? ``` from gensim.models import KeyedVectors from huggingface_hub import hf_hub_download model = KeyedVectors.load_word2vec_format(hf_hub_download(repo_id="Word2vec/nlpl_184", filename="model.bin"), binary=True, unicode_errors="ignore") ``` ## Citation Fares, Murhaf; Kutuzov, Andrei; Oepen, Stephan & Velldal, Erik (2017). Word vectors, reuse, and replicability: Towards a community repository of large-text resources, In Jörg Tiedemann (ed.), Proceedings of the 21st Nordic Conference on Computational Linguistics, NoDaLiDa, 22-24 May 2017. Linköping University Electronic Press. ISBN 978-91-7685-601-7 This archive is part of the NLPL Word Vectors Repository (http://vectors.nlpl.eu/repository/), version 2.0, published on Friday, December 27, 2019. Please see the file 'meta.json' in this archive and the overall repository metadata file http://vectors.nlpl.eu/repository/20.json for additional information. The life-time identifier for this model is: http://vectors.nlpl.eu/repository/20/184.zip
Word2vec/nlpl_183
Word2vec
2023-07-06T07:27:39Z
0
0
null
[ "word2vec", "rus", "dataset:Russian_National_Corpus", "license:cc-by-4.0", "region:us" ]
null
2023-07-05T07:54:53Z
--- language: rus license: cc-by-4.0 tags: - word2vec datasets: Russian_National_Corpus --- ## Information A word2vec model trained by Andrey Kutuzov ([email protected]) on a vocabulary of size 248118 corresponding to 270000000 tokens from the dataset `Russian_National_Corpus`. The model is trained with the following properties: lemmatization and postag with the algorith Gensim Continuous Skipgram with window of 5 and dimension of 300. ## How to use? ``` from gensim.models import KeyedVectors from huggingface_hub import hf_hub_download model = KeyedVectors.load_word2vec_format(hf_hub_download(repo_id="Word2vec/nlpl_183", filename="model.bin"), binary=True, unicode_errors="ignore") ``` ## Citation Fares, Murhaf; Kutuzov, Andrei; Oepen, Stephan & Velldal, Erik (2017). Word vectors, reuse, and replicability: Towards a community repository of large-text resources, In Jörg Tiedemann (ed.), Proceedings of the 21st Nordic Conference on Computational Linguistics, NoDaLiDa, 22-24 May 2017. Linköping University Electronic Press. ISBN 978-91-7685-601-7 This archive is part of the NLPL Word Vectors Repository (http://vectors.nlpl.eu/repository/), version 2.0, published on Friday, December 27, 2019. Please see the file 'meta.json' in this archive and the overall repository metadata file http://vectors.nlpl.eu/repository/20.json for additional information. The life-time identifier for this model is: http://vectors.nlpl.eu/repository/20/183.zip
digiplay/Zevinemix_v1.0
digiplay
2023-07-06T07:24:33Z
255
3
diffusers
[ "diffusers", "safetensors", "stable-diffusion", "stable-diffusion-diffusers", "text-to-image", "license:other", "autotrain_compatible", "endpoints_compatible", "diffusers:StableDiffusionPipeline", "region:us" ]
text-to-image
2023-07-06T04:38:41Z
--- license: other tags: - stable-diffusion - stable-diffusion-diffusers - text-to-image - diffusers inference: true --- https://civitai.com/models/103015?modelVersionId=110251 Sample image I made : ![46105ee5-0d15-4fef-869c-8001b8c3bd68.jpeg](https://cdn-uploads.huggingface.co/production/uploads/646c83c871d0c8a6e4455854/AdPItkBFc4Ot3nsb0zm21.jpeg) ![5ab99e32-e1c8-4e05-a8b6-7c53a2b4b521.jpeg](https://cdn-uploads.huggingface.co/production/uploads/646c83c871d0c8a6e4455854/wrn3QMiDqZvxUz1UTc2O1.jpeg) Original Author's DEMO images : ![](https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/66ac4643-739f-45a4-a7be-1d9f4ce568df/00020-2280478265.jpeg) ![](https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/3bd9f933-ec26-4082-9c9a-3b24fb4a668f/00021-1004882248.jpeg) ![](https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/b96bf700-6858-45e7-9bdb-29514dcac6c3/00024-2424101811.jpeg) ![](https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/d813c897-c852-4d9a-93db-e5870cf1abfc/00037-2057319243.jpeg)
atiiisham988/distilbert-base-uncased-finetuned-imdb
atiiisham988
2023-07-06T07:01:14Z
115
0
transformers
[ "transformers", "pytorch", "tensorboard", "distilbert", "fill-mask", "generated_from_trainer", "dataset:imdb", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]
fill-mask
2023-07-06T06:57:35Z
--- license: apache-2.0 tags: - generated_from_trainer datasets: - imdb model-index: - name: distilbert-base-uncased-finetuned-imdb results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # distilbert-base-uncased-finetuned-imdb This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the imdb dataset. It achieves the following results on the evaluation set: - Loss: 2.4721 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 2e-05 - train_batch_size: 64 - eval_batch_size: 64 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 3.0 ### Training results | Training Loss | Epoch | Step | Validation Loss | |:-------------:|:-----:|:----:|:---------------:| | 2.7086 | 1.0 | 157 | 2.4897 | | 2.5796 | 2.0 | 314 | 2.4230 | | 2.5269 | 3.0 | 471 | 2.4354 | ### Framework versions - Transformers 4.30.2 - Pytorch 2.0.1+cu118 - Datasets 2.13.1 - Tokenizers 0.13.3
afaan00733/my_awesome_model
afaan00733
2023-07-06T06:56:30Z
105
0
transformers
[ "transformers", "pytorch", "distilbert", "text-classification", "generated_from_trainer", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]
text-classification
2023-07-04T21:18:08Z
--- license: apache-2.0 tags: - generated_from_trainer metrics: - accuracy model-index: - name: my_awesome_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_model This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 0.6546 - Accuracy: 0.4737 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 2e-05 - train_batch_size: 16 - eval_batch_size: 16 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 2 ### Training results | Training Loss | Epoch | Step | Validation Loss | Accuracy | |:-------------:|:-----:|:----:|:---------------:|:--------:| | No log | 1.0 | 2 | 0.6732 | 0.4737 | | No log | 2.0 | 4 | 0.6546 | 0.4737 | ### Framework versions - Transformers 4.30.2 - Pytorch 2.0.1 - Datasets 2.13.1 - Tokenizers 0.13.3
rohanbalkondekar/spicy-caiman
rohanbalkondekar
2023-07-06T06:55:23Z
10
0
transformers
[ "transformers", "pytorch", "llama", "text-generation", "gpt", "llm", "large language model", "h2o-llmstudio", "en", "autotrain_compatible", "text-generation-inference", "region:us" ]
text-generation
2023-07-06T06:48:59Z
--- language: - en library_name: transformers tags: - gpt - llm - large language model - h2o-llmstudio inference: false thumbnail: https://h2o.ai/etc.clientlibs/h2o/clientlibs/clientlib-site/resources/images/favicon.ico --- # Model Card ## Summary This model was trained using [H2O LLM Studio](https://github.com/h2oai/h2o-llmstudio). - Base model: [lmsys/vicuna-7b-v1.3](https://huggingface.co/lmsys/vicuna-7b-v1.3) ## Usage To use the model with the `transformers` library on a machine with GPUs, first make sure you have the `transformers`, `accelerate` and `torch` libraries installed. ```bash pip install transformers==4.30.1 pip install accelerate==0.20.3 pip install torch==2.0.0 ``` ```python import torch from transformers import pipeline generate_text = pipeline( model="BeRohan/spicy-caiman", torch_dtype="auto", trust_remote_code=True, use_fast=True, device_map={"": "cuda:0"}, ) res = generate_text( "Why is drinking water so healthy?", min_new_tokens=2, max_new_tokens=256, do_sample=False, num_beams=1, temperature=float(0.3), repetition_penalty=float(1.2), renormalize_logits=True ) print(res[0]["generated_text"]) ``` You can print a sample prompt after the preprocessing step to see how it is feed to the tokenizer: ```python print(generate_text.preprocess("Why is drinking water so healthy?")["prompt_text"]) ``` ```bash <|prompt|>Why is drinking water so healthy?</s><|answer|> ``` Alternatively, you can download [h2oai_pipeline.py](h2oai_pipeline.py), store it alongside your notebook, and construct the pipeline yourself from the loaded model and tokenizer. If the model and the tokenizer are fully supported in the `transformers` package, this will allow you to set `trust_remote_code=False`. ```python import torch from h2oai_pipeline import H2OTextGenerationPipeline from transformers import AutoModelForCausalLM, AutoTokenizer tokenizer = AutoTokenizer.from_pretrained( "BeRohan/spicy-caiman", use_fast=True, padding_side="left", trust_remote_code=True, ) model = AutoModelForCausalLM.from_pretrained( "BeRohan/spicy-caiman", torch_dtype="auto", device_map={"": "cuda:0"}, trust_remote_code=True, ) generate_text = H2OTextGenerationPipeline(model=model, tokenizer=tokenizer) res = generate_text( "Why is drinking water so healthy?", min_new_tokens=2, max_new_tokens=256, do_sample=False, num_beams=1, temperature=float(0.3), repetition_penalty=float(1.2), renormalize_logits=True ) print(res[0]["generated_text"]) ``` You may also construct the pipeline from the loaded model and tokenizer yourself and consider the preprocessing steps: ```python from transformers import AutoModelForCausalLM, AutoTokenizer model_name = "BeRohan/spicy-caiman" # either local folder or huggingface model name # Important: The prompt needs to be in the same format the model was trained with. # You can find an example prompt in the experiment logs. prompt = "<|prompt|>How are you?</s><|answer|>" tokenizer = AutoTokenizer.from_pretrained( model_name, use_fast=True, trust_remote_code=True, ) model = AutoModelForCausalLM.from_pretrained( model_name, torch_dtype="auto", device_map={"": "cuda:0"}, trust_remote_code=True, ) model.cuda().eval() inputs = tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to("cuda") # generate configuration can be modified to your needs tokens = model.generate( **inputs, min_new_tokens=2, max_new_tokens=256, do_sample=False, num_beams=1, temperature=float(0.3), repetition_penalty=float(1.2), renormalize_logits=True )[0] tokens = tokens[inputs["input_ids"].shape[1]:] answer = tokenizer.decode(tokens, skip_special_tokens=True) print(answer) ``` ## Model Architecture ``` LlamaForCausalLM( (model): LlamaModel( (embed_tokens): Embedding(32000, 4096, padding_idx=0) (layers): ModuleList( (0-31): 32 x LlamaDecoderLayer( (self_attn): LlamaAttention( (q_proj): Linear(in_features=4096, out_features=4096, bias=False) (k_proj): Linear(in_features=4096, out_features=4096, bias=False) (v_proj): Linear(in_features=4096, out_features=4096, bias=False) (o_proj): Linear(in_features=4096, out_features=4096, bias=False) (rotary_emb): LlamaRotaryEmbedding() ) (mlp): LlamaMLP( (gate_proj): Linear(in_features=4096, out_features=11008, bias=False) (down_proj): Linear(in_features=11008, out_features=4096, bias=False) (up_proj): Linear(in_features=4096, out_features=11008, bias=False) (act_fn): SiLUActivation() ) (input_layernorm): LlamaRMSNorm() (post_attention_layernorm): LlamaRMSNorm() ) ) (norm): LlamaRMSNorm() ) (lm_head): Linear(in_features=4096, out_features=32000, bias=False) ) ``` ## Model Configuration This model was trained using H2O LLM Studio and with the configuration in [cfg.yaml](cfg.yaml). Visit [H2O LLM Studio](https://github.com/h2oai/h2o-llmstudio) to learn how to train your own large language models. ## Model Validation Model validation results using [EleutherAI lm-evaluation-harness](https://github.com/EleutherAI/lm-evaluation-harness). ```bash CUDA_VISIBLE_DEVICES=0 python main.py --model hf-causal-experimental --model_args pretrained=BeRohan/spicy-caiman --tasks openbookqa,arc_easy,winogrande,hellaswag,arc_challenge,piqa,boolq --device cuda &> eval.log ``` ## Disclaimer Please read this disclaimer carefully before using the large language model provided in this repository. Your use of the model signifies your agreement to the following terms and conditions. - Biases and Offensiveness: The large language model is trained on a diverse range of internet text data, which may contain biased, racist, offensive, or otherwise inappropriate content. By using this model, you acknowledge and accept that the generated content may sometimes exhibit biases or produce content that is offensive or inappropriate. The developers of this repository do not endorse, support, or promote any such content or viewpoints. - Limitations: The large language model is an AI-based tool and not a human. It may produce incorrect, nonsensical, or irrelevant responses. It is the user's responsibility to critically evaluate the generated content and use it at their discretion. - Use at Your Own Risk: Users of this large language model must assume full responsibility for any consequences that may arise from their use of the tool. The developers and contributors of this repository shall not be held liable for any damages, losses, or harm resulting from the use or misuse of the provided model. - Ethical Considerations: Users are encouraged to use the large language model responsibly and ethically. By using this model, you agree not to use it for purposes that promote hate speech, discrimination, harassment, or any form of illegal or harmful activities. - Reporting Issues: If you encounter any biased, offensive, or otherwise inappropriate content generated by the large language model, please report it to the repository maintainers through the provided channels. Your feedback will help improve the model and mitigate potential issues. - Changes to this Disclaimer: The developers of this repository reserve the right to modify or update this disclaimer at any time without prior notice. It is the user's responsibility to periodically review the disclaimer to stay informed about any changes. By using the large language model provided in this repository, you agree to accept and comply with the terms and conditions outlined in this disclaimer. If you do not agree with any part of this disclaimer, you should refrain from using the model and any content generated by it.
Broonion/RLcourse-pb-cartport
Broonion
2023-07-06T06:53:57Z
0
0
null
[ "CartPole-v1", "reinforce", "reinforcement-learning", "custom-implementation", "deep-rl-class", "model-index", "region:us" ]
reinforcement-learning
2023-07-06T06:53:45Z
--- tags: - CartPole-v1 - reinforce - reinforcement-learning - custom-implementation - deep-rl-class model-index: - name: RLcourse-pb-cartport results: - task: type: reinforcement-learning name: reinforcement-learning dataset: name: CartPole-v1 type: CartPole-v1 metrics: - type: mean_reward value: 500.00 +/- 0.00 name: mean_reward verified: false --- # **Reinforce** Agent playing **CartPole-v1** This is a trained model of a **Reinforce** agent playing **CartPole-v1** . To learn to use this model and train yours check Unit 4 of the Deep Reinforcement Learning Course: https://huggingface.co/deep-rl-course/unit4/introduction
IliyanGochev/whisper-small-bg
IliyanGochev
2023-07-06T06:50:12Z
18
0
transformers
[ "transformers", "pytorch", "whisper", "automatic-speech-recognition", "whisper-event", "generated_from_trainer", "bg", "dataset:mozilla-foundation/common_voice_13_0", "license:apache-2.0", "model-index", "endpoints_compatible", "region:us" ]
automatic-speech-recognition
2023-07-05T08:04:03Z
--- language: - bg license: apache-2.0 tags: - whisper-event - generated_from_trainer datasets: - mozilla-foundation/common_voice_13_0 metrics: - wer model-index: - name: whisper-small-bg results: - task: name: Automatic Speech Recognition type: automatic-speech-recognition dataset: name: mozilla-foundation/common_voice_13_0 bg type: mozilla-foundation/common_voice_13_0 config: bg split: test args: bg metrics: - name: Wer type: wer value: 44.67291341315287 --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # whisper-small-bg This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the mozilla-foundation/common_voice_13_0 bg dataset. It achieves the following results on the evaluation set: - Loss: 9.0612 - Wer: 44.6729 ## 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: 32 - eval_batch_size: 16 - seed: 42 - distributed_type: multi-GPU - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_steps: 500 - training_steps: 5000 ### Training results | Training Loss | Epoch | Step | Validation Loss | Wer | |:-------------:|:-----:|:----:|:---------------:|:-------:| | 4.9319 | 6.76 | 1000 | 10.0774 | 73.9892 | | 2.6116 | 13.51 | 2000 | 11.4089 | 67.0484 | | 0.9607 | 20.27 | 3000 | 11.8266 | 60.9448 | | 0.3464 | 27.03 | 4000 | 9.9500 | 52.1213 | | 0.0122 | 33.78 | 5000 | 9.0612 | 44.6729 | ### Framework versions - Transformers 4.31.0.dev0 - Pytorch 2.0.1+cu117 - Datasets 2.12.0 - Tokenizers 0.13.3
JennnDexter/pokemon-lora
JennnDexter
2023-07-06T06:44:42Z
2
0
diffusers
[ "diffusers", "tensorboard", "stable-diffusion", "stable-diffusion-diffusers", "text-to-image", "lora", "base_model:runwayml/stable-diffusion-v1-5", "base_model:adapter:runwayml/stable-diffusion-v1-5", "license:creativeml-openrail-m", "region:us" ]
text-to-image
2023-06-12T06:24:16Z
--- license: creativeml-openrail-m base_model: runwayml/stable-diffusion-v1-5 tags: - stable-diffusion - stable-diffusion-diffusers - text-to-image - diffusers - lora inference: true --- # LoRA text2image fine-tuning - JennnDexter/pokemon-lora These are LoRA adaption weights for runwayml/stable-diffusion-v1-5. The weights were fine-tuned on the lambdalabs/pokemon-blip-captions dataset. You can find some example images in the following. ![img_0](./image_0.png) ![img_1](./image_1.png) ![img_2](./image_2.png) ![img_3](./image_3.png)
aroot/eng-mya-simcse_central
aroot
2023-07-06T06:36:12Z
103
0
transformers
[ "transformers", "pytorch", "tensorboard", "mbart", "text2text-generation", "translation", "generated_from_trainer", "autotrain_compatible", "endpoints_compatible", "region:us" ]
translation
2023-07-06T06:14:05Z
--- tags: - translation - generated_from_trainer metrics: - bleu model-index: - name: eng-mya-simcse_central 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. --> # eng-mya-simcse_central This model is a fine-tuned version of [facebook/mbart-large-50-many-to-many-mmt](https://huggingface.co/facebook/mbart-large-50-many-to-many-mmt) on the None dataset. It achieves the following results on the evaluation set: - Loss: 1.8980 - Bleu: 4.1973 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 2e-05 - train_batch_size: 32 - eval_batch_size: 32 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 3 - mixed_precision_training: Native AMP ### Training results ### Framework versions - Transformers 4.26.1 - Pytorch 2.0.1+cu117 - Datasets 2.12.0 - Tokenizers 0.13.3
hchung1017/aihub_012_streaming_transformer
hchung1017
2023-07-06T06:35:19Z
0
0
espnet
[ "espnet", "audio", "automatic-speech-recognition", "ko", "dataset:aihub_012", "arxiv:1804.00015", "license:cc-by-4.0", "region:us" ]
automatic-speech-recognition
2023-07-06T06:33:08Z
--- tags: - espnet - audio - automatic-speech-recognition language: ko datasets: - aihub_012 license: cc-by-4.0 --- ## ESPnet2 ASR model ### `hchung1017/aihub_012_streaming_transformer` This model was trained by hchung1017 using aihub_012 recipe in [espnet](https://github.com/espnet/espnet/). ### Demo: How to use in ESPnet2 Follow the [ESPnet installation instructions](https://espnet.github.io/espnet/installation.html) if you haven't done that already. ```bash cd espnet git checkout f4d7fead71e2a99541a8d3d66d6e00a33d9e82df pip install -e . cd egs2/aihub_012/asr1 ./run.sh --skip_data_prep false --skip_train true --download_model hchung1017/aihub_012_streaming_transformer ``` <!-- Generated by scripts/utils/show_asr_result.sh --> # RESULTS ## Environments - date: `Thu Jun 22 19:10:44 KST 2023` - python version: `3.8.16 (default, Mar 2 2023, 03:21:46) [GCC 11.2.0]` - espnet version: `espnet 202304` - pytorch version: `pytorch 1.13.1` - Git hash: `f4d7fead71e2a99541a8d3d66d6e00a33d9e82df` - Commit date: `Wed May 24 14:58:35 2023 -0400` ## exp/asr_train_asr_streaming_transformer_raw_ko_bpe5000_sp/decode_asr_streaming_asr_model_valid.acc.ave ### WER |dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err| |---|---|---|---|---|---|---|---|---| |org/dev|797676|3794053|89.3|9.3|1.3|1.5|12.1|29.5| ### CER |dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err| |---|---|---|---|---|---|---|---|---| |org/dev|797676|17636048|94.6|3.1|2.4|1.7|7.2|29.5| ### TER |dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err| |---|---|---|---|---|---|---|---|---| |org/dev|797676|4325914|87.8|8.3|3.9|1.5|13.8|29.5| ## ASR config <details><summary>expand</summary> ``` config: conf/train_asr_streaming_transformer.yaml print_config: false log_level: INFO dry_run: false iterator_type: sequence output_dir: exp/asr_train_asr_streaming_transformer_raw_ko_bpe5000_sp ngpu: 1 seed: 0 num_workers: 1 num_att_plot: 0 dist_backend: nccl dist_init_method: env:// dist_world_size: 8 dist_rank: 0 local_rank: 0 dist_master_addr: localhost dist_master_port: 32945 dist_launcher: null multiprocessing_distributed: true unused_parameters: false sharded_ddp: false cudnn_enabled: true cudnn_benchmark: false cudnn_deterministic: true collect_stats: false write_collected_feats: false max_epoch: 50 patience: null val_scheduler_criterion: - valid - acc early_stopping_criterion: - valid - cer_ctc - min best_model_criterion: - - valid - acc - max keep_nbest_models: 10 nbest_averaging_interval: 0 grad_clip: 5 grad_clip_type: 2.0 grad_noise: false accum_grad: 1 no_forward_run: false resume: true train_dtype: float32 use_amp: false log_interval: null use_matplotlib: true use_tensorboard: true create_graph_in_tensorboard: false use_wandb: false wandb_project: null wandb_id: null wandb_entity: null wandb_name: null wandb_model_log_interval: -1 detect_anomaly: false pretrain_path: null init_param: [] ignore_init_mismatch: false freeze_param: [] num_iters_per_epoch: null batch_size: 20 valid_batch_size: null batch_bins: 35000000 valid_batch_bins: null train_shape_file: - exp/asr_stats_raw_ko_bpe5000_sp/train/speech_shape - exp/asr_stats_raw_ko_bpe5000_sp/train/text_shape.bpe valid_shape_file: - exp/asr_stats_raw_ko_bpe5000_sp/valid/speech_shape - exp/asr_stats_raw_ko_bpe5000_sp/valid/text_shape.bpe batch_type: numel valid_batch_type: null fold_length: - 51200 - 150 sort_in_batch: descending sort_batch: descending multiple_iterator: false chunk_length: 500 chunk_shift_ratio: 0.5 num_cache_chunks: 1024 chunk_excluded_key_prefixes: [] train_data_path_and_name_and_type: - - /data/dump/aihub_012/raw/train_sp/wav.scp - speech - sound - - /data/dump/aihub_012/raw/train_sp/text - text - text valid_data_path_and_name_and_type: - - /data/dump/aihub_012/raw/dev/wav.scp - speech - sound - - /data/dump/aihub_012/raw/dev/text - text - text allow_variable_data_keys: false max_cache_size: 0.0 max_cache_fd: 32 valid_max_cache_size: null exclude_weight_decay: false exclude_weight_decay_conf: {} optim: adam optim_conf: lr: 0.0015 scheduler: warmuplr scheduler_conf: warmup_steps: 25000 token_list: - <blank> - <unk> - ▁I - ▁YOU - '''' - S - ▁WHAT - ▁A - ▁IT - ▁TO - ▁IS - ▁THE - ▁ARE - ▁CAN - ▁OKAY - ▁YES - ▁DO - ▁THAT - ▁SEE - T - ▁HE - ▁HOW - ▁ME - ▁HAVE - ▁MY - ▁GOOD - ▁REALLY - ▁SO - ▁FOR - ▁AM - ▁SURE - ▁OH - ▁GO - ▁WHY - ▁NO - ▁YOUR - ▁RIGHT - ▁HELP - ’ - ▁DON - ▁NOT - ▁HI - ▁HERE - ▁DID - ▁LIKE - ▁AND - ▁TOO - ▁SHE - ▁THIS - ▁HELLO - M - ▁KNOW - ▁WANT - RE - ▁NEED - ▁WILL - ▁ABOUT - ▁THERE - ▁LET - ▁OF - ▁IN - ▁BE - ▁BUT - ▁THINK - ▁SOMETHING - ▁LOOK - ▁NOW - ▁NICE - ▁THEN - ▁ - ▁WE - ▁GREAT - ▁THANK - ▁WITH - ▁TELL - ▁PROBLEM - ▁HER - ▁GOING - ▁WAS - ▁DOING - ▁ASK - ▁THANKS - ▁HEY - ▁BACK - ▁WRONG - ▁THEY - ▁ON - ▁HIM - ▁UP - ▁AT - LL - ▁WELL - ▁GET - ▁WHERE - VERY - ▁SOME - ▁PEOPLE - ▁ALL - ▁MEAN - ▁PLEASE - ▁TIME - ▁WHO - ▁GOT - ▁WELCOME - ▁MAKE - ▁COME - ▁MEET - ▁NEW - ▁LOT - ▁MOM - ▁SAID - ▁SHOULD - ▁HAPPY - ▁HIS - ▁BUSY - ▁BYE - ▁QUESTION - ▁SAY - ▁TAKE - ▁MORE - ▁SORRY - ▁IDEA - ▁OUT - ▁FINE - ▁PLAY - ▁ANY - ▁AGAIN - ▁BECAUSE - ▁FROM - ▁AN - ▁WHEN - ▁TRY - ▁HAS - ▁TODAY - ▁READY - ▁HOPE - ▁GIVE - ▁BIG - ▁FRIEND - ▁WRITE - ▁EAT - ▁ONE - ▁BAD - ▁MUCH - ▁SOON - ▁MANY - ED - ▁THEM - ▁ANGRY - ▁LATER - ING - ▁MAYBE - ▁DAD - ▁FIND - ▁DOWN - ▁WORRY - ▁SHOW - ▁COURSE - ▁DAY - ▁SOUNDS - ▁DOES - ▁STRANGE - ▁TALK - ▁FUN - ▁REMEMBER - ▁ANYTHING - ▁BUY - ▁LETTER - ▁JUST - ▁MADE - ▁READ - ▁CANNOT - ▁WANTS - ▁WOW - ▁DIDN - ▁IF - ▁GLAD - ▁WAY - ▁MUST - ▁SCHOOL - ▁BOOK - ▁LOOKING - ▁TOLD - ▁NAME - ▁HEAR - ▁TOY - ▁TRUE - ▁TEACHER - ▁US - ▁WORK - ▁TWO - ▁SONG - ▁HARD - ▁LOVE - ▁THINGS - ▁SING - ▁BETTER - ▁HOME - ▁LINKER - ▁UNDERSTAND - ▁LOOKS - ▁KIND - ▁HOUSE - LUE - ▁DRESS - ▁BY - ▁BEST - ▁LONG - ▁NEWS - ▁WENT - ▁HAPPENED - ▁OLD - ▁KEEP - ▁NEXT - ▁CHECK - D - ▁SPECIAL - ▁USE - ▁LIKES - ▁EVERYTHING - ▁FEEL - ▁ROBOT - ▁SAD - ▁PLEASURE - ▁JOE - ▁COOL - ▁TOMORROW - ▁LUCK - ▁DOESN - ▁BOX - ▁AROUND - ▁HOMEWORK - ▁ALWAYS - ▁MORGAN - ▁PUT - ▁THESE - ▁GAVE - ▁HEARD - ▁WAIT - ▁PRESENT - ▁SOMEONE - ▁PARTY - ▁BIRTHDAY - ▁RANDY - ▁FRIENDS - ▁MONEY - ▁DONE - ▁CAR - ▁COFFEE - ▁MUSIC - ▁BEN - ▁BEEN - ▁STILL - ▁GREEN - ▁STAR - ▁PERSON - ▁WERE - ▁STORY - ▁ELSE - ▁IDEAS - ▁TOGETHER - ▁MILK - ▁WOULD - ▁SOUND - ▁THAN - ▁TALKED - ▁EVERY - ▁NEEDS - ▁SAW - ▁HAIR - ▁CHANGE - ▁WORRIED - ▁EASY - ▁FOOD - ▁DOG - VE - ▁CONCERT - ▁MAKING - ▁MONSTER - ▁BOY - ▁PHOTO - ▁SCARY - ▁RED - ▁BROTHER - ▁FIRST - ▁DANCE - ▁BEFORE - ▁PRETTY - ▁DRINK - ▁WISH - ▁HARRY - ▁CALM - ▁CAT - ▁WEAR - ▁BLUE - ▁MESSAGE - ▁TRUST - ▁ONLY - ▁HAD - ▁THREE - ▁AWAY - ▁MIND - ▁MAKES - ▁GRANDMOTHER - ▁WATCH - ▁EMMA - ▁AMY - ▁TIRED - ▁CLASS - ▁MAN - ▁DAN - ▁COULD - ▁BRING - ▁SMALL - ▁ANYWAY - ▁OUR - ▁ROOM - ▁AFTER - ▁BELIEVE - ▁BOOKS - ▁TEN - ▁DEVILMON - ▁JOB - ▁OVER - ▁COMING - ▁STOP - ▁FUNNY - ▁DIANA - ▁TOYS - ▁FAST - ▁MORNING - ▁NUMBER - ▁NOTHING - ▁TOWN - ▁OPEN - ▁OTHER - ▁PHONE - ▁CARE - ▁LEAVE - ▁CONTEST - ▁WOODY - ▁THINKING - Y - ▁ANOTHER - A - ▁ENGLISH - ▁SICK - ▁BRAVE - ▁TROY - ▁EATING - ▁SLEEP - ▁THEIR - ▁SELL - ▁DELICIOUS - ▁OFF - ▁WATER - ▁PICTURE - ▁CAME - ▁EVERYONE - ▁PAPER - ▁PARK - ▁PAINT - ▁SHOP - ▁CREAM - ▁TV - ▁BOUGHT - ▁CAREFUL - ▁ROBBY - ▁FOUND - ▁STONE - ▁SISTER - ▁HURRY - ▁BAG - ▁WAKE - ▁SYRUP - ▁DRAW - ▁ENERGY - ▁SHOES - ▁IMPORTANT - ▁NEVER - ▁LISTEN - ▁WON - ▁DOOR - ▁POP - ▁LAST - ▁DIFFERENT - ▁FISH - ▁SAVE - ▁HEALTHY - ▁UNCLE - ▁NIGHT - UCH - ▁PLACE - ▁DARK - ▁GUESS - ▁LATE - ▁PIE - N - ▁PRACTICE - ▁MONICA - ▁ANYONE - ▁READING - ▁COLOR - ▁SALLY - ▁BLACK - ▁MOVIE - ▁TROUBLE - ▁COLD - ▁STUDY - ▁LITTLE - ▁WHITE - ▁CHEER - ▁SCARED - ▁POSTER - ▁TALKING - ▁TEACH - ▁WALK - ▁CAKE - ▁INTO - ▁FIGHT - ▁ALREADY - ▁SLEEPY - ▁STRONG - ▁OLIVIA - ▁CALL - ▁WROTE - ▁ICE - ▁OR - ▁SCOTT - ▁LIBRARY - ▁NANCY - ▁LUMY - ▁HAT - ▁YET - ▁ALEX - ▁SHORT - ▁CLOTHES - ▁YESTERDAY - ▁FAVORITE - ▁SWEET - ▁FIVE - ▁HOLD - ▁LUNCH - ▁PLAYING - ▁GARY - ▁HANDS - ▁LEFT - ▁ASKED - ▁CHEESE - ▁FACE - ▁BORROW - ▁SPEAK - ▁INTERESTING - ▁MAY - ▁BEAR - ▁SIGN - ▁SHADOW - ▁FLOWERS - ▁PINO - ▁ERIN - ▁FOREST - ▁GAME - ▁MR - ▁WANTED - ▁RUN - ▁SPELL - ▁PEN - ▁SHOPPING - ▁COOK - ▁DAYS - ▁BED - ▁BEAUTIFUL - ▁MUSEUM - ▁CLEAN - ▁REST - ▁SAME - ▁DOCTOR - ▁YOURSELF - ▁DINNER - ▁DANGEROUS - ▁SECRET - ▁STORE - ▁TREE - ▁MIGHT - ▁MAYOR - ▁CHARLIE - ▁PIZZA - ▁FOUR - ▁SIR - ▁SEEN - ▁TURN - ▁ENJOY - ▁CLARA - ▁ANYTIME - ▁LIVE - ▁LOST - ▁SANDRA - ▁DURING - ▁MYSELF - ▁TALL - ▁MINE - ▁CHOOSE - ▁TOOK - ▁WAITING - ▁S - ▁SUNNY - ▁SINGING - ▁ACADEMY - ▁AHEAD - ▁HURT - ▁CLOCK - ▁PAINTING - ▁RAN - ▁ALONE - ▁USED - ▁PLAN - ▁THEATER - ▁HAND - ▁WEEK - ▁CATCH - ▁SEND - ▁CUBE - ▁ERIC - ▁WOOD - ▁HOT - ▁DEVILMONS - ▁FREE - ▁STAY - ▁PROMISE - ▁RULE - ▁HUNGRY - ▁WORKING - ▁HAPPEN - ▁VIKI - ▁FAMILY - ▁CHICKEN - ▁FORGET - ▁YELLOW - ▁BROWN - ▁VACATION - ▁KELLY - ▁JACK - ▁SINGER - ▁HAMMER - ▁SAYS - ▁TRAIN - ▁FIX - ▁CUTE - ▁EVEN - ▁SANTA - ▁SLEEPING - ▁BUS - ▁BARBECUE - ▁AGREE - ▁COULDN - ▁MISS - E - ▁GRACE - ▁TRASH - ▁BABY - ▁LUMA - ▁CHILDREN - ▁EXCUSE - ▁DPOP - ▁OUTSIDE - ▁ORDER - ▁MATTER - ▁RIDE - ▁SUMMER - ▁CLOSE - ▁MOVE - ▁JUICE - ▁TOUCH - ▁CARD - ▁THOSE - ▁HAIRSTYLE - ▁RICH - ▁BREAK - ▁ANYMORE - ▁TRIP - ▁EYES - ▁LEARN - IC - ▁YOUNGER - ▁SMELLS - ▁CHRIS - ▁ITEMS - ▁STONES - ▁CUT - ▁STUDENT - ▁CALLED - ▁SHINE - ▁ATE - ▁PERFECT - ▁BETIA - ▁MOVING - LY - ▁FIRE - ▁D - ▁CHRISTMAS - ▁RUNNING - ▁LINE - ▁JACKET - ▁WHICH - ▁GIFT - ▁SMILE - ▁WEARING - ▁STELLA - ▁SEVEN - ▁ANSWER - ▁YEAR - ▁MOST - ▁WENDY - RA - ▁BALL - ▁THING - ▁FIFTY - ▁YOUNG - ▁FRONT - ▁LIKED - ▁WINDOW - ▁BEING - ▁RICE - ▁HOBBY - ▁BRUCE - ▁ALVIN - ▁CHAIR - ▁ELEVEN - ▁INTERVIEW - ▁TRUMPET - ▁DRAWING - ▁WHILE - ▁HAV - ▁NEWSPAPER - ▁WRITING - ▁FRUIT - ▁BEHIND - ▁EVENT - ▁HAVEN - ▁BELLOW - ▁YEARS - ▁DIV - ▁VICTORIA - ▁SENT - ▁STYLE - ▁LUNA - ▁AUNT - ▁DREAM - ▁PICTURES - ▁LEO - ▁QUESTIONS - ▁PRICE - ▁APPLE - ▁SCHEDULE - ▁TABLE - ▁PLANT - ▁BELL - ▁SUSAN - ▁SHIRT - ▁GRANDFATHER - ▁EXPENSIVE - ▁GUYS - ▁THOUGHT - ▁OSCAR - ▁TIMES - ▁ACTUALLY - ▁CHANCE - ▁PAY - ▁WASH - ▁JUGGLING - ▁JULIA - ▁MAKEUP - ▁PIANO - ▁GOES - ▁QUIZ - ▁OFTEN - ▁THIRTY - ▁SMART - ▁WEEKEND - ▁CHOCOLATE - ▁BATHROOM - ▁CANDY - ▁SPEECH - ▁FEELING - ▁RADIO - ▁HECTOR - ▁KNOWS - ▁GRANDMA - ▁SEEM - ER - ▁START - ▁PENCIL - ▁SUNDAY - ▁WORD - ▁MOUSE - ▁PLAYGROUND - ▁BREAD - ▁MAGIC - ▁CD - ▁BROKEN - ▁COLIN - ▁DIRTY - ▁MOTHER - ▁DESK - ▁BORING - ▁SOUP - ▁ONCE - ▁WORKED - ▁COUNT - ▁EXCITED - ▁PARADE - ▁GUITAR - ▁PM - ▁FINISH - ▁BLOCK - ▁FISHING - ▁VOICE - ▁ROGER - ▁WORKS - ▁PLAYER - ▁GLASSES - ▁LAB - ▁SIGH - ▁LOVES - ▁MODEL - ▁EXERCISE - ▁O - ▁POINT - ▁SWIMMING - ▁MARKET - ▁NOTE - ▁SECOND - ▁LUCKY - ▁BROKE - ▁CAVE - ▁SHALL - ▁KID - ▁HANG - ▁MICHAEL - ▁DANCING - ▁COM - ▁MASK - TING - ▁KYLE - ▁FRIDAY - ▁MELOD - ▁DOUGLAS - ▁ENOUGH - ▁LEARNED - ▁ALICE - ▁NEWSPAPERS - ▁NEAR - ▁GIRL - ▁LAURA - ▁BANK - ▁ORANGE - ▁HEART - ▁SNACKS - ▁BANANA - ▁AFRAID - ▁NOISE - ▁AARON - ▁SIDE - ▁POSSIBLE - ▁ISN - ▁UPSET - ▁KATHY - ▁ENTER - ▁STATUE - ▁FAVOR - ▁CAPSULE - ▁CLUB - ▁BORED - ▁STREET - ▁FAR - ▁BROUGHT - ▁HENRY - ▁BRIAN - ▁FLOOR - ▁RECORD - ▁SUN - ▁BORN - ▁GONE - ▁ELEPHANT - ▁FATHER - ▁BEAT - ▁MISTAKE - NY - ▁MEGAN - ▁JIN - ▁CARL - ▁FACTORY - ▁HORSE - ▁STANLEY - ▁WIN - ▁AFTERNOON - ▁LIVED - ▁HIGH - ▁LEAVING - ▁MINUTES - ▁WALL - ▁SURPRISE - ▁DAVID - ▁TWENTY - ▁BIRD - ▁NICK - ▁REASON - ▁OWN - ▁STEVE - ▁LADY - ▁COMES - ▁STATION - ▁DOLL - ▁JADE - ▁STAND - ▁FAMOUS - ▁PLAYED - ▁TSHIRT - ▁HUEY - ▁SEA - ▁SIX - ▁REPORT - ▁POPULAR - ▁PICK - ▁TONY - ▁TINA - ▁KIDS - ▁WEATHER - ▁TREES - ▁TIFFANY - ▁WONDERFUL - ▁RING - ▁SOMEWHERE - ▁LIGHT - ▁NOSE - ▁AUDREY - ▁CAMERA - ▁GARDEN - ▁SOCCER - ▁PIG - ▁FRESH - ▁NOBODY - ▁AMANDA - ▁SURPRISED - ▁STOPPED - ▁CITY - ▁KOREAN - ▁HISTORY - ▁STUDENTS - ▁COOKING - L - ▁LOUD - ▁LOSE - ▁PINK - ▁LIE - ▁CRAYONS - ▁HEALTH - ▁HANDWRITING - ▁JOIN - ▁THROW - ▁INFORMATION - ▁DIFFICULT - ▁SOMETIMES - ▁BIKE - ▁WOMAN - ▁FLOWER - ▁WORDS - ▁GHOST - ▁RICKY - R - ▁TEETH - ▁SAYING - ▁PIECE - ▁DR - ▁CHANGED - ▁SIT - ▁ARTICLE - ▁ARM - ▁BECOME - ▁MONKEY - ▁YEAH - ▁JUDY - ▁FOLLOW - ▁ALSO - ▁GAMES - ▁BAND - ▁COMPUTER - ▁ANDRE - ▁EATS - ▁MATH - ▁EXACTLY - ▁ART - ▁JUMP - ▁FOODS - ▁PRESENTS - ▁RABBIT - ▁SMELL - ▁HEAVY - ▁SWIM - ▁RICHARD - ▁GRASS - ▁BOTHER - ▁PANTS - ES - ▁ALMOST - ▁HELPING - ▁ZOO - ▁SHOULDN - ▁FAN - ▁EGGS - ▁ELLA - ▁RESTAURANT - ▁CHIPS - ▁BIGGER - ▁MONDAY - ▁CATS - ▁STUDYING - ▁TONIGHT - ▁BRADY - ▁SERIOUS - ▁FORGOT - ▁VISIT - ▁BUILDING - ▁SET - ▁HANDSOME - ▁CLAUS - ▁RALPH - ▁COMPANY - ▁SEAT - ▁ANDREW - ▁WITHOUT - EN - ▁MEAT - ▁BOARD - ▁CLASSES - ▁FLY - ▁BIT - ▁ANGELA - ▁POLICE - ▁BET - ▁FINISHED - ▁EITHER - ▁SKY - ▁POLIA - ▁EIGHT - ▁AMAZING - ▁INSIDE - ▁SATURDAY - ▁DINOSAUR - ▁DEVERYTHING - ▁BRUSH - ▁VIVIEN - ▁BREAKFAST - ▁QUICKLY - ▁HEAD - ▁CAROL - ▁EACH - ▁BANANAS - ▁JAZZ - ▁OWEN - ▁LEAVES - ▁HELPED - ▁WINTER - ▁REAL - ▁TRUTH - ▁RIVER - ▁ROAD - ▁ANNA - ▁INTERESTED - ▁EVERYBODY - ▁HIMSELF - ▁TAKES - ▁LADDER - ▁BOTH - ▁CLASSROOM - ▁STUDIED - ▁HALL - MAS - ▁STARTED - ▁THO - ▁REFUND - ▁EARLY - ▁MARK - ▁TRIED - ▁CRY - ▁CUP - ▁DEAL - ▁LEGS - ▁PARTNER - ▁NINE - ▁MONTH - ▁CRYSTAL - ▁MRS - ▁WHOM - ▁QUIET - ▁TICKET - ▁TRYING - ▁JELLY - ▁TEST - ▁OFFICE - ▁BICYCLE - ▁HOSPITAL - ▁POOL - ▁DOGS - ▁LIVES - ▁NOISY - ▁TASTE - ▁FEET - ▁PASTA - ▁HANS - AL - ▁PAST - ▁PRIZE - ▁KEY - ▁COUPON - ▁TIMMY - ▁AREN - ▁MEMO - ▁TEACHE - ▁PRACTICING - ▁ANIMAL - ▁MOUTH - ▁WORLD - ▁UNDER - ▁WATCHING - ▁FELL - ▁DRIVE - ▁BEACH - ▁CLEAR - ▁JOKES - ▁GAVIN - ▁ADD - CLOCK - ▁HELPER - ▁JULIE - ▁WEIRD - ▁SINCE - ▁MILLER - ▁TIE - ▁FRUITS - ▁HOUR - ▁ANIMALS - ▁TWICE - ▁WARM - ▁LARGE - ▁UNTI - ▁JAMES - ▁DOLLARS - ▁STORIES - ▁MEAL - ▁APPLES - ▁CRYING - ▁DIET - ▁HEADPHONES - ▁MEMORI - ▁COMPLIMENT - ▁TRIANGLE - ▁DIARY - ▁TOWER - ▁EYE - ▁SALE - ▁BUILT - ▁CARROT - ▁ORDERED - ▁ITEM - ▁SLOW - ▁NAOMI - ▁TUESDAY - ▁SENSE - ▁PARENTS - ▁GIV - ▁BUSINESS - ▁EVER - ▁TYLER - ▁FORWARD - ▁CELL - ▁SHUT - ▁COAT - ▁PRINCE - ▁HATE - ▁PUPPET - ▁FULL - ▁WOULDN - ▁TERRIBLE - ▁CARDS - ▁MAP - ▁STAMP - ▁SNACK - ▁SNOW - ▁RUBY - ▁SLOWLY - ▁EDDY - ▁EASILY - ▁LAZY - ▁BLOCKS - ▁EARS - ▁COLORS - ▁TTEOKBOKKI - ▁CAREFULLY - ▁MARRIED - ▁VILLAGE - ▁HEADACHE - ▁MOUNTAIN - ▁PETER - ▁FAT - ▁MARRY - WEEN - ▁RYAN - ▁DISHES - ▁JIM - ▁FIELD - ▁CINDY - ▁FEW - ▁STARS - ▁UMBRELLA - ▁GROW - ▁FROG - ▁RULER - ▁BASKETBALL - ▁PART - ▁ORLANDO - ▁CORRECT - ▁GRANDPA - ▁ADVICE - ▁ARMS - SE - ▁PHOTOS - ▁KICKBOARD - ▁JACOB - ▁DANGER - ▁BOOTS - ▁GIANT - ▁BATH - ▁VISITOR - ▁PROMISED - ▁SNAKE - ▁GLASS - ▁RAISE - ▁SPICY - ▁TURNED - ▁MEETING - ▁VIOLIN - ▁MINUTE - ▁DAISY - ▁BUTTON - ▁OTHERS - ▁DELIVERY - ▁WASN - ▁JOGGING - ▁SOFA - ▁FINGERS - ▁NICOLE - ▁TALLER - ▁RUNS - ▁BENJAMIN - ▁GOLD - ▁LUCAS - ▁SNOWMAN - ▁LOVED - ▁SANDWICH - ▁STRAIGHT - ▁AGAINST - ▁BALLOONS - ▁KEPT - ▁CLOSED - ▁PENS - ▁MAX - ▁LEG - ▁FILL - ▁QUIT - ▁ANYBODY - ▁JEFF - ▁ANN - ▁EVAN - ▁MISSED - ▁TAEKWONDO - ▁JOY - ▁PUSH - ▁WOODWARD - ▁ROSS - ▁LISA - ▁PULL - ▁NECTAR - ▁VASE - ▁RABBITS - ▁BOW - ▁BUGS - ▁SAFE - GETTING - ▁CASH - ▁LAMP - ▁DOLLS - ▁YUMMY - ▁MEDICINE - ▁SPORTS - ▁ENDS - ▁BASEBALL - ▁THROUGH - ▁CENTER - ▁FIGHTER - ERS - ▁PACKAGE - ▁WORMS - ▁SHAPE - ▁DISAPPOINTED - ▁PHILLIP - ▁DINOSAURS - ▁SALAD - ▁HAMBURGER - ▁COOKIES - ▁PASS - ▁CHEAP - ▁STAGE - ▁COLORED - ▁TYPE - ▁EVENING - ▁CRIED - ▁SHOWER - ▁WALLET - ▁FIFTEEN - ▁HERO - ▁USUALLY - ▁GATE - ▁TEAM - ▁PLANE - ▁DRESSES - ▁SOLD - ▁CRAYON - LE - ▁HIDE - ▁BODY - ▁MEN - ▁HAIRSTYLES - ▁BOAT - ▁WONDER - ▁RAIN - ▁FEELS - ▁NERVOUS - ▁CHILD - ▁MIRROR - ▁BUG - ▁LONGER - ▁LOUIS - ▁AIR - ▁STOMACHACHE - ▁ASKING - ▁OWNER - ▁KNEW - ▁BELT - I - ▁MAGAZINE - ▁HOP - ▁SUGAR - ▁END - ▁TAKING - ▁LIGHTS - ▁EMPTY - ▁PUPPY - ▁DUCK - ▁SUPERMARKET - ▁APARTMENT - ▁ADDRESS - ▁MACHINE - ▁JASON - ▁CARRY - ▁DRY - ▁EXCITING - ▁BOTTLE - ▁RIDING - ▁CHARCOAL - ▁TRAVIS - ▁UGLY - ▁CAUGHT - ▁PROBAB - ▁PROJECT - ▁LISTENING - ▁JUGGLE - ▁ROPE - ▁BILL - ▁HOURS - ▁MOLLY - ▁SOPHIE - ▁WEARS - ▁LIFE - ▁CAFE - ▁HURTS - ▁RELAX - ▁TED - ▁COPY - ▁COTTON - ▁ALONG - ▁OFFER - ▁DATE - ▁LI - ▁YOUTUBE - ▁JOKE - ▁BARREL - ▁DIED - ▁SINGS - ▁SEVERAL - ▁TALENT - ▁CARTER - ▁PASSWORD - ▁CASE - ▁SCISSORS - ▁YORK - ▁FANTASTIC - ▁CLOUDY - ▁ROUND - ▁BUILD - ▁PRINCESS - ▁RAINY - ▁GRAPES - ▁SKIRT - ▁LION - ▁FASTER - ▁FASHION - ▁AD - ▁EXPLAIN - ▁DOCK - ▁MATCH - ▁BOMB - ▁STADIUM - ▁WOODS - ▁FALL - ▁MAD - ▁TRUCK - ▁STEP - ▁ANSWERS - ▁KIDDING - ▁MOON - ▁BEAN - ▁PICKED - ▁LESSON - ▁KNOWN - ▁HAPPENING - ▁BLUEBERRIES - ▁SANDWICHES - ▁BUTTER - ▁BEDROOM - ▁ABOVE - ▁LEGO - ▁HELENA - ▁FOOTPRINT - ▁SHIP - ▁TAP - ▁HILL - ▁CHURCH - ▁GOODBYE - ▁LEMON - ▁HUNDRED - ▁COWARD - ▁ARRIVED - ▁WATERMELON - ▁BOXES - ▁FINALLY - ▁MAIN - ▁KEVIN - BINGO - ▁BONES - ▁SPOKE - ▁DONUTS - ▁HENNA - ▁LETTERS - ▁PAM - ▁LESS - ▁WEDDING - ▁POCKET - ▁SHY - ▁NOWHERE - ▁MIC - ▁NAMES - ▁SONGS - MED - ▁DECIDED - ▁KITCHEN - ▁SHINING - ▁LOVELY - ▁SEASON - ▁STEAK - ▁DRUM - ▁TEDDY - ▁SHINY - ▁GIRLS - ▁AUDITION - ▁ACTING - ▁NECK - ▁ROSA - ▁SNEAKERS - ▁SHOE - ▁QUITE - ▁HOTEL - ▁LEATHER - ▁WIND - ▁COUSIN - ▁JANET - ▁ONIONS - ▁DEAD - ▁PROUD - ▁PET - ▁HELPFUL - ▁TOILET - ▁FORTY - ▁JAKE - ▁BUTTERFLY - ▁KICK - ▁BIRDS - ▁ABROAD - ▁TEA - ▁STARTS - ▁MEALS - ▁AIRSHIPS - ▁SOFT - ▁MATT - ▁BLANKET - ▁WINDY - ▁PLAYS - ▁COVER - ▁WEIGHT - ▁PURPLE - ▁HIDING - ▁TAGS - ▁F - ▁WHATEVER - ▁AIRSHIP - ▁LIVING - ▁MAT - ▁KINDERGARTEN - ▁POND - ▁LAUNDRY - O - ▁NOTEBOOK - ▁HELEN - ▁SWEATER - ▁TEACHING - ▁FAULT - ▁SQUARE - ▁HONEST - ▁LOUDER - CAME - ▁3 - ▁DROP - ▁GUY - ▁GIRLFRIEND - ▁RAINING - ▁SPIDER - ▁FLYER - ▁WATCHED - ▁B - ▁LOW - ▁COUSINS - ▁OLDER - DY - ▁ROCK - ▁MOMENT - ▁SHEET - ▁LAUGH - ▁BLUEBERRY - ▁NEIGHBORHOOD - ▁GRADE - ▁STICKER - ▁OPENING - ▁ALRIGHT - ▁OFFICER - ▁PI - ▁WEDNESDAY - ▁BITE - ▁CONTINUE - TIME - ▁SAIN - ▁COSTUME - ▁MOVED - ▁BOOKCASE - ▁DENTIST - ▁STOPS - ▁SAM - ▁APRIL - ▁THIRSTY - ▁MOOD - ▁PEA - ▁ENTRY - ▁SERVICE - ▁ABLE - ▁FRIED - ▁W - ▁FLASH - ▁KATRINA - ▁REPAIR - ▁TI - ▁GIMBAP - NDA - ▁ANNIVERSARY - ▁NAMED - ▁WRITTEN - ▁CUSTOMERS - ▁COLLECT - ▁BONGOS - ▁EGG - ▁BAT - ▁RIBS - ▁SAT - ▁RETURN - LIGHT - BACK - CA - NESS - ▁FACES - ▁CALLING - ▁HOLIDAY - ▁HOLE - ▁MILLION - ▁DELIVER - ▁10 - ▁TAXI - ▁HASN - ▁MINDS - ▁DONALD - ▁MISTAKES - ▁SPRING - ▁MENTION - ▁NEITHER - ▁TOWEL - ▁BEANS - ▁WILLIAM - ▁BRIGHT - ▁STOMACH - ▁CANDIES - ▁BURGERS - ▁FEAR - ▁DECIDE - ▁FEVER - ▁FANS - ▁STUDIO - ▁LIAR - ▁BREAKING - ▁SLEPT - ▁TAIL - ▁BURGER - ▁MOVIES - ▁SMOKE - ▁DANIEL - ▁WAITER - ▁PENCILS - ▁CROSS - ▁KOREA - ▁GUARD - ▁LEARNING - ▁SUBWAY - ▁CARS - ▁SKIP - ▁MIX - ▁JEANS - ▁LIST - ▁POST - ▁TRAVEL - ▁BORROWED - ▁AWESOME - ▁RECORDER - ▁FLOUR - ▁COW - ▁CAMPING - ▁DRIVING - ▁FELT - ▁WINNER - ▁CHARACTER - ▁BALLOON - ▁RIDDLE - W - FUL - ▁NECKLACE - ▁GLOVES - ▁CHANGING - ▁CRACKED - ▁DROPPED - ▁ROBERT - ▁BAKERY - ▁GRILL - ▁INVITED - ▁LAND - ▁PORK - ▁TELEPHONE - ▁SKI - ▁GUEST - ▁AMBER - ▁SHARP - ▁KITE - ▁DELI - ▁MART - ANNA - ▁CIRCLE - ▁FLYING - ▁SHAKE - ▁DANCER - ▁POLICEMAN - ▁DESSERT - ▁SHOCK - ▁BLOOD - ▁MENU - ▁BUMP - ▁NOVEL - ▁SKIN - ▁SHOULDERS - ▁MICHELLE - ▁CROSSED - ▁TICKETS - ▁DRANK - ▁OUTFIT - ▁LAKE - ▁PAINTER - ▁ALIEN - ▁RAINBOW - ▁WORE - ▁BAR - ▁BROTHERS - ▁DISH - ▁SIMILAR - ▁DISPLAY - ▁GIRAFFE - ▁FANCY - ▁THIEF - ▁HALLWAY - ▁WAVE - ▁CARROTS - PE - ▁ELDER - ▁SOMEBODY - ▁TRAFFIC - ▁ACTOR - ▁RUMORS - ▁CHOSE - ▁CAUS - ▁DRESSED - ▁ROSE - ▁LYING - ▁PANDA - ▁PEAR - ▁SUGGEST - ▁DECISION - ▁NOISES - ▁TAKEN - ▁GARLIC - ▁CHINESE - ▁ITCHY - ▁SWORD - ▁WAITED - ▁NONE - ▁SIZE - ▁ACCEPT - ▁CAPTAIN - ▁GRAY - ▁IDOL - ▁SMALLER - ▁USUAL - ▁THOUSAND - ▁LONELY - ▁RETURNED - ▁JENNY - ▁PRACTICED - ▁NEEDED - ▁PAIN - ▁RAP - ▁THIN - ▁EVERYWHERE - ▁SUIT - ▁BUSH - ▁SON - ▁COMPLIMENTS - ▁FAILED - ▁RUG - ▁PAID - ▁MANGO - ▁BOYFRIEND - ▁SCARF - ELA - ▁CROWD - ▁ONLINE - ▁GREW - ▁SOCKS - ▁SEAGULLS - ▁USING - ▁MELTED - ▁OIL - ▁ADULTS - ▁KATE - ▁WHISTLING - ▁PRAY - ▁POOR - ▁SAUCE - ▁PACKED - ▁HATS - ▁BUYING - ▁AGO - ▁SCIENCE - ▁TUNNEL - ▁DRESSING - ▁MISSING - ▁FESTIVAL - ▁THURSDAY - ▁PAIR - ▁SITTING - ▁SUITCASE - ▁SHAPES - ▁WILLY - ▁HUGE - ▁SHOUTED - EVER - ▁FAIR - ▁TASTES - ▁CAFETERIA - ▁BINGO - ▁BEGINS - ▁DOLLAR - ▁GRILLING - ▁ALIVE - ▁DINO - ▁LIFT - ▁TOP - ION - ▁STUFF - ▁FROZEN - ▁ACROSS - ▁SEOUL - ▁FRIES - ▁TAUGHT - ▁VIDEO - ▁CREDIT - ▁HAPPENS - ▁RACE - ▁TOUR - ▁SPAGHETTI - ▁SWING - ▁INVITATION - ▁COUNTRYSIDE - ▁STAIRS - ▁HIGHER - ▁RANGER - BAG - ▁PULLED - ▁LIPSTICK - ▁VALLEY - ▁NAP - ▁FUTURE - ▁SILENT - ▁SPEAKER - ▁GIVEN - ▁JUMPING - ▁AUTUMN - ▁HOLDING - ▁BOB - ▁PLANNING - ▁SUPPOSE - ▁CLUES - ▁ANSWERED - ▁STICK - ▁WASHED - ▁CURLY - ▁RUINED - ▁SMILING - ▁UNHAPPY - ▁KIMBAP - ▁CAUSE - ▁CHUNKMONS - ▁REPEAT - STOOD - ▁8 - ▁SHEEP - ▁LOUDLY - ▁SLIDE - ▁KING - ▁LIME - ▁SKATING - ▁SERVE - ▁SAND - ▁POWER - ▁MUSICIANS - ▁RESTROOM - ▁SOMEDAY - ▁GYM - ▁GOD - ▁COOKIE - ▁NUMBERS - ▁WARNING - ▁CLASSMATE - ▁COMPLAIN - ▁LAUGHED - ▁BEES - ▁SAFELY - ▁DESIGNER - ▁ORANGES - B - ▁RETURNS - ▁SPEAKING - ▁GINA - ▁MARTI - ▁FEELINGS - MAN - ▁TULIP - ▁BAZAAR - ▁EMAIL - ▁STRAWBERRY - ▁PRESS - ▁SALT - ▁PHEW - ▁COWS - ▁ENTRANCE - ▁LEAF - ▁PAN - ▁SOUR - ▁DISEASE - ▁OPENED - ▁LUGGAGE - ▁SWIMSUIT - ▁PASSED - ▁ALISON - ▁SHOVELS - ▁SENTENCES - ▁GROUND - ▁STAYING - ▁SALES - ▁JAM - ▁WRAP - ▁LATELY - ▁SHRIMP - ▁TWELVE - ▁CHEAPER - ▁CHECKING - ▁SEAWEED - ▁LO - ▁TURTLES - ▁DNN - ▁WHE - ▁ACT - ▁LIZARD - ▁SUCCEED - ▁STRING - ▁BASKET - ▁HINT - ▁VEGETABLES - ▁FOOL - ▁SHOT - ▁ADULT - ▁GREG - ▁TASTY - ▁FARM - ▁LIPS - ▁STARFISH - ▁NAILS - C - ▁FR - ▁TEARS - ▁SUPERSTAR - ▁CLEANS - ▁HEAT - ▁SILLY - ▁WIG - ▁BELLA - WOKE - ▁5 - ▁BOYS - IVA - ▁IMAGINE - ▁LAUGHING - ▁WASHING - ▁FLAT - ▁STICKERS - ▁PRETTIER - ▁KILL - ▁FLIGHT - ▁WOMEN - ▁MOMMY - ▁CAMP - ▁MEMBERS - ▁CUSTOMER - ▁E - ▁SINGERS - 'ON' - ▁CONTROL - ▁TIGER - ▁ZEBRA - ▁IMPOSSIBLE - ▁CONSOLE - ▁CLUE - ▁FOLD - ▁BEE - ▁ANDY - ▁SEATS - ▁POUND - ▁SANG - ▁DIAMOND - ▁BATS - ▁ARTIST - ▁BABIES - ▁GARAGE - ▁INSTEAD - ▁OLDFASHION - ▁GIFTS - ▁RODE - BIG - ▁MOUNTAINS - ▁THUNDER - ▁DONKEY - ▁PIGEON - ROOM - ▁WORSE - ▁HAMBURGERS - ▁ERASER - ▁TAMBOURINE - ▁BREATH - ▁ANNOYED - ▁HALLOWEEN - ▁KNOCK - ▁STUPID - ▁BANDAGE - ▁PINEAPPLE - OUT - ▁SALTY - ▁POTATO - ▁MILES - ▁COMMENT - ▁TREATED - ▁EAR - ▁SLEDDING - ▁VIOLET - ▁BOTTLES - ▁BRILLIANT - ▁AUNTIE - ▁SPEND - ▁REACH - ▁PAYING - ▁APOLOGIZE - ▁CORNER - ▁FORGIVE - ▁RELIEF - ▁BEHAVE - ▁DIE - ▁PRETTIEST - ▁H - ▁HEN - ▁POUR - ▁NEEDLE - ▁WORRIES - ▁LARGER - ▁CRAZY - TYFIVE - ▁DISCOUNT - ▁HEADED - ▁TWENTYFIVE - ▁SOMETIME - ▁REPORTER - ▁FEED - ▁KIMCHI - ▁TENNIS - ▁DOLPHIN - ▁SUNGLASSES - ▁THREW - ▁COUNTRY - ▁HUSBAND - ▁JAPAN - ▁TOMATOES - ▁OK - ▁POET - ▁LUKE - ▁LEND - ▁LOWER - ▁SHOVEL - ▁AMERICA - ▁BLOSSOMS - OH - K - ▁SAFETY - TALK - ▁ASLEEP - ▁MINER - ▁PERIOD - ▁STORYBOOK - ▁BOWLS - ▁DOUBT - ▁MEMORY - ▁SKINNY - ▁EARTHQUAKE - ▁2 - ▁BALLS - ▁POTATOES - ▁TROUSERS - ▁WAR - ▁FUR - ▁RUMOR - ▁CONGRATULATIONS - ▁EASYGOING - ▁NURSE - ▁FLIES - ▁GROWING - ▁SMILES - ▁CHOICE - ▁ERASE - ▁COMFORTABLE - ▁GUIDE - ▁PE - ▁CLEVER - ▁PEACE - ▁AFTERSCHOOL - ▁SOAP - ▁POPCORN - ▁SUNBLOCK - ▁INVITE - ▁AWAKE - ▁FEMALE - ▁HIKING - ▁FOLLOWED - ▁BUMPER - ▁FILLED - ▁HIPPO - ▁COMEDIAN - ▁SILK - ▁COST - IES - ▁AWFUL - ▁SIBLING - ▁PIES - ▁BURNING - ▁CRASH - ZIPPED - ▁SPACE - ▁LYRICS - ▁HANDMADE - ▁PER - ▁ROUGH - ▁THROWING - ▁STATIONERY - ▁WORM - ▁PAGE - ▁CLASSMATES - ▁EXAM - ▁FINAL - ▁BLOW - ▁CHINA - U - TH - ▁BATTER - ▁HONEY - ▁MISTAKEN - ▁DEPARTMENT - GREAT - ▁SHIRTS - ▁COMPETITION - ▁YOGURT - MBER - ▁DRINKS - ▁WOLF - ▁ISLAND - ▁GROCER - ▁SHARON - ▁BREATHE - ▁ANNOYING - ▁LIED - ▁SPA - ▁KANGAROOS - ▁ALIKE - ▁PENGUIN - ▁BRIGHTCOLORED - ▁4 - ▁MESSAGES - ▁INVENTION - ▁WIPE - BIRD - ▁PRECIOUS - ▁FLEW - ▁CH - ▁APART - ▁MIDNIGHT - ▁SPEN - ▁SHELLS - ▁GIN - ▁NATURAL - ▁THIRD - ▁BADLY - ▁PLATES - ▁JOSHUA - ▁MIDDLE - ▁SWEAT - ▁TOES - ▁TIP - ▁TEASE - ▁BOOKSHOP - ▁COUGHING - ▁GUN - ▁WASTE - UMOR - AR - ▁SPREAD - ▁GOAT - ▁SPROUTS - ▁BALLET - ▁SNAKES - ▁SCRATCHED - ▁AMONG - DANGER - KGO - NISH - ▁FEE - ▁JANE - ▁TEMPER - ▁CROWDED - ▁BONO - ▁CHEF - ▁SAMPLE - ▁LIONS - ▁RULES - ▁DREW - ▁WORTH - ▁MAGICIAN - ▁GLUE - ▁TOUGH - ▁TOUCHE - ▁TUNA - ▁BAKE - ▁LAUGHTER - ▁HALF - ▁HELMET - ▁UH - ▁COPIES - ▁DIFFERENCE - ▁FORK - ▁STARTING - ▁CRIES - ▁SPROUT - SNOW - ▁SCARE - ▁DRUMS - ▁PHANTOPIA - ▁VOUCHER - ▁FARMER - ▁CHANGES - ▁SPILL - AN - ▁COMPLETELY - ▁PRACTICES - CHAIR - ▁MISSE - ▁RACHEL - ▁SEEK - EST - ▁SISTERS - ▁BLAME - ▁PACK - ▁BOIL - ▁REQUEST - ▁SH - ▁WIRE - ▁POT - ▁ONION - ▁CLOSER - ▁MICE - ▁SCRATCH - ▁DUCKS - THANK - ▁RECEIVE - ▁CABBAGE - ▁SEEDS - ▁JEJU - ▁SUDDENLY - RAY - ▁KIWI - ▁POWDER - ERRY - ▁MESSY - ▁RID - ▁CHAMPION - ▁ARGUE - ▁RECIPE - ▁MICROPHONE - ▁SCOLDED - TRY - ▁STRONGER - ▁EXPECT - ▁WEEKS - AKER - ▁JUMPED - ▁RAINS - ▁OREPHIA - ▁PIGS - LOSING - ▁PRAYING - ▁DUE - ▁SOUTH - ▁PUNCH - ▁CREATIVE - ▁FINISHING - ▁HARMONI - ▁CLOWN - ▁SALON - ▁SINK - H - ▁TOOL - ▁ALARM - VISION - GY - ▁FAIL - ▁DRAWER - ▁HAIRBAND - ▁X - ▁ARTICLES - ▁DEEP - ▁EARLIER - ▁EXTRA - ▁DOWNTOWN - ▁LEFTHAND - PTER - ▁NOODLES - ▁CONSIDER - ▁ACCOUNT - ▁DEER - ▁SEAN - RABBITS - TY - ▁CREAMS - ▁LUCY - ▁BOUN - ▁HORNS - EMENT - ▁NOON - ▁SMILED - ▁NINETEEN - ▁TURNS - ▁MUFFLER - ▁ROAR - ▁HARDLY - ▁SPELLED - ▁SPOTS - ▁SHORTS - ▁JUMPS - ▁RECENTLY - ▁STOLEN - ▁WITHIN - ▁ENGLAND - ▁PENDANT - ▁MARY - ▁AMUS - ▁SERIOUSLY - ▁FALLS - ▁SPOONS - ▁SAVED - ▁STOLE - ▁STUCK - ▁G - ▁DUMPLINGS - ▁GERMAN - ▁PLACES - ▁OCARINA - ▁QUEENSTEIN - ▁BRANDON - ▁DWARFS - ▁TOFU - ▁SPRAY - PARD - ▁CROSSING - ▁PIGEONS - ▁NOTICE - CE - LTY - ▁BASEMENT - ▁TABLET - ▁COUPONS - ▁PROGRAM - ▁SOCK - ▁GUI - ▁NUT - ▁OLIVE - ▁PREFER - ▁MUSHROOM - ▁FIGHTING - ▁DENERGY - ▁STORAGE - ▁POLITE - IST - ▁KICKBOARDS - GAGE - ▁DROWN - ▁MANAGE - ▁DRIVER - P - ▁WEEKENDS - ▁SHOULDER - ▁MUD - ▁SEVENTY - ALLY - ▁POSTCARD - ▁PIECES - ▁HICCUPS - ▁CHARACTERS - ▁CLEANING - ▁DIS - ▁JG - ▁JOSEPH - ▁TITLE - ▁CDS - ▁BOSTON - ▁BRACELET - ▁PERMISSION - ▁STEW - ▁RAT - ▁SKATE - ▁CHEST - ▁FOOT - ▁CLIMB - ▁AUDIENCE - ▁DUFAR - ▁GRANDPARENTS - ▁FIT - ▁TOUCHING - ▁ELEPHANTS - ▁TSHIRTS - ▁APPOINTMENT - ▁FOREVER - ▁STARVING - ▁LESSONS - ▁COUPLE - ▁TOTO - ▁DRINKING - ▁ARRIVE - ▁GREE - ▁SPOT - ▁HELD - ▁EARTH - ▁DAUGHTER - ▁SLICE - ▁CASTLE - ▁FEEDING - ▁COVERED - ▁FAM - ▁AGE - ▁AUSTIN - ▁DEAR - ▁NATI - ▁CELEBRATE - ▁MEATBALLS - ▁STRETCH - ▁SOLVE - ▁USEFUL - ▁SCAR - DDING - ▁ALLERG - ▁RINGING - ▁SAILING - ▁SNOWING - ▁LATEST - ▁LIES - ▁ACADEMIES - ▁MUSICIAN - ▁STA - ▁FROGS - ▁STOMP - ▁KEYBOARD - ▁FAIRY - ▁CLAP - ▁HAM - ▁TOWARDS - ▁RESERVATIONS - ▁SHOUT - SORRY - ▁PUPPIES - ▁WEAK - ▁ORIGINAL - ▁RESPECT - ▁TABLES - ▁COMPUTERS - ▁TOWELS - ▁CRAFTSMEN - ▁ELE - ▁REPAIRED - ▁PRINT - ▁BLOOM - ▁WISELY - ▁SCOLD - ▁TWINKL - ▁CANCEL - ▁KIM - ▁STAINED - ▁LAP - ▁DRI - ▁SHARK - ▁KANGAROO - MENTARY - THEY - ▁DALLAS - ▁SEESAW - ▁WHISPER - CAL - ▁DWARF - ▁SUNDAYS - ALK - ▁DOUBLE - ▁SHAKING - ▁PREPAR - ▁YOYO - ▁SKILLS - ▁OCTOPUS - ▁INSTRUMENTS - ▁MAIL - ▁ALIENS - ▁JESSI - ▁CHERRY - ▁INCONVENIENCE - ▁CERTAIN - ▁BEEF - CON - 'OFF' - ▁GATHERED - ▁PRODUCTS - CONVENIENCE - ▁RESTAURANTS - ▁MONKEYS - ▁FIGURE - ▁QUICK - ▁GAIN - ▁PENALTY - ▁INLINE - ▁INTRODUCE - ▁OVERSLEPT - ▁POL - ▁HOWEVER - ▁GORILLA - ▁MEMBER - ▁PLU - ▁ANGER - ▁AQUARIUM - ▁GAS - ELY - ▁TIES - ▁PUNISHED - ▁CUCUMBERS - ▁TINY - ▁RISE - ▁GHOSTS - ▁WIFE - MOND - ▁RARE - ▁BARN - ▁SMELLY - GAN - ▁REASONS - ▁BURNED - ▁ANNOUNCE - ▁CAPSULES - ▁PICNIC - ▁GLOVE - FF - RANCE - ▁TREAT - ▁JOG - ▁BULLS - ▁JJAKGUNG - ▁PROVE - ▁BAGS - ▁RUDOLPH - ▁MC - ▁TRICKS - RIOR - ” - ▁HAPPILY - ▁REMIND - ▁DIVER - BE - ▁HATES - ▁SPOON - ▁SIZES - ▁THROAT - ▁UN - CRAFTS - ▁BRIDGE - ▁CONFUSED - DONALD - KEEPER - ▁SIBLINGS - ▁DENNIS - ▁EMBARRASSED - ▁PATRICK - DWARFS - ▁PREGNANT - ▁VOTE - ▁WHIPPED - ▁10000 - ▁SUPPORT - ▁TOOTH - ▁STANDING - ▁CLOSET - ▁NEEDLES - ▁SWEEP - ▁RAISED - ▁PEE - ▁CONTACT - ▁JEALOUS - ▁SURVEY - BOX - ▁CROSSWALK - ▁WALKING - ▁SOP - ▁SITE - ▁OWE - ▁FOURTEEN - ▁PLANTING - ▁CHANNELS - ▁WIGGL - ▁OURSELVES - ▁SCENE - ▁BAS - ▁LETTUCE - ▁NICKNAME - ▁GRABB - ▁ELEVATOR - ▁COP - ▁FALLING - ▁DESERVE - ▁FILM - ▁SOPHOMORE - ▁WOUND - ▁PROTEST - ▁PEACHES - ▁CHILL - ▁COURT - ▁ROOF - ▁CHARGE - ▁FINGER - ▁HANBOK - ▁TAPDANCE - ▁JAPANESE - ▁MELON - ▁BATTLE - ▁LEAS - ▁PARTS - BATHING - ▁CRUNCHY - ▁PAUL - ▁WHISTLE - ▁CAKES - ▁HEAL - ▁SHELL - ▁GUM - ▁CARPENTER - ▁HEAVILY - ▁N - ▁LEMONS - ▁HARDER - ▁ROW - ▁STEAM - ▁STUDIES - ▁LOTTERY - ▁BITTER - ▁MOW - ▁EATEN - ▁SPORT - ▁SHORTER - ▁STEAL - ▁GRADUATE - ▁PUZZLE - ▁CEREMONY - ▁RAINCOAT - ▁KISS - HAP - WAY - ▁DEPART - ▁LANGUAGE - ▁BITTEN - ▁BUSAN - ▁L - ▁TIGHT - ▁BELOW - ▁PERFECTLY - KE - ▁NATURE - ▁MISUNDERST - ▁CLOUD - ▁DRAG - ▁CARTOON - ▁COCONUT - ▁GOLF - ▁THIRTEEN - ▁DYING - ▁PETE - ▁MALL - ▁BIN - ICAL - ▁ALIB - ▁BREEZE - ▁FRENCH - ▁DATING - ROW - ▁WATERING - ARD - ▁DESERT - ▁PRAISE - ▁INTERNET - ▁STRICT - ▁MOSQUITOES - TLE - ▁SKILL - ▁BEHAV - ▁KTX - ▁LONDON - ▁TASTING - ▁VAN - ▁COUGHED - ▁NICELY - ▁HARM - ▁BOOKSHELF - ▁CRICKET - ▁EDGE - ▁PILLOW - ▁RECTANGLE - ▁STRESS - ▁FOOTBALL - ▁LAW - ▁CHOPSTICKS - WHAT - ▁TWINS - ▁AUSTRALIA - ▁LAMB - ▁MAYO - ▁DESIGN - ▁BLEW - ▁GLORY - ▁ROCKCLIMBING - ▁DUTY - ▁ENTERTAINMENT - ▁THEMSELVES - ▁YOG - ▁BUCKET - ▁BIRTH - ▁FALSE - ▁PATTERN - ▁THREAD - ▁SOLDIER - ▁BATTERY - ▁KNEES - ▁HEADS - ▁DELIVERED - ROUTE - ▁SIMPLE - ▁WATERFALL - ▁SWITCH - ▁EFFORT - ▁UNUSUAL - ▁SLIPPED - ▁REG - ▁SUITS - ▁CHANNEL - ▁MINI - ▁PLASTIC - ▁RECOMMEND - ▁RUBBER - ▁THANKFUL - ▁ROLL - ▁SOLV - ▁CLAPS - ▁BUD - ▁CINEMA - ▁SHELF - ▁LOSS - ▁WOMANS - ▁CANADA - ▁EXPRESS - ▁SHARING - ▁LOOSEN - ▁CHOCO - ▁RUNNY - ▁REPL - ▁BOWL - ▁FULLY - ▁SOMEHOW - ▁UNIQUE - ▁CARES - ▁NOODLE - ▁JETLAG - ▁LAPTOP - ▁TOOTHPASTE - ▁JON - ▁AIRPORT - ▁JOO - YER - ▁CAP - ▁HOLLY - ▁JOHNSON - ▁ZERO - ▁LEADER - ▁OX - ▁SQUEEZE - PY - GET - ▁FIN - ▁ZIP - ▁SEPTEMBER - ▁TEMPERATURE - THIRTY - ▁GOODLOOKING - ▁GUAR - ANTEE - ▁LOG - ▁WILD - ▁BOOTH - ▁PEPPERS - ▁FORGOTTEN - BALL - ▁AB - CALORIE - ▁POLICY - ICO - ▁INCLUDED - ▁LIGHTEN - ▁BLAMED - ▁LONGTIME - OOD - ▁JEAN - ▁DECK - ▁MANNER - ALTH - ▁PERSONALLY - TRUCK - PT - ▁GUT - ▁CRASHED - ▁FLO - ▁REACT - ▁ABSENT - KYO - ▁BLUSH - ▁DONATE - DOCK - ▁COMPLAINING - ▁DESCRI - ▁GEORG - ▁RECOVER - ▁WALNUT - ▁LUNG - ▁BUDDY - ENSE - ▁PASSES - ▁PLUM - HALF - ▁SE - ▁TURTLE - ▁FRANC - ▁KOALA - ▁TURKEY - ▁CARPET - ▁ANYWHERE - ▁R - ▁SKIING - ▁FOCUS - ▁HARV - ▁JANUARY - ▁PRESIDENT - ▁TWENTYONE - ▁WRESTLE - ▁CANCER - ▁CHEATING - ▁HOMEMADE - ▁WEEKDAY - ▁K - THER - ▁DREAMS - ▁APPRECIATE - ▁BRAIN - ▁SAUSAGES - SOMETHING - GAR - ▁SMOOTH - ▁SLIM - ▁FENCE - JURY - LIES - ▁SPIDERS - EADLINE - EVEREST - ▁SCORES - ▁JOKING - ▁REJECT - ▁STEPMOTHER - ▁CRIM - ▁DIGGING - ▁QUEEN - ▁MALE - ▁SNORES - ▁EXPLAINED - ▁HOUSEWORK - ▁BEDTIME - BEAT - WORKING - ▁SMELLING - ▁GRAPE - ▁INSTRUCTIONS - ▁SUNSCREEN - ▁WORKDAY - ▁HOLES - ATER - UP - RIDA - ▁VINE - ▁HERSELF - ▁NIGHTMARE - ▁SNAP - ▁INSU - ▁BURNS - GIV - ▁MOUNT - ▁NEGATIVE - ▁ADVANTAGE - ▁DIFFICULTIES - ▁7 - ▁REMAINS - CHECK - ▁TRAVELING - ▁IMAGIN - G - ▁BENNY - ▁JOHN - ▁ATHLET - ▁COOPE - ▁DICTIONARY - ▁HAPPINESS - ▁RAPPER - ▁SLIPPERY - ▁SUNRISE - ▁TAPDANCING - ORABLE - ▁NOTICING - ▁WAITLIST - ▁CUCUMBER - FTH - ▁GUESTS - ▁COLLEGE - ▁STOCK - HH - ▁TALE - POP - ▁MEXIC - ▁FREEZER - ▁REFUSE - ▁SWIMMER - ▁THOUGHTFUL - DIVING - WORKED - ▁COURAGE - ▁ERRANDS - ▁LISTENED - ▁GRUM - ▁WEB - ▁TWEL - GED - ▁CABIN - ▁REHEARSAL - ▁SKETCHBOOK - ▁DAYCARE - ▁PARTIES - OBBY - ▁SEAL - WHERE - ▁ROSES - INE - ▁ACCIDENT - ▁PERSONALITY - ▁SPECIFIC - ▁RINGS - ▁BLOOMED - ▁AW - YARD - ▁ENTERED - ▁BELLY - ▁FUNNIER - ▁NARROWMINDED - USY - ▁JOURNAL - ▁JER - ▁PRICES - BREAK - ▁BILLS - SOLUT - ▁11 - ▁REFILL - ▁BAKED - ▁ALPHABET - CONNECTED - ▁GOATS - ▁WASHE - ▁CHOP - PHLE - ▁NONSENSE - ▁WADDL - ▁PETS - ▁DECORATE - LUSH - ▁FORGETTING - ▁EMILY - ▁BICYCLES - ▁SHOWN - ▁BUCK - ▁BAIT - ▁100 - ▁MOVER - ▁HEL - ▁WINNING - ▁ROCKET - ▁FANG - ▁CA - ▁DEPRESS - ▁BEAUTY - ▁DAILY - ▁ENGINEER - ▁MUFFIN - ▁WRITER - ▁OPINIONS - ▁TRACKS - ▁PAUSE - ▁PUZZLED - URE - SEY - ▁WRAPS - ▁SOCIAL - ▁GRADES - ▁WARMLY - ▁YOYOS - ▁CHEW - ▁BULGOGI - ▁BARKING - ▁SENTENCE - ▁THOUGH - ▁POO - ALIAN - ▁EVE - ICED - ▁RAIS - ▁DISTURB - ▁ITSELF - ▁ORIGAMI - ▁TISSUE - ▁JOHNNY - ▁BURN - ▁COOKS - ▁CANDLE - ▁OBVIOUS - ▁SANDPAPER - ▁SUPPLIES - ▁CHEWY - ATIONS - ▁FLAVOR - ▁KIWIS - ▁MASTER - ▁YELLING - ▁CUPS - ▁BL - LAINE - ▁STIMULAT - ▁TIRES - ▁PRETEND - ▁CLEANED - ▁RUSSIA - ▁FRECKLES - ▁FART - ▁CHEETAH - ▁RUDE - ▁TRAINS - ▁LOTTE - ▁PAGES - ▁POSTCARDS - ▁KEYS - ME - ▁BOOKSTORE - ▁HOST - ▁SHORTCUT - ▁SHOOTS - ▁OPINION - ▁APRON - ▁COPIED - LLOWED - ▁STICKY - ▁PREPARE - ▁HEADQUARTERS - ▁REPAIRS - ▁WHALE - ▁POOP - ▁RESEMBLE - ▁SHARE - ▁LOLL - ▁EXERCISES - ▁PROGRAMS - ▁BLINK - ▁FLAG - ▁LAY - ▁FASTEST - ▁SNEEZE - ▁ENDED - J - ▁MARKER - HER - ▁ASSISTANT - ▁CURRY - ▁PURSE - ▁SLIPPERS - ▁UNDERSTANDING - ▁PIT - ▁INDOOR - ▁CROWN - ▁CURIOUS - ▁SYSTEM - ▁CABLE - ▁MOSQUITO - ▁PHARMACY - ▁EVERLAND - ▁WINDOWS - ▁BOOGER - ▁TIRING - ▁PAPERS - ▁PEANUT - ▁PARDON - ▁AH - ▁FOX - ▁RESELL - ▁RESULT - ▁TWIST - ▁SLED - ▁TALLEST - ▁RIBBONS - ▁RECEI - ▁SQUIRREL - ▁CUTLET - ▁HEIGHT - ▁HURTING - ▁TRAP - ▁WRAPPER - ITED - ▁FRIGHTENED - ▁PATIENT - ▁CANCELED - ▁SHELVE - ▁NET - OOPS - ▁MESS - ▁MERRY - ▁PLATE - ▁COMPLAINT - ▁SITUATION - ▁PARIS - ▁STRAW - ▁DIVIDE - ▁GOAL - ▁SHRIMPS - X - SPECIAL - GOTTEN - F - ▁COLLECTED - ▁AFFORD - ▁HUNG - ▁CHAMBER - ▁AIRPLANE - ▁CHA - ▁WALLS - ▁REGULAR - ▁EXPERIENCE - ▁PILOT - ▁250 - ▁LEMONADE - ▁FURTHER - ▁RAC - IN - ▁SWALLOW - ▁CLOSING - ▁CLASSROOMS - ACK - ▁RENT - ▁ADS - ▁TENTH - ▁FRY - ▁HOTDOG - ▁ANGEL - ▁PEACH - ▁HIDDEN - ▁GOOSE - ▁SMALLEST - ▁ROCKS - ▁COOKED - ▁CORN - ▁SIGNS - ▁ANXIOUS - ▁LIGHTNING - ▁SNOWBALL - ▁BESIDE - ▁ANTS - ▁ALLOWANCE - ▁COUNTRIES - ▁POUCH - ▁SLIP - ▁POEM - ▁RAMEN - ▁ROLLING - ▁PATIENTS - ▁SCREEN - ▁PRESENTATION - ▁CAST - ▁FLUTE - ▁HU - ▁ZEBRAS - ▁COMPARE - ▁WIDE - ▁FORSYTHIA - ▁SENIOR - ▁DONATED - ▁FACTS - RD - ▁FOG - ▁ROLE - ▁PEARS - ▁BUTTONS - COME - ▁HAIRCUT - ONDE - ▁ENV - ▁CHASED - THE - '4' - ▁TRACK - ▁STRANGER - ASOL - ▁CHIN - ▁PUBLI - ▁DUN - ▁JUNE - ▁20 - ▁DOUGHNUT - ▁DADDY - PORT - ▁EMBARRASSING - ▁UNCOMFORTABLE - ▁FOREHEAD - ▁RELATIVES - ▁DOODLE - ▁GENTLEMAN - ▁TAPE - ▁BANKER - ▁ACTRESS - ▁SORT - ▁REDESIGN - ▁GRADERS - ▁KICKING - ▁LA - UK - ▁BARBECUING - ▁BULLY - RATE - ▁JUN - ▁KOREANS - ▁CORPORATION - ▁HEAVIE - ▁IMPROVE - ▁OCEAN - ▁LG - ▁LAYER - ▁BRIGHTLY - ▁CRABS - ▁PAR - ▁BLANK - ▁CALENDAR - ▁CROCODILE - ▁SALARY - ▁CHUSEOK - ▁CUTEST - ▁NOR - ▁MYSTER - ▁BEND - ▁INCLUDE - ▁EXCELLENT - ▁PAINFUL - ▁SKEWERS - ▁CHEERING - SIZE - BELT - RCH - ▁PLEASANT - ▁PATH - ▁QUALITY - ▁STINGS - ▁REPAIRING - ▁DELAY - ▁RIDES - ▁ELSA - ▁SECURITY - ▁TWENTIETH - ▁PC - AH - ▁NOTES - RAL - ▁NORMAL - ▁DIRECT - ▁CENT - ▁APOLOGY - ▁GARBAGE - ▁GEE - ▁WATCHES - ▁SCISSOR - ▁CULT - ▁ECONOMY - ▁SEASHELL - ▁HA - ▁HORSES - ▁WHEELS - BYE - ▁HABIT - ▁VI - OOKIE - ▁BAKING - ▁CHERISH - ▁JESUS - ▁KLEA - ▁PARTICIPATE - ▁NICER - ▁LISTING - ▁SUPP - IELD - ▁CRISPY - ▁EYESIGHT - ▁TWITCH - ▁WORST - ▁GREETING - ▁DRYER - ▁LINES - ▁DEPRESSED - RENT - ▁ROLLS - LAND - ▁DOCUMENT - ▁COCKROACH - ▁TAX - ▁LIBER - ▁FRIGHT - ▁GARDENVIEW - ▁JAR - ▁ONESELF - ▁PELICAN - ▁RUSH - ▁BAKER - ▁EXPLODED - ▁CARNATIONS - ▁BUBBLES - ▁BREAKS - ▁EUROPE - ▁EXCHANGE - ▁SMASH - ▁TORONTO - ▁CEO - ▁BLEEDING - ▁IMAGINED - ▁KIL - ▁POU - ▁TAB - ▁CRUS - OGRAMS - ▁ALASKA - ▁FROWNED - MAIL - TWINKL - ▁SINGLE - ▁INVENT - ▁ROD - ▁EMERGENCY - PORTER - ▁COMB - ▁HUG - TI - '...' - SMITH - ▁AVOID - ▁JJAKKUNG - ▁MATERIALS - ▁LOSES - ▁LU - INA - FREE - ▁SERV - ▁FLU - ▁REEL - ▁BACKPACK - ▁REPRINT - ▁SIXTEEN - ▁ZENA - ROL - ▁AWARD - ▁TENK - ▁NETWORK - ▁WORKER - ▁REDUCE - GUE - ▁PROTECT - ▁CONCERN - ▁CRIMINAL - ▁FIREFIGHTER - ▁INCHEON - ▁SUWON - ▁VIEWER - OVER - ▁ELEVATORS - OR - ▁IMPRESSED - ▁SHAME - ▁STRAP - ▁YIELD - ▁WARNED - ▁HANDOUT - ▁LUNCHTIME - URY - IED - AY - WIFE - GUN - ▁ISSUE - RRIE - ▁SANDCASTLE - ▁FIGURES - ▁LOV - ▁POKE - ▁FREESTYLE - ▁CHAIN - ▁EVERYDAY - OK - ALY - ▁RATING - ▁SPIT - ▁SAIL - ▁AMBULANCE - ▁ENORMOUS - ▁SELFCONT - ▁MEMORIZED - ▁GIRAFFES - ▁SNOWS - ▁PLANTS - ▁LEAD - ▁EXHIBITION - ▁FOUGHT - ▁MARBLE - 'YES' - ▁PICKE - ▁WRONGLY - ▁HURR - ▁CONVERSATION - ▁DETAIL - ▁WORRYING - ▁SAVING - ▁TU - ▁SECRETLY - AWAY - ▁GROWS - ▁CONTRA - ▁SCRAMBLE - BES - ▁PROMISES - ▁CHAIRS - ▁GOGGLES - ▁OTHERWISE - ▁VICTOR - ▁THORNS - ▁WORTHWHILE - ▁HIPPOS - ▁TRICK - ▁OBSERVATORY - ▁SHAMPOO - ▁COKE - ▁DRAMA - ▁DELAYED - ▁GUTS - ▁AZALEA - ▁WRAPP - TIE - HEAD - ▁BIGGEST - ▁ENEMIES - ▁PUMPKIN - ▁DOCUMENTARY - ▁ATOPY - ▁COUGH - ▁TOUCHED - ▁AWARDS - EWER - VER - ▁BEARS - ▁CACTUS - ▁LOCK - ▁LIT - ▁SKETCH - ZEN - ▁DRAGG - ▁SQUEEZED - ▁SCOT - SHY - ▁CALCULAT - ▁APPEARED - ▁RAINED - ▁WINGS - ▁CLOTH - ▁DIG - ▁DONGSENG - ▁SPONGE - ▁STUBBORN - ▁WAIST - ▁FLE - ▁TAG - CH - ▁CR - ▁UMBRELLAS - ▁TOOTHBRUSH - ▁POCKETS - ▁PAJAMA - ▁HALLA - ▁GATHER - ▁BOSS - ▁DETERGENT - ▁DOCUMENTS - ▁GENEROUS - ▁TOTAL - ▁CURTAIN - ▁PUDD - ▁THICK - NSIBLE - ▁HOLIDAYS - ▁TICKLES - FLAVORED - ▁COVID - ▁GIFTWRAP - ▁BLINKING - ▁JUNG - HOK - LEANING - ▁IDOLS - ▁DRO - ▁FOUNTAIN - ▁PHYSIC - ▁PRESCRIPTION - ▁LATTE - ▁TONGUE - ▁NA - WORLD - ▁SURGERY - ADLINE - ▁STUFFY - ▁WAFFLES - ▁15 - ▁LOGO - ▁SHORTCUTS - ▁RESPECTED - ▁INVENTIONS - ▁ARTISTS - RAFFI - ▁FOSSIL - ▁GOLDCREST - ▁MALTESE - UGGING - ▁BUCKWHEAT - ▁PROFESS - ▁SQUID - ▁CORRECTION - IT - LOOKING - ▁GENIUS - ▁WHALES - ▁OPPA - ▁DONKEYS - ▁ELECTRIC - ▁FAKE - ▁JUNIOR - ▁MEDAL - ▁SONGPYEON - ▁MO - ▁LOCKED - ▁MEMORIZE - ▁DIZZY - ▁CAMELS - ▁Y - ▁CARING - ▁PERFORMANCE - ▁ERRAND - ▁STRIPE - ▁SIL - ▁REDESIGNED - ▁TIPS - SCRIPT - ▁BISCUIT - ▁TORN - ▁BRUSHE - ▁STREETS - ▁RELIEVED - ▁HOPS - ESSER - ▁INSTRUMENT - ▁ADVANCE - ▁GESTURE - ▁MUGWORT - ▁PROMOT - ▁PIN - ▁SHAD - IONAL - '72' - ▁HEAVEN - ▁SLOPE - ▁HAIRDR - YOU - ▁OWNERS - ▁PLANS - ▁SUNFLOWERS - ▁CHIMNEY - ▁HIPHOP - ▁FOURTH - ▁C - ▁COUNTS - ▁BARK - SCOPE - ▁ATOPIC - ▁DEATH - ▁FORMALLY - ▁TWIN - ▁QUIETLY - ▁TEAS - ▁MIN - ▁CE - ▁DEPENDS - ▁TRANSFERRED - ▁HANDY - ▁CLEARLY - CHOCO - ▁HOTDOGS - ▁FROWN - ▁RUB - ▁PERFORM - ▁ATTRACT - ▁DUST - ▁REVIEW - ▁SIGNBOARD - ▁ENDURE - ▁RIDD - CKED - ▁CIRCLES - ▁AIRPLANES - ▁MI - GING - Q - ▁YURI - ▁30 - ▁OFFICERS - ▁ALMONDS - ▁SOLVED - ▁WEREN - ▁ALBUM - ▁UNDERGROUND - ▁WRINKLES - IL - ▁TALES - SOKCHO - ▁GROCERIES - ▁RECEIV - ▁BARE - ▁PEEL - ▁COCKROACHES - ▁DEEPLY - ▁STATIONS - ▁DANCED - ▁CHUBBY - ▁SATURDAYS - ▁WING - ▁CRAFTSMAN - ▁OCCASION - ▁WINE - ▁TELE - ▁BLUETOOTH - ▁DISAPPEARED - ▁SUBM - ▁FARTED - ▁PREPARED - LIST - ▁CONDITION - ▁PORTRAIT - '23' - ▁POINTS - ▁TAMBOURINES - ▁TEND - ▁SELFISH - ▁SUBJECT - RUPTE - ▁LICKING - ▁WATERMELONS - ▁DIES - ▁BLOWING - ▁SOIL - NIFE - ▁BLAND - ▁RECYCLED - ▁SIXTY - ▁LENGTH - ILING - ▁SURVIVED - ▁HABITS - WANT - ▁GRAND - ▁SAVORY - ▁APPLAUSE - ▁APPLY - ▁MEANER - ▁DISEASES - ▁FRUSTRATING - ▁NOTIFICATION - ▁CHEOMSEONGDAE - ▁BADGE - ▁ABOARD - ▁DISNEYLAND - ▁LEE - ▁SHARPEN - ▁KETTLES - ▁HERESY - ▁CRAM - ▁BRONZE - ▁HARSH - ▁EBS - ▁GREY - ▁POSE - ▁PICKLES - ▁LEN - ▁TIGERS - ARY - ▁CLAR - ▁EDUCATION - ▁NEIGH - ▁ADDITION - ▁REASONABLE - ▁DUMPING - ▁SPACES - ▁LIGHTER - ▁SPELLING - Z - ▁CATCHING - ▁LEVEL - ▁UPSTAIRS - ▁RINK - ▁HANDLE - AVING - ▁BOWED - ▁BEAUTIFULLY - ▁FARTS - ▁BOLT - ▁FAMILIAR - BBLE - DO - ▁FILE - ▁TREATMENT - ▁PASTOR - ▁EEK - ▁BLOOMING - CIAL - TRAINED - ▁APPEAR - ▁KNEE - ▁WHEEL - RIAN - ▁ATTEND - ▁CONFESS - ▁DVD - ▁WITNESS - ▁BATMAN - ID - ▁BANGS - ▁YARD - ▁LOTION - ▁RECYCLE - ▁PRI - ▁BURDEN - ▁SCRA - ▁VEGETA - ▁TOENAILS - SUALLY - ▁YAM - FORD - ▁FORMAL - ▁POK - ▁FROZE - ▁MULTIPLICATION - ▁SEJONG - ▁TRIES - ▁SUNSHINE - ▁HERBS - ▁STRIPES - ▁CLIMBING - ▁SKIPP - FFE - ▁DAMAGE - ▁RIDICULOUS - ▁QUACK - ▁PINNOCHIO - SIDE - ▁STANDARD - ▁TRADITION - GIANT - ▁YELL - ▁SUPER - ▁OVERREACT - ▁PERFUME - ▁UNDERCOOK - BEC - ▁MAPS - ▁PARTNERS - ▁SPINACH - ▁TTEOKGUK - ▁JAJANGMYEON - ▁DIRECTLY - VATE - STEE - ▁MOUSES - ▁SNOWED - ▁IGNORE - GIFT - ▁LOCKER - ▁SURVIV - ▁P - BBLES - DAIRY - ▁TOOLS - STAR - LING - ▁BB - ▁ACCESSORIES - ▁NINTENDO - ▁BIBIMBAP - ▁DERMATITIS - ▁ANNOUNCED - ▁LICK - ▁AZALEAS - ▁PEPPER - VAS - ▁BODIES - ▁EXPAND - PED - FLOWING - ▁MIXED - ▁GROUP - ▁SAUSAGE - ▁CEREAL - ▁EASIEST - ▁OVERSLEEP - ▁SATISF - ▁150 - ▁BAY - ▁DIP - UN - AK - ▁COINS - ▁SURPRISES - ▁WAK - OL - ▁EVILDOING - ▁EYEBROWS - ▁HEADBAND - ▁KETCHUP - ▁PROPERLY - ▁STRAWBERRIES - ▁UNFORTUNATE - ITY - LIKE - ONG - ▁WISHES - ▁CONSTRUCTION - ▁RESEARCH - ▁RIPPED - ▁FOREIGNERS - ▁SANDALS - ▁GOLDEN - ▁PERFORMANCES - ▁STEALING - HA - ▁SPARE - ▁KPOP - ▁LEASH - ▁TIGHTLY - CM - ▁COMME - ▁500 - ▁ANCHOVIES - ▁BANKBOOK - ▁COVIDNINETEEN - ▁DEFINIT - ▁UPRIGHT - ▁MISSION - BAL - PHONES - HO - ▁GENERAL - ▁OVEN - ▁MARCH - V - HU - ▁GROWN - ▁BROADCAST - ▁GANGWONDO - ▁REFRESHING - ▁DICE - ▁RACK - ▁PERM - ▁SUITCASES - ▁16 - ▁ENVELOPE - ▁HOOKED - ▁ROOT - ▁TEXT - ▁CAGE - GO - ▁MUS - ▁DOUGHNUTS - ▁WASTING - ▁BETIAN - ▁PRESENTING - ▁BRUISE - ▁ALOUD - ▁AUDITORIUM - ▁BTS - PLE - RAISED - MOTION - ▁GENTLE - ONIA - ▁EASIER - ▁FONDUE - ▁SEASICK - ▁VR - ▁DOLPHINS - ▁MATCHES - UR - ACHE - ▁CICADAS - ▁LEAN - ▁REPORTS - YING - ▁CLOUDS - ▁WOLVES - ▁HEEL - ▁FRESHMAN - ▁SCREAMED - ▁RELATIVE - ARIN - ▁BUR - ▁PASTE - ▁FRIENDLY - ABLE - ▁VISITING - ▁INVIT - ▁LOUDSPEAKERS - ▁NNN - ▁OINTMENT - ▁SWAN - CLES - ▁GARDENING - ▁HICCUP - IM - '0' - ND - BA - ▁JULY - ▁SEMESTER - ▁SUSHI - ▁UNIVERSE - ▁TOSUN - ▁PILLS - ▁TAN - ▁NEAT - ▁FEATHER - ▁ANNEX - ▁PENGO - ▁SICKNESS - ▁CANDLES - LO - ▁SCRUB - ▁SHOOT - ▁TH - ▁CRACK - PLAIN - ▁FRIDGE - ▁ANSWERING - ▁INDOORS - ▁APOLOGIZED - ▁COMEDIANS - ▁WOR - ▁SPIN - ▁DRACULA - ▁DRAGONFLIES - ▁EXTINGUISHER - ▁GRADUATION - ▁LADIES - ▁EX - ▁PLANNED - ▁50 - ▁MILLIONS - ▁TANGERINES - ▁DRAWN - ▁CLEANER - ▁DECORATIONS - ▁SPI - ▁VARI - ▁DRAGONFLY - ▁SCENT - ▁GAYAGEUM - ▁CL - ▁MONTHS - ▁PAJAMAS - ▁RESTING - ISE - ▁BADGES - WORK - KY - ▁ADORES - ▁COLA - ▁MOTOR - ▁PRODUCE - ▁THOROUGHLY - ▁VOWELS - ▁COMMON - PING - ▁SUNFLOWER - ▁FOLDING - ▁DECORAT - '8' - ▁SCREAM - ▁CONNECT - ▁AUGUST - ▁PURPOSE - ▁PIAN - ▁CHIMNEYS - ▁MONDAYS - JU - ▁BEETLE - ▁PEED - ▁INTEREST - ▁BAN - ▁SNOR - ▁MA - ▁SEW - ▁COIN - ▁HAN - ▁ALPHABETS - ▁TONKATSU - ▁HOPEFULLY - ▁ICECREAM - ▁REGULARLY - ▁GALBI - ▁CHAS - ▁REALIZE - ▁WORKERS - ▁BOATS - ▁INTERRUPT - ▁SUBTRACT - ▁ORGANIZING - ▁HISTORIC - ▁POTTER - ATION - ▁CHARGER - ▁BAL - ▁SUNLIGHT - ▁DYE - ▁SHOELACES - ▁EVENLY - RY - '30' - BIKE - ▁CRAWL - ▁CHOOS - ▁ROBBINS - ▁SHOOK - ▁SPLASH - ASKIN - ▁UNTIE - YMP - ▁STING - IOUS - ▁PA - ▁CAROLS - ▁SUDDEN - ▁MACKEREL - ▁NOSEBLEED - ▁SCREW - ▁HANOK - TOMS - ▁STRA - DAY - ▁RIBBON - MILKY - BEAN - ▁TOMATO - ▁NATIONAL - ▁SPRITE - ▁PANIX - ▁WISE - ZED - ▁CHEWING - ▁FOOTS - ▁SHAKES - ADA - 'NO' - ▁DIFFERENTLY - SLEEVE - ▁930 - ▁GYEONGJU - ▁RAPUNZEL - ▁ROMANTIC - ▁FARTHER - ▁CAPE - IER - ETY - ▁HARDEST - ▁TURNING - ▁3000 - GENEROUS - ▁BOO - ▁ATTENTION - ▁DWARVES - ▁HAKNYEON - ▁OUTDOOR - ▁RESORT - ▁SWOLLEN - ▁PINCH - ▁PURE - STER - ▁GRAB - ▁BIO - ▁HURRICANE - ▁JUDGE - ▁LANE - ▁OINK - ▁SPRAINED - ▁THIEVES - ▁TRAPPED - BIL - ▁RANCH - ▁TWENTYTH - ▁ANNE - OLD - NIGHT - ▁HEIGHTS - ▁BRICK - ▁GRATEFUL - ▁VITAMIN - ▁HAMSTER - ▁USELESS - ▁INVENTOR - ▁ULSAN - ▁PRETENDING - ▁PANDAS - GGING - UL - AG - COMING - ▁HUNT - ▁REMOVE - ▁OCTOBER - ▁SEPARATE - ▁YAWN - ▁PALE - ▁UM - ▁FLOATING - ▁CO - HAVE - ▁SNOWY - ▁SHOELACE - GRAPHY - ▁MELT - ▁FISHBONE - UG - ▁CHIL - ▁POOPED - ▁YUT - ▁PILL - '0000' - ▁SURVIVE - ▁EXAMIN - ▁TRU - ▁BACKGROUND - ▁BEGINNING - ▁MACARONS - ▁SURFING - ▁VERANDA - ▁ASSEMBLE - ▁HANGUL - ▁REACTION - ▁DAUGHTERS - MENT - QUET - RMALLY - ANG - ▁LID - ▁RESERVATION - SOON - ▁FLIP - CAN - ▁JUICY - ▁KINGDOM - ▁SOCIETY - ▁TADPOLE - ▁JAMSIL - ▁WI - ▁GRADUATED - ▁PRE - ▁SCRATCHING - ▁PO - ▁APPEARS - ILY - FAT - FOOD - ▁DISAPPEAR - ▁FAINT - ▁FLOAT - ▁RUBB - ▁TRANSFER - ▁COMFORT - ▁BALLERINA - ▁DESCRIPTION - ▁GENTLY - ▁HAPPIER - ▁RINGTONE - ▁ARGUING - ▁CONDITIONER - PM - IET - CU - ▁EARTHQUAKES - ▁CHICK - ▁TR - ▁TYPHOON - ▁BUNS - ▁RUNNER - NDC - ▁WAH - ▁JELL - ENDY - ▁COMMU - ▁FARMS - ▁SLEEVES - ▁BEETLES - LOW - ▁MEATBALL - ALKIE - ▁MAGNIF - ▁CONNIE - ▁NEIGHBOR - ▁OPERA - ▁PINOCCHIO - ▁SHOEMAKER - ▁CRAFT - ▁ONESIX - ▁FLOW - WD - HOO - ▁PRESENTATIONS - ▁CHIP - ITE - ▁ANIMAT - ▁DUB - ▁FLOOD - ▁KAKAO - ▁RESU - ▁UNBELIEVABLE - ▁GRIN - ▁HEALTHIER - ▁SIXTH - ▁CHOSEN - ▁LOSER - ▁BLED - REALLY - ▁IGNOR - ▁PRODUCT - RIST - ▁DISCOURAGED - ▁DODGE - ▁FORECAST - ▁OWL - ▁TREASURE - ▁UNIFORM - ▁LOCAT - ▁TUBE - DON - ▁FOLDED - ▁WEIGH - ▁RUIN - ▁CRUSH - ▁PARAD - ▁OBESE - ▁ORGANIZE - ▁PRINCIPAL - ▁RATTLING - ▁RESERVE - ▁RHYM - ▁SIP - ▁UNDERWATER - ▁TAEG - ▁TRAVELLING - ▁STACK - ▁RI - ▁BUNDLES - YEAR - SAME - AND - ▁CHEESECAKE - ▁EPISODE - ▁FAMILIES - ▁FIFTH - ▁RHINITIS - ▁SAUNA - NCHES - ▁EXCE - TIQUE - ▁COMBO - ▁STRINGS - ▁COLORFUL - ▁FLOWS - ▁COOLEST - ▁OPPAS - ATING - ATE - ▁MELTS - ▁CHOPSTICK - ▁BRANCH - ▁FRUSTRATED - ▁GREASY - ▁EXIST - ▁WAVING - ▁APP - ▁SODA - ▁FALLEN - ▁PRO - SHAPED - NG - ▁CONNECTED - ▁12 - ▁BANDAID - ▁DISTANCE - ▁DRAIN - ▁MEASURE - ▁TEMPLE - ▁WORKBOOK - ▁EIGHTAM - ▁WARN - ▁BURNT - BOARD - ▁DE - IFF - RTH - ▁MUSHROOMS - ▁POWERFUL - STICK - ▁VOUCHERS - ▁BLEED - ▁BRAID - ▁CREPE - ▁HAWKING - ▁FLAM - ▁SCORE - ▁RELEASED - ▁TICKLED - BU - FISH - ATIVE - CLUSI - ▁CLINIC - ▁CROOKED - ▁RELAY - ▁SCOOTER - ▁SEBASTIAN - ▁SUFFER - ▁TEENAGER - ▁BATHHOUSE - ▁WRIST - ▁BAKERIES - ▁BRANCHES - ▁SAMYUKGU - ▁SCU - ENDER - ▁INGREDIENTS - ▁INVENTED - ▁BOWING - SSES - WAR - ▁PRESSED - ▁SQUEEZ - SIGNED - WON - ▁70 - ▁APPROACH - ▁CHAPPED - ▁DUMB - ▁FREEZING - ▁MAGNIFIER - ENTIAL - IE - ▁CLOSELY - ▁DIAPERS - OUS - ▁DIRT - ▁CENTIMETER - ▁FLOWERPOT - ▁FOAM - ▁POLITIC - ▁PORRIDGE - ▁PEDIATRICIAN - ▁FIREWORKS - ▁TROUBLEMAKER - ▁PILLAR - ▁EVACUATE - ▁SILLA - EUK - ANDING - ▁FAINTED - ERMAN - ▁SEAGULL - ▁CHICKS - ▁SWEATING - INGO - PAPER - ▁AGREED - ▁CLAPP - VA - ▁STRENGTH - SOONGSIL - ‘ - ▁CONVENIENT - ▁DECEMBER - ▁FORTUNATELY - ▁FURNITURE - ▁HAGWON - ▁LOUNGE - ▁MOKDONG - ▁PALM - ▁SPRINKLE - ▁STIRFR - RUNK - ▁ANKLE - ▁SELF - ▁SEVENTH - LESS - ▁DIVING - ADE - ▁RANG - SHINY - WITH - ▁BRAVELY - ▁BADMINTON - ▁BULGUKSA - ▁KARAOKE - ▁ADMIT - ▁GINGER - ▁LAID - ▁SNOWBOARD - ▁HOPPING - ▁UDO - ▁BULGING - ▁CARP - ▁FACT - ▁GROUPS - ▁ENTERING - ▁RIP - ▁MAR - LOCK - ▁JE - ▁ADMISSION - ▁CHRYSANTHEMUM - ▁DIARIES - ▁DISPOSABLE - ▁LOACH - ▁PARROT - ▁SCULPTURE - ▁TERRIF - ▁VOLUME - ▁REPRESENTATIVE - ▁MEOW - ▁CHEEK - ▁JEJUDO - ▁HARMFUL - ▁BRUISED - ▁MINERAL - AINT - ▁EDIT - WARDS - HY - ▁VIEW - ▁EXACT - ROUGHT - OCKPAPERSCISSORS - ▁CHESTNUT - ▁HAWAII - ▁PIMPLES - ▁REMOTE - ▁SOLUTION - ▁COMPETE - ▁SOFTLY - ▁BUNDLE - ▁LIP - ▁GRADER - WOO - RIS - STORY - DAYS - COLORED - FOR - ▁COLLAPSE - ▁STEPP - ▁BRILL - RSELVES - ▁ACCORDING - ▁BACON - ▁BAEK - ▁BUTTERFLIES - ▁COSMOS - ▁CYCLING - ▁DISTRICT - ▁ESTATE - ▁HUMID - ▁MERMAID - ▁PAPRIKA - ▁PHONICS - ▁BELONG - ▁YUKJANG - ▁ANIMATION - ▁FLIPP - ▁DUMPLING - ▁BLOSSOM - UNG - ▁EXPLORE - ▁INSECTS - ▁JI - HEART - GHTS - ▁ASTRONAUT - ▁BELLHAMMER - ▁LICENSE - ▁NEPTUNE - ▁OPPOS - ▁REFRIGERATOR - ▁STONEBUSH - ▁1000 - ▁APPLI - ▁SUBTRACTION - ▁HOOD - ▁WIDER - ▁BROOM - ▁UNIVERSITY - ▁PRINCESSES - ▁MINT - ▁PARENT - ▁PEEING - ▁ADORE - DONG - ▁SP - ANCE - ▁EXPLOR - TTEOKBOKKI - WHEEL - ▁ABANDONED - ▁CALLUSES - ▁COSMETICS - ▁LADYBUG - ▁MARIA - ▁PRONUNCIATION - ▁BOUQUET - ▁SOGGY - ▁LEFTOVERS - ▁MIKE - ▁TANK - ▁SPAC - ▁FRAME - MADE - IVAL - ▁YE - ▁GATHERING - IAN - ▁KITTENS - IBLE - ▁ABBREVIAT - ▁CHAPAGETTI - ▁ENGINES - ▁EQUIPMENT - ▁INTERSECTION - ▁SANITIZER - ▁DOKDO - ▁GENERATOR - ▁MEDIUM - ▁BALANCE - ▁CHART - ▁TELEVISION - ▁JAJANG - ▁LOLLY - ▁PHOTOGRAPH - ORD - ▁KKA - ▁SOLES - ▁BALM - ▁DECORATION - ▁THORN - ▁ARMY - ▁YU - EEK - NK - BOY - LENGTH - TONY - HEN - ▁RELEASE - ▁LOOSE - ▁COMPLETE - KYOCHON - ▁ARCADE - ▁BRIM - ▁CORONA - ▁CRANE - ▁CUPCAKE - ▁KITCHENWARE - ▁LULLABY - ▁MODER - ▁MUSKET - ▁OBEDIEN - ▁PIKACHU - ▁PROVERBS - ▁SALMON - ▁YUKGAEJANG - ▁TANNED - ▁VILLA - ▁DIRECTIONS - ▁CLAY - ▁ADMIR - ▁DIRECTOR - ▁DAMAGED - ▁BURST - ▁TOPIC - ▁DOODLED - ▁COMPAR - ▁BUBBLE - ▁HO - ▁KISSE - ▁JO - ▁BLOATED - ▁CONSONANTS - ▁DOWNLOAD - ▁ELBOW - ▁FUNNIEST - ▁PORORO - ▁SLOTS - ▁VACUUM - ▁BOTTOM - ▁MANDELA - ▁IMSIL - ▁VIP - ▁TOMMY - EATURE - ▁PINE - ▁EIGHTTHIRTY - ▁HIDEANDSEEK - ▁COLLAPSED - ▁UNDERSTOOD - ▁CRUSHED - ▁TRI - OF - ▁DI - ▁CARNATION - ORY - NAILS - LENT - ▁PUBLISH - PLACE - ▁CLIP - ILLA - ▁SUNSHIN - ▁ACTUAL - ▁SUCCESS - COCK - ▁60 - ▁BENEFITS - ▁CLAW - ▁HAUNT - ▁LIBRARIES - ▁LOTTERIA - ▁MERCURY - ▁MITTEN - ▁SWAM - ▁ROTTEN - ▁SERVANT - DENTAL - ▁LEGEND - ▁ROT - ▁PRICKED - ▁230 - ▁TUB - ▁WINK - ▁HUNTER - ▁SCREAMING - ▁FINALE - ▁SOAPY - ▁REDESIGNING - NNA - ▁DIAPER - ▁BANG - IK - CHAN - TIER - ▁MOR - ▁METERS - ▁HUGG - DAE - FTER - CHO - SHIP - EITHER - CTIVE - ▁KI - ▁RU - ▁BRAND - ▁AMOUNT - ▁EXPLANATION - ▁HAIRPIN - ▁HORRIBLE - ▁INTERIOR - ▁LANDSLIDE - ▁NEVERTHELESS - ▁PERSIMMON - ▁POSTPONE - ▁SCIENTIST - ▁SLACK - ▁STORM - ▁STREAM - ▁SURPRISING - ▁URGENT - ▁ZOMBIE - ▁STOOL - ▁LOAD - NAMBU - ▁ANNOUNCEMENT - IKES - GRAN - ▁ABC - ▁COMPLE - ▁FASCINATING - ▁REMOVED - ▁CRAWLING - ▁INTERRUPTING - RELLA - RAGE - ▁PEELING - ▁HUMANS - ▁MON - ▁BEGIN - ▁VEGETABLE - ▁SLEEVE - GLE - ▁THA - ISH - TRAINER - '7' - ROAD - DRIVER - ▁PRETEN - ▁ALLOW - UZZLE - ▁DEMONSTRAT - ▁STIR - ▁BROC - ▁CARCASON - ▁EQUALLY - ▁EXPERIMENT - ▁HESITAT - ▁SPINNING - ▁MENTOR - ▁ABBREVIATION - ▁RASHES - ▁ASSEMBLING - ▁DUNG - MEMOR - ▁PEACEFUL - ▁HARDENS - OSU - SSUED - ▁FRECKLE - TIOUS - ▁REALIZ - ▁SQUA - LIFE - THINK - ▁BIK - ▁KNIT - ZZA - ▁ALITTLE - ▁BAREFOOT - ▁CONCENTRATE - ▁DALGONA - ▁GUIDEBOOK - ▁KIDZANIA - ▁PALACE - ▁ROSHEN - ▁TEXTBOOK - ▁TUNAKIMBAP - OTTEOK - ▁830 - ▁HOSE - ITIES - NIX - ▁FIFTEENCM - ▁IMAGE - ▁CHEESEKIMBAP - ▁HOTTER - ▁PATT - ▁CLIPPE - ▁FOXES - EAGLE - ▁QUE - NDING - ▁DETER - AP - YEO - UED - ▁PAI - ▁EXCITEDLY - ▁WAVED - ▁BUL - BUT - ▁METER - KIMBAP - HAND - WATCHING - ▁CONVERS - ▁FLICK - ▁PEDIATRIC - NAMENT - REIGN - ▁BIKINI - ▁BUCKWHEATCREPE - ▁JENGA - ▁LAUNCH - ▁OPTICIAN - ▁PIGTAIL - ▁SIMON - ▁SUBSCRIBE - ▁TICKLISH - NELS - ▁PINWHEEL - INATED - ▁DRUG - ▁ONESIXCM - ▁EIGHTH - ▁SMARTEST - ▁HUNTING - ▁PIL - UMMY - ITION - UNNI - ▁SU - ▁POWERFULL - ▁WAFFLE - DIA - ▁TICK - EIGHT - PICKED - FIFTY - WENT - ▁BOT - ▁REPRESENT - OKKI - ▁COCOA - ▁CUSHION - ▁FARTHEST - ▁PENTAGON - ▁SLIDING - ▁SWEAR - ▁MOLD - ▁BBOY - ▁80 - ▁WATERPROOF - ▁RAIL - ▁CREATED - ▁CHIRPING - ▁SEARCH - SEOK - ▁TOAST - ▁BETRAYE - JOR - ▁NI - ZI - ▁SLAMM - ▁GU - ▁NAG - ▁SERVED - UFFY - ▁INSECT - ▁ZIPPE - LP - YEONG - ESSION - IPPED - ▁CELEBRAT - ▁CHANG - '50' - POST - ENTI - ▁DISAPPOINT - ▁QU - ▁FOREIGN - ▁POSSIB - ▁CONGRATULAT - ADOW - ▁TAE - CAFÉ - ▁COURIER - ▁DAEJEON - ▁DOWNSTAIRS - ▁EXPER - ▁PREFERENCE - ▁LACT - ▁OCCUR - ORIENT - ▁SPACIOUS - INARY - ▁KNITTING - ▁LIBERTY - VILLE - RB - ▁BARKED - DAN - ▁TIN - ATOR - ▁PHO - RIED - ▁JINDA - OUND - HOE - ▁STRETCHE - ▁SNEEZ - EVI - QUALITY - MOM - ▁BLIND - HYEON - ECTION - ROKE - ▁ANCHOVY - ▁ASHAMED - ▁COASTER - ▁CONFUSING - ▁CYCLIST - ▁DANDELION - ▁FIREFLIES - ▁HYUNG - ▁KNOWLEDGE - ▁NARACULA - ▁SCAB - ▁VOCABULARY - ▁CONFIDENT - ▁RELAT - ▁FOOLISH - ▁NINEAM - ▁ZO - ▁BOU - ▁FLATTERED - ▁BLINDING - ▁SKATER - ▁ROLLER - ▁FIRM - COTT - NURI - ▁WARMER - ▁LONGEST - ▁TICKLE - ▁AMERICAN - GI - AGGED - CHARGE - TODAY - ▁CREATE - UMPING - JJAEK - ▁BEGINNER - ▁CLICKING - ▁CORRIDORS - ▁DAZZLING - ▁DERMATOLOGIST - ▁DILIGENT - ▁FEBRUARY - ▁FISHBOWL - ▁GARAETTEOK - ▁GARGLE - ▁INJURED - ▁MANTISES - ▁NAKSEONGDAE - ▁ROAST - ▁SNITCH - ▁SLIMMER - ▁DISCHARGE - ▁SOAKED - ▁SELECTED - ▁VICE - ▁INFECT - ▁CONTAINER - ▁NEATLY - ▁STARSHAPED - LOTTEWORLD - ▁SUPPLEMENT - ▁EIGHTTH - ISTERS - ▁TICKL - ▁STRAIGHTEN - ▁SKINN - RANGE - ▁TANGERINE - ▁STO - PREPARED - SPROUT - TWELVE - TONIGHT - ▁RECOGNI - VAN - BEEN - ▁EXPLODE - ▁CHUBB - ANGGU - ▁SAVI - ▁950 - ▁ADJUST - ▁CASTANETS - ▁FAITH - ▁GONGJU - ▁GRAIN - ▁GROSS - ▁JUPITER - ▁MAGPIE - ▁SAIPAN - ▁SKULL - ▁SPARROW - ▁VACCINATED - ▁VIGOROUSLY - ▁AUTOMATIC - ▁NEARBY - SEVENTEEN - ▁TWENTI - ▁NIKE - ▁SEORA - DATORS - ▁PONG - ▁730 - ▁SCARIER - ▁TRUNK - ▁BETRAYER - ▁CHEESEGIMBAP - ONGDAE - ▁SEVERE - ▁SPOONFUL - CTATION - ▁WITCH - ▁LIMIT - ▁EATTTEOKBOKKI - GEOUS - ▁CRAWLED - ▁SUC - AVED - AGE - ▁KITTEN - ▁SKEWER - IZED - ▁TEAR - WAVE - ▁RACI - ▁CONTAIN - ▁TRO - ▁GUGUDAN - ▁GEPPET - ▁PHARMACI - MULGUK - PPAK - SAMJANG - ▁ACORN - ▁APPETITE - ▁BRUNCH - ▁BUMMER - ▁DIARRHEA - ▁FLAP - ▁GERMS - ▁GWANSUN - ▁HOMETOWN - ▁KILOMETERS - ▁MARRIAGE - ▁PRANKS - ▁RADISH - '5' - ′ - 수 - '2' - ́ - 子 - 예 - 요 - '3' - É - '6' - '9' - “ - . - '1' - 단 - <sos/eos> init: null input_size: null ctc_conf: ignore_nan_grad: true joint_net_conf: null use_preprocessor: true token_type: bpe bpemodel: data/ko_token_list/bpe_unigram5000/bpe.model non_linguistic_symbols: null cleaner: null g2p: null speech_volume_normalize: null rir_scp: null rir_apply_prob: 1.0 noise_scp: null noise_apply_prob: 1.0 noise_db_range: '13_15' short_noise_thres: 0.5 aux_ctc_tasks: [] frontend: default frontend_conf: fs: 16k specaug: null specaug_conf: {} normalize: global_mvn normalize_conf: stats_file: exp/asr_stats_raw_ko_bpe5000_sp/train/feats_stats.npz model: espnet model_conf: ctc_weight: 0.3 lsm_weight: 0.1 length_normalized_loss: false preencoder: null preencoder_conf: {} encoder: contextual_block_transformer encoder_conf: output_size: 256 attention_heads: 4 linear_units: 2048 num_blocks: 12 dropout_rate: 0.1 positional_dropout_rate: 0.1 attention_dropout_rate: 0.0 input_layer: conv2d normalize_before: true block_size: 40 hop_size: 16 look_ahead: 16 init_average: true ctx_pos_enc: true postencoder: null postencoder_conf: {} decoder: transformer decoder_conf: attention_heads: 4 linear_units: 2048 num_blocks: 6 dropout_rate: 0.1 positional_dropout_rate: 0.1 self_attention_dropout_rate: 0.0 src_attention_dropout_rate: 0.0 preprocessor: default preprocessor_conf: {} required: - output_dir - token_list version: '202304' distributed: true ``` </details> ### Citing ESPnet ```BibTex @inproceedings{watanabe2018espnet, author={Shinji Watanabe and Takaaki Hori and Shigeki Karita and Tomoki Hayashi and Jiro Nishitoba and Yuya Unno and Nelson Yalta and Jahn Heymann and Matthew Wiesner and Nanxin Chen and Adithya Renduchintala and Tsubasa Ochiai}, title={{ESPnet}: End-to-End Speech Processing Toolkit}, year={2018}, booktitle={Proceedings of Interspeech}, pages={2207--2211}, doi={10.21437/Interspeech.2018-1456}, url={http://dx.doi.org/10.21437/Interspeech.2018-1456} } ``` or arXiv: ```bibtex @misc{watanabe2018espnet, title={ESPnet: End-to-End Speech Processing Toolkit}, author={Shinji Watanabe and Takaaki Hori and Shigeki Karita and Tomoki Hayashi and Jiro Nishitoba and Yuya Unno and Nelson Yalta and Jahn Heymann and Matthew Wiesner and Nanxin Chen and Adithya Renduchintala and Tsubasa Ochiai}, year={2018}, eprint={1804.00015}, archivePrefix={arXiv}, primaryClass={cs.CL} } ```
cherrue/RandomCrop_Rescale_epoch_3_learning_rate_5e_5_decay_0_01
cherrue
2023-07-06T06:30:06Z
63
0
transformers
[ "transformers", "tf", "vit", "image-classification", "generated_from_keras_callback", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]
image-classification
2023-07-06T05:35:06Z
--- license: apache-2.0 tags: - generated_from_keras_callback model-index: - name: cherrue/pricetag_classifier 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. --> # cherrue/pricetag_classifier This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on an unknown dataset. It achieves the following results on the evaluation set: - Train Loss: 1.0546 - Validation Loss: 1.2226 - Train Accuracy: 0.3846 - Epoch: 2 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - optimizer: {'name': 'AdamWeightDecay', 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 5e-05, 'decay_steps': 1251, '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 | Validation Loss | Train Accuracy | Epoch | |:----------:|:---------------:|:--------------:|:-----:| | 1.3379 | 1.2276 | 0.5128 | 0 | | 1.1973 | 1.1561 | 0.4615 | 1 | | 1.0546 | 1.2226 | 0.3846 | 2 | ### Framework versions - Transformers 4.28.0 - TensorFlow 2.12.0 - Datasets 2.13.1 - Tokenizers 0.13.3
Waterhorse/chessgpt-base-v1
Waterhorse
2023-07-06T06:19:40Z
83
6
transformers
[ "transformers", "pytorch", "gpt_neox", "text-generation", "en", "dataset:Waterhorse/chess_data", "arxiv:2306.09200", "license:apache-2.0", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]
text-generation
2023-06-02T22:03:14Z
--- license: apache-2.0 language: - en datasets: - Waterhorse/chess_data --- # Chessgpt-Base-3B-v1 Chessgpt-Base-v1 is the base model of Chessgpt. - Base Model: [Chessgpt-base-v1](https://huggingface.co/Waterhorse/chessgpt-base-v1) - Chat Version: [chessgpt-chat-v1](https://huggingface.co/Waterhorse/chessgpt-chat-v1) Also, we are actively working on the development of the next-generation model, ChessGPT-V2. We welcome any contribution, especially on chess related dataset. For related matters, please contact [email protected]. ## Model Details - **Model type**: Language Model - **Language(s)**: English - **License**: Apache 2.0 - **Model Description**: A 2.8B parameter pretrained language model in Chess. ## GPU Inference This requires a GPU with 8GB memory. ```python import torch import transformers from transformers import AutoTokenizer, AutoModelForCausalLM MIN_TRANSFORMERS_VERSION = '4.25.1' # check transformers version assert transformers.__version__ >= MIN_TRANSFORMERS_VERSION, f'Please upgrade transformers to version {MIN_TRANSFORMERS_VERSION} or higher.' # init tokenizer = AutoTokenizer.from_pretrained("Waterhorse/chessgpt-base-v1") model = AutoModelForCausalLM.from_pretrained("Waterhorse/chessgpt-base-v1", torch_dtype=torch.float16) model = model.to('cuda:0') # infer # Conversation between two prompt = "Q: 1.e4 c5, what is the name of this opening?A:" inputs = tokenizer(prompt, return_tensors='pt').to(model.device) input_length = inputs.input_ids.shape[1] outputs = model.generate( **inputs, max_new_tokens=128, do_sample=True, temperature=0.7, top_p=0.7, top_k=50, return_dict_in_generate=True, ) token = outputs.sequences[0, input_length:] output_str = tokenizer.decode(token) print(output_str) ``` # Uses Excluded uses are described below. ### Direct Use `chessgpt-base-v1` is mainly for research on large language model, especially for those research about policy learning and language modeling. #### Out-of-Scope Use `chessgpt-base-v1` is a language model trained on chess related data and may not perform well for other use cases beyond chess domain. #### Bias, Risks, and Limitations Just as with any language model, chessgpt-base-v1 carries inherent limitations that necessitate careful consideration. Specifically, it may occasionally generate responses that are irrelevant or incorrect, particularly when tasked with interpreting complex or ambiguous queries. Additionally, given that its training is rooted in online data, the model may inadvertently reflect and perpetuate common online stereotypes and biases. # Evaluation Please refer to our [paper](https://arxiv.org/abs/2306.09200) and [code](https://github.com/waterhorse1/ChessGPT)for benchmark results. # Citation Information ```bash @article{feng2023chessgpt, title={ChessGPT: Bridging Policy Learning and Language Modeling}, author={Feng, Xidong and Luo, Yicheng and Wang, Ziyan and Tang, Hongrui and Yang, Mengyue and Shao, Kun and Mguni, David and Du, Yali and Wang, Jun}, journal={arXiv preprint arXiv:2306.09200}, year={2023} } ```
saintzeno/a2c-PandaReachDense-v3
saintzeno
2023-07-06T06:10:45Z
3
0
stable-baselines3
[ "stable-baselines3", "PandaReachDense-v3", "deep-reinforcement-learning", "reinforcement-learning", "model-index", "region:us" ]
reinforcement-learning
2023-07-06T05:52:59Z
--- library_name: stable-baselines3 tags: - PandaReachDense-v3 - deep-reinforcement-learning - reinforcement-learning - stable-baselines3 model-index: - name: A2C results: - task: type: reinforcement-learning name: reinforcement-learning dataset: name: PandaReachDense-v3 type: PandaReachDense-v3 metrics: - type: mean_reward value: -0.22 +/- 0.11 name: mean_reward verified: false --- # **A2C** Agent playing **PandaReachDense-v3** This is a trained model of a **A2C** agent playing **PandaReachDense-v3** using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3). ## Usage (with Stable-baselines3) TODO: Add your code ```python from stable_baselines3 import ... from huggingface_sb3 import load_from_hub ... ```
Ryukijano/whisper-small-dv
Ryukijano
2023-07-06T05:36:17Z
78
0
transformers
[ "transformers", "pytorch", "tensorboard", "whisper", "automatic-speech-recognition", "dataset:mozilla-foundation/common_voice_13_0", "license:mit", "endpoints_compatible", "region:us" ]
automatic-speech-recognition
2023-07-05T06:25:50Z
--- license: mit datasets: - mozilla-foundation/common_voice_13_0 metrics: - wer --- --- # Whisper Small DV Model ![Model Banner](https://uploads-ssl.webflow.com/614c82ed388d53640613982e/63eb5ebedd3a9a738e22a03f_open%20ai%20whisper.jpg) ## Model Description The `whisper-small-dv` model is an advanced Automatic Speech Recognition (ASR) model, trained on the extensive [Mozilla Common Voice 13.0](https://commonvoice.mozilla.org/en/datasets) dataset. This model is capable of transcribing spoken language into written text with high accuracy, making it a valuable tool for a wide range of applications, from transcription services to voice assistants. ## Training The model was trained using the PyTorch framework and the Transformers library. Training metrics and visualizations can be viewed on TensorBoard. ## Performance The model's performance was evaluated on a held-out test set. The evaluation metrics and results can be found in the "Eval Results" section. ## Usage The model can be used for any ASR task. To use the model, you can load it using the Transformers library: ```python from transformers import Wav2Vec2ForCTC, Wav2Vec2Processor # Load the model model = Wav2Vec2ForCTC.from_pretrained("Ryukijano/whisper-small-dv") processor = Wav2Vec2Processor.from_pretrained("Ryukijano/whisper-small-dv") # Use the model for ASR inputs = processor("path_to_audio_file", return_tensors="pt", padding=True) logits = model(inputs.input_values).logits predicted_ids = torch.argmax(logits, dim=-1) transcription = processor.decode(predicted_ids[0]) ``` ## License This model is released under the MIT license. --- P
eigenscribe/etzHayim
eigenscribe
2023-07-06T05:34:59Z
0
0
null
[ "license:creativeml-openrail-m", "region:us" ]
null
2023-07-06T05:33:49Z
--- license: creativeml-openrail-m ---
insub/distilbert-base-uncased-finetuned-imdb
insub
2023-07-06T05:22:05Z
124
0
transformers
[ "transformers", "pytorch", "tensorboard", "distilbert", "fill-mask", "generated_from_trainer", "dataset:imdb", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]
fill-mask
2023-07-06T05:17:00Z
--- license: apache-2.0 tags: - generated_from_trainer datasets: - imdb model-index: - name: distilbert-base-uncased-finetuned-imdb results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # distilbert-base-uncased-finetuned-imdb This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the imdb dataset. It achieves the following results on the evaluation set: - Loss: 2.4721 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 2e-05 - train_batch_size: 64 - eval_batch_size: 64 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 3.0 ### Training results | Training Loss | Epoch | Step | Validation Loss | |:-------------:|:-----:|:----:|:---------------:| | 2.7086 | 1.0 | 157 | 2.4897 | | 2.5796 | 2.0 | 314 | 2.4230 | | 2.5269 | 3.0 | 471 | 2.4354 | ### Framework versions - Transformers 4.30.2 - Pytorch 2.0.1+cu118 - Datasets 2.13.1 - Tokenizers 0.13.3
aroot/eng-fra-simcse_random
aroot
2023-07-06T05:13:07Z
110
0
transformers
[ "transformers", "pytorch", "tensorboard", "mbart", "text2text-generation", "translation", "generated_from_trainer", "autotrain_compatible", "endpoints_compatible", "region:us" ]
translation
2023-07-06T04:53:15Z
--- tags: - translation - generated_from_trainer metrics: - bleu model-index: - name: eng-fra-simcse_random 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. --> # eng-fra-simcse_random This model is a fine-tuned version of [facebook/mbart-large-50-many-to-many-mmt](https://huggingface.co/facebook/mbart-large-50-many-to-many-mmt) on the None dataset. It achieves the following results on the evaluation set: - Loss: 1.1475 - Bleu: 31.8135 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 2e-05 - train_batch_size: 32 - eval_batch_size: 32 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 3 - mixed_precision_training: Native AMP ### Training results ### Framework versions - Transformers 4.26.1 - Pytorch 2.0.1+cu117 - Datasets 2.12.0 - Tokenizers 0.13.3
nhung/layoutxlm-de-durch
nhung
2023-07-06T05:02:06Z
74
0
transformers
[ "transformers", "pytorch", "tensorboard", "layoutlmv2", "token-classification", "generated_from_trainer", "dataset:xfun", "license:cc-by-nc-sa-4.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]
token-classification
2023-07-06T02:20:52Z
--- license: cc-by-nc-sa-4.0 tags: - generated_from_trainer datasets: - xfun model-index: - name: layoutxlm-de-durch 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. --> # layoutxlm-de-durch This model is a fine-tuned version of [microsoft/layoutxlm-base](https://huggingface.co/microsoft/layoutxlm-base) on the xfun 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: 6.25e-06 - train_batch_size: 2 - eval_batch_size: 2 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_ratio: 0.1 - training_steps: 15000 ### Training results ### Framework versions - Transformers 4.27.4 - Pytorch 1.10.0+cu111 - Datasets 2.11.0 - Tokenizers 0.13.3
squeeze-ai-lab/sq-xgen-7b-8k-base-w3-s45
squeeze-ai-lab
2023-07-06T04:46:32Z
0
0
null
[ "arxiv:2306.07629", "region:us" ]
null
2023-07-06T03:46:53Z
**SqueezeLLM** is a post-training quantization framework that incorporates a new method called Dense-and-Sparse Quantization to enable efficient LLM serving. **TLDR:** Deploying LLMs is difficult due to their large memory size. This can be addressed with reduced precision quantization. But a naive method hurts performance. We address this with a new Dense-and-Sparse Quantization method. Dense-and-Sparse splits weight matrices into two components: A dense component that can be heavily quantized without affecting model performance, as well as a sparse part that preserves sensitive and outlier parts of the weight matrices With this approach, we are able to serve larger models with smaller memory footprint, the same latency, and yet higher accuracy and quality. For more details please check out our [paper](https://arxiv.org/pdf/2306.07629.pdf). ## Model description 3-bit XGen-7B Base model with 8K sequence length quantized using SqueezeLLM. More details on the quantization method can be found in the [paper](https://arxiv.org/pdf/2306.07629.pdf). More detailed model descriptions can be found in the [link](https://huggingface.co/Salesforce/xgen-7b-8k-base). * **Base Model:** [XGen-7B-8K-Base](https://huggingface.co/Salesforce/xgen-7b-8k-base) (by Salesforce AI Research) * **Bitwidth:** 3-bit * **Sparsity Level:** 0.45% ## Links * **Paper**: [https://arxiv.org/pdf/2306.07629.pdf](https://arxiv.org/pdf/2306.07629.pdf) * **Code**: [https://github.com/SqueezeAILab/SqueezeLLM](https://github.com/SqueezeAILab/SqueezeLLM) --- license: other ---
mazeinmouse/a2c-AntBulletEnv-v0
mazeinmouse
2023-07-06T04:34:47Z
0
0
stable-baselines3
[ "stable-baselines3", "AntBulletEnv-v0", "deep-reinforcement-learning", "reinforcement-learning", "model-index", "region:us" ]
reinforcement-learning
2023-07-06T04:33:37Z
--- 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: 1651.08 +/- 126.30 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 ... ```
headflame02/AchaxV4
headflame02
2023-07-06T04:30:16Z
0
0
null
[ "license:creativeml-openrail-m", "region:us" ]
null
2023-07-06T04:29:24Z
--- license: creativeml-openrail-m ---
aroot/eng-mya-wsample.32a
aroot
2023-07-06T04:23:10Z
103
0
transformers
[ "transformers", "pytorch", "tensorboard", "mbart", "text2text-generation", "translation", "generated_from_trainer", "autotrain_compatible", "endpoints_compatible", "region:us" ]
translation
2023-07-06T04:01:01Z
--- tags: - translation - generated_from_trainer metrics: - bleu model-index: - name: eng-mya-wsample.32a 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. --> # eng-mya-wsample.32a This model is a fine-tuned version of [facebook/mbart-large-50-many-to-many-mmt](https://huggingface.co/facebook/mbart-large-50-many-to-many-mmt) on the None dataset. It achieves the following results on the evaluation set: - Loss: 1.8284 - Bleu: 4.7194 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 2e-05 - train_batch_size: 32 - eval_batch_size: 32 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 3 - mixed_precision_training: Native AMP ### Training results ### Framework versions - Transformers 4.26.1 - Pytorch 2.0.1+cu117 - Datasets 2.12.0 - Tokenizers 0.13.3
lovelyxs/PPO-LunarLander-v2
lovelyxs
2023-07-06T04:11:32Z
0
0
stable-baselines3
[ "stable-baselines3", "LunarLander-v2", "deep-reinforcement-learning", "reinforcement-learning", "model-index", "region:us" ]
reinforcement-learning
2023-07-06T03:54:28Z
--- library_name: stable-baselines3 tags: - LunarLander-v2 - deep-reinforcement-learning - reinforcement-learning - stable-baselines3 model-index: - name: PPO results: - task: type: reinforcement-learning name: reinforcement-learning dataset: name: LunarLander-v2 type: LunarLander-v2 metrics: - type: mean_reward value: 265.53 +/- 16.26 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 ... ```
digiplay/CoffeeMix_v1
digiplay
2023-07-06T03:55:09Z
307
3
diffusers
[ "diffusers", "safetensors", "stable-diffusion", "stable-diffusion-diffusers", "text-to-image", "license:other", "autotrain_compatible", "endpoints_compatible", "diffusers:StableDiffusionPipeline", "region:us" ]
text-to-image
2023-07-06T02:17:13Z
--- license: other tags: - stable-diffusion - stable-diffusion-diffusers - text-to-image - diffusers inference: true --- Model info: https://civitai.com/models/40630?modelVersionId=45847 Sample image I made : ![0235d726-e2c8-4923-bf03-c543f2ac4a60.jpeg](https://cdn-uploads.huggingface.co/production/uploads/646c83c871d0c8a6e4455854/C2Bd8j0hjY-9ml-Q1Od2y.jpeg) Original Author's DEMO images : ![](https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/7e65781b-309a-4686-2b94-a73eae211600/00144-1649392094.jpeg) ![](https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/708f60ef-9802-4543-cfa2-d3dd29722100/00164-3364070768.jpeg) ![](https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/729df7f3-ae0c-4ca1-b6e4-59faf294a100/00140-3641118898.jpeg)
aroot/eng-guj-wsample.43a
aroot
2023-07-06T03:44:33Z
103
0
transformers
[ "transformers", "pytorch", "tensorboard", "mbart", "text2text-generation", "translation", "generated_from_trainer", "autotrain_compatible", "endpoints_compatible", "region:us" ]
translation
2023-07-06T03:21:38Z
--- tags: - translation - generated_from_trainer metrics: - bleu model-index: - name: eng-guj-wsample.43a 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. --> # eng-guj-wsample.43a This model is a fine-tuned version of [facebook/mbart-large-50-many-to-many-mmt](https://huggingface.co/facebook/mbart-large-50-many-to-many-mmt) on the None dataset. It achieves the following results on the evaluation set: - Loss: 3.2191 - Bleu: 2.9237 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 2e-05 - train_batch_size: 32 - eval_batch_size: 32 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 3 - mixed_precision_training: Native AMP ### Training results ### Framework versions - Transformers 4.26.1 - Pytorch 2.0.1+cu117 - Datasets 2.12.0 - Tokenizers 0.13.3
mrizalf7/t5-small-finetuned-xsum
mrizalf7
2023-07-06T03:42:24Z
105
0
transformers
[ "transformers", "pytorch", "tensorboard", "t5", "text2text-generation", "generated_from_trainer", "dataset:xsum", "license:apache-2.0", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]
text2text-generation
2023-07-06T00:32:49Z
--- license: apache-2.0 tags: - generated_from_trainer datasets: - xsum model-index: - name: t5-small-finetuned-xsum 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-small-finetuned-xsum This model is a fine-tuned version of [t5-small](https://huggingface.co/t5-small) on the xsum dataset. ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 2e-05 - train_batch_size: 16 - eval_batch_size: 16 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 1 - mixed_precision_training: Native AMP ### Framework versions - Transformers 4.28.0 - Pytorch 2.0.1+cu118 - Datasets 2.13.1 - Tokenizers 0.13.3
aroot/eng-guj-wsample.32a
aroot
2023-07-06T03:39:41Z
103
0
transformers
[ "transformers", "pytorch", "tensorboard", "mbart", "text2text-generation", "translation", "generated_from_trainer", "autotrain_compatible", "endpoints_compatible", "region:us" ]
translation
2023-07-06T03:21:39Z
--- tags: - translation - generated_from_trainer metrics: - bleu model-index: - name: eng-guj-wsample.32a 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. --> # eng-guj-wsample.32a This model is a fine-tuned version of [facebook/mbart-large-50-many-to-many-mmt](https://huggingface.co/facebook/mbart-large-50-many-to-many-mmt) on the None dataset. It achieves the following results on the evaluation set: - Loss: 3.2257 - Bleu: 3.1070 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 2e-05 - train_batch_size: 32 - eval_batch_size: 32 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 3 - mixed_precision_training: Native AMP ### Training results ### Framework versions - Transformers 4.26.1 - Pytorch 2.0.1+cu117 - Datasets 2.12.0 - Tokenizers 0.13.3
Sandrro/text_to_subfunction_v6
Sandrro
2023-07-06T03:24:24Z
107
0
transformers
[ "transformers", "pytorch", "tensorboard", "bert", "text-classification", "generated_from_trainer", "license:mit", "autotrain_compatible", "endpoints_compatible", "region:us" ]
text-classification
2023-07-05T20:05:18Z
--- license: mit tags: - generated_from_trainer metrics: - f1 model-index: - name: text_to_subfunction_v6 results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # text_to_subfunction_v6 This model is a fine-tuned version of [cointegrated/rubert-tiny2](https://huggingface.co/cointegrated/rubert-tiny2) on the None dataset. It achieves the following results on the evaluation set: - Loss: 3.2720 - F1: 0.4415 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 5e-05 - train_batch_size: 4 - eval_batch_size: 4 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 20 - mixed_precision_training: Native AMP ### Training results | Training Loss | Epoch | Step | Validation Loss | F1 | |:-------------:|:-----:|:-----:|:---------------:|:------:| | 3.5055 | 1.0 | 4365 | 3.4067 | 0.1639 | | 2.5598 | 2.0 | 8730 | 2.6935 | 0.2833 | | 2.1499 | 3.0 | 13095 | 2.3594 | 0.3420 | | 1.6575 | 4.0 | 17460 | 2.2243 | 0.3921 | | 1.2463 | 5.0 | 21825 | 2.1722 | 0.4105 | | 0.9624 | 6.0 | 26190 | 2.1955 | 0.4341 | | 0.7407 | 7.0 | 30555 | 2.2434 | 0.4449 | | 0.5608 | 8.0 | 34920 | 2.3604 | 0.4329 | | 0.4233 | 9.0 | 39285 | 2.4747 | 0.4361 | | 0.2433 | 10.0 | 43650 | 2.5562 | 0.4404 | | 0.2154 | 11.0 | 48015 | 2.6678 | 0.4374 | | 0.1811 | 12.0 | 52380 | 2.8158 | 0.4341 | | 0.1374 | 13.0 | 56745 | 2.9037 | 0.4425 | | 0.1406 | 14.0 | 61110 | 3.0182 | 0.4366 | | 0.1135 | 15.0 | 65475 | 3.0941 | 0.4440 | | 0.0992 | 16.0 | 69840 | 3.1516 | 0.4437 | | 0.1159 | 17.0 | 74205 | 3.2001 | 0.4418 | | 0.0809 | 18.0 | 78570 | 3.2489 | 0.4373 | | 0.1035 | 19.0 | 82935 | 3.2650 | 0.4407 | | 0.0558 | 20.0 | 87300 | 3.2720 | 0.4415 | ### Framework versions - Transformers 4.27.1 - Pytorch 2.1.0.dev20230414+cu117 - Datasets 2.9.0 - Tokenizers 0.13.3
BaoKien/deberta-base-finetuned-squad-v2
BaoKien
2023-07-06T03:22:36Z
13
0
transformers
[ "transformers", "pytorch", "tensorboard", "deberta", "question-answering", "generated_from_trainer", "dataset:squad_v2", "license:mit", "endpoints_compatible", "region:us" ]
question-answering
2023-07-06T01:19:43Z
--- license: mit tags: - generated_from_trainer datasets: - squad_v2 model-index: - name: deberta-base-finetuned-squad-v2 results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # deberta-base-finetuned-squad-v2 This model is a fine-tuned version of [microsoft/deberta-base](https://huggingface.co/microsoft/deberta-base) on the squad_v2 dataset. It achieves the following results on the evaluation set: - Loss: 0.9221 ## 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 | |:-------------:|:-----:|:-----:|:---------------:| | 0.753 | 1.0 | 8238 | 0.7286 | | 0.5378 | 2.0 | 16476 | 0.7578 | | 0.3881 | 3.0 | 24714 | 0.9221 | ### Performance - 'exact': 81.84115219405373 - 'f1': 85.19125695340612 - 'total': 11873 - 'HasAns_exact': 80.24628879892038 - 'HasAns_f1': 86.95610556811602 - 'HasAns_total': 5928 - 'NoAns_exact': 83.43145500420522 - 'NoAns_f1': 83.43145500420522 - 'NoAns_total': 5945 - 'best_exact': 81.84115219405373 - 'best_exact_thresh': 0.9994916319847107 - 'best_f1': 85.19125695340657 - 'best_f1_thresh': 0.9994916319847107 - 'total_time_in_seconds': 294.34524957099984 - 'samples_per_second': 40.33698528277447 - 'latency_in_seconds': 0.024791143735450168 ### Framework versions - Transformers 4.30.2 - Pytorch 2.0.1+cu118 - Datasets 2.13.1 - Tokenizers 0.13.3
squeeze-ai-lab/sq-xgen-7b-8k-inst-w3-s0
squeeze-ai-lab
2023-07-06T03:15:42Z
0
0
null
[ "arxiv:2306.07629", "region:us" ]
null
2023-07-05T23:32:13Z
**SqueezeLLM** is a post-training quantization framework that incorporates a new method called Dense-and-Sparse Quantization to enable efficient LLM serving. **TLDR:** Deploying LLMs is difficult due to their large memory size. This can be addressed with reduced precision quantization. But a naive method hurts performance. We address this with a new Dense-and-Sparse Quantization method. Dense-and-Sparse splits weight matrices into two components: A dense component that can be heavily quantized without affecting model performance, as well as a sparse part that preserves sensitive and outlier parts of the weight matrices With this approach, we are able to serve larger models with smaller memory footprint, the same latency, and yet higher accuracy and quality. For more details please check out our [paper](https://arxiv.org/pdf/2306.07629.pdf). ## Model description 3-bit XGen-7B instruction-tuned model (i.e. finetuned model on public domain instructional data) with 8K sequence length quantized using SqueezeLLM. More details on the quantization method can be found in the [paper](https://arxiv.org/pdf/2306.07629.pdf). More detailed model descriptions can be found in the [link](https://huggingface.co/Salesforce/xgen-7b-8k-inst). * **Base Model:** [XGen-7B-8K-Inst](https://huggingface.co/Salesforce/xgen-7b-8k-inst) (by Salesforce AI Research) * **Bitwidth:** 3-bit * **Sparsity Level:** 0% (dense-only) ## Links * **Paper**: [https://arxiv.org/pdf/2306.07629.pdf](https://arxiv.org/pdf/2306.07629.pdf) * **Code**: [https://github.com/SqueezeAILab/SqueezeLLM](https://github.com/SqueezeAILab/SqueezeLLM) --- license: other ---
squeeze-ai-lab/sq-xgen-7b-8k-inst-w4-s0
squeeze-ai-lab
2023-07-06T03:15:32Z
0
1
null
[ "arxiv:2306.07629", "region:us" ]
null
2023-07-05T23:33:19Z
**SqueezeLLM** is a post-training quantization framework that incorporates a new method called Dense-and-Sparse Quantization to enable efficient LLM serving. **TLDR:** Deploying LLMs is difficult due to their large memory size. This can be addressed with reduced precision quantization. But a naive method hurts performance. We address this with a new Dense-and-Sparse Quantization method. Dense-and-Sparse splits weight matrices into two components: A dense component that can be heavily quantized without affecting model performance, as well as a sparse part that preserves sensitive and outlier parts of the weight matrices With this approach, we are able to serve larger models with smaller memory footprint, the same latency, and yet higher accuracy and quality. For more details please check out our [paper](https://arxiv.org/pdf/2306.07629.pdf). ## Model description 4-bit XGen-7B instruction-tuned model (i.e. finetuned model on public domain instructional data) with 8K sequence length quantized using SqueezeLLM. More details on the quantization method can be found in the [paper](https://arxiv.org/pdf/2306.07629.pdf). More detailed model descriptions can be found in the [link](https://huggingface.co/Salesforce/xgen-7b-8k-inst). * **Base Model:** [XGen-7B-8K-Inst](https://huggingface.co/Salesforce/xgen-7b-8k-inst) (by Salesforce AI Research) * **Bitwidth:** 4-bit * **Sparsity Level:** 0% (dense-only) ## Links * **Paper**: [https://arxiv.org/pdf/2306.07629.pdf](https://arxiv.org/pdf/2306.07629.pdf) * **Code**: [https://github.com/SqueezeAILab/SqueezeLLM](https://github.com/SqueezeAILab/SqueezeLLM) --- license: other ---
squeeze-ai-lab/sq-xgen-7b-8k-base-w4-s0
squeeze-ai-lab
2023-07-06T03:14:48Z
0
0
null
[ "arxiv:2306.07629", "region:us" ]
null
2023-07-05T23:31:51Z
**SqueezeLLM** is a post-training quantization framework that incorporates a new method called Dense-and-Sparse Quantization to enable efficient LLM serving. **TLDR:** Deploying LLMs is difficult due to their large memory size. This can be addressed with reduced precision quantization. But a naive method hurts performance. We address this with a new Dense-and-Sparse Quantization method. Dense-and-Sparse splits weight matrices into two components: A dense component that can be heavily quantized without affecting model performance, as well as a sparse part that preserves sensitive and outlier parts of the weight matrices With this approach, we are able to serve larger models with smaller memory footprint, the same latency, and yet higher accuracy and quality. For more details please check out our [paper](https://arxiv.org/pdf/2306.07629.pdf). ## Model description 4-bit XGen-7B Base model with 8K sequence length quantized using SqueezeLLM. More details on the quantization method can be found in the [paper](https://arxiv.org/pdf/2306.07629.pdf). More detailed model descriptions can be found in the [link](https://huggingface.co/Salesforce/xgen-7b-8k-base). * **Base Model:** [XGen-7B-8K-Base](https://huggingface.co/Salesforce/xgen-7b-8k-base) (by Salesforce AI Research) * **Bitwidth:** 4-bit * **Sparsity Level:** 0% (dense-only) ## Links * **Paper**: [https://arxiv.org/pdf/2306.07629.pdf](https://arxiv.org/pdf/2306.07629.pdf) * **Code**: [https://github.com/SqueezeAILab/SqueezeLLM](https://github.com/SqueezeAILab/SqueezeLLM) --- license: other ---
squeeze-ai-lab/sq-xgen-7b-8k-base-w3-s0
squeeze-ai-lab
2023-07-06T03:14:31Z
0
0
null
[ "arxiv:2306.07629", "region:us" ]
null
2023-07-05T23:31:15Z
**SqueezeLLM** is a post-training quantization framework that incorporates a new method called Dense-and-Sparse Quantization to enable efficient LLM serving. **TLDR:** Deploying LLMs is difficult due to their large memory size. This can be addressed with reduced precision quantization. But a naive method hurts performance. We address this with a new Dense-and-Sparse Quantization method. Dense-and-Sparse splits weight matrices into two components: A dense component that can be heavily quantized without affecting model performance, as well as a sparse part that preserves sensitive and outlier parts of the weight matrices With this approach, we are able to serve larger models with smaller memory footprint, the same latency, and yet higher accuracy and quality. For more details please check out our [paper](https://arxiv.org/pdf/2306.07629.pdf). ## Model description 3-bit XGen-7B Base model with 8K sequence length quantized using SqueezeLLM. More details on the quantization method can be found in the [paper](https://arxiv.org/pdf/2306.07629.pdf). More detailed model descriptions can be found in the [link](https://huggingface.co/Salesforce/xgen-7b-8k-base). * **Base Model:** [XGen-7B-8K-Base](https://huggingface.co/Salesforce/xgen-7b-8k-base) (by Salesforce AI Research) * **Bitwidth:** 3-bit * **Sparsity Level:** 0% (dense-only) ## Links * **Paper**: [https://arxiv.org/pdf/2306.07629.pdf](https://arxiv.org/pdf/2306.07629.pdf) * **Code**: [https://github.com/SqueezeAILab/SqueezeLLM](https://github.com/SqueezeAILab/SqueezeLLM) --- license: other ---
h2oai/h2ogpt-research-oasst1-llama-65b
h2oai
2023-07-06T03:11:31Z
1,502
9
transformers
[ "transformers", "pytorch", "llama", "text-generation", "gpt", "llm", "large language model", "open-source", "en", "dataset:h2oai/openassistant_oasst1_h2ogpt_graded", "license:other", "autotrain_compatible", "text-generation-inference", "region:us" ]
text-generation
2023-05-13T18:11:13Z
--- license: other language: - en library_name: transformers inference: false thumbnail: https://h2o.ai/etc.clientlibs/h2o/clientlibs/clientlib-site/resources/images/favicon.ico tags: - gpt - llm - large language model - open-source datasets: - h2oai/openassistant_oasst1_h2ogpt_graded --- # h2oGPT Model Card ## Summary H2O.ai's `h2ogpt-research-oasst1-llama-65b` is a 65 billion parameter instruction-following large language model (NOT licensed for commercial use). - Base model: [decapoda-research/llama-65b-hf](https://huggingface.co/decapoda-research/llama-65b-hf) - Fine-tuning dataset: [h2oai/openassistant_oasst1_h2ogpt_graded](https://huggingface.co/datasets/h2oai/openassistant_oasst1_h2ogpt_graded) - Data-prep and fine-tuning code: [H2O.ai GitHub](https://github.com/h2oai/h2ogpt) - Training logs: [zip](https://huggingface.co/h2oai/h2ogpt-research-oasst1-llama-65b/blob/main/llama-65b-hf.h2oaiopenassistant_oasst1_h2ogpt_graded.1_epochs.113510499324f0f007cbec9d9f1f8091441f2469.3.zip) ## Chatbot - Run your own chatbot: [H2O.ai GitHub](https://github.com/h2oai/h2ogpt) [![H2O.ai GitHub](https://user-images.githubusercontent.com/6147661/232930822-e7170e4d-8aa1-4f7a-ad70-ece9cdd8b0cb.png)](https://github.com/h2oai/h2ogpt) ## Usage To use the model with the `transformers` library on a machine with GPUs, first make sure you have the following libraries installed. ```bash pip install transformers==4.29.2 pip install accelerate==0.19.0 pip install torch==2.0.1 pip install einops==0.6.1 ``` ```python import torch from transformers import pipeline, AutoTokenizer tokenizer = AutoTokenizer.from_pretrained("h2oai/h2ogpt-research-oasst1-llama-65b", padding_side="left") generate_text = pipeline(model="h2oai/h2ogpt-research-oasst1-llama-65b", tokenizer=tokenizer, torch_dtype=torch.bfloat16, trust_remote_code=True, device_map="auto", prompt_type="human_bot") res = generate_text("Why is drinking water so healthy?", max_new_tokens=100) print(res[0]["generated_text"]) ``` Alternatively, if you prefer to not use `trust_remote_code=True` you can download [instruct_pipeline.py](https://huggingface.co/h2oai/h2ogpt-research-oasst1-llama-65b/blob/main/h2oai_pipeline.py), store it alongside your notebook, and construct the pipeline yourself from the loaded model and tokenizer: ```python import torch from h2oai_pipeline import H2OTextGenerationPipeline from transformers import AutoModelForCausalLM, AutoTokenizer tokenizer = AutoTokenizer.from_pretrained("h2oai/h2ogpt-research-oasst1-llama-65b", padding_side="left") model = AutoModelForCausalLM.from_pretrained("h2oai/h2ogpt-research-oasst1-llama-65b", torch_dtype=torch.bfloat16, device_map="auto") generate_text = H2OTextGenerationPipeline(model=model, tokenizer=tokenizer, prompt_type="human_bot") res = generate_text("Why is drinking water so healthy?", max_new_tokens=100) print(res[0]["generated_text"]) ``` ## Model Architecture ``` LlamaForCausalLM( (model): LlamaModel( (embed_tokens): Embedding(32000, 8192, padding_idx=31999) (layers): ModuleList( (0-79): 80 x LlamaDecoderLayer( (self_attn): LlamaAttention( (q_proj): Linear(in_features=8192, out_features=8192, bias=False) (k_proj): Linear(in_features=8192, out_features=8192, bias=False) (v_proj): Linear(in_features=8192, out_features=8192, bias=False) (o_proj): Linear(in_features=8192, out_features=8192, bias=False) (rotary_emb): LlamaRotaryEmbedding() ) (mlp): LlamaMLP( (gate_proj): Linear(in_features=8192, out_features=22016, bias=False) (down_proj): Linear(in_features=22016, out_features=8192, bias=False) (up_proj): Linear(in_features=8192, out_features=22016, bias=False) (act_fn): SiLUActivation() ) (input_layernorm): LlamaRMSNorm() (post_attention_layernorm): LlamaRMSNorm() ) ) (norm): LlamaRMSNorm() ) (lm_head): Linear(in_features=8192, out_features=32000, bias=False) ) ``` ## Model Configuration ```json LlamaConfig { "_name_or_path": "h2oai/h2ogpt-research-oasst1-llama-65b", "architectures": [ "LlamaForCausalLM" ], "bos_token_id": 0, "custom_pipelines": { "text-generation": { "impl": "h2oai_pipeline.H2OTextGenerationPipeline", "pt": "AutoModelForCausalLM" } }, "eos_token_id": 1, "hidden_act": "silu", "hidden_size": 8192, "initializer_range": 0.02, "intermediate_size": 22016, "max_position_embeddings": 2048, "max_sequence_length": 2048, "model_type": "llama", "num_attention_heads": 64, "num_hidden_layers": 80, "pad_token_id": -1, "rms_norm_eps": 1e-05, "tie_word_embeddings": false, "torch_dtype": "float16", "transformers_version": "4.30.1", "use_cache": true, "vocab_size": 32000 } ``` ## Model Validation Model validation results using [EleutherAI lm-evaluation-harness](https://github.com/EleutherAI/lm-evaluation-harness). TBD ## Disclaimer Please read this disclaimer carefully before using the large language model provided in this repository. Your use of the model signifies your agreement to the following terms and conditions. - Biases and Offensiveness: The large language model is trained on a diverse range of internet text data, which may contain biased, racist, offensive, or otherwise inappropriate content. By using this model, you acknowledge and accept that the generated content may sometimes exhibit biases or produce content that is offensive or inappropriate. The developers of this repository do not endorse, support, or promote any such content or viewpoints. - Limitations: The large language model is an AI-based tool and not a human. It may produce incorrect, nonsensical, or irrelevant responses. It is the user's responsibility to critically evaluate the generated content and use it at their discretion. - Use at Your Own Risk: Users of this large language model must assume full responsibility for any consequences that may arise from their use of the tool. The developers and contributors of this repository shall not be held liable for any damages, losses, or harm resulting from the use or misuse of the provided model. - Ethical Considerations: Users are encouraged to use the large language model responsibly and ethically. By using this model, you agree not to use it for purposes that promote hate speech, discrimination, harassment, or any form of illegal or harmful activities. - Reporting Issues: If you encounter any biased, offensive, or otherwise inappropriate content generated by the large language model, please report it to the repository maintainers through the provided channels. Your feedback will help improve the model and mitigate potential issues. - Changes to this Disclaimer: The developers of this repository reserve the right to modify or update this disclaimer at any time without prior notice. It is the user's responsibility to periodically review the disclaimer to stay informed about any changes. By using the large language model provided in this repository, you agree to accept and comply with the terms and conditions outlined in this disclaimer. If you do not agree with any part of this disclaimer, you should refrain from using the model and any content generated by it.
aroot/eng-fra-wsample.32a
aroot
2023-07-06T03:04:47Z
108
0
transformers
[ "transformers", "pytorch", "tensorboard", "mbart", "text2text-generation", "translation", "generated_from_trainer", "autotrain_compatible", "endpoints_compatible", "region:us" ]
translation
2023-07-06T02:44:41Z
--- tags: - translation - generated_from_trainer metrics: - bleu model-index: - name: eng-fra-wsample.32a 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. --> # eng-fra-wsample.32a This model is a fine-tuned version of [facebook/mbart-large-50-many-to-many-mmt](https://huggingface.co/facebook/mbart-large-50-many-to-many-mmt) on the None dataset. It achieves the following results on the evaluation set: - Loss: 1.1237 - Bleu: 32.9191 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 2e-05 - train_batch_size: 32 - eval_batch_size: 32 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 3 - mixed_precision_training: Native AMP ### Training results ### Framework versions - Transformers 4.26.1 - Pytorch 2.0.1+cu117 - Datasets 2.12.0 - Tokenizers 0.13.3
Bellaaazzzzz/models_fill
Bellaaazzzzz
2023-07-06T02:41:19Z
1
0
diffusers
[ "diffusers", "tensorboard", "stable-diffusion", "stable-diffusion-diffusers", "text-to-image", "controlnet", "base_model:runwayml/stable-diffusion-v1-5", "base_model:adapter:runwayml/stable-diffusion-v1-5", "license:creativeml-openrail-m", "region:us" ]
text-to-image
2023-07-06T02:35:57Z
--- license: creativeml-openrail-m base_model: runwayml/stable-diffusion-v1-5 tags: - stable-diffusion - stable-diffusion-diffusers - text-to-image - diffusers - controlnet inference: true --- # controlnet-Bellaaazzzzz/models_fill These are controlnet weights trained on runwayml/stable-diffusion-v1-5 with new type of conditioning. You can find some example images below. Validation result of 1 round. ![images_0_0)](./images_0_0.png) Validation result of 2 round. ![images_1_0)](./images_1_0.png)
csikasote/wav2vec2-large-mms-1b-bem-colab
csikasote
2023-07-06T02:40:47Z
9
0
transformers
[ "transformers", "pytorch", "tensorboard", "wav2vec2", "automatic-speech-recognition", "generated_from_trainer", "base_model:facebook/mms-1b-all", "base_model:finetune:facebook/mms-1b-all", "license:cc-by-nc-4.0", "endpoints_compatible", "region:us" ]
automatic-speech-recognition
2023-07-05T22:46:43Z
--- license: cc-by-nc-4.0 base_model: facebook/mms-1b-all tags: - generated_from_trainer metrics: - wer model-index: - name: wav2vec2-large-mms-1b-bem-colab 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. --> # wav2vec2-large-mms-1b-bem-colab This model is a fine-tuned version of [facebook/mms-1b-all](https://huggingface.co/facebook/mms-1b-all) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 0.1638 - Wer: 0.3223 ## 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: 0.001 - 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: 200 - num_epochs: 10 ### Training results | Training Loss | Epoch | Step | Validation Loss | Wer | |:-------------:|:-----:|:----:|:---------------:|:------:| | 2.2095 | 1.03 | 200 | 0.2066 | 0.3850 | | 0.4028 | 2.06 | 400 | 0.1861 | 0.3539 | | 0.3751 | 3.09 | 600 | 0.1781 | 0.3417 | | 0.3631 | 4.12 | 800 | 0.1739 | 0.3392 | | 0.3481 | 5.15 | 1000 | 0.1688 | 0.3340 | | 0.3391 | 6.19 | 1200 | 0.1690 | 0.3319 | | 0.3301 | 7.22 | 1400 | 0.1654 | 0.3285 | | 0.3237 | 8.25 | 1600 | 0.1667 | 0.3262 | | 0.3186 | 9.28 | 1800 | 0.1638 | 0.3223 | ### Framework versions - Transformers 4.31.0.dev0 - Pytorch 2.0.1+cu118 - Datasets 2.13.1 - Tokenizers 0.13.3
saintzeno/a2c-AntBulletEnv-v0
saintzeno
2023-07-06T02:12:44Z
2
0
stable-baselines3
[ "stable-baselines3", "AntBulletEnv-v0", "deep-reinforcement-learning", "reinforcement-learning", "model-index", "region:us" ]
reinforcement-learning
2023-07-06T01:49:03Z
--- 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: 1201.73 +/- 71.71 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 ... ```
Huggingfly/Reinforce-Cartpole-v1
Huggingfly
2023-07-06T01:38:51Z
0
0
null
[ "CartPole-v1", "reinforce", "reinforcement-learning", "custom-implementation", "deep-rl-class", "model-index", "region:us" ]
reinforcement-learning
2023-07-06T01:38:41Z
--- tags: - CartPole-v1 - reinforce - reinforcement-learning - custom-implementation - deep-rl-class model-index: - name: Reinforce-Cartpole-v1 results: - task: type: reinforcement-learning name: reinforcement-learning dataset: name: CartPole-v1 type: CartPole-v1 metrics: - type: mean_reward value: 500.00 +/- 0.00 name: mean_reward verified: false --- # **Reinforce** Agent playing **CartPole-v1** This is a trained model of a **Reinforce** agent playing **CartPole-v1** . To learn to use this model and train yours check Unit 4 of the Deep Reinforcement Learning Course: https://huggingface.co/deep-rl-course/unit4/introduction
geovani2006/openchatgpt
geovani2006
2023-07-06T01:14:01Z
0
0
null
[ "license:bigscience-openrail-m", "region:us" ]
null
2023-07-06T01:14:01Z
--- license: bigscience-openrail-m ---
anujsahani01/finetuned_Mbart_mr_en
anujsahani01
2023-07-06T01:08:06Z
120
0
transformers
[ "transformers", "pytorch", "safetensors", "mbart", "text2text-generation", "generated_from_trainer", "license:mit", "autotrain_compatible", "endpoints_compatible", "region:us" ]
text2text-generation
2023-07-05T17:34:56Z
--- license: mit tags: - generated_from_trainer model-index: - name: finetuned_Mbart_mr_en results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # finetuned_Mbart_mr_en This model is a fine-tuned version of [facebook/mbart-large-50](https://huggingface.co/facebook/mbart-large-50) 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: 0.0005 - train_batch_size: 12 - eval_batch_size: 12 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_steps: 50 - training_steps: 10000 ### Training results ### Framework versions - Transformers 4.30.2 - Pytorch 2.0.1+cu118 - Datasets 2.13.1 - Tokenizers 0.13.3
dmatekenya/whisper-small_finetuned_sw_chich
dmatekenya
2023-07-06T00:54:56Z
4
0
transformers
[ "transformers", "pytorch", "tensorboard", "whisper", "automatic-speech-recognition", "generated_from_trainer", "base_model:openai/whisper-small", "base_model:finetune:openai/whisper-small", "license:apache-2.0", "endpoints_compatible", "region:us" ]
automatic-speech-recognition
2023-07-05T20:02:12Z
--- license: apache-2.0 base_model: openai/whisper-small tags: - generated_from_trainer metrics: - wer model-index: - name: whisper-small_finetuned_sw_chich results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # whisper-small_finetuned_sw_chich This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the None dataset. It achieves the following results on the evaluation set: - Loss: 1.7430 - Wer: 80.1992 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 1e-05 - train_batch_size: 16 - eval_batch_size: 16 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: constant_with_warmup - lr_scheduler_warmup_steps: 50 - training_steps: 2000 ### Training results | Training Loss | Epoch | Step | Validation Loss | Wer | |:-------------:|:-----:|:----:|:---------------:|:-------:| | 0.0324 | 4.39 | 500 | 1.5624 | 84.6754 | | 0.0151 | 8.77 | 1000 | 1.6639 | 82.4073 | | 0.0099 | 13.16 | 1500 | 1.7377 | 78.8912 | | 0.0081 | 17.54 | 2000 | 1.7430 | 80.1992 | ### Framework versions - Transformers 4.31.0.dev0 - Pytorch 2.0.1+cu118 - Datasets 2.13.1 - Tokenizers 0.13.3
jeffreykthomas/bloom-7b-fine-tuned-stanford
jeffreykthomas
2023-07-06T00:51:45Z
3
0
transformers
[ "transformers", "pytorch", "bloom", "question-answering", "license:bigscience-openrail-m", "text-generation-inference", "endpoints_compatible", "region:us" ]
question-answering
2023-06-30T21:42:30Z
--- license: bigscience-openrail-m ---
chaudha7/DiaryFlow
chaudha7
2023-07-06T00:49:49Z
0
0
null
[ "region:us" ]
null
2023-07-06T00:43:32Z
### Model Description This is a fine-tuned Bloom-7b model. It was a demo project which I wanted to try to alleviate the seriousness and rapid pace around the "LLM" usecases. This model has been trained on a custom chatGPT-created dataset (https://huggingface.co/datasets/chaudha7/Diary-Entry-To-Rap) which turns diary entries into short rap songs with a motivational ending. Just something fun for the users. ### Developed by: Aashay Chaudhari ## Training procedure The following `bits and bytes` quantization config was used during training: - load_in_8bit: True - load_in_4bit: False - llm_int8_threshold: 6.0 - llm_int8_skip_modules: None - llm_int8_enable_fp32_cpu_offload: False - llm_int8_has_fp16_weight: False - bnb_4bit_quant_type: fp4 - bnb_4bit_use_double_quant: False - bnb_4bit_compute_dtype: float32 ### Framework versions ### Results ### Input: Dear Diary, Oh boy, today was such an incredible day! I woke up with a burst of excitement in my heart because it was my birthday! Double digits, baby! Mom and Dad surprised me with a brand new bike, just like the one I've been dreaming about for ages. We went for a ride in the park, and I felt like I was flying! My friends came over for a super fun party, and we played games, danced, and laughed until our tummies hurt. Grandma baked the most delicious chocolate cake, and I blew out all the candles with one big breath. The best part? I got some awesome presents, like a shiny diary (just like you, Diary!), art supplies, and a book about adventures. I can't wait to read it tonight! Tonight, as I snuggle under my cozy blanket, I can't help but feel so grateful for the love and joy that surrounds me. Being 10 feels amazing, Diary. I can't wait to see what other incredible adventures await me this year! Until tomorrow, Emily ### Output: (Verse) Today's my birthday, feeling so alive, Double digits, yo, I'm ready to strive. Got a brand-new bike, flying through the air, Riding in the park, without a single care. Friends came over, we had a blast, Playing games, dancing, memories that'll last. Grandma's chocolate cake, candles all aglow, Blowing them out, a wish ready to grow. Shiny diary, art supplies, and books, Unleashing my creativity, no limits, no hooks. Grateful for love and joy, can't help but smile, Ten years old, embracing life's every mile. (Motivational Ending) No matter the age, dreams light up the way, Believe in yourself, make the most of today. Adventures await, with each step you take, Keep shining, keep growing, there's no limit to what you'll make.
CalamitousVisibility/UK_Energy_Industry_Complaints_Identifier_ver1
CalamitousVisibility
2023-07-06T00:28:38Z
109
0
transformers
[ "transformers", "pytorch", "distilbert", "text-classification", "generated_from_trainer", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]
text-classification
2023-07-05T22:24:13Z
--- license: apache-2.0 tags: - generated_from_trainer metrics: - accuracy - f1 model-index: - name: UK_Energy_Industry_Complaints_Identifier_ver1 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. --> # UK_Energy_Industry_Complaints_Identifier_ver1 This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on a balanced dataset consisting of 17,620 publicy available customer reviews of various domestic energy suppliers in the United Kingdom. It achieves the following results on the evaluation set: - Loss: 0.3369 - Accuracy: 0.9561 - F1: [0.95594347 0.95621041] ## 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: 4 - eval_batch_size: 4 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 4 ### Training results ### Framework versions - Transformers 4.28.1 - Pytorch 2.0.1 - Datasets 2.13.1 - Tokenizers 0.11.0
Lucas-lab/distilbert-base-uncased-finetuned-cola
Lucas-lab
2023-07-06T00:13:07Z
61
0
transformers
[ "transformers", "tf", "tensorboard", "distilbert", "text-classification", "generated_from_keras_callback", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]
text-classification
2023-07-02T20:28:15Z
--- license: apache-2.0 tags: - generated_from_keras_callback model-index: - name: Lucas-lab/distilbert-base-uncased-finetuned-cola 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. --> # Lucas-lab/distilbert-base-uncased-finetuned-cola This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset. It achieves the following results on the evaluation set: - Train Loss: 0.1848 - Validation Loss: 0.5885 - Train Matthews Correlation: 0.5019 - Epoch: 2 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - optimizer: {'name': 'Adam', 'weight_decay': None, 'clipnorm': None, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': True, 'is_legacy_optimizer': False, 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 1602, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}}, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False} - training_precision: float32 ### Training results | Train Loss | Validation Loss | Train Matthews Correlation | Epoch | |:----------:|:---------------:|:--------------------------:|:-----:| | 0.5153 | 0.4879 | 0.4331 | 0 | | 0.3121 | 0.5405 | 0.4874 | 1 | | 0.1848 | 0.5885 | 0.5019 | 2 | ### Framework versions - Transformers 4.30.2 - TensorFlow 2.12.0 - Datasets 2.13.1 - Tokenizers 0.13.3
eluzhnica/mpt-7b-instruct-peft-compatible
eluzhnica
2023-07-05T23:35:23Z
18
0
transformers
[ "transformers", "pytorch", "mpt", "text-generation", "Composer", "MosaicML", "llm-foundry", "custom_code", "dataset:mosaicml/dolly_hhrlhf", "arxiv:2205.14135", "arxiv:2108.12409", "arxiv:2010.04245", "license:cc-by-sa-3.0", "autotrain_compatible", "text-generation-inference", "region:us" ]
text-generation
2023-07-05T23:14:18Z
--- license: cc-by-sa-3.0 datasets: - mosaicml/dolly_hhrlhf tags: - Composer - MosaicML - llm-foundry inference: false --- # MPT-7B-Instruct This is the MPT-7B-Instruct but with added support to finetune using peft (tested with qlora). It is not finetuned further, the weights are the same as the original MPT-7B-Instruct. I have not traced through the whole huggingface stack to see if this is working correctly but it does finetune with qlora and outputs are reasonable. Inspired by implementations here https://huggingface.co/cekal/mpt-7b-peft-compatible/commits/main https://huggingface.co/mosaicml/mpt-7b/discussions/42. The original description for MosaicML team below: MPT-7B-Instruct is a model for short-form instruction following. It is built by finetuning [MPT-7B](https://huggingface.co/mosaicml/mpt-7b) on a [dataset](https://huggingface.co/datasets/sam-mosaic/dolly_hhrlhf) derived from the [Databricks Dolly-15k](https://huggingface.co/datasets/databricks/databricks-dolly-15k) and the [Anthropic Helpful and Harmless (HH-RLHF)](https://huggingface.co/datasets/Anthropic/hh-rlhf) datasets. * License: _CC-By-SA-3.0_ * [Demo on Hugging Face Spaces](https://huggingface.co/spaces/mosaicml/mpt-7b-instruct) This model was trained by [MosaicML](https://www.mosaicml.com) and follows a modified decoder-only transformer architecture. ## Model Date May 5, 2023 ## Model License CC-By-SA-3.0 ## Documentation * [Blog post: Introducing MPT-7B: A New Standard for Open-Source, Commercially Usable LLMs](https://www.mosaicml.com/blog/mpt-7b) * [Codebase (mosaicml/llm-foundry repo)](https://github.com/mosaicml/llm-foundry/) * Questions: Feel free to contact us via the [MosaicML Community Slack](https://mosaicml.me/slack)! ### Example Question/Instruction **Longboi24**: > What is a quoll? **MPT-7B-Instruct**: >A Quoll (pronounced “cool”) is one of Australia’s native carnivorous marsupial mammals, which are also known as macropods or wallabies in other parts around Asia and South America ## How to Use Note: This model requires that `trust_remote_code=True` be passed to the `from_pretrained` method. This is because we use a custom model architecture that is not yet part of the `transformers` package. It includes options for many training efficiency features such as [FlashAttention (Dao et al. 2022)](https://arxiv.org/pdf/2205.14135.pdf), [ALiBi](https://arxiv.org/abs/2108.12409), QK LayerNorm, and more. ```python import transformers model = transformers.AutoModelForCausalLM.from_pretrained( 'mosaicml/mpt-7b-instruct', trust_remote_code=True ) ``` Note: This model requires that `trust_remote_code=True` be passed to the `from_pretrained` method. This is because we use a custom `MPT` model architecture that is not yet part of the Hugging Face `transformers` package. `MPT` includes options for many training efficiency features such as [FlashAttention](https://arxiv.org/pdf/2205.14135.pdf), [ALiBi](https://arxiv.org/abs/2108.12409), [QK LayerNorm](https://arxiv.org/abs/2010.04245), and more. To use the optimized [triton implementation](https://github.com/openai/triton) of FlashAttention, you can load the model on GPU (`cuda:0`) with `attn_impl='triton'` and with `bfloat16` precision: ```python import torch import transformers name = 'mosaicml/mpt-7b-instruct' config = transformers.AutoConfig.from_pretrained(name, trust_remote_code=True) config.attn_config['attn_impl'] = 'triton' config.init_device = 'cuda:0' # For fast initialization directly on GPU! model = transformers.AutoModelForCausalLM.from_pretrained( name, config=config, torch_dtype=torch.bfloat16, # Load model weights in bfloat16 trust_remote_code=True ) ``` Although the model was trained with a sequence length of 2048, ALiBi enables users to increase the maximum sequence length during finetuning and/or inference. For example: ```python import transformers name = 'mosaicml/mpt-7b-instruct' config = transformers.AutoConfig.from_pretrained(name, trust_remote_code=True) config.max_seq_len = 4096 # (input + output) tokens can now be up to 4096 model = transformers.AutoModelForCausalLM.from_pretrained( name, config=config, trust_remote_code=True ) ``` This model was trained with the [EleutherAI/gpt-neox-20b](https://huggingface.co/EleutherAI/gpt-neox-20b) tokenizer. ```python from transformers import AutoTokenizer tokenizer = AutoTokenizer.from_pretrained("EleutherAI/gpt-neox-20b") ``` The model can then be used, for example, within a text-generation pipeline. Note: when running Torch modules in lower precision, it is best practice to use the [torch.autocast context manager](https://pytorch.org/docs/stable/amp.html). ```python from transformers import pipeline pipe = pipeline('text-generation', model=model, tokenizer=tokenizer, device='cuda:0') with torch.autocast('cuda', dtype=torch.bfloat16): print( pipe('Here is a recipe for vegan banana bread:\n', max_new_tokens=100, do_sample=True, use_cache=True)) ``` ### Formatting This model was trained on data formatted in the dolly-15k format: ```python INSTRUCTION_KEY = "### Instruction:" RESPONSE_KEY = "### Response:" INTRO_BLURB = "Below is an instruction that describes a task. Write a response that appropriately completes the request." PROMPT_FOR_GENERATION_FORMAT = """{intro} {instruction_key} {instruction} {response_key} """.format( intro=INTRO_BLURB, instruction_key=INSTRUCTION_KEY, instruction="{instruction}", response_key=RESPONSE_KEY, ) example = "James decides to run 3 sprints 3 times a week. He runs 60 meters each sprint. How many total meters does he run a week? Explain before answering." fmt_ex = PROMPT_FOR_GENERATION_FORMAT.format(instruction=example) ``` In the above example, `fmt_ex` is ready to be tokenized and sent through the model. ## Model Description The architecture is a modification of a standard decoder-only transformer. The model has been modified from a standard transformer in the following ways: * It uses [FlashAttention](https://arxiv.org/pdf/2205.14135.pdf) * It uses [ALiBi (Attention with Linear Biases)](https://arxiv.org/abs/2108.12409) and does not use positional embeddings * It does not use biases | Hyperparameter | Value | |----------------|-------| |n_parameters | 6.7B | |n_layers | 32 | | n_heads | 32 | | d_model | 4096 | | vocab size | 50432 | | sequence length | 2048 | ## PreTraining Data For more details on the pretraining process, see [MPT-7B](https://huggingface.co/mosaicml/mpt-7b). The data was tokenized using the [EleutherAI/gpt-neox-20b](https://huggingface.co/EleutherAI/gpt-neox-20b) tokenizer. ### Training Configuration This model was trained on 8 A100-40GBs for about 2.3 hours using the [MosaicML Platform](https://www.mosaicml.com/platform). The model was trained with sharded data parallelism using [FSDP](https://pytorch.org/docs/stable/fsdp.html) and used the AdamW optimizer. ## Limitations and Biases _The following language is modified from [EleutherAI's GPT-NeoX-20B](https://huggingface.co/EleutherAI/gpt-neox-20b)_ MPT-7B-Instruct can produce factually incorrect output, and should not be relied on to produce factually accurate information. MPT-7B-Instruct was trained on various public datasets. While great efforts have been taken to clean the pretraining data, it is possible that this model could generate lewd, biased or otherwise offensive outputs. ## Acknowledgements This model was finetuned by Sam Havens and the MosaicML NLP team ## MosaicML Platform If you're interested in [training](https://www.mosaicml.com/training) and [deploying](https://www.mosaicml.com/inference) your own MPT or LLMs on the MosaicML Platform, [sign up here](https://forms.mosaicml.com/demo?utm_source=huggingface&utm_medium=referral&utm_campaign=mpt-7b). ## Disclaimer The license on this model does not constitute legal advice. We are not responsible for the actions of third parties who use this model. Please cosult an attorney before using this model for commercial purposes. ## Citation Please cite this model using the following format: ``` @online{MosaicML2023Introducing, author = {MosaicML NLP Team}, title = {Introducing MPT-7B: A New Standard for Open-Source, Commercially Usable LLMs}, year = {2023}, url = {www.mosaicml.com/blog/mpt-7b}, note = {Accessed: 2023-03-28}, % change this date urldate = {2023-03-28} % change this date } ```
ahmedALM1221/swinv2-large-patch4-window12to16-192to256-22kto1k-ft-finetuned-eurosat-50
ahmedALM1221
2023-07-05T23:21:55Z
7
0
transformers
[ "transformers", "pytorch", "tensorboard", "swinv2", "image-classification", "generated_from_trainer", "dataset:imagefolder", "license:apache-2.0", "model-index", "autotrain_compatible", "endpoints_compatible", "region:us" ]
image-classification
2023-07-04T18:45:38Z
--- license: apache-2.0 tags: - generated_from_trainer datasets: - imagefolder metrics: - accuracy model-index: - name: swinv2-large-patch4-window12to16-192to256-22kto1k-ft-finetuned-eurosat-50 results: - task: name: Image Classification type: image-classification dataset: name: imagefolder type: imagefolder config: Augmented-Final split: train args: Augmented-Final metrics: - name: Accuracy type: accuracy value: 0.9753340184994861 --- <!-- 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. --> # swinv2-large-patch4-window12to16-192to256-22kto1k-ft-finetuned-eurosat-50 This model is a fine-tuned version of [microsoft/swinv2-large-patch4-window12to16-192to256-22kto1k-ft](https://huggingface.co/microsoft/swinv2-large-patch4-window12to16-192to256-22kto1k-ft) on the imagefolder dataset. It achieves the following results on the evaluation set: - Loss: 0.0909 - Accuracy: 0.9753 ## 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-06 - train_batch_size: 16 - eval_batch_size: 16 - seed: 42 - gradient_accumulation_steps: 2 - total_train_batch_size: 32 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_ratio: 0.9 - num_epochs: 12 ### Training results | Training Loss | Epoch | Step | Validation Loss | Accuracy | |:-------------:|:-----:|:----:|:---------------:|:--------:| | 2.0236 | 1.0 | 122 | 1.9878 | 0.1305 | | 1.88 | 2.0 | 244 | 1.7957 | 0.2867 | | 1.5421 | 3.0 | 366 | 1.3813 | 0.5149 | | 0.9489 | 4.0 | 488 | 0.9015 | 0.7030 | | 0.8734 | 5.0 | 610 | 0.6616 | 0.7667 | | 0.6562 | 6.0 | 732 | 0.5095 | 0.8140 | | 0.5788 | 7.0 | 854 | 0.4036 | 0.8520 | | 0.6737 | 8.0 | 976 | 0.3157 | 0.8921 | | 0.4687 | 9.0 | 1098 | 0.2146 | 0.9281 | | 0.3775 | 10.0 | 1220 | 0.2020 | 0.9353 | | 0.3226 | 11.0 | 1342 | 0.1549 | 0.9558 | | 0.2452 | 12.0 | 1464 | 0.0909 | 0.9753 | ### Framework versions - Transformers 4.30.2 - Pytorch 2.0.1+cu118 - Datasets 2.13.1 - Tokenizers 0.13.3
hopkins/eng-mya-simcse.near2.4440
hopkins
2023-07-05T22:49:46Z
103
0
transformers
[ "transformers", "pytorch", "tensorboard", "mbart", "text2text-generation", "translation", "generated_from_trainer", "autotrain_compatible", "endpoints_compatible", "region:us" ]
translation
2023-07-05T22:28:28Z
--- tags: - translation - generated_from_trainer metrics: - bleu model-index: - name: eng-mya-simcse.near2.4440 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. --> # eng-mya-simcse.near2.4440 This model is a fine-tuned version of [facebook/mbart-large-50-many-to-many-mmt](https://huggingface.co/facebook/mbart-large-50-many-to-many-mmt) on the None dataset. It achieves the following results on the evaluation set: - Loss: 1.8502 - Bleu: 4.8797 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 2e-05 - train_batch_size: 32 - eval_batch_size: 32 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 3 - mixed_precision_training: Native AMP ### Training results ### Framework versions - Transformers 4.26.1 - Pytorch 2.0.1+cu117 - Datasets 2.12.0 - Tokenizers 0.13.3
hopkins/eng-mya-simcse.dev2.4440
hopkins
2023-07-05T22:46:19Z
104
0
transformers
[ "transformers", "pytorch", "tensorboard", "mbart", "text2text-generation", "translation", "generated_from_trainer", "autotrain_compatible", "endpoints_compatible", "region:us" ]
translation
2023-07-05T22:24:42Z
--- tags: - translation - generated_from_trainer metrics: - bleu model-index: - name: eng-mya-simcse.dev2.4440 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. --> # eng-mya-simcse.dev2.4440 This model is a fine-tuned version of [facebook/mbart-large-50-many-to-many-mmt](https://huggingface.co/facebook/mbart-large-50-many-to-many-mmt) on the None dataset. It achieves the following results on the evaluation set: - Loss: 1.8287 - Bleu: 4.8012 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 2e-05 - train_batch_size: 32 - eval_batch_size: 32 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 3 - mixed_precision_training: Native AMP ### Training results ### Framework versions - Transformers 4.26.1 - Pytorch 2.0.1+cu117 - Datasets 2.12.0 - Tokenizers 0.13.3
spacemanidol/flan-t5-large-xsum
spacemanidol
2023-07-05T22:16:56Z
106
2
transformers
[ "transformers", "pytorch", "safetensors", "t5", "text2text-generation", "generated_from_trainer", "dataset:xsum", "license:apache-2.0", "model-index", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]
text2text-generation
2023-02-17T21:56:26Z
--- license: apache-2.0 tags: - generated_from_trainer datasets: - xsum metrics: - rouge model-index: - name: large results: - task: name: Summarization type: summarization dataset: name: xsum type: xsum config: default split: validation args: default metrics: - name: Rouge1 type: rouge value: 39.7125 --- <!-- 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. --> # large This model is a fine-tuned version of [google/flan-t5-large](https://huggingface.co/google/flan-t5-large) on the xsum dataset. It achieves the following results on the evaluation set: - Loss: nan - Rouge1: 39.7125 - Rouge2: 16.3418 - Rougel: 31.7246 - Rougelsum: 31.7214 - Gen Len: 26.7397 ## 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: 8 - eval_batch_size: 16 - seed: 42 - gradient_accumulation_steps: 8 - total_train_batch_size: 64 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: constant - num_epochs: 3.0 - mixed_precision_training: Native AMP ### Training results ### Framework versions - Transformers 4.27.0.dev0 - Pytorch 1.9.0+cu111 - Datasets 2.5.1 - Tokenizers 0.12.1
asenella/mmnist_MMVAEPlusconfig_resnet_seed_0_ratio_0_c
asenella
2023-07-05T22:07:37Z
0
0
null
[ "multivae", "en", "license:apache-2.0", "region:us" ]
null
2023-07-05T22:07:20Z
--- 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") ```
hopkins/eng-guj-simcse.dev2.4440
hopkins
2023-07-05T22:04:11Z
104
0
transformers
[ "transformers", "pytorch", "tensorboard", "mbart", "text2text-generation", "translation", "generated_from_trainer", "autotrain_compatible", "endpoints_compatible", "region:us" ]
translation
2023-07-05T21:47:27Z
--- tags: - translation - generated_from_trainer metrics: - bleu model-index: - name: eng-guj-simcse.dev2.4440 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. --> # eng-guj-simcse.dev2.4440 This model is a fine-tuned version of [facebook/mbart-large-50-many-to-many-mmt](https://huggingface.co/facebook/mbart-large-50-many-to-many-mmt) on the None dataset. It achieves the following results on the evaluation set: - Loss: 3.2375 - Bleu: 2.9236 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 2e-05 - train_batch_size: 32 - eval_batch_size: 32 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 3 - mixed_precision_training: Native AMP ### Training results ### Framework versions - Transformers 4.26.1 - Pytorch 2.0.1+cu117 - Datasets 2.12.0 - Tokenizers 0.13.3
nekoboost/ppo-LunarLander-v2
nekoboost
2023-07-05T21:58:49Z
1
0
stable-baselines3
[ "stable-baselines3", "LunarLander-v2", "deep-reinforcement-learning", "reinforcement-learning", "model-index", "region:us" ]
reinforcement-learning
2023-07-05T21:58:34Z
--- 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: -202.98 +/- 120.09 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 ... ```
josero23/irrut
josero23
2023-07-05T21:55:44Z
1
0
diffusers
[ "diffusers", "safetensors", "text-to-image", "stable-diffusion", "license:creativeml-openrail-m", "autotrain_compatible", "endpoints_compatible", "diffusers:StableDiffusionPipeline", "region:us" ]
text-to-image
2023-07-05T21:42:44Z
--- license: creativeml-openrail-m tags: - text-to-image - stable-diffusion --- ### irrut Dreambooth model trained by josero23 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:
newconew/speecht5_finetuned_voxpopuli_nl
newconew
2023-07-05T21:55:25Z
80
0
transformers
[ "transformers", "pytorch", "tensorboard", "speecht5", "text-to-audio", "generated_from_trainer", "dataset:voxpopuli", "base_model:microsoft/speecht5_tts", "base_model:finetune:microsoft/speecht5_tts", "license:mit", "endpoints_compatible", "region:us" ]
text-to-audio
2023-07-05T19:33:24Z
--- license: mit base_model: microsoft/speecht5_tts tags: - generated_from_trainer datasets: - voxpopuli model-index: - name: speecht5_finetuned_voxpopuli_nl results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # speecht5_finetuned_voxpopuli_nl This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on the voxpopuli dataset. It achieves the following results on the evaluation set: - Loss: 0.4612 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 1e-05 - train_batch_size: 4 - eval_batch_size: 2 - seed: 42 - gradient_accumulation_steps: 8 - total_train_batch_size: 32 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_steps: 500 - training_steps: 4000 ### Training results | Training Loss | Epoch | Step | Validation Loss | |:-------------:|:-----:|:----:|:---------------:| | 0.5194 | 4.3 | 1000 | 0.4806 | | 0.494 | 8.61 | 2000 | 0.4670 | | 0.4929 | 12.91 | 3000 | 0.4642 | | 0.4914 | 17.21 | 4000 | 0.4612 | ### Framework versions - Transformers 4.31.0.dev0 - Pytorch 2.0.1+cu118 - Datasets 2.13.1 - Tokenizers 0.13.3
Deigant/t5-base-daily-dialog-finetuned-1
Deigant
2023-07-05T21:51:36Z
105
0
transformers
[ "transformers", "pytorch", "tensorboard", "t5", "text2text-generation", "generated_from_trainer", "license:apache-2.0", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]
text2text-generation
2023-07-05T20:43:31Z
--- license: apache-2.0 tags: - generated_from_trainer model-index: - name: t5-base-daily-dialog-finetuned-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. --> # t5-base-daily-dialog-finetuned-1 This model is a fine-tuned version of [t5-base](https://huggingface.co/t5-base) on the None dataset. It achieves the following results on the evaluation set: - eval_loss: 0.6520 - eval_runtime: 29.7693 - eval_samples_per_second: 271.051 - eval_steps_per_second: 16.964 - epoch: 0.83 - step: 4500 ## 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-06 - train_batch_size: 16 - eval_batch_size: 16 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_steps: 500 - num_epochs: 3 ### Framework versions - Transformers 4.30.2 - Pytorch 2.0.1+cu118 - Datasets 2.13.1 - Tokenizers 0.13.3
hopkins/eng-fra-simcse.dev2.4440
hopkins
2023-07-05T21:32:34Z
103
0
transformers
[ "transformers", "pytorch", "tensorboard", "mbart", "text2text-generation", "translation", "generated_from_trainer", "autotrain_compatible", "endpoints_compatible", "region:us" ]
translation
2023-07-05T21:12:42Z
--- tags: - translation - generated_from_trainer metrics: - bleu model-index: - name: eng-fra-simcse.dev2.4440 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. --> # eng-fra-simcse.dev2.4440 This model is a fine-tuned version of [facebook/mbart-large-50-many-to-many-mmt](https://huggingface.co/facebook/mbart-large-50-many-to-many-mmt) on the None dataset. It achieves the following results on the evaluation set: - Loss: 1.1146 - Bleu: 33.6862 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 2e-05 - train_batch_size: 32 - eval_batch_size: 32 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 3 - mixed_precision_training: Native AMP ### Training results ### Framework versions - Transformers 4.26.1 - Pytorch 2.0.1+cu117 - Datasets 2.12.0 - Tokenizers 0.13.3
jeffboudier/vision-transformers-spain-or-italy-fan
jeffboudier
2023-07-05T21:29:05Z
296
1
transformers
[ "transformers", "pytorch", "tensorboard", "safetensors", "vit", "image-classification", "huggingpics", "model-index", "autotrain_compatible", "endpoints_compatible", "region:us" ]
image-classification
2022-03-02T23:29:05Z
--- tags: - image-classification - pytorch - huggingpics metrics: - accuracy model-index: - name: vision-transformers--spain-or-italy-fan results: - task: name: Image Classification type: image-classification metrics: - name: Accuracy type: accuracy value: 0.5666666626930237 --- # vision-transformers--spain-or-italy-fan 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 #### italy soccer fan ![italy soccer fan](images/italy_soccer_fan.jpg) #### spain soccer fan ![spain soccer fan](images/spain_soccer_fan.jpg)
cleandata/whisper-small-dv
cleandata
2023-07-05T21:27:43Z
79
0
transformers
[ "transformers", "tensorboard", "safetensors", "whisper", "automatic-speech-recognition", "generated_from_trainer", "dv", "dataset:mozilla-foundation/common_voice_13_0", "license:apache-2.0", "model-index", "endpoints_compatible", "region:us" ]
automatic-speech-recognition
2023-07-05T20:25:03Z
--- language: - dv license: apache-2.0 tags: - generated_from_trainer datasets: - mozilla-foundation/common_voice_13_0 metrics: - wer model-index: - name: Whisper Small Dv - local results: - task: name: Automatic Speech Recognition type: automatic-speech-recognition dataset: name: Common Voice 13 type: mozilla-foundation/common_voice_13_0 config: dv split: test args: dv metrics: - name: Wer type: wer value: 13.245470668011267 --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # Whisper Small Dv This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the Common Voice 13 dataset. It achieves the following results on the evaluation set: - Loss: 0.1680 - Wer Ortho: 62.1074 - Wer: 13.2455 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 1e-05 - train_batch_size: 16 - eval_batch_size: 16 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: constant_with_warmup - lr_scheduler_warmup_steps: 50 - training_steps: 500 ### Training results | Training Loss | Epoch | Step | Validation Loss | Wer Ortho | Wer | |:-------------:|:-----:|:----:|:---------------:|:---------:|:-------:| | 0.1233 | 1.63 | 500 | 0.1680 | 62.1074 | 13.2455 | ### Framework versions - Transformers 4.30.2 - Pytorch 2.0.1+cu118 - Datasets 2.13.1 - Tokenizers 0.13.3
kejolong/kunoichi
kejolong
2023-07-05T21:23:28Z
0
0
null
[ "license:creativeml-openrail-m", "region:us" ]
null
2023-07-05T21:21:08Z
--- license: creativeml-openrail-m ---
KevinQuijano/model
KevinQuijano
2023-07-05T21:12:27Z
1
0
diffusers
[ "diffusers", "tensorboard", "stable-diffusion", "stable-diffusion-diffusers", "text-to-image", "dreambooth", "base_model:CompVis/stable-diffusion-v1-4", "base_model:finetune:CompVis/stable-diffusion-v1-4", "license:creativeml-openrail-m", "autotrain_compatible", "endpoints_compatible", "diffusers:StableDiffusionPipeline", "region:us" ]
text-to-image
2023-07-05T14:32:19Z
--- license: creativeml-openrail-m base_model: CompVis/stable-diffusion-v1-4 instance_prompt: a photo of sks dog tags: - stable-diffusion - stable-diffusion-diffusers - text-to-image - diffusers - dreambooth inference: true --- # DreamBooth - KevinQuijano/model This is a dreambooth model derived from CompVis/stable-diffusion-v1-4. The weights were trained on a photo of sks dog using [DreamBooth](https://dreambooth.github.io/). You can find some example images in the following. DreamBooth for the text encoder was enabled: False.
NasimB/gpt2-concat-aochiles-14k
NasimB
2023-07-05T20:51:07Z
5
0
transformers
[ "transformers", "pytorch", "gpt2", "text-generation", "generated_from_trainer", "dataset:generator", "license:mit", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]
text-generation
2023-07-05T18:35:59Z
--- license: mit tags: - generated_from_trainer datasets: - generator model-index: - name: gpt2-concat-aochiles-14k 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-concat-aochiles-14k This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on the generator dataset. It achieves the following results on the evaluation set: - Loss: 3.0042 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 64 - eval_batch_size: 64 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: cosine - lr_scheduler_warmup_steps: 1000 - num_epochs: 7 - mixed_precision_training: Native AMP ### Training results | Training Loss | Epoch | Step | Validation Loss | |:-------------:|:-----:|:-----:|:---------------:| | 6.7211 | 0.29 | 500 | 5.6349 | | 5.3799 | 0.59 | 1000 | 5.1983 | | 5.0235 | 0.88 | 1500 | 4.9554 | | 4.7478 | 1.18 | 2000 | 4.8045 | | 4.5979 | 1.47 | 2500 | 4.6854 | | 4.4961 | 1.76 | 3000 | 4.5843 | | 4.3569 | 2.06 | 3500 | 4.5164 | | 4.1739 | 2.35 | 4000 | 4.4680 | | 4.149 | 2.65 | 4500 | 4.4129 | | 4.1093 | 2.94 | 5000 | 4.3581 | | 3.8978 | 3.24 | 5500 | 4.3622 | | 3.8629 | 3.53 | 6000 | 4.3327 | | 3.8463 | 3.82 | 6500 | 4.3044 | | 3.726 | 4.12 | 7000 | 4.3127 | | 3.5714 | 4.41 | 7500 | 4.3116 | | 3.5846 | 4.71 | 8000 | 4.2872 | | 3.5668 | 5.0 | 8500 | 4.2693 | | 3.3167 | 5.29 | 9000 | 4.3073 | | 3.3274 | 5.59 | 9500 | 4.3060 | | 3.3202 | 5.88 | 10000 | 4.3010 | | 3.2207 | 6.18 | 10500 | 4.3137 | | 3.1707 | 6.47 | 11000 | 4.3147 | | 3.1663 | 6.76 | 11500 | 4.3166 | ### Framework versions - Transformers 4.26.1 - Pytorch 1.11.0+cu113 - Datasets 2.13.0 - Tokenizers 0.13.3
choward/csv
choward
2023-07-05T20:46:13Z
0
0
null
[ "text-generation", "region:us" ]
text-generation
2023-07-05T20:42:22Z
--- pipeline_tag: text-generation ---
Gaborandi/Clinical-Longformer-MLM-pubmed
Gaborandi
2023-07-05T20:42:18Z
107
0
transformers
[ "transformers", "pytorch", "tensorboard", "safetensors", "longformer", "fill-mask", "generated_from_trainer", "autotrain_compatible", "endpoints_compatible", "region:us" ]
fill-mask
2022-06-22T02:00:45Z
--- tags: - generated_from_trainer model-index: - name: Clinical-Longformer-MLM-pubmed 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. --> # Clinical-Longformer-MLM-pubmed This model is a fine-tuned version of [yikuan8/Clinical-Longformer](https://huggingface.co/yikuan8/Clinical-Longformer) on the None dataset. It achieves the following results on the evaluation set: - Loss: 1.3126 ## 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: 1 - eval_batch_size: 8 - seed: 42 - gradient_accumulation_steps: 4 - total_train_batch_size: 4 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 3.0 - mixed_precision_training: Native AMP ### Training results | Training Loss | Epoch | Step | Validation Loss | |:-------------:|:-----:|:----:|:---------------:| | No log | 1.0 | 471 | 1.3858 | | No log | 2.0 | 942 | 1.3160 | | No log | 3.0 | 1413 | 1.2951 | ### Framework versions - Transformers 4.17.0 - Pytorch 1.8.0 - Datasets 2.2.2 - Tokenizers 0.11.6
Gaborandi/Bert_news_classifier
Gaborandi
2023-07-05T20:42:02Z
118
0
transformers
[ "transformers", "pytorch", "safetensors", "bert", "text-classification", "autotrain_compatible", "endpoints_compatible", "region:us" ]
text-classification
2023-03-10T06:40:52Z
- Fine-tuned BERT model on news data - the model used this data: https://www.kaggle.com/datasets/sadikaljarif/fake-news-detection-dataset-english - the model achieved AUC score = 0.9990 with just 3 epochs
Gaborandi/MedBERT-breastcancer
Gaborandi
2023-07-05T20:41:38Z
54
0
transformers
[ "transformers", "pytorch", "tensorboard", "safetensors", "bert", "fill-mask", "generated_from_trainer", "license:mit", "autotrain_compatible", "endpoints_compatible", "region:us" ]
fill-mask
2022-12-31T18:51:41Z
--- license: mit tags: - generated_from_trainer model-index: - name: MedBERT-breastcancer 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. --> # MedBERT-breastcancer This model is a fine-tuned version of [Charangan/MedBERT](https://huggingface.co/Charangan/MedBERT) on the None dataset. It achieves the following results on the evaluation set: - Loss: 0.9742 ## 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: 1 - eval_batch_size: 8 - seed: 42 - gradient_accumulation_steps: 4 - total_train_batch_size: 4 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 4 - mixed_precision_training: Native AMP ### Training results | Training Loss | Epoch | Step | Validation Loss | |:-------------:|:-----:|:-----:|:---------------:| | No log | 1.0 | 12263 | 1.0881 | | No log | 2.0 | 24526 | 1.0259 | | No log | 3.0 | 36789 | 0.9937 | | No log | 4.0 | 49052 | 0.9831 | ### Framework versions - Transformers 4.25.1 - Pytorch 1.8.0 - Datasets 2.2.2 - Tokenizers 0.13.2
egarciamartin/poca-SoccerTwos
egarciamartin
2023-07-05T20:40:50Z
0
0
ml-agents
[ "ml-agents", "tensorboard", "onnx", "SoccerTwos", "deep-reinforcement-learning", "reinforcement-learning", "ML-Agents-SoccerTwos", "region:us" ]
reinforcement-learning
2023-07-05T20:40:07Z
--- library_name: ml-agents tags: - SoccerTwos - deep-reinforcement-learning - reinforcement-learning - ML-Agents-SoccerTwos --- # **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://unity-technologies.github.io/ml-agents/ML-Agents-Toolkit-Documentation/ We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub: - A *short tutorial* where you teach Huggy the Dog 🐶 to fetch the stick and then play with him directly in your browser: https://huggingface.co/learn/deep-rl-course/unitbonus1/introduction - A *longer tutorial* to understand how works ML-Agents: https://huggingface.co/learn/deep-rl-course/unit5/introduction ### Resume the training ```bash mlagents-learn <your_configuration_file_path.yaml> --run-id=<run_id> --resume ``` ### Watch your Agent play You can watch your agent **playing directly in your browser** 1. If the environment is part of ML-Agents official environments, go to https://huggingface.co/unity 2. Step 1: Find your model_id: egarciamartin/poca-SoccerTwos 3. Step 2: Select your *.nn /*.onnx file 4. Click on Watch the agent play 👀
vinson099/DatasetModel
vinson099
2023-07-05T20:34:01Z
191
0
transformers
[ "transformers", "pytorch", "tensorboard", "vit", "image-classification", "generated_from_trainer", "dataset:imagefolder", "license:apache-2.0", "model-index", "autotrain_compatible", "endpoints_compatible", "region:us" ]
image-classification
2023-07-05T18:00:46Z
--- license: apache-2.0 tags: - generated_from_trainer datasets: - imagefolder metrics: - accuracy model-index: - name: DatasetModel results: - task: name: Image Classification type: image-classification dataset: name: imagefolder type: imagefolder config: flower_photos split: train[:500] args: flower_photos metrics: - name: Accuracy type: accuracy value: 1.0 --- <!-- 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. --> # DatasetModel This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the imagefolder dataset. It achieves the following results on the evaluation set: - Loss: 0.6457 - Accuracy: 1.0 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 5e-05 - train_batch_size: 16 - eval_batch_size: 16 - 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_ratio: 0.1 - num_epochs: 3 ### Training results | Training Loss | Epoch | Step | Validation Loss | Accuracy | |:-------------:|:-----:|:----:|:---------------:|:--------:| | No log | 0.96 | 6 | 1.2651 | 0.99 | | 1.3875 | 1.92 | 12 | 0.7931 | 1.0 | | 1.3875 | 2.88 | 18 | 0.6457 | 1.0 | ### Framework versions - Transformers 4.30.2 - Pytorch 2.0.1+cu117 - Datasets 2.13.1 - Tokenizers 0.13.3
SaffalPoosh/falcon_7B_instruct_safetensors
SaffalPoosh
2023-07-05T20:27:23Z
16
0
transformers
[ "transformers", "safetensors", "RefinedWebModel", "text-generation", "custom_code", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]
text-generation
2023-07-05T20:13:30Z
Converted using oobabooga script to safetensors to test the TGI LLM inference engine
durdana/alpaca7B-lora
durdana
2023-07-05T20:25:35Z
0
0
peft
[ "peft", "region:us" ]
null
2023-07-05T20:25:31Z
--- library_name: peft --- ## Training procedure ### Framework versions - PEFT 0.4.0.dev0
jordyvl/EElayoutlmv3_jordyvl_rvl_cdip_100_examples_per_class_2023-07-05_weighted
jordyvl
2023-07-05T20:02:58Z
103
0
transformers
[ "transformers", "pytorch", "layoutlmv3", "text-classification", "generated_from_trainer", "license:cc-by-nc-sa-4.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]
text-classification
2023-07-05T17:53:13Z
--- license: cc-by-nc-sa-4.0 tags: - generated_from_trainer metrics: - accuracy model-index: - name: EElayoutlmv3_jordyvl_rvl_cdip_100_examples_per_class_2023-07-05_weighted results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # EElayoutlmv3_jordyvl_rvl_cdip_100_examples_per_class_2023-07-05_weighted This model is a fine-tuned version of [microsoft/layoutlmv3-base](https://huggingface.co/microsoft/layoutlmv3-base) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 1.0783 - Accuracy: 0.71 - Exit 0 Accuracy: 0.115 - Exit 1 Accuracy: 0.1575 - Exit 2 Accuracy: 0.185 - Exit 3 Accuracy: 0.0875 - Exit 4 Accuracy: 0.0625 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 2e-05 - train_batch_size: 12 - eval_batch_size: 4 - seed: 42 - gradient_accumulation_steps: 24 - total_train_batch_size: 288 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 60 ### Training results | Training Loss | Epoch | Step | Validation Loss | Accuracy | Exit 0 Accuracy | Exit 1 Accuracy | Exit 2 Accuracy | Exit 3 Accuracy | Exit 4 Accuracy | |:-------------:|:-----:|:----:|:---------------:|:--------:|:---------------:|:---------------:|:---------------:|:---------------:|:---------------:| | No log | 0.72 | 2 | 2.7602 | 0.1125 | 0.0925 | 0.0675 | 0.0875 | 0.0625 | 0.0625 | | No log | 1.72 | 4 | 2.7309 | 0.115 | 0.1175 | 0.0675 | 0.1075 | 0.0625 | 0.0625 | | No log | 2.72 | 6 | 2.6967 | 0.1325 | 0.095 | 0.06 | 0.1175 | 0.0625 | 0.0625 | | No log | 3.72 | 8 | 2.6631 | 0.17 | 0.085 | 0.0575 | 0.1275 | 0.0625 | 0.0625 | | No log | 4.72 | 10 | 2.6242 | 0.205 | 0.085 | 0.0575 | 0.1225 | 0.0625 | 0.0625 | | No log | 5.72 | 12 | 2.5736 | 0.2175 | 0.0875 | 0.0825 | 0.12 | 0.0625 | 0.0625 | | No log | 6.72 | 14 | 2.5410 | 0.215 | 0.09 | 0.08 | 0.12 | 0.0625 | 0.0625 | | No log | 7.72 | 16 | 2.5229 | 0.2325 | 0.1 | 0.0925 | 0.13 | 0.0625 | 0.0625 | | No log | 8.72 | 18 | 2.4841 | 0.2525 | 0.1 | 0.1 | 0.1325 | 0.0625 | 0.0625 | | No log | 9.72 | 20 | 2.4382 | 0.29 | 0.1 | 0.1025 | 0.1325 | 0.0625 | 0.0625 | | No log | 10.72 | 22 | 2.3823 | 0.3 | 0.1 | 0.1275 | 0.1325 | 0.0625 | 0.0625 | | No log | 11.72 | 24 | 2.3389 | 0.3275 | 0.1 | 0.1175 | 0.1225 | 0.0625 | 0.0625 | | No log | 12.72 | 26 | 2.3002 | 0.35 | 0.0975 | 0.12 | 0.1225 | 0.0625 | 0.0625 | | No log | 13.72 | 28 | 2.2421 | 0.36 | 0.0975 | 0.125 | 0.1275 | 0.0625 | 0.0625 | | No log | 14.72 | 30 | 2.2026 | 0.3575 | 0.1025 | 0.13 | 0.125 | 0.0625 | 0.0625 | | No log | 15.72 | 32 | 2.1712 | 0.375 | 0.105 | 0.1375 | 0.125 | 0.0625 | 0.0625 | | No log | 16.72 | 34 | 2.0999 | 0.4075 | 0.1 | 0.145 | 0.125 | 0.0625 | 0.0625 | | No log | 17.72 | 36 | 2.0414 | 0.4225 | 0.1025 | 0.145 | 0.1275 | 0.0625 | 0.0625 | | No log | 18.72 | 38 | 1.9981 | 0.4375 | 0.0975 | 0.1425 | 0.13 | 0.0625 | 0.0625 | | No log | 19.72 | 40 | 1.9369 | 0.4575 | 0.1025 | 0.14 | 0.1425 | 0.0625 | 0.0625 | | No log | 20.72 | 42 | 1.8903 | 0.4975 | 0.1025 | 0.14 | 0.145 | 0.0625 | 0.0625 | | No log | 21.72 | 44 | 1.8242 | 0.525 | 0.1025 | 0.1425 | 0.15 | 0.0625 | 0.0625 | | No log | 22.72 | 46 | 1.7520 | 0.5325 | 0.11 | 0.1475 | 0.1475 | 0.0625 | 0.0625 | | No log | 23.72 | 48 | 1.7203 | 0.5525 | 0.1125 | 0.1475 | 0.1525 | 0.0625 | 0.0625 | | No log | 24.72 | 50 | 1.6753 | 0.565 | 0.1125 | 0.1475 | 0.155 | 0.0625 | 0.0625 | | No log | 25.72 | 52 | 1.6245 | 0.575 | 0.1125 | 0.1475 | 0.155 | 0.0625 | 0.0625 | | No log | 26.72 | 54 | 1.5832 | 0.61 | 0.11 | 0.15 | 0.1525 | 0.0625 | 0.0625 | | No log | 27.72 | 56 | 1.5404 | 0.61 | 0.11 | 0.1475 | 0.155 | 0.0625 | 0.0625 | | No log | 28.72 | 58 | 1.4958 | 0.6125 | 0.11 | 0.1475 | 0.1575 | 0.0625 | 0.0625 | | No log | 29.72 | 60 | 1.4613 | 0.6325 | 0.11 | 0.1475 | 0.1575 | 0.0625 | 0.0625 | | No log | 30.72 | 62 | 1.4479 | 0.63 | 0.11 | 0.1525 | 0.16 | 0.0625 | 0.0625 | | No log | 31.72 | 64 | 1.4101 | 0.64 | 0.1125 | 0.1525 | 0.165 | 0.0625 | 0.0625 | | No log | 32.72 | 66 | 1.3699 | 0.655 | 0.1125 | 0.1525 | 0.1675 | 0.0625 | 0.0625 | | No log | 33.72 | 68 | 1.3427 | 0.6725 | 0.115 | 0.1525 | 0.165 | 0.0625 | 0.0625 | | No log | 34.72 | 70 | 1.3161 | 0.6825 | 0.115 | 0.1525 | 0.1625 | 0.0625 | 0.0625 | | No log | 35.72 | 72 | 1.2896 | 0.7025 | 0.115 | 0.1525 | 0.1675 | 0.0625 | 0.0625 | | No log | 36.72 | 74 | 1.2720 | 0.705 | 0.11 | 0.1525 | 0.185 | 0.0625 | 0.0625 | | No log | 37.72 | 76 | 1.2471 | 0.71 | 0.11 | 0.1525 | 0.1775 | 0.0625 | 0.0625 | | No log | 38.72 | 78 | 1.2307 | 0.71 | 0.11 | 0.155 | 0.1775 | 0.0625 | 0.0625 | | No log | 39.72 | 80 | 1.2174 | 0.7175 | 0.1125 | 0.155 | 0.1825 | 0.0625 | 0.0625 | | No log | 40.72 | 82 | 1.1991 | 0.705 | 0.1125 | 0.1525 | 0.1775 | 0.0625 | 0.0625 | | No log | 41.72 | 84 | 1.1867 | 0.71 | 0.1175 | 0.1525 | 0.18 | 0.065 | 0.0625 | | No log | 42.72 | 86 | 1.1764 | 0.7025 | 0.115 | 0.1525 | 0.18 | 0.0675 | 0.0625 | | No log | 43.72 | 88 | 1.1601 | 0.715 | 0.115 | 0.1525 | 0.1825 | 0.0725 | 0.0625 | | No log | 44.72 | 90 | 1.1410 | 0.7175 | 0.115 | 0.1525 | 0.18 | 0.075 | 0.0625 | | No log | 45.72 | 92 | 1.1408 | 0.71 | 0.115 | 0.155 | 0.1825 | 0.075 | 0.0625 | | No log | 46.72 | 94 | 1.1443 | 0.7075 | 0.115 | 0.155 | 0.1825 | 0.0775 | 0.0625 | | No log | 47.72 | 96 | 1.1364 | 0.705 | 0.115 | 0.155 | 0.1775 | 0.0825 | 0.0625 | | No log | 48.72 | 98 | 1.1251 | 0.71 | 0.115 | 0.155 | 0.175 | 0.085 | 0.0625 | | No log | 49.72 | 100 | 1.1113 | 0.7175 | 0.115 | 0.155 | 0.1775 | 0.085 | 0.0625 | | No log | 50.72 | 102 | 1.1040 | 0.7175 | 0.115 | 0.155 | 0.18 | 0.0875 | 0.0625 | | No log | 51.72 | 104 | 1.0972 | 0.715 | 0.115 | 0.155 | 0.18 | 0.0875 | 0.0625 | | No log | 52.72 | 106 | 1.0938 | 0.7175 | 0.115 | 0.1575 | 0.1825 | 0.0875 | 0.0625 | | No log | 53.72 | 108 | 1.0931 | 0.71 | 0.115 | 0.1575 | 0.185 | 0.0875 | 0.0625 | | No log | 54.72 | 110 | 1.0887 | 0.7075 | 0.115 | 0.1575 | 0.185 | 0.0875 | 0.0625 | | No log | 55.72 | 112 | 1.0865 | 0.7125 | 0.115 | 0.1575 | 0.1875 | 0.0875 | 0.0625 | | No log | 56.72 | 114 | 1.0828 | 0.7125 | 0.115 | 0.1575 | 0.1875 | 0.0875 | 0.0625 | | No log | 57.72 | 116 | 1.0801 | 0.7075 | 0.115 | 0.1575 | 0.1875 | 0.0875 | 0.0625 | | No log | 58.72 | 118 | 1.0786 | 0.7125 | 0.115 | 0.1575 | 0.1875 | 0.0875 | 0.0625 | | No log | 59.72 | 120 | 1.0783 | 0.71 | 0.115 | 0.1575 | 0.185 | 0.0875 | 0.0625 | ### Framework versions - Transformers 4.26.1 - Pytorch 1.13.1.post200 - Datasets 2.9.0 - Tokenizers 0.13.2
pszemraj/gpt2-medium-vaguely-human-dialogue
pszemraj
2023-07-05T19:57:49Z
15
0
transformers
[ "transformers", "pytorch", "safetensors", "gpt2", "text-generation", "gpt", "en", "license:mit", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]
text-generation
2022-03-02T23:29:05Z
--- language: - en tags: - text-generation - gpt2 - gpt license: mit widget: - text: |+ Do you like my new haircut? person beta: example_title: haircut - text: |+ I love to learn new things.. are you willing to teach me something? person beta: example_title: teaching - text: |+ What's your favorite animal? Mine is the dog? person beta: example_title: favorite - text: |+ how much does it cost? person beta: example_title: money inference: parameters: min_length: 2 max_length: 64 length_penalty: 0.6 no_repeat_ngram_size: 3 do_sample: true top_p: 0.85 top_k: 10 repetition_penalty: 2.1 pipeline_tag: text-generation --- <!-- 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. --> # pszemraj/gpt2-medium-vaguely-human-dialogue This model is a fine-tuned version of [gpt2-medium](https://huggingface.co/gpt2-medium) on a parsed version of Wizard of Wikipedia. Because the batch size was so large, it learned a general understanding of words that makes sense together but does not specifically respond to anything - sort of like an alien learning to imitate human words to convince others that it is human. It achieves the following results on the evaluation set: - Loss: 4.3281 ## Model description - a decent example of what happens when your batch size is too large and the global optima does not reflect specific prompts / use cases. ## Intended uses & limitations - there are no intended uses ## Training and evaluation data - a parsed version of the wizard of Wikipedia dataset ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 2e-05 - train_batch_size: 32 - eval_batch_size: 32 - seed: 42 - distributed_type: multi-GPU - gradient_accumulation_steps: 2 - total_train_batch_size: 64 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: cosine - lr_scheduler_warmup_ratio: 0.05 - num_epochs: 10 ### Training results | Training Loss | Epoch | Step | Validation Loss | |:-------------:|:-----:|:----:|:---------------:| | 34.991 | 1.0 | 837 | 14.8359 | | 12.2881 | 2.0 | 1674 | 9.375 | | 8.5071 | 3.0 | 2511 | 7.2148 | | 7.6031 | 4.0 | 3348 | 6.1758 | | 6.4808 | 5.0 | 4185 | 5.5820 | | 5.8562 | 6.0 | 5022 | 5.0977 | | 5.6094 | 7.0 | 5859 | 4.8203 | | 5.2591 | 8.0 | 6696 | 4.5977 | | 5.0031 | 9.0 | 7533 | 4.4219 | | 4.8837 | 10.0 | 8370 | 4.3281 | ### Framework versions - Transformers 4.16.1 - Pytorch 1.10.0+cu111 - Tokenizers 0.11.0
AWolters/ByT5_DutchSpellingNormalization
AWolters
2023-07-05T19:53:42Z
62
0
transformers
[ "transformers", "tf", "t5", "text2text-generation", "text2text generation", "spelling normalization", "19th-century Dutch", "nl", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]
text2text-generation
2023-07-01T16:11:47Z
--- language: - nl tags: - text2text generation - spelling normalization - 19th-century Dutch license: apache-2.0 --- # 19th Century Dutch Spelling Normalization This repository contains a pretrained and finetuned model of the original __google/ByT5-small__. This model has been pretrained and finetuned for the task of 19th-century Dutch spelling normalization. We first pretrained the model with 2 million sentences from Dutch historical novels. Afterward, we finetuned the model with a 10k dataset consisting of 19th-century Dutch sentences; these sentences were automatically annotated by a rule-based system built for 19th-century Dutch spelling normalization (van Cranenburgh and van Noord, 2022). The finetuned model is only available in the TensorFlow format but can be converted to a PyTorch environment. The pretrained only weights are available in the PyTorch environment; note that this model has to be finetuned first. The pretrained only weights are available in the directory __Pretrained_ByT5__. The train and validation sets used for finetuning are available in the main repository. For further information about the model, please see the [GitHub](https://github.com/Awolters123/Master-Thesis) repository. ## How to use: ``` from transformers import AutoTokenizer, TFT5ForConditionalGeneration tokenizer = AutoTokenizer.from_pretrained('AWolters/ByT5_DutchSpellingNormalization') model = TFT5ForConditionalGeneration.from_pretrained('AWolters/ByT5_DutchSpellingNormalization') text = 'De menschen waren aan het werk.' tokenized = tokenizer(text, return_tensors='tf') prediction = model.generate(input_ids=tokenized['input_ids'], attention_mask=tokenized['attention_mask'], max_new_tokens=100) print(tokenizer.decode(prediction[0], text_target=True, skip_special_tokens=True)) ``` ## Setup: The model has been finetuned with the following (hyper)parameters values: _Learn rate_: 5e-5 _Batch size_: 32 _Optimizer_: AdamW _Epochs_: 30, with earlystopping To further finetune the model, use the __T5Trainer.py__ script.
khushpreet/eyedisease
khushpreet
2023-07-05T19:51:05Z
0
0
keras
[ "keras", "tf-keras", "medical", "image-classification", "arxiv:1910.09700", "region:us" ]
image-classification
2023-07-05T19:48:02Z
--- metrics: - accuracy library_name: keras pipeline_tag: image-classification tags: - medical --- # 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]
sebasvaron/my_awesome_model
sebasvaron
2023-07-05T19:50:19Z
103
0
transformers
[ "transformers", "pytorch", "tensorboard", "distilbert", "text-classification", "generated_from_trainer", "dataset:imdb", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]
text-classification
2023-07-05T19:45:00Z
--- license: apache-2.0 tags: - generated_from_trainer datasets: - imdb model-index: - name: my_awesome_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_model This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the imdb dataset. ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 2e-05 - train_batch_size: 16 - eval_batch_size: 16 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 2 ### Framework versions - Transformers 4.30.2 - Pytorch 2.0.1+cu118 - Datasets 2.13.1 - Tokenizers 0.13.3
aroot/wsample.43a
aroot
2023-07-05T19:38:28Z
3
0
transformers
[ "transformers", "pytorch", "tensorboard", "mbart", "text2text-generation", "translation", "generated_from_trainer", "autotrain_compatible", "endpoints_compatible", "region:us" ]
translation
2023-07-05T18:34:22Z
--- tags: - translation - generated_from_trainer metrics: - bleu model-index: - name: wsample.43a 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. --> # wsample.43a This model is a fine-tuned version of [facebook/mbart-large-50-many-to-many-mmt](https://huggingface.co/facebook/mbart-large-50-many-to-many-mmt) on the None dataset. It achieves the following results on the evaluation set: - Loss: 1.8306 - Bleu: 4.7146 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 2e-05 - train_batch_size: 32 - eval_batch_size: 32 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 3 ### Training results ### Framework versions - Transformers 4.30.2 - Pytorch 2.0.1 - Datasets 2.12.0 - Tokenizers 0.11.0
aroot/wsample.32a
aroot
2023-07-05T19:38:12Z
3
0
transformers
[ "transformers", "pytorch", "tensorboard", "mbart", "text2text-generation", "translation", "generated_from_trainer", "autotrain_compatible", "endpoints_compatible", "region:us" ]
translation
2023-07-05T18:34:12Z
--- tags: - translation - generated_from_trainer metrics: - bleu model-index: - name: wsample.32a 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. --> # wsample.32a This model is a fine-tuned version of [facebook/mbart-large-50-many-to-many-mmt](https://huggingface.co/facebook/mbart-large-50-many-to-many-mmt) on the None dataset. It achieves the following results on the evaluation set: - Loss: 1.8284 - Bleu: 4.7412 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 2e-05 - train_batch_size: 32 - eval_batch_size: 32 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 3 ### Training results ### Framework versions - Transformers 4.30.2 - Pytorch 2.0.1 - Datasets 2.12.0 - Tokenizers 0.11.0
joydragon/Reinforce-Pixelcopter-PLE-v0
joydragon
2023-07-05T19:14:01Z
0
0
null
[ "Pixelcopter-PLE-v0", "reinforce", "reinforcement-learning", "custom-implementation", "deep-rl-class", "model-index", "region:us" ]
reinforcement-learning
2023-07-05T18:30:19Z
--- tags: - Pixelcopter-PLE-v0 - reinforce - reinforcement-learning - custom-implementation - deep-rl-class model-index: - name: Reinforce-Pixelcopter-PLE-v0 results: - task: type: reinforcement-learning name: reinforcement-learning dataset: name: Pixelcopter-PLE-v0 type: Pixelcopter-PLE-v0 metrics: - type: mean_reward value: 20.40 +/- 19.70 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
wizofavalon/distilgpt2-finetuned-wikitext2
wizofavalon
2023-07-05T19:09:13Z
62
0
transformers
[ "transformers", "tf", "tensorboard", "gpt2", "text-generation", "generated_from_keras_callback", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]
text-generation
2023-07-05T18:56:22Z
--- license: apache-2.0 tags: - generated_from_keras_callback model-index: - name: wizofavalon/distilgpt2-finetuned-wikitext2 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. --> # wizofavalon/distilgpt2-finetuned-wikitext2 This model is a fine-tuned version of [distilgpt2](https://huggingface.co/distilgpt2) on an unknown dataset. It achieves the following results on the evaluation set: - Train Loss: 3.8588 - Validation Loss: 3.6766 - 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': 2e-05, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False, 'weight_decay_rate': 0.01} - training_precision: float32 ### Training results | Train Loss | Validation Loss | Epoch | |:----------:|:---------------:|:-----:| | 3.8588 | 3.6766 | 0 | ### Framework versions - Transformers 4.30.2 - TensorFlow 2.12.0 - Datasets 2.13.1 - Tokenizers 0.13.3
maubers/emily_yeppers
maubers
2023-07-05T19:08:47Z
13
0
transformers
[ "transformers", "pytorch", "tensorboard", "gpt_neo", "text-generation", "autotrain_compatible", "endpoints_compatible", "region:us" ]
text-generation
2023-07-05T17:28:43Z
## Overview This contains Emily Yeppers, a bot who likes to talk about very inappropriate things and how vital they are to the existence of our species (the truth, technically) using GPT-Neo. The bot streams new content from specified subreddits and responds when certain target phrases are detected in comments and submissions, or when it is mentioned or directly replied to. She is designed to function as a Reddit bot. See the Github page for more information. She WILL generate inappropriate content, as she was trained on comments posted in inappropriate subreddits. ## Setup and Installation (for Reddit) See https://github.com/maubers/emily_yeppers
jlpan/santacoder-finetuned-the-stack-bash
jlpan
2023-07-05T19:03:38Z
8
0
transformers
[ "transformers", "pytorch", "tensorboard", "gpt2", "text-generation", "generated_from_trainer", "custom_code", "license:bigcode-openrail-m", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]
text-generation
2023-06-27T21:51:19Z
--- license: bigcode-openrail-m tags: - generated_from_trainer model-index: - name: santacoder-finetuned-the-stack-bash 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. --> # santacoder-finetuned-the-stack-bash This model is a fine-tuned version of [bigcode/santacoder](https://huggingface.co/bigcode/santacoder) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 1.3654 ## 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: 1 - eval_batch_size: 1 - seed: 42 - gradient_accumulation_steps: 4 - total_train_batch_size: 4 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: cosine - lr_scheduler_warmup_steps: 100 - training_steps: 2000 ### Training results | Training Loss | Epoch | Step | Validation Loss | |:-------------:|:-----:|:----:|:---------------:| | 1.6322 | 0.25 | 500 | 1.5498 | | 3.9791 | 0.5 | 1000 | 1.4721 | | 0.3946 | 0.75 | 1500 | 1.3971 | | 1.5232 | 1.0 | 2000 | 1.3654 | ### Framework versions - Transformers 4.30.2 - Pytorch 2.0.1+cu118 - Datasets 2.13.1 - Tokenizers 0.13.3
konverner/due_eshop_21_multilabel
konverner
2023-07-05T18:59:21Z
4
0
sentence-transformers
[ "sentence-transformers", "pytorch", "mpnet", "setfit", "text-classification", "arxiv:2209.11055", "license:apache-2.0", "region:us" ]
text-classification
2023-07-04T22:21:59Z
--- license: apache-2.0 tags: - setfit - sentence-transformers - text-classification pipeline_tag: text-classification --- # konverner/due_eshop_21_multilabel This is a [SetFit model](https://github.com/huggingface/setfit) that can be used for text classification. The model has been trained using an efficient few-shot learning technique that involves: 1. Fine-tuning a [Sentence Transformer](https://www.sbert.net) with contrastive learning. 2. Training a classification head with features from the fine-tuned Sentence Transformer. ## Usage To use this model for inference, first install the SetFit library: ```bash python -m pip install setfit ``` You can then run inference as follows: ```python from setfit import SetFitModel # Download from Hub and run inference model = SetFitModel.from_pretrained("konverner/due_eshop_21_multilabel") # Run inference preds = model(["i loved the spiderman movie!", "pineapple on pizza is the worst 🤮"]) ``` ## BibTeX entry and citation info ```bibtex @article{https://doi.org/10.48550/arxiv.2209.11055, doi = {10.48550/ARXIV.2209.11055}, url = {https://arxiv.org/abs/2209.11055}, author = {Tunstall, Lewis and Reimers, Nils and Jo, Unso Eun Seo and Bates, Luke and Korat, Daniel and Wasserblat, Moshe and Pereg, Oren}, keywords = {Computation and Language (cs.CL), FOS: Computer and information sciences, FOS: Computer and information sciences}, title = {Efficient Few-Shot Learning Without Prompts}, publisher = {arXiv}, year = {2022}, copyright = {Creative Commons Attribution 4.0 International} } ```
bk6000/dqn-SpaceInvadersNoFrameskip-v4
bk6000
2023-07-05T18:50:44Z
1
0
stable-baselines3
[ "stable-baselines3", "SpaceInvadersNoFrameskip-v4", "deep-reinforcement-learning", "reinforcement-learning", "model-index", "region:us" ]
reinforcement-learning
2023-07-05T18:09:35Z
--- 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: 337.50 +/- 114.85 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 bk6000 -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 bk6000 -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 bk6000 ``` ## 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', 500000.0), ('optimize_memory_usage', False), ('policy', 'CnnPolicy'), ('target_update_interval', 1000), ('train_freq', 4), ('normalize', False)]) ``` # Environment Arguments ```python {'render_mode': 'rgb_array'} ```
alesthehuman/poca-SoccerTwos
alesthehuman
2023-07-05T18:14:32Z
24
0
ml-agents
[ "ml-agents", "tensorboard", "onnx", "SoccerTwos", "deep-reinforcement-learning", "reinforcement-learning", "ML-Agents-SoccerTwos", "region:us" ]
reinforcement-learning
2023-07-05T18:13:38Z
--- library_name: ml-agents tags: - SoccerTwos - deep-reinforcement-learning - reinforcement-learning - ML-Agents-SoccerTwos --- # **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://unity-technologies.github.io/ml-agents/ML-Agents-Toolkit-Documentation/ We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub: - A *short tutorial* where you teach Huggy the Dog 🐶 to fetch the stick and then play with him directly in your browser: https://huggingface.co/learn/deep-rl-course/unitbonus1/introduction - A *longer tutorial* to understand how works ML-Agents: https://huggingface.co/learn/deep-rl-course/unit5/introduction ### Resume the training ```bash mlagents-learn <your_configuration_file_path.yaml> --run-id=<run_id> --resume ``` ### Watch your Agent play You can watch your agent **playing directly in your browser** 1. If the environment is part of ML-Agents official environments, go to https://huggingface.co/unity 2. Step 1: Find your model_id: alesthehuman/poca-SoccerTwos 3. Step 2: Select your *.nn /*.onnx file 4. Click on Watch the agent play 👀
Tubido/Taxi-v3-001
Tubido
2023-07-05T18:06:11Z
0
0
null
[ "Taxi-v3", "q-learning", "reinforcement-learning", "custom-implementation", "model-index", "region:us" ]
reinforcement-learning
2023-07-05T18:06:09Z
--- tags: - Taxi-v3 - q-learning - reinforcement-learning - custom-implementation model-index: - name: Taxi-v3-001 results: - task: type: reinforcement-learning name: reinforcement-learning dataset: name: Taxi-v3 type: Taxi-v3 metrics: - type: mean_reward value: 7.56 +/- 2.71 name: mean_reward verified: false --- # **Q-Learning** Agent playing1 **Taxi-v3** This is a trained model of a **Q-Learning** agent playing **Taxi-v3** . ## Usage ```python model = load_from_hub(repo_id="Tubido/Taxi-v3-001", 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"]) ```
PraveenJesu/openai-whisper-medium-zrx-peft-lora-v2.2.2
PraveenJesu
2023-07-05T18:01:17Z
0
0
peft
[ "peft", "region:us" ]
null
2023-07-05T18:01:14Z
--- library_name: peft --- ## Training procedure The following `bitsandbytes` quantization config was used during training: - load_in_8bit: True - load_in_4bit: False - llm_int8_threshold: 6.0 - llm_int8_skip_modules: None - llm_int8_enable_fp32_cpu_offload: False - llm_int8_has_fp16_weight: False - bnb_4bit_quant_type: fp4 - bnb_4bit_use_double_quant: False - bnb_4bit_compute_dtype: float32 ### Framework versions - PEFT 0.4.0.dev0
jordyvl/EElayoutlmv3_jordyvl_rvl_cdip_100_examples_per_class_2023-07-05_ent_g75
jordyvl
2023-07-05T17:52:32Z
103
0
transformers
[ "transformers", "pytorch", "layoutlmv3", "text-classification", "generated_from_trainer", "license:cc-by-nc-sa-4.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]
text-classification
2023-07-05T15:38:04Z
--- license: cc-by-nc-sa-4.0 tags: - generated_from_trainer metrics: - accuracy model-index: - name: EElayoutlmv3_jordyvl_rvl_cdip_100_examples_per_class_2023-07-05_ent_g75 results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # EElayoutlmv3_jordyvl_rvl_cdip_100_examples_per_class_2023-07-05_ent_g75 This model is a fine-tuned version of [microsoft/layoutlmv3-base](https://huggingface.co/microsoft/layoutlmv3-base) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 1.2759 - Accuracy: 0.6825 - Exit 0 Accuracy: 0.11 - Exit 1 Accuracy: 0.155 - Exit 2 Accuracy: 0.345 - Exit 3 Accuracy: 0.425 - Exit 4 Accuracy: 0.5225 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 2e-05 - train_batch_size: 12 - eval_batch_size: 4 - seed: 42 - gradient_accumulation_steps: 24 - total_train_batch_size: 288 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 60 ### Training results | Training Loss | Epoch | Step | Validation Loss | Accuracy | Exit 0 Accuracy | Exit 1 Accuracy | Exit 2 Accuracy | Exit 3 Accuracy | Exit 4 Accuracy | |:-------------:|:-----:|:----:|:---------------:|:--------:|:---------------:|:---------------:|:---------------:|:---------------:|:---------------:| | No log | 0.72 | 2 | 2.7601 | 0.1075 | 0.0825 | 0.0675 | 0.1025 | 0.0625 | 0.0625 | | No log | 1.72 | 4 | 2.7328 | 0.1125 | 0.07 | 0.065 | 0.1225 | 0.0625 | 0.0625 | | No log | 2.72 | 6 | 2.6968 | 0.13 | 0.075 | 0.06 | 0.1325 | 0.0625 | 0.0625 | | No log | 3.72 | 8 | 2.6594 | 0.18 | 0.075 | 0.06 | 0.1175 | 0.0625 | 0.0625 | | No log | 4.72 | 10 | 2.6206 | 0.1925 | 0.085 | 0.0575 | 0.11 | 0.0625 | 0.0625 | | No log | 5.72 | 12 | 2.5710 | 0.2125 | 0.09 | 0.08 | 0.115 | 0.0625 | 0.0625 | | No log | 6.72 | 14 | 2.5334 | 0.2275 | 0.095 | 0.08 | 0.12 | 0.0575 | 0.0625 | | No log | 7.72 | 16 | 2.5094 | 0.245 | 0.095 | 0.095 | 0.135 | 0.0725 | 0.0625 | | No log | 8.72 | 18 | 2.4631 | 0.2825 | 0.095 | 0.0975 | 0.17 | 0.0925 | 0.065 | | No log | 9.72 | 20 | 2.4152 | 0.3025 | 0.1 | 0.1275 | 0.205 | 0.1075 | 0.0625 | | No log | 10.72 | 22 | 2.3737 | 0.325 | 0.1075 | 0.1225 | 0.24 | 0.12 | 0.065 | | No log | 11.72 | 24 | 2.3302 | 0.3175 | 0.1125 | 0.1175 | 0.2375 | 0.1475 | 0.0675 | | No log | 12.72 | 26 | 2.2746 | 0.34 | 0.1125 | 0.125 | 0.255 | 0.155 | 0.095 | | No log | 13.72 | 28 | 2.2527 | 0.35 | 0.1125 | 0.125 | 0.2625 | 0.175 | 0.095 | | No log | 14.72 | 30 | 2.2101 | 0.3425 | 0.1075 | 0.13 | 0.27 | 0.2125 | 0.095 | | No log | 15.72 | 32 | 2.1811 | 0.355 | 0.1075 | 0.14 | 0.29 | 0.24 | 0.095 | | No log | 16.72 | 34 | 2.1368 | 0.38 | 0.105 | 0.145 | 0.305 | 0.245 | 0.0925 | | No log | 17.72 | 36 | 2.0855 | 0.395 | 0.1075 | 0.145 | 0.3175 | 0.2475 | 0.095 | | No log | 18.72 | 38 | 2.0559 | 0.4 | 0.1125 | 0.145 | 0.305 | 0.255 | 0.1025 | | No log | 19.72 | 40 | 2.0277 | 0.41 | 0.115 | 0.145 | 0.295 | 0.28 | 0.105 | | No log | 20.72 | 42 | 1.9746 | 0.445 | 0.12 | 0.145 | 0.28 | 0.2875 | 0.1025 | | No log | 21.72 | 44 | 1.9346 | 0.4525 | 0.12 | 0.145 | 0.265 | 0.25 | 0.1025 | | No log | 22.72 | 46 | 1.8926 | 0.4925 | 0.12 | 0.145 | 0.255 | 0.25 | 0.11 | | No log | 23.72 | 48 | 1.8581 | 0.5025 | 0.115 | 0.1475 | 0.26 | 0.3 | 0.1075 | | No log | 24.72 | 50 | 1.8403 | 0.4975 | 0.11 | 0.1475 | 0.2725 | 0.3325 | 0.11 | | No log | 25.72 | 52 | 1.8162 | 0.5 | 0.1125 | 0.1475 | 0.2875 | 0.3575 | 0.1125 | | No log | 26.72 | 54 | 1.7562 | 0.5475 | 0.115 | 0.1475 | 0.295 | 0.3575 | 0.115 | | No log | 27.72 | 56 | 1.7205 | 0.5725 | 0.1175 | 0.15 | 0.295 | 0.37 | 0.115 | | No log | 28.72 | 58 | 1.7041 | 0.555 | 0.1175 | 0.15 | 0.295 | 0.36 | 0.11 | | No log | 29.72 | 60 | 1.7018 | 0.5525 | 0.12 | 0.15 | 0.305 | 0.36 | 0.1125 | | No log | 30.72 | 62 | 1.6532 | 0.58 | 0.12 | 0.15 | 0.3025 | 0.3725 | 0.1125 | | No log | 31.72 | 64 | 1.6218 | 0.58 | 0.12 | 0.15 | 0.3125 | 0.3725 | 0.1175 | | No log | 32.72 | 66 | 1.5888 | 0.59 | 0.115 | 0.1475 | 0.32 | 0.38 | 0.1325 | | No log | 33.72 | 68 | 1.5778 | 0.6 | 0.115 | 0.1475 | 0.315 | 0.3875 | 0.1425 | | No log | 34.72 | 70 | 1.5500 | 0.59 | 0.1225 | 0.15 | 0.315 | 0.3875 | 0.155 | | No log | 35.72 | 72 | 1.5216 | 0.61 | 0.13 | 0.15 | 0.31 | 0.3875 | 0.17 | | No log | 36.72 | 74 | 1.5024 | 0.6175 | 0.1275 | 0.15 | 0.3075 | 0.4125 | 0.1675 | | No log | 37.72 | 76 | 1.4787 | 0.615 | 0.12 | 0.1525 | 0.32 | 0.4025 | 0.165 | | No log | 38.72 | 78 | 1.4635 | 0.6175 | 0.1175 | 0.1525 | 0.325 | 0.4125 | 0.1625 | | No log | 39.72 | 80 | 1.4455 | 0.6225 | 0.12 | 0.155 | 0.3225 | 0.4225 | 0.165 | | No log | 40.72 | 82 | 1.4304 | 0.625 | 0.12 | 0.155 | 0.33 | 0.425 | 0.1675 | | No log | 41.72 | 84 | 1.4170 | 0.6425 | 0.1175 | 0.155 | 0.3325 | 0.425 | 0.21 | | No log | 42.72 | 86 | 1.4052 | 0.64 | 0.1175 | 0.155 | 0.335 | 0.4275 | 0.245 | | No log | 43.72 | 88 | 1.3965 | 0.6425 | 0.1125 | 0.155 | 0.34 | 0.4125 | 0.2775 | | No log | 44.72 | 90 | 1.3766 | 0.645 | 0.1125 | 0.155 | 0.3425 | 0.4075 | 0.315 | | No log | 45.72 | 92 | 1.3611 | 0.6575 | 0.11 | 0.155 | 0.345 | 0.41 | 0.33 | | No log | 46.72 | 94 | 1.3513 | 0.6575 | 0.11 | 0.155 | 0.3425 | 0.4175 | 0.34 | | No log | 47.72 | 96 | 1.3520 | 0.665 | 0.11 | 0.155 | 0.3425 | 0.4275 | 0.36 | | No log | 48.72 | 98 | 1.3373 | 0.67 | 0.11 | 0.155 | 0.3425 | 0.425 | 0.3875 | | No log | 49.72 | 100 | 1.3213 | 0.6775 | 0.11 | 0.155 | 0.3425 | 0.4175 | 0.405 | | No log | 50.72 | 102 | 1.3124 | 0.6825 | 0.11 | 0.155 | 0.3425 | 0.41 | 0.445 | | No log | 51.72 | 104 | 1.3080 | 0.68 | 0.1075 | 0.155 | 0.34 | 0.41 | 0.455 | | No log | 52.72 | 106 | 1.3037 | 0.675 | 0.105 | 0.1575 | 0.3425 | 0.4175 | 0.4775 | | No log | 53.72 | 108 | 1.2987 | 0.6825 | 0.11 | 0.1575 | 0.345 | 0.425 | 0.4875 | | No log | 54.72 | 110 | 1.2943 | 0.6775 | 0.1075 | 0.1575 | 0.3475 | 0.425 | 0.5025 | | No log | 55.72 | 112 | 1.2889 | 0.68 | 0.1075 | 0.1575 | 0.3475 | 0.425 | 0.51 | | No log | 56.72 | 114 | 1.2829 | 0.68 | 0.1075 | 0.16 | 0.3475 | 0.4225 | 0.5175 | | No log | 57.72 | 116 | 1.2793 | 0.68 | 0.1075 | 0.155 | 0.3475 | 0.4225 | 0.5225 | | No log | 58.72 | 118 | 1.2769 | 0.68 | 0.11 | 0.155 | 0.345 | 0.4225 | 0.5225 | | No log | 59.72 | 120 | 1.2759 | 0.6825 | 0.11 | 0.155 | 0.345 | 0.425 | 0.5225 | ### Framework versions - Transformers 4.26.1 - Pytorch 1.13.1.post200 - Datasets 2.9.0 - Tokenizers 0.13.2
jorgeortizfuentes/nominal-groups-recognition-bert-base-spanish-wwm-cased
jorgeortizfuentes
2023-07-05T17:44:00Z
115
0
transformers
[ "transformers", "tensorboard", "safetensors", "bert", "token-classification", "generated_from_trainer", "es", "dataset:jorgeortizfuentes/spanish_nominal_groups_conll2003", "autotrain_compatible", "endpoints_compatible", "region:us" ]
token-classification
2023-07-05T06:42:53Z
--- language: - es tags: - generated_from_trainer datasets: - jorgeortizfuentes/spanish_nominal_groups_conll2003 model-index: - name: nominal-groups-recognition-bert-base-spanish-wwm-cased 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. --> # nominal-groups-recognition-bert-base-spanish-wwm-cased This model is a fine-tuned version of [dccuchile/bert-base-spanish-wwm-cased](https://huggingface.co/dccuchile/bert-base-spanish-wwm-cased) on the jorgeortizfuentes/spanish_nominal_groups_conll2003 dataset. It achieves the following results on the evaluation set: - Loss: 0.3568 - Ng Precision: 0.7280 - Ng Recall: 0.7767 - Ng F1: 0.7516 - Ng Number: 3198 - Overall Precision: 0.7280 - Overall Recall: 0.7767 - Overall F1: 0.7516 - Overall Accuracy: 0.8992 ## 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: 13 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 5 ### Training results | Training Loss | Epoch | Step | Validation Loss | Ng Precision | Ng Recall | Ng F1 | Ng Number | Overall Precision | Overall Recall | Overall F1 | Overall Accuracy | |:-------------:|:-----:|:----:|:---------------:|:------------:|:---------:|:------:|:---------:|:-----------------:|:--------------:|:----------:|:----------------:| | 0.3955 | 1.0 | 228 | 0.2778 | 0.7129 | 0.7492 | 0.7306 | 3198 | 0.7129 | 0.7492 | 0.7306 | 0.8924 | | 0.2186 | 2.0 | 456 | 0.2763 | 0.7318 | 0.7711 | 0.7509 | 3198 | 0.7318 | 0.7711 | 0.7509 | 0.8990 | | 0.1586 | 3.0 | 684 | 0.2960 | 0.7274 | 0.7733 | 0.7496 | 3198 | 0.7274 | 0.7733 | 0.7496 | 0.8992 | | 0.119 | 4.0 | 912 | 0.3330 | 0.7283 | 0.7727 | 0.7498 | 3198 | 0.7283 | 0.7727 | 0.7498 | 0.8982 | | 0.0943 | 5.0 | 1140 | 0.3568 | 0.7280 | 0.7767 | 0.7516 | 3198 | 0.7280 | 0.7767 | 0.7516 | 0.8992 | ### Framework versions - Transformers 4.30.2 - Pytorch 2.0.1+cu118 - Datasets 2.13.1 - Tokenizers 0.13.3
NasimB/gpt2-concat-cl-rarity-11-135k-mod-datasets-rarity1-root3
NasimB
2023-07-05T17:36:09Z
5
0
transformers
[ "transformers", "pytorch", "gpt2", "text-generation", "generated_from_trainer", "dataset:generator", "license:mit", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]
text-generation
2023-07-05T15:21:37Z
--- license: mit tags: - generated_from_trainer datasets: - generator model-index: - name: gpt2-concat-cl-rarity-11-135k-mod-datasets-rarity1-root3 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-concat-cl-rarity-11-135k-mod-datasets-rarity1-root3 This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on the generator dataset. It achieves the following results on the evaluation set: - Loss: 4.7842 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 64 - eval_batch_size: 64 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: cosine - lr_scheduler_warmup_steps: 1000 - num_epochs: 1 - mixed_precision_training: Native AMP ### Training results | Training Loss | Epoch | Step | Validation Loss | |:-------------:|:-----:|:----:|:---------------:| | 6.6744 | 0.05 | 500 | 5.8476 | | 5.4179 | 0.11 | 1000 | 5.4438 | | 5.0636 | 0.16 | 1500 | 5.2289 | | 4.8263 | 0.21 | 2000 | 5.0980 | | 4.6688 | 0.27 | 2500 | 5.0253 | | 4.5377 | 0.32 | 3000 | 4.9573 | | 4.427 | 0.37 | 3500 | 4.9024 | | 4.3275 | 0.43 | 4000 | 4.8730 | | 4.2279 | 0.48 | 4500 | 4.8377 | | 4.1432 | 0.53 | 5000 | 4.8105 | | 4.0517 | 0.59 | 5500 | 4.7917 | | 3.9751 | 0.64 | 6000 | 4.7647 | | 3.893 | 0.69 | 6500 | 4.7603 | | 3.8238 | 0.74 | 7000 | 4.7474 | | 3.771 | 0.8 | 7500 | 4.7374 | | 3.7292 | 0.85 | 8000 | 4.7341 | | 3.6984 | 0.9 | 8500 | 4.7283 | | 3.6812 | 0.96 | 9000 | 4.7263 | ### Framework versions - Transformers 4.26.1 - Pytorch 1.11.0+cu113 - Datasets 2.13.0 - Tokenizers 0.13.3
Tubido/q-FrozenLake-v1-4x4-noSlippery
Tubido
2023-07-05T17:28:01Z
0
0
null
[ "FrozenLake-v1-4x4-no_slippery", "q-learning", "reinforcement-learning", "custom-implementation", "model-index", "region:us" ]
reinforcement-learning
2023-07-05T17:27:59Z
--- 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="Tubido/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"]) ```
MysticShadow427/roberta-meld
MysticShadow427
2023-07-05T17:21:14Z
0
0
keras
[ "keras", "tf-keras", "region:us" ]
null
2023-07-05T17:19:52Z
--- library_name: keras --- ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: | Hyperparameters | Value | | :-- | :-- | | name | Adam | | weight_decay | None | | clipnorm | None | | global_clipnorm | None | | clipvalue | None | | use_ema | False | | ema_momentum | 0.99 | | ema_overwrite_frequency | None | | jit_compile | True | | is_legacy_optimizer | False | | learning_rate | 9.999999747378752e-06 | | beta_1 | 0.9 | | beta_2 | 0.999 | | epsilon | 1e-07 | | amsgrad | False | | training_precision | float32 | ## Model Plot <details> <summary>View Model Plot</summary> ![Model Image](./model.png) </details>
ddoc/def
ddoc
2023-07-05T17:04:15Z
0
0
null
[ "region:us" ]
null
2023-07-05T17:03:23Z
# Deforum Stable Diffusion — official extension for AUTOMATIC1111's webui <p align="left"> <a href="https://github.com/deforum-art/sd-webui-deforum/commits"><img alt="Last Commit" src="https://img.shields.io/github/last-commit/deforum-art/deforum-for-automatic1111-webui"></a> <a href="https://github.com/deforum-art/sd-webui-deforum/issues"><img alt="GitHub issues" src="https://img.shields.io/github/issues/deforum-art/deforum-for-automatic1111-webui"></a> <a href="https://github.com/deforum-art/sd-webui-deforum/stargazers"><img alt="GitHub stars" src="https://img.shields.io/github/stars/deforum-art/deforum-for-automatic1111-webui"></a> <a href="https://github.com/deforum-art/sd-webui-deforum/network"><img alt="GitHub forks" src="https://img.shields.io/github/forks/deforum-art/deforum-for-automatic1111-webui"></a> </a> </p> ## Need help? See our [FAQ](https://github.com/deforum-art/sd-webui-deforum/wiki/FAQ-&-Troubleshooting) ## Getting Started 1. Install [AUTOMATIC1111's webui](https://github.com/AUTOMATIC1111/stable-diffusion-webui/). 2. Now two ways: either clone the repo into the `extensions` directory via git commandline launched within in the `stable-diffusion-webui` folder ```sh git clone https://github.com/deforum-art/sd-webui-deforum extensions/deforum ``` Or download this repository, locate the `extensions` folder within your WebUI installation, create a folder named `deforum` and put the contents of the downloaded directory inside of it. Then restart WebUI. 3. Open the webui, find the Deforum tab at the top of the page. 4. Enter the animation settings. Refer to [this general guide](https://docs.google.com/document/d/1pEobUknMFMkn8F5TMsv8qRzamXX_75BShMMXV8IFslI/edit) and [this guide to math keyframing functions in Deforum](https://docs.google.com/document/d/1pfW1PwbDIuW0cv-dnuyYj1UzPqe23BlSLTJsqazffXM/edit?usp=sharing). However, **in this version prompt weights less than zero don't just like in original Deforum!** Split the positive and the negative prompt in the json section using --neg argument like this "apple:\`where(cos(t)>=0, cos(t), 0)\`, snow --neg strawberry:\`where(cos(t)<0, -cos(t), 0)\`" 5. To view animation frames as they're being made, without waiting for the completion of an animation, go to the 'Settings' tab and set the value of this toolbar **above zero**. Warning: it may slow down the generation process. ![adsdasunknown](https://user-images.githubusercontent.com/14872007/196064311-1b79866a-e55b-438a-84a7-004ff30829ad.png) 6. Run the script and see if you got it working or even got something. **In 3D mode a large delay is expected at first** as the script loads the depth models. In the end, using the default settings the whole thing should consume 6.4 GBs of VRAM at 3D mode peaks and no more than 3.8 GB VRAM in 3D mode if you launch the webui with the '--lowvram' command line argument. 7. After the generation process is completed, click the button with the self-describing name to show the video or gif result right in the GUI! 8. Join our Discord where you can post generated stuff, ask questions and more: https://discord.gg/deforum. <br> * There's also the 'Issues' tab in the repo, for well... reporting issues ;) 9. Profit! ## Known issues * This port is not fully backward-compatible with the notebook and the local version both due to the changes in how AUTOMATIC1111's webui handles Stable Diffusion models and the changes in this script to get it to work in the new environment. *Expect* that you may not get exactly the same result or that the thing may break down because of the older settings. ## Screenshots Amazing raw Deforum animation by [Pxl.Pshr](https://www.instagram.com/pxl.pshr): * Turn Audio ON! (Audio credits: SKRILLEX, FRED AGAIN & FLOWDAN - RUMBLE (PHACE'S DNB FLIP)) https://user-images.githubusercontent.com/121192995/224450647-39529b28-be04-4871-bb7a-faf7afda2ef2.mp4 Setting file of that video: [here](https://github.com/deforum-art/sd-webui-deforum/files/11353167/PxlPshrWinningAnimationSettings.txt). <br> Main extension tab: ![image](https://user-images.githubusercontent.com/121192995/226101131-43bf594a-3152-45dd-a5d1-2538d0bc221d.png) Keyframes tab: ![image](https://user-images.githubusercontent.com/121192995/226101140-bfe6cce7-9b78-4a1d-be9a-43e1fc78239e.png)
oknashar/distilbert-base-uncased-finetuned-emotion
oknashar
2023-07-05T16:42:28Z
105
0
transformers
[ "transformers", "pytorch", "tensorboard", "distilbert", "text-classification", "generated_from_trainer", "base_model:distilbert/distilbert-base-uncased", "base_model:finetune:distilbert/distilbert-base-uncased", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]
text-classification
2023-07-05T15:20:24Z
--- license: apache-2.0 base_model: distilbert-base-uncased tags: - generated_from_trainer metrics: - accuracy - f1 model-index: - name: distilbert-base-uncased-finetuned-emotion results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # distilbert-base-uncased-finetuned-emotion This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an mteb/emotion dataset. It achieves the following results on the evaluation set: - Loss: 0.1803 - Accuracy: 0.94 - F1: 0.9400 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 2e-05 - train_batch_size: 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 ### Training results | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:| | 0.5017 | 1.0 | 250 | 0.2116 | 0.9295 | 0.9305 | | 0.1763 | 2.0 | 500 | 0.1617 | 0.936 | 0.9369 | | 0.1267 | 3.0 | 750 | 0.1492 | 0.9385 | 0.9386 | | 0.0979 | 4.0 | 1000 | 0.1495 | 0.9395 | 0.9392 | | 0.0787 | 5.0 | 1250 | 0.1602 | 0.935 | 0.9349 | | 0.067 | 6.0 | 1500 | 0.1588 | 0.9405 | 0.9401 | | 0.0557 | 7.0 | 1750 | 0.1675 | 0.9415 | 0.9413 | | 0.0452 | 8.0 | 2000 | 0.1764 | 0.937 | 0.9365 | | 0.0375 | 9.0 | 2250 | 0.1765 | 0.9405 | 0.9406 | | 0.0337 | 10.0 | 2500 | 0.1803 | 0.94 | 0.9400 | ### Framework versions - Transformers 4.31.0.dev0 - Pytorch 2.0.0 - Datasets 2.1.0 - Tokenizers 0.13.3
adisrini11/AIE-Assessment
adisrini11
2023-07-05T16:39:39Z
105
0
transformers
[ "transformers", "pytorch", "distilbert", "text-classification", "generated_from_trainer", "dataset:tweet_eval", "license:apache-2.0", "model-index", "autotrain_compatible", "endpoints_compatible", "region:us" ]
text-classification
2023-06-18T21:32:35Z
--- license: apache-2.0 tags: - generated_from_trainer datasets: - tweet_eval metrics: - accuracy model-index: - name: AIE-Assessment results: - task: name: Text Classification type: text-classification dataset: name: tweet_eval type: tweet_eval config: emotion split: test args: emotion metrics: - name: Accuracy type: accuracy value: 0.800844475721323 --- <!-- 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. --> # AIE-Assessment This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the tweet_eval dataset. It achieves the following results on the evaluation set: - Loss: 0.5687 - Accuracy: 0.8008 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 2e-05 - train_batch_size: 16 - eval_batch_size: 16 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 2 ### Training results | Training Loss | Epoch | Step | Validation Loss | Accuracy | |:-------------:|:-----:|:----:|:---------------:|:--------:| | No log | 1.0 | 204 | 0.6383 | 0.7910 | | No log | 2.0 | 408 | 0.5687 | 0.8008 | ### Framework versions - Transformers 4.29.2 - Pytorch 2.0.1 - Datasets 2.12.0 - Tokenizers 0.11.0