DrishtiSharma
wav2vec2-large-xls-r-300m-mr-v2
StableDiffusion-Prompt-Generator-GPT-Neo-125M
whisper-large-v2-serbian
whisper-large-v2-punjabi
finetuned-ViT-Indian-Food-Classification-v3
finetuned-SwinT-Indian-Food-Classification-v3
finetuned-ViT-Indian-Food-Classification-v1
finetuned-SwinT-Indian-Food-Classification-v2
finetuned-SwinT-Indian-Food-Classification-v1
whisper-large-v2-marathi
whisper-large-v2-punjabi-700-steps
whisper-large-v2-hungarian
wav2vec2-large-xls-r-300m-as-g1
whisper-large-v2-lithuanian
whisper-large-v2-hindi-2.5k-steps
whisper-medium-assamese
PPO-LunarLander-v2-8M-steps-successive-training
PPO-LunarLander-v2-12M-steps-successive-training
ppo-Huggy
PPO-Huggy-8-Epochs
qwen1.5-q4km-gguf
wav2vec2-large-xls-r-300m-or-d5
bert-large-uncased-hate-offensive-normal-speech-lr-2e-05
whisper-large-v2-kazakh
wav2vec2-large-xls-r-300m-hi-CV7
sentence-t5-large-quora-text-similarity
whisper-large-v2-punjabi-100-steps-LoRA
llama2-7b-int4-dolly-15k-english-flash-attention2-w-packing
wav2vec2-large-xls-r-300m-hsb-v1
test-coqui
wav2vec2-large-xls-r-300m-kk-with-LM
dqn-SpaceInvadersNoFrameskip-v4-2M-steps
SoccerTwos-numlayers-8
SoccerTwos-numlayers-4-2M-steps
distilbert-base-multilingual-cased-language-detection-fp16-false-bs-8
doplhin-2.1-mistral-7b-orpo-ultrafeedback-binarized-preferences
whisper-large-v2-malayalam
wav2vec2-base-finetuned-sentiment-mesd-v9
whisper-large-v2-kk-v1
wav2vec2-large-xls-r-300m-bg-d2
wav2vec2-large-xls-r-300m-hsb-v2
llama-2-7b-int4-alpaca-normal-attention-tp-2-merged
siglip_from_gemma-3-4b-it
finetuned-ViT-human-action-recognition-v1
wav2vec2-large-xls-r-300m-bg-v1
wav2vec2-large-xls-r-300m-br-d2
wav2vec2-large-xls-r-300m-hi-cv8
wav2vec2-large-xls-r-300m-hi-wx1
wav2vec2-large-xls-r-300m-pa-IN-dx1
wav2vec2-large-xls-r-300m-sat-a3
wav2vec2-xls-r-300m-rm-sursilv-d11
wav2vec2-xls-r-pa-IN-a1
lwg_cartoon_faces
SoccerTwos-numlayers-16
SoccerTwos-numlayers-64
SoccerTwos-numlayers-4
SoccerTwos-numlayers-2
speecht5_finetuned_voxpopuli_nl_test
speecht5_finetuned_voxpopuli_es_20k_steps_bs_8
wav2vec2-base-finetuned-gtzan-bs-16
distilbert-base-multilingual-cased-language-detection-fp16-false
distilbert-base-multilingual-cased-language-detection-fp16-true-bs-8
distilbert-base-multilingual-cased-language-detection-fp16-false-bs-64
DialoGPT-large-faqs-block-size-128-bs-16-lr-7e-6
DialoGPT-large-faqs-block-size-128-bs-16-lr-1e-05-deepspeed-stage2
bert-large-uncased-hate-offensive-normal-speech-lr-1e-05
llama2-7b-int4-dolly-15k-english-standard-attention-w-packing
Wav2vec2 Large Xls R 300m As V9
This model is a fine-tuned version of facebook/wav2vec2-xls-r-300m on the commonvoice dataset. It achieves the following results on the evaluation set: - Loss: 1.1679 - Wer: 0.5761 1. To evaluate on mozilla-foundation/commonvoice80 with test split python eval.py --modelid DrishtiSharma/wav2vec2-large-xls-r-300m-as-v9 --dataset mozilla-foundation/commonvoice80 --config as --split test --logoutputs 2. To evaluate on speech-recognition-community-v2/devdata Assamese (as) language isn't available in speech-recognition-community-v2/devdata The following hyperparameters were used during training: - learningrate: 0.000111 - trainbatchsize: 16 - evalbatchsize: 8 - seed: 42 - gradientaccumulationsteps: 2 - totaltrainbatchsize: 32 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lrschedulertype: linear - lrschedulerwarmupsteps: 300 - numepochs: 200 - mixedprecisiontraining: Native AMP | Training Loss | Epoch | Step | Validation Loss | Wer | |:-------------:|:------:|:----:|:---------------:|:------:| | 8.3852 | 10.51 | 200 | 3.6402 | 1.0 | | 3.5374 | 21.05 | 400 | 3.3894 | 1.0 | | 2.8645 | 31.56 | 600 | 1.3143 | 0.8303 | | 1.1784 | 42.1 | 800 | 0.9417 | 0.6661 | | 0.7805 | 52.62 | 1000 | 0.9292 | 0.6237 | | 0.5973 | 63.15 | 1200 | 0.9489 | 0.6014 | | 0.4784 | 73.67 | 1400 | 0.9916 | 0.5962 | | 0.4138 | 84.21 | 1600 | 1.0272 | 0.6121 | | 0.3491 | 94.72 | 1800 | 1.0412 | 0.5984 | | 0.3062 | 105.26 | 2000 | 1.0769 | 0.6005 | | 0.2707 | 115.77 | 2200 | 1.0708 | 0.5752 | | 0.2459 | 126.31 | 2400 | 1.1285 | 0.6009 | | 0.2234 | 136.82 | 2600 | 1.1209 | 0.5949 | | 0.2035 | 147.36 | 2800 | 1.1348 | 0.5842 | | 0.1876 | 157.87 | 3000 | 1.1480 | 0.5872 | | 0.1669 | 168.41 | 3200 | 1.1496 | 0.5838 | | 0.1595 | 178.92 | 3400 | 1.1721 | 0.5778 | | 0.1505 | 189.46 | 3600 | 1.1654 | 0.5744 | | 0.1486 | 199.97 | 3800 | 1.1679 | 0.5761 | - Transformers 4.16.1 - Pytorch 1.10.0+cu111 - Datasets 1.18.2 - Tokenizers 0.11.0
poem-gen-gpt2-small-spanish
whisper-medium-hindi
StableDiffusion-Prompt-Generator-GPT-Neo-125M-k1
roberta-large-lora-patent-classification-2e-4
finetuned-ConvNext-Indian-food
speecht5_finetuned_voxpopuli_es_20k_steps_16_batch_size
wav2vec2-base-finetuned-gtzan-bs-8
distilbert-base-multilingual-cased-language-detection-fp16-true-bs-32
distilbert-base-multilingual-cased-language-detection-fp16-false-bs-32
distilbert-base-multilingual-cased-language-detection-fp16-true-bs-4
DialoGPT-large-faqs-block-size-128-bs-16-lr-1e-5
DialoGPT-large-faqs-block-size-64-bs-16-lr-1e-05
DialoGPT-large-faqs-block-size-32-bs-16-lr-1e-05
DialoGPT-large-faqs-block-size-400-bs-16-lr-1e-05
mbart-large-50-en-es-translation-lr-1e-05-weight-decay-0.0
mbart-large-50-en-es-translation-lr-1e-05-weight-decay-0.01
llama2-7b-int4-dolly-15k-hindi-flash-attention2-w-packing
llama2-7b-int4-dolly-15k-english-unsloth-w-packing-qk-modules
mixtral-8x7b-instruct-v0.1-english-to-hinglish-translation
gemma-7b-it-dolly-15k-japanese-brainstorming-ipo
siglip-from-gemma-3-4b-pt
siglip_from_gemma-3-12b-pt
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [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] - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019). - 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]
whisper-large-v2-slovenian
llama-2-7b-flash-attention2-lora-patent-classification
wav2vec2-large-xls-r-300m-br-d10
wav2vec2-large-xls-r-300m-myv-v1
wav2vec2-large-xls-r-300m-or-dx12
wav2vec2-large-xls-r-300m-vot-final-a2
wav2vec2-xls-r-300m-rm-vallader-d1
autonlp-Text-Classification-Catalonia-Independence-AutoNLP-633018323
wav2vec2-base-finetuned-ks
wav2vec2-base-finetuned-sentiment-mesd-v2
poem-gen-spanish-t5-small-d2
whisper-large-v2-azerbaijani
whisper-large-v2-hungarian-400-steps
whisper-large-v2-hindi-to-nepali-transfer-learning-200-steps
StableDiffusion-Prompt-Generator-GPT-Neo-125M-v1
roberta-base-rotten_tomatoes-v1
ppo-Pyramids
speecht5_finetuned_voxpopuli_es_20k_steps_16_test1
codet5-small-Generate-docstrings-for-Python-bs-32
distilbert-base-multilingual-cased-language-detection-fp16-true
distilbert-base-multilingual-cased-language-detection-fp16-true-bs-64
distilbert-base-multilingual-cased-language-detection-fp16-true-bs-128
distilbert-base-multilingual-cased-language-detection-fp16-false-bs-128
DialoGPT-large-faqs-block-size128-bs-16
DialoGPT-large-faqs-block-size-128-bs-16-lr-2e-5
DialoGPT-large-faqs-block-size-128-bs-16-lr-0.5e-5
DialoGPT-large-faqs-block-size-128-bs-16-lr-5e-5
DialoGPT-large-faqs-block-size-128-bs-16-lr-2e-6
DialoGPT-large-faqs-block-size-256-bs-16-lr-1e-05
DialoGPT-large-faqs-block-size-16-bs-16-lr-1e-05
DialoGPT-large-faqs-block-size-350-bs-16-lr-1e-05
DialoGPT-large-faqs-block-size-128-bs-16-lr-1e-05-deepspeed-True
mbart-large-50-en-es-translation-lr-1e-05-weight-decay-0.0001
bert-base-uncased-hate-offensive-normal-speech-lr-2e-05
codebert-base-password-strength-classifier-normal-weight-balancing
roberta-large-lora-patent-classification-2e-5
llama2-7b-english-to-hinglish-translation
llama-pro-8b-english-to-hinglish-translation-merged
llama2-7b-chat-guanaco-1k-qa-unsloth-w-packing
whisper-large-v2-hausa
wav2vec2-large-xls-r-300m-ab-CV7
whisper-medium-serbian
codet5-small-generate-docstrings-codexglue-python-bs-32
wav2vec2-large-xls-r-300m-bas-v1
wav2vec2-large-xls-r-300m-hsb-v3
wav2vec2-large-xls-r-300m-sr-v4
wav2vec2-xls-r-300m-pa-IN-r5
distilbert-base-uncased-finetuned-emotion
xlm-roberta-base-finetuned-panx-de
poem-gen-t5-small
xls-r-es-test-lm-finetuned-sentiment-mesd
poem-gen-spanish-t5-small-d3
lwg_pokemon
TEST123
LayoutLMv3-Finetuned-CORD_100
whisper-large-v2-hindi-5k-steps
a2c-AntBulletEnv-v0
a2c-PandaReachDense-v2
speecht5_finetuned_voxpopuli_es_20k_steps_batch_size_32
distilhubert-finetuned-gtzan
distilhubert-finetuned-gtzan-bs-8
distilhubert-finetuned-gtzan-bs-16
hubert-base-ls960-finetuned-gtzan-bs-8
hubert-base-ls960-finetuned-gtzan-bs-4
distilhubert-finetuned-gtzan-bs-4
distilhubert-finetuned-gtzan-bs-4-fp16-false
distilhubert-finetuned-gtzan-bs-8-fp16-false
distilhubert-finetuned-gtzan-bs-16-fp16-false
distilbert-base-multilingual-cased-language-detection-fp16-false-bs-4
DialoGPT-large-faqs-block-size-128-bs-16-lr-1e-6
DialoGPT-large-faqs-block-size-128-bs-16-lr-5e-6
mbart-large-50-en-es-translation-lr-1e-05-weight-decay-0.001
mbart-large-50-en-es-translation-lr-1e-05-weight-decay-0.1
llama-2-7b-databricks-dolly-15k
bert-large-uncased-Hate_Offensive_or_Normal_Speech
distilbert-base-uncased-hate-offensive-normal-speech-lr-2e-05
fBERT-hate-offensive-normal-speech-lr-2e-05
hateBERT-hate-offensive-normal-speech-lr-2e-05
roberta-large-hate-offensive-normal-speech-lr-2e-05
bert-base-uncased-cosmos-mcqa
llama-2-7b-int4-alpaca-flash-attention-tp-2-merged
llama-2-7b-int4-alpaca-flash-attention-tp-1-merged
llama-2-7b-int4-alpaca-normal-attention-tp-1-merged
llama-2-7b-int4-dolly-15k-flashatn-r-32-merged
mistral-7b-bnb-4bit-dolly-15k-english-unsloth-w-packing
llama2-7b-tweet-summarization
llama-2-7b-english-riddles-espanol-reasoning-merged
llama2-7b-chat-guanaco-1k-qa-flashatn2-without-packing
llama-7b-chat-hf-medqa-packing-false-padding-left
llama2-7b-chat-hf-mental-health
zephyr-7B-beta-bitext-customer-support
dense-baseline
aya-c4-sparsity-0.5-gmp
smollm2-1.7b-instruct-lrsc-cosine-hindi-subset-fp16
- Developed by: DrishtiSharma - License: apache-2.0 - Finetuned from model : unsloth/SmolLM2-1.7B-Instruct This llama model was trained 2x faster with Unsloth and Huggingface's TRL library.
GEMMA-9B-A60
GEMMA-9B-A90
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [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] - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019). - 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]
GEMMA-9B-B90
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [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] - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019). - 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]