DrishtiSharma

194 models • 1 total models in database
Sort by:

wav2vec2-large-xls-r-300m-mr-v2

license:apache-2.0
116
0

StableDiffusion-Prompt-Generator-GPT-Neo-125M

105
18

whisper-large-v2-serbian

license:apache-2.0
65
3

whisper-large-v2-punjabi

license:apache-2.0
53
1

finetuned-ViT-Indian-Food-Classification-v3

license:apache-2.0
47
2

finetuned-SwinT-Indian-Food-Classification-v3

license:apache-2.0
43
0

finetuned-ViT-Indian-Food-Classification-v1

license:apache-2.0
41
0

finetuned-SwinT-Indian-Food-Classification-v2

license:apache-2.0
40
0

finetuned-SwinT-Indian-Food-Classification-v1

license:apache-2.0
38
0

whisper-large-v2-marathi

license:apache-2.0
27
2

whisper-large-v2-punjabi-700-steps

license:apache-2.0
19
1

whisper-large-v2-hungarian

license:apache-2.0
18
2

wav2vec2-large-xls-r-300m-as-g1

license:apache-2.0
17
0

whisper-large-v2-lithuanian

license:apache-2.0
17
0

whisper-large-v2-hindi-2.5k-steps

license:apache-2.0
16
2

whisper-medium-assamese

license:apache-2.0
15
0

PPO-LunarLander-v2-8M-steps-successive-training

15
0

PPO-LunarLander-v2-12M-steps-successive-training

14
0

ppo-Huggy

12
0

PPO-Huggy-8-Epochs

12
0

qwen1.5-q4km-gguf

12
0

wav2vec2-large-xls-r-300m-or-d5

license:apache-2.0
11
0

bert-large-uncased-hate-offensive-normal-speech-lr-2e-05

license:apache-2.0
11
0

whisper-large-v2-kazakh

license:apache-2.0
10
3

wav2vec2-large-xls-r-300m-hi-CV7

license:apache-2.0
9
0

sentence-t5-large-quora-text-similarity

8
2

whisper-large-v2-punjabi-100-steps-LoRA

8
0

llama2-7b-int4-dolly-15k-english-flash-attention2-w-packing

NaNK
base_model:NousResearch/Llama-2-7b-hf
8
0

wav2vec2-large-xls-r-300m-hsb-v1

license:apache-2.0
7
0

test-coqui

7
0

wav2vec2-large-xls-r-300m-kk-with-LM

license:apache-2.0
6
2

dqn-SpaceInvadersNoFrameskip-v4-2M-steps

6
0

SoccerTwos-numlayers-8

6
0

SoccerTwos-numlayers-4-2M-steps

6
0

distilbert-base-multilingual-cased-language-detection-fp16-false-bs-8

license:apache-2.0
6
0

doplhin-2.1-mistral-7b-orpo-ultrafeedback-binarized-preferences

NaNK
license:apache-2.0
6
0

whisper-large-v2-malayalam

license:apache-2.0
5
4

wav2vec2-base-finetuned-sentiment-mesd-v9

license:apache-2.0
5
2

whisper-large-v2-kk-v1

license:apache-2.0
5
2

wav2vec2-large-xls-r-300m-bg-d2

license:apache-2.0
5
1

wav2vec2-large-xls-r-300m-hsb-v2

license:apache-2.0
5
0

llama-2-7b-int4-alpaca-normal-attention-tp-2-merged

NaNK
llama
5
0

siglip_from_gemma-3-4b-it

NaNK
5
0

finetuned-ViT-human-action-recognition-v1

license:apache-2.0
4
7

wav2vec2-large-xls-r-300m-bg-v1

license:apache-2.0
4
1

wav2vec2-large-xls-r-300m-br-d2

license:apache-2.0
4
0

wav2vec2-large-xls-r-300m-hi-cv8

license:apache-2.0
4
0

wav2vec2-large-xls-r-300m-hi-wx1

license:apache-2.0
4
0

wav2vec2-large-xls-r-300m-pa-IN-dx1

license:apache-2.0
4
0

wav2vec2-large-xls-r-300m-sat-a3

license:apache-2.0
4
0

wav2vec2-xls-r-300m-rm-sursilv-d11

license:apache-2.0
4
0

wav2vec2-xls-r-pa-IN-a1

license:apache-2.0
4
0

lwg_cartoon_faces

license:mit
4
0

SoccerTwos-numlayers-16

4
0

SoccerTwos-numlayers-64

4
0

SoccerTwos-numlayers-4

4
0

SoccerTwos-numlayers-2

4
0

speecht5_finetuned_voxpopuli_nl_test

license:mit
4
0

speecht5_finetuned_voxpopuli_es_20k_steps_bs_8

license:mit
4
0

wav2vec2-base-finetuned-gtzan-bs-16

license:apache-2.0
4
0

distilbert-base-multilingual-cased-language-detection-fp16-false

license:apache-2.0
4
0

distilbert-base-multilingual-cased-language-detection-fp16-true-bs-8

license:apache-2.0
4
0

distilbert-base-multilingual-cased-language-detection-fp16-false-bs-64

license:apache-2.0
4
0

DialoGPT-large-faqs-block-size-128-bs-16-lr-7e-6

license:mit
4
0

DialoGPT-large-faqs-block-size-128-bs-16-lr-1e-05-deepspeed-stage2

license:mit
4
0

bert-large-uncased-hate-offensive-normal-speech-lr-1e-05

license:apache-2.0
4
0

llama2-7b-int4-dolly-15k-english-standard-attention-w-packing

NaNK
base_model:NousResearch/Llama-2-7b-hf
4
0

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

license:apache-2.0
4
0

poem-gen-gpt2-small-spanish

license:apache-2.0
3
1

whisper-medium-hindi

license:apache-2.0
3
1

StableDiffusion-Prompt-Generator-GPT-Neo-125M-k1

3
1

roberta-large-lora-patent-classification-2e-4

license:mit
3
1

finetuned-ConvNext-Indian-food

license:apache-2.0
3
0

speecht5_finetuned_voxpopuli_es_20k_steps_16_batch_size

license:mit
3
0

wav2vec2-base-finetuned-gtzan-bs-8

license:apache-2.0
3
0

distilbert-base-multilingual-cased-language-detection-fp16-true-bs-32

license:apache-2.0
3
0

distilbert-base-multilingual-cased-language-detection-fp16-false-bs-32

license:apache-2.0
3
0

distilbert-base-multilingual-cased-language-detection-fp16-true-bs-4

license:apache-2.0
3
0

DialoGPT-large-faqs-block-size-128-bs-16-lr-1e-5

license:mit
3
0

DialoGPT-large-faqs-block-size-64-bs-16-lr-1e-05

license:mit
3
0

DialoGPT-large-faqs-block-size-32-bs-16-lr-1e-05

license:mit
3
0

DialoGPT-large-faqs-block-size-400-bs-16-lr-1e-05

license:mit
3
0

mbart-large-50-en-es-translation-lr-1e-05-weight-decay-0.0

NaNK
license:mit
3
0

mbart-large-50-en-es-translation-lr-1e-05-weight-decay-0.01

NaNK
license:mit
3
0

llama2-7b-int4-dolly-15k-hindi-flash-attention2-w-packing

NaNK
base_model:NousResearch/Llama-2-7b-hf
3
0

llama2-7b-int4-dolly-15k-english-unsloth-w-packing-qk-modules

NaNK
base_model:unsloth/llama-2-7b
3
0

mixtral-8x7b-instruct-v0.1-english-to-hinglish-translation

NaNK
license:apache-2.0
3
0

gemma-7b-it-dolly-15k-japanese-brainstorming-ipo

NaNK
3
0

siglip-from-gemma-3-4b-pt

NaNK
3
0

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]

NaNK
3
0

whisper-large-v2-slovenian

license:apache-2.0
2
1

llama-2-7b-flash-attention2-lora-patent-classification

NaNK
base_model:NousResearch/Llama-2-7b-hf
2
1

wav2vec2-large-xls-r-300m-br-d10

license:apache-2.0
2
0

wav2vec2-large-xls-r-300m-myv-v1

license:apache-2.0
2
0

wav2vec2-large-xls-r-300m-or-dx12

license:apache-2.0
2
0

wav2vec2-large-xls-r-300m-vot-final-a2

license:apache-2.0
2
0

wav2vec2-xls-r-300m-rm-vallader-d1

license:apache-2.0
2
0

autonlp-Text-Classification-Catalonia-Independence-AutoNLP-633018323

2
0

wav2vec2-base-finetuned-ks

license:apache-2.0
2
0

wav2vec2-base-finetuned-sentiment-mesd-v2

license:apache-2.0
2
0

poem-gen-spanish-t5-small-d2

license:mit
2
0

whisper-large-v2-azerbaijani

license:apache-2.0
2
0

whisper-large-v2-hungarian-400-steps

license:apache-2.0
2
0

whisper-large-v2-hindi-to-nepali-transfer-learning-200-steps

license:apache-2.0
2
0

StableDiffusion-Prompt-Generator-GPT-Neo-125M-v1

2
0

roberta-base-rotten_tomatoes-v1

license:mit
2
0

ppo-Pyramids

2
0

speecht5_finetuned_voxpopuli_es_20k_steps_16_test1

license:mit
2
0

codet5-small-Generate-docstrings-for-Python-bs-32

license:apache-2.0
2
0

distilbert-base-multilingual-cased-language-detection-fp16-true

license:apache-2.0
2
0

distilbert-base-multilingual-cased-language-detection-fp16-true-bs-64

license:apache-2.0
2
0

distilbert-base-multilingual-cased-language-detection-fp16-true-bs-128

license:apache-2.0
2
0

distilbert-base-multilingual-cased-language-detection-fp16-false-bs-128

license:apache-2.0
2
0

DialoGPT-large-faqs-block-size128-bs-16

license:mit
2
0

DialoGPT-large-faqs-block-size-128-bs-16-lr-2e-5

license:mit
2
0

DialoGPT-large-faqs-block-size-128-bs-16-lr-0.5e-5

license:mit
2
0

DialoGPT-large-faqs-block-size-128-bs-16-lr-5e-5

license:mit
2
0

DialoGPT-large-faqs-block-size-128-bs-16-lr-2e-6

license:mit
2
0

DialoGPT-large-faqs-block-size-256-bs-16-lr-1e-05

license:mit
2
0

DialoGPT-large-faqs-block-size-16-bs-16-lr-1e-05

license:mit
2
0

DialoGPT-large-faqs-block-size-350-bs-16-lr-1e-05

license:mit
2
0

DialoGPT-large-faqs-block-size-128-bs-16-lr-1e-05-deepspeed-True

license:mit
2
0

mbart-large-50-en-es-translation-lr-1e-05-weight-decay-0.0001

NaNK
license:mit
2
0

bert-base-uncased-hate-offensive-normal-speech-lr-2e-05

license:apache-2.0
2
0

codebert-base-password-strength-classifier-normal-weight-balancing

2
0

roberta-large-lora-patent-classification-2e-5

license:mit
2
0

llama2-7b-english-to-hinglish-translation

NaNK
base_model:NousResearch/Llama-2-7b-hf
2
0

llama-pro-8b-english-to-hinglish-translation-merged

NaNK
llama
2
0

llama2-7b-chat-guanaco-1k-qa-unsloth-w-packing

NaNK
base_model:unsloth/llama-2-7b-chat-bnb-4bit
2
0

whisper-large-v2-hausa

license:apache-2.0
1
5

wav2vec2-large-xls-r-300m-ab-CV7

license:apache-2.0
1
1

whisper-medium-serbian

license:apache-2.0
1
1

codet5-small-generate-docstrings-codexglue-python-bs-32

license:apache-2.0
1
1

wav2vec2-large-xls-r-300m-bas-v1

license:apache-2.0
1
0

wav2vec2-large-xls-r-300m-hsb-v3

license:apache-2.0
1
0

wav2vec2-large-xls-r-300m-sr-v4

license:apache-2.0
1
0

wav2vec2-xls-r-300m-pa-IN-r5

license:apache-2.0
1
0

distilbert-base-uncased-finetuned-emotion

1
0

xlm-roberta-base-finetuned-panx-de

1
0

poem-gen-t5-small

license:apache-2.0
1
0

xls-r-es-test-lm-finetuned-sentiment-mesd

license:apache-2.0
1
0

poem-gen-spanish-t5-small-d3

1
0

lwg_pokemon

license:mit
1
0

TEST123

1
0

LayoutLMv3-Finetuned-CORD_100

license:cc-by-nc-sa-4.0
1
0

whisper-large-v2-hindi-5k-steps

license:apache-2.0
1
0

a2c-AntBulletEnv-v0

1
0

a2c-PandaReachDense-v2

1
0

speecht5_finetuned_voxpopuli_es_20k_steps_batch_size_32

license:mit
1
0

distilhubert-finetuned-gtzan

1
0

distilhubert-finetuned-gtzan-bs-8

license:apache-2.0
1
0

distilhubert-finetuned-gtzan-bs-16

license:apache-2.0
1
0

hubert-base-ls960-finetuned-gtzan-bs-8

NaNK
license:apache-2.0
1
0

hubert-base-ls960-finetuned-gtzan-bs-4

1
0

distilhubert-finetuned-gtzan-bs-4

license:apache-2.0
1
0

distilhubert-finetuned-gtzan-bs-4-fp16-false

license:apache-2.0
1
0

distilhubert-finetuned-gtzan-bs-8-fp16-false

license:apache-2.0
1
0

distilhubert-finetuned-gtzan-bs-16-fp16-false

license:apache-2.0
1
0

distilbert-base-multilingual-cased-language-detection-fp16-false-bs-4

license:apache-2.0
1
0

DialoGPT-large-faqs-block-size-128-bs-16-lr-1e-6

license:mit
1
0

DialoGPT-large-faqs-block-size-128-bs-16-lr-5e-6

license:mit
1
0

mbart-large-50-en-es-translation-lr-1e-05-weight-decay-0.001

NaNK
license:mit
1
0

mbart-large-50-en-es-translation-lr-1e-05-weight-decay-0.1

NaNK
license:mit
1
0

llama-2-7b-databricks-dolly-15k

NaNK
llama
1
0

bert-large-uncased-Hate_Offensive_or_Normal_Speech

license:apache-2.0
1
0

distilbert-base-uncased-hate-offensive-normal-speech-lr-2e-05

license:apache-2.0
1
0

fBERT-hate-offensive-normal-speech-lr-2e-05

1
0

hateBERT-hate-offensive-normal-speech-lr-2e-05

1
0

roberta-large-hate-offensive-normal-speech-lr-2e-05

license:mit
1
0

bert-base-uncased-cosmos-mcqa

license:apache-2.0
1
0

llama-2-7b-int4-alpaca-flash-attention-tp-2-merged

NaNK
llama
1
0

llama-2-7b-int4-alpaca-flash-attention-tp-1-merged

NaNK
llama
1
0

llama-2-7b-int4-alpaca-normal-attention-tp-1-merged

NaNK
llama
1
0

llama-2-7b-int4-dolly-15k-flashatn-r-32-merged

NaNK
llama
1
0

mistral-7b-bnb-4bit-dolly-15k-english-unsloth-w-packing

NaNK
license:apache-2.0
1
0

llama2-7b-tweet-summarization

NaNK
base_model:NousResearch/Llama-2-7b-hf
1
0

llama-2-7b-english-riddles-espanol-reasoning-merged

NaNK
llama
1
0

llama2-7b-chat-guanaco-1k-qa-flashatn2-without-packing

NaNK
base_model:NousResearch/Llama-2-7b-chat-hf
1
0

llama-7b-chat-hf-medqa-packing-false-padding-left

NaNK
base_model:NousResearch/Llama-2-7b-chat-hf
1
0

llama2-7b-chat-hf-mental-health

NaNK
base_model:NousResearch/Llama-2-7b-chat-hf
1
0

zephyr-7B-beta-bitext-customer-support

NaNK
license:mit
1
0

dense-baseline

1
0

aya-c4-sparsity-0.5-gmp

1
0

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.

NaNK
llama
1
0

GEMMA-9B-A60

NaNK
1
0

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]

NaNK
1
0

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]

NaNK
1
0

whisper-large-v2-vietnamese

license:apache-2.0
0
2

wav2vec2-large-xls-r-300m-as-with-LM-v2

license:apache-2.0
0
1

wav2vec2-xls-r-300m-kk-n2

license:apache-2.0
0
1

whisper-medium-serbian-v1

license:apache-2.0
0
1

whisper-large-v2-ne-NP-v1

license:apache-2.0
0
1

whisper-large-v2-lithuanian-400-steps

license:apache-2.0
0
1

whisper-large-v2-breton-3k-steps

license:apache-2.0
0
1