Imran ullah

#3 opened 4 days ago by

New activity in nvidia/Llama-3.1-Nemotron-70B-Instruct-HF 5 days ago

the model is not optimize in term of inference

#7 opened 5 days ago by

New activity in FINGU-AI/QWEN2.5-14B-Bnk-FP16 11 days ago

Update README.md

#2 opened 11 days ago by

Update README.md

#1 opened 11 days ago by

New activity in Imran1/Qwen2.5-72B-Instruct-FP8 13 days ago

Update inference.py

#8 opened 13 days ago by

Update inference.py

#7 opened 13 days ago by

Update inference.py

#6 opened 13 days ago by

Upload requirements.txt

#5 opened 13 days ago by

Upload inference.py

#4 opened 13 days ago by

New activity in vinayaggarwal5050/tts-hindi-v1.0 21 days ago

Create requirements.txt

#1 opened 21 days ago by

New activity in amphion/naturalspeech3_facodec 21 days ago

how to use as a text to speech?

#3 opened 21 days ago by

New activity in iiiorg/piiranha-v1-detect-personal-information about 1 month ago

Can we convert it back into original text

#2 opened about 1 month ago by

Paper • 2401.10020 • Published Jan 18 • 143 •

commented a paper 4 months ago

Self-Rewarding Language Models

17

New activity in Alibaba-NLP/gte-Qwen2-7B-instruct 4 months ago

Training embadding Issues.

2

#8 opened 4 months ago by

New activity in meta-llama/Meta-Llama-3-8B-Instruct 5 months ago

Why there is not pad token?

25

#101 opened 5 months ago by

New activity in FINGU-AI/qwen-finance 5 months ago

Update app.py

#2 opened 5 months ago by

Update app.py

#1 opened 5 months ago by

New activity in Imran1/dogtestset 6 months ago

[bot] Conversion to Parquet

#1 opened 11 months ago by

parquet-converter

New activity in Imran1/newdatasetdogb 6 months ago

[bot] Conversion to Parquet

#1 opened 11 months ago by

parquet-converter

New activity in nvidia/Llama3-ChatQA-1.5-8B 6 months ago

Chat template

15

#5 opened 6 months ago by

bartowski

New activity in microsoft/Phi-3-mini-4k-instruct 6 months ago

the phi3 model not learning from training data using orpo.

3

#44 opened 6 months ago by

New activity in Qwen/Qwen1.5-MoE-A2.7B-Chat 7 months ago

Can I fine tune the Qwen MOE?

#2 opened 7 months ago by

New activity in myshell-ai/MeloTTS-English-v2 8 months ago

Fine tuning for low resource language

#1 opened 8 months ago by

New activity in openai/whisper-large-v3 8 months ago

How to adapt for low resource language?

9

#73 opened 9 months ago by

New activity in facebook/w2v-bert-2.0 8 months ago

fine tuning not working .

#20 opened 8 months ago by

New activity in sanchit-gandhi/whisper-small-hi-flax 9 months ago

How to adapt whisper for low resource language.

#3 opened 9 months ago by

New activity in facebook/w2v-bert-2.0 9 months ago

tokenizer issues

2

#15 opened 9 months ago by

New activity in microsoft/phi-2 9 months ago

How to fine-tune this? + Training code

43

#19 opened 10 months ago by

cekal

in fine tuning the model begin with zero loss.

6

#85 opened 9 months ago by

New activity in berkeley-nest/Starling-LM-7B-alpha 10 months ago

Issues in the tokenizer

4

#25 opened 10 months ago by

New activity in THUDM/cogvlm-chat-hf 11 months ago

How to deploy this model on sage maker and use as a api

#7 opened 11 months ago by

New activity in openai/whisper-large-v2 about 1 year ago

Why not print the entire text of the audio?

13

#50 opened over 1 year ago by

wadexiao

New activity in tiiuae/falcon-7b over 1 year ago

How to push or shere adapter to the hub?

7

#52 opened over 1 year ago by

New activity in bigscience/bloomz-560m over 1 year ago

Evaluation error !!!

#10 opened over 1 year ago by

New activity in tiiuae/falcon-40b over 1 year ago

ValueError: The following model_kwargs are not used by the model: ['token_type_ids'] (note: typos in the generate arguments will also show up in this list)

4

#7 opened over 1 year ago by

New activity in tiiuae/falcon-7b-instruct over 1 year ago

ValueError: The following `model_kwargs` are not used by the model: ['token_type_ids'] (note: typos in the generate arguments will also show up in this list)

4

#2 opened over 1 year ago by

New activity in Imran1/gpt2-urdu-news over 1 year ago

Adding `safetensors` variant of this model

#1 opened over 1 year ago by

SFconvertbot

New activity in bigscience/bloom over 1 year ago

What are the best prompt engineering for bloom?

#218 opened over 1 year ago by

The bloom7b model not support contrastive search nor do_sample with peft and just repeating the output

5

#217 opened over 1 year ago by