Shuyue Jia (Bruce)

shuyuej's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes

New activity in shuyuej/e5-mistral-7b-instruct-GPTQ 3 months ago

missing model.safetensors.index.json

3

#1 opened 4 months ago by kresimirfijacko

New activity in shuyuej/Mistral-Nemo-Instruct-2407-GPTQ 3 months ago

Can you create gptq 8 bits quants?

1

#1 opened 4 months ago by rjmehta

New activity in hugging-quants/Meta-Llama-3.1-405B-Instruct-GPTQ-INT4 3 months ago

Can you provide one model using `group_size=1024` to make the model smaller?

#15 opened 3 months ago by shuyuej

New activity in hugging-quants/Meta-Llama-3.1-405B-Instruct-GPTQ-INT4 4 months ago

OOM Error

#13 opened 4 months ago by shuyuej

Update quantize_config.json

1

#12 opened 4 months ago by shuyuej

Update config.json

1

#11 opened 4 months ago by shuyuej

Source codes to quantize the LLaMA 3.1 405B model

3

#10 opened 4 months ago by shuyuej

New activity in hugging-quants/Meta-Llama-3.1-70B-Instruct-GPTQ-INT4 4 months ago

Request for Mistral Large Instruct GPTQ INT4

4

#2 opened 4 months ago by sparsh35

New activity in mistralai/Mamba-Codestral-7B-v0.1 4 months ago

Missing config.json

5

#6 opened 4 months ago by wxl2001

New activity in openerotica/c4ai-command-r-plus-GPTQ-ERQ 4 months ago

Where can we download `quant.py`?

1

#1 opened 4 months ago by shuyuej

New activity in CohereForAI/c4ai-command-r-v01 4 months ago

Learning Rate during pretraining

1

#58 opened 4 months ago by shuyuej

New activity in Salesforce/SFR-Embedding-2_R 4 months ago

About the tokenizer - Why use LLaMA tokenizer?

#5 opened 4 months ago by shuyuej

New activity in dunzhang/stella_en_1.5B_v5 4 months ago

Model max_seq_length

6

#6 opened 4 months ago by shuyuej

New activity in Salesforce/SFR-Embedding-2_R 4 months ago

Model max_seq_length

1

#4 opened 4 months ago by shuyuej

New activity in openlifescienceai/open_medical_llm_leaderboard 6 months ago

Where can we find `eval_medical_llm.py` and `main.py`

1

#15 opened 6 months ago by shuyuej

New activity in google/gemma-7b 6 months ago

Fine-Tune a gemma model for question answering

17

#62 opened 9 months ago by Iamexperimenting

New activity in google/gemma-7b 7 months ago

Weird Performance Issue with Gemma-7b compared to Gemma-2b with Qlora

6

#91 opened 7 months ago by UserDAN

New activity in mistralai/Mixtral-8x7B-Instruct-v0.1 7 months ago

What is the actual context size of mistralai/Mixtral-8x7B-Instruct-v0.1 model

3

#186 opened 8 months ago by Pradeep1995

New activity in google/gemma-7b 8 months ago

Very different results with float16. [Actually, gemma-7b-it does not work with float16]

6

#33 opened 9 months ago by EarthWorm001