Hugging Face's logo
Marc Sun's picture
24 28 55

Marc Sun

marcsun13
muhtasham's profile picture giadap's profile picture pcuenq's profile picture
·
_marcsun
SunMarc

AI & ML interests

LLM, Quantization, Training, Inference

Articles

Organizations

Hugging Face's profile picture Hugging Face Internal Testing Organization's profile picture HuggingFaceM4's profile picture Hugging Face OSS Metrics's profile picture accelerate's profile picture MLX Community's profile picture LocalLLaMA's profile picture Quanto library's profile picture

marcsun13's activity

New activity in google/flan-t5-xxl about 1 month ago

ValueError: Need either a `state_dict` or a `save_folder` containing offloaded weights.

5
#53 opened 10 months ago by tuannguyends
New activity in huggingface/documentation-images about 2 months ago

Upload NousResearch-Llama-2-7b-hf_Perplexity.png

1
#292 opened about 2 months ago by marcsun13

Upload NousResearch-Llama-2-7b-hf_Perplexity.png
#291 opened about 2 months ago by marcsun13
New activity in mlx-community/Llama-2-7b-chat-4-bit 5 months ago

Update README.md

1
#4 opened 5 months ago by marcsun13

Update README.md
#3 opened 5 months ago by marcsun13
New activity in mlx-community/Mistral-7B-Instruct-v0.2-4-bit 5 months ago

Update README.md
#5 opened 5 months ago by marcsun13

Update config.json

1
#4 opened 5 months ago by marcsun13
New activity in mistralai/Mixtral-8x7B-Instruct-v0.1 5 months ago

Intuition for quality decrease after quantization

4
#23 opened 5 months ago by krumeto
New activity in mistralai/Mistral-7B-v0.1 6 months ago

Adding `safetensors` variant of this model

2
#91 opened 6 months ago by lcahill
New activity in hf-accelerate/model-memory-usage 6 months ago

Llama-2 models don't work since they have auth token required. I have an auth token but it is not doisplaying

7
#16 opened 8 months ago by sayambhu

Determining Minimum GPU Memory and Input Text Length Calculation in Model Training

2
#19 opened 7 months ago by kobe8-24
New activity in mistralai/Mistral-7B-v0.1 6 months ago

Does Mistral support accelerate library?

4
#65 opened 7 months ago by Sp1der
New activity in marcsun13/Llama-2-13B-AWQ 6 months ago

Update config.json
#1 opened 6 months ago by ybelkada
New activity in marcsun13/opt-125m-awq 7 months ago

Update config.json
#3 opened 7 months ago by ybelkada

Update config.json
#2 opened 7 months ago by ybelkada

Update config.json
#1 opened 7 months ago by ybelkada
New activity in huggingface/documentation-images 8 months ago

Upload A100_use_cache_True.jpg
#181 opened 8 months ago by marcsun13

add images to 163_overview-quantization-transformers

1
#180 opened 8 months ago by marcsun13

add overview-quantization-transformers blog images
#179 opened 8 months ago by marcsun13

add images for overview-quantization-transformers blog

1
#178 opened 8 months ago by marcsun13

overview-quantization-transformers blog images
#177 opened 8 months ago by marcsun13

add images to overview-quantization-transformers folder
#176 opened 8 months ago by marcsun13
New activity in hf-accelerate/model-memory-usage 9 months ago

Add link to the access token

1
#5 opened 9 months ago by marcsun13

Model Memory Consumption of Llama-2 models, access granted

8
#4 opened 9 months ago by arkoi