Marc Sun's picture

Marc Sun

marcsun13

·

AI & ML interests

LLM, Quantization, Training, Inference

Recent Activity

upvoted an article about 16 hours ago

Fine-tuning Llama 2 70B using PyTorch FSDP

liked a model 6 days ago

deepseek-ai/DeepSeek-R1-0528

reacted to sayakpaul's post with 🚀 8 days ago

Diffusers supports a good variety of quantization backends. It can be challenging to navigate through them, given the complex nature of diffusion pipelines in general. So, @derekl35 set out to write a comprehensive guide that puts users in the front seat. Explore the different backends we support, learn the trade-offs they offer, and finally, check out the cool space we built that lets you compare quantization results. Give it a go here: https://lnkd.in/gf8Pi4-2

View all activity

Organizations

marcsun13's activity

New activity in hf-accelerate/accelerate_examples 15 days ago

add multi_xpu configuration

#5 opened 21 days ago by

New activity in hf-accelerate/model-memory-usage 29 days ago

Error accessing Llama4 models: 'does not have any library metadata on the Hub'

#39 opened about 1 month ago by

New activity in hf-accelerate/model-memory-usage about 1 month ago

GPTQ group size effects vRAM usage

#18 opened over 1 year ago by

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

#19 opened over 1 year ago by

microsoft/Florence-2-base raises error without any detail

#36 opened 9 months ago by

For Llama-2 model, I tried to get the memory usage, it says I do not have the access

#35 opened 9 months ago by

Improve name of the model detection to allow several URL usages

#28 opened about 1 year ago by

meta-llama/Meta-Llama-3.1-8B-Instruct ....why not found this

#34 opened 9 months ago by

Llama3 is not found using link and API token

#31 opened about 1 year ago by

Question about Gradient calculation

#30 opened about 1 year ago by

How to Calculate GPU usage for re-training Microsoft/speechT5_tts ?

#27 opened about 1 year ago by

huggingfacerohit

Unable to Access Gated Model Repository databricks/dbrx-instruct

#26 opened about 1 year ago by

Data Wrong, THUDM/chatglm3-6b

#20 opened over 1 year ago by

Analyzing tool for inference

#13 opened over 1 year ago by

Dropdown menu of models

#2 opened almost 2 years ago by

Plz fix it!!!

#33 opened 10 months ago by

This space is no longer working

#38 opened 4 months ago by

New activity in meta-llama/Llama-3.1-405B-Instruct-FP8 11 months ago

Upload folder using huggingface_hub

#4 opened 11 months ago by

New activity in meta-llama/Llama-3.1-405B-FP8 11 months ago

Upload folder using huggingface_hub

#8 opened 11 months ago by

Upload folder using huggingface_hub

#8 opened 11 months ago by