52 50 75

Marc Sun

marcsun13

AI & ML interests

LLM, Quantization, Training, Inference

Recent Activity

new activity about 11 hours ago

hf-accelerate/model-memory-usage:Error accessing Llama4 models: 'does not have any library metadata on the Hub'

new activity about 11 hours ago

hf-accelerate/model-memory-usage:GPTQ group size effects vRAM usage

new activity about 11 hours ago

hf-accelerate/model-memory-usage:Determining Minimum GPU Memory and Input Text Length Calculation in Model Training

View all activity

Organizations

marcsun13's activity

upvoted a collection 10 days ago

Gemma 3 QAT

Collection

Quantization Aware Trained (QAT) Gemma 3 checkpoints. The model preserves similar quality as half precision while using 3x less memory • 15 items • Updated 10 days ago • 172

upvoted an article 18 days ago

Article

Memory-efficient Diffusion Transformers with Quanto and Diffusers

Jul 30, 2024

• 66

upvoted an article 23 days ago

Article

Welcome Llama 4 Maverick & Scout on Hugging Face!

24 days ago

• 141

upvoted a collection 23 days ago

Llama 4

Collection

Llama 4 release • 10 items • Updated 23 days ago • 455

upvoted an article about 1 month ago

Article

NVIDIA's GTC 2025 Announcement for Physical AI Developers: New Open Models and Datasets

Mar 18

• 35

upvoted 2 articles about 2 months ago

Article

Welcome Gemma 3: Google's all new multimodal, multilingual, long context open LLM

Mar 12

• 403

Article

LLM Inference on Edge: A Fun and Easy Guide to run LLMs via React Native on your Phone!

Mar 7

• 53

upvoted a paper 5 months ago

LoftQ: LoRA-Fine-Tuning-Aware Quantization for Large Language Models

Paper • 2310.08659 • Published Oct 12, 2023 • 28

upvoted an article 6 months ago

Article

Fixing Gradient Accumulation

Oct 16, 2024

• 53

upvoted 2 articles 7 months ago

Article

Fine-tuning LLMs to 1.58bit: extreme quantization made easy

Sep 18, 2024

• 239

Article

Accelerate 1.0.0

Sep 13, 2024

• 52

upvoted an article 8 months ago

Article

SmolLM - blazingly fast and remarkably powerful

Jul 16, 2024

• 358

upvoted an article 9 months ago

Article

XetHub is joining Hugging Face!

Aug 8, 2024

• 92

upvoted an article 11 months ago

Article

Benchmarking Text Generation Inference

May 29, 2024

• 31

upvoted a paper 11 months ago

Scaling Laws and Compute-Optimal Training Beyond Fixed Training Durations

Paper • 2405.18392 • Published May 28, 2024 • 12

upvoted an article 11 months ago

Article

License to Call: Introducing Transformers Agents 2.0

May 13, 2024

• 131

upvoted a paper about 1 year ago

BitNet: Scaling 1-bit Transformers for Large Language Models

Paper • 2310.11453 • Published Oct 17, 2023 • 101

upvoted an article about 1 year ago

Article

Welcome Llama 3 - Meta's new open LLM

Apr 18, 2024

• 287

upvoted a collection about 1 year ago

Meta Llama 3

Collection

This collection hosts the transformers and original repos of the Meta Llama 3 and Llama Guard 2 releases • 5 items • Updated Dec 6, 2024 • 750