Marc Sun

marcsun13's activity

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

upvoted a paper 3 days ago

SINQ: Sinkhorn-Normalized Quantization for Calibration-Free Low-Precision LLM Weights

Paper • 2509.22944 • Published Sep 26 • 78

upvoted 2 articles 9 days ago

view article

Article

Classement compar:IA : des votes des utilisateurs au classement participatif des modèles

By •

10 days ago

• 6

view article

Article

On the Shifting Global Compute Landscape

By and 1 other •

15 days ago

• 47

upvoted 2 articles 3 months ago

view article

Article

Accelerate ND-Parallel: A guide to Efficient Multi-GPU Training

Aug 8

• 79

view article

Article

Welcome GPT OSS, the new open-source model family from OpenAI!

Aug 5

• 505

upvoted 2 articles 4 months ago

view article

Article

Introducing Trackio: A Lightweight Experiment Tracking Library from Hugging Face

Jul 29

• 195

view article

Article

Fast LoRA inference for Flux with Diffusers and PEFT

Jul 23

• 50

upvoted 2 articles 5 months ago

view article

Article

Transformers backend integration in SGLang

Jun 23

• 54

view article

Article

(LoRA) Fine-Tuning FLUX.1-dev on Consumer Hardware

Jun 19

• 92

upvoted a changelog 5 months ago

view changelog

Changelog

New Inference Providers Dashboard

Jun 5

• 65

upvoted an article 5 months ago

view article

Article

Fine-tuning Llama 2 70B using PyTorch FSDP

Sep 13, 2023

• 30

upvoted a collection 6 months ago

Flux quantized checkpoints

Collection

This collection regroups quantized flux checkpoints that we used in this blogpost: https://huggingface.co/blog/diffusers-quantization • 5 items • Updated May 21 • 2

upvoted 2 articles 6 months ago

view article

Article

The Transformers Library: standardizing model definitions

May 15

• 120

view article

Article

Exploring Quantization Backends in Diffusers

May 21

• 44

upvoted a collection 6 months ago

EXL3 models

Collection

36 items • Updated 3 days ago • 38

upvoted 2 articles 7 months ago

view article

Article

Introducing AutoRound: Intel’s Advanced Quantization for LLMs and VLMs

Apr 29

• 41

view article

Article

🔥 Announcing FLUX-Juiced: The Fastest Image Generation Endpoint (2.6 times faster)!

By and 3 others •

Apr 23

• 12

upvoted a collection 7 months 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 Jul 10 • 209

upvoted 2 articles 7 months ago

view article

Article

Memory-efficient Diffusion Transformers with Quanto and Diffusers

Jul 30, 2024

• 68

view article

Article

Welcome Llama 4 Maverick & Scout on Hugging Face

Apr 5

• 146