37 42 67

Marc Sun

marcsun13

AI & ML interests

LLM, Quantization, Training, Inference

Recent Activity

reacted to sayakpaul's post with 🔥 3 days ago

Commits speak louder than words 🤪 * 4 new video models * Multiple image models, including SANA & Flux Control * New quantizers -> GGUF & TorchAO * New training scripts Enjoy this holiday-special Diffusers release 🤗 Notes: https://github.com/huggingface/diffusers/releases/tag/v0.32.0

updated a model 3 days ago

hf-internal-testing/tiny-flux-dev-pipe-sharded-checkpoint-DDUF

updated a Space 24 days ago

DDUF/dduf-check

View all activity

Articles

Organizations

marcsun13's activity

upvoted a paper 25 days ago

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

Paper • 2310.08659 • Published Oct 12, 2023 • 25

upvoted an article 3 months ago

Article

Fixing Gradient Accumulation

Oct 16, 2024

• 46

upvoted 3 articles 4 months ago

Article

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

Sep 18, 2024

• 215

Article

Accelerate 1.0.0

Sep 13, 2024

• 52

Article

SmolLM - blazingly fast and remarkably powerful

Jul 16, 2024

• 296

upvoted an article 5 months ago

Article

XetHub is joining Hugging Face!

Aug 8, 2024

• 81

upvoted an article 7 months ago

Article

Benchmarking Text Generation Inference

May 29, 2024

• 29

upvoted a paper 7 months ago

Scaling Laws and Compute-Optimal Training Beyond Fixed Training Durations

Paper • 2405.18392 • Published May 28, 2024 • 12

upvoted an article 7 months ago

Article

License to Call: Introducing Transformers Agents 2.0

May 13, 2024

• 123

upvoted a paper 9 months ago

BitNet: Scaling 1-bit Transformers for Large Language Models

Paper • 2310.11453 • Published Oct 17, 2023 • 96

upvoted an article 9 months ago

Article

Welcome Llama 3 - Meta's new open LLM

Apr 18, 2024

• 281

upvoted a collection 9 months 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 • 698

upvoted 8 articles 9 months ago

Article

Vision Language Models Explained

Apr 11, 2024

• 239

Article

Introducing Idefics2: A Powerful 8B Vision-Language Model for the community

Apr 15, 2024

• 171

Article

Overview of natively supported quantization schemes in 🤗 Transformers

Sep 12, 2023

• 11

Article

Making LLMs lighter with AutoGPTQ and transformers

Aug 23, 2023

• 37

Article

A Gentle Introduction to 8-bit Matrix Multiplication for transformers at scale using transformers, accelerate and bitsandbytes

Aug 17, 2022

• 67

Article

Making LLMs even more accessible with bitsandbytes, 4-bit quantization and QLoRA

May 24, 2023

• 105

Article

Binary and Scalar Embedding Quantization for Significantly Faster & Cheaper Retrieval

Mar 22, 2024

• 70

Article

quanto: a pytorch quantization toolkit

Mar 18, 2024

• 33

Marc Sun

AI & ML interests

Recent Activity

Articles

Introducing SynthID Text

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

Accelerate 1.0.0

Llama 3.1 - 405B, 70B & 8B with multilinguality and long context

quanto: a pytorch quantization toolkit

Overview of natively supported quantization schemes in 🤗 Transformers

Making LLMs lighter with AutoGPTQ and transformers

Organizations

marcsun13's activity

Fixing Gradient Accumulation

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

Accelerate 1.0.0

SmolLM - blazingly fast and remarkably powerful

XetHub is joining Hugging Face!

Benchmarking Text Generation Inference

License to Call: Introducing Transformers Agents 2.0

Welcome Llama 3 - Meta's new open LLM

Vision Language Models Explained

Introducing Idefics2: A Powerful 8B Vision-Language Model for the community

Overview of natively supported quantization schemes in 🤗 Transformers

Making LLMs lighter with AutoGPTQ and transformers

A Gentle Introduction to 8-bit Matrix Multiplication for transformers at scale using transformers, accelerate and bitsandbytes

Making LLMs even more accessible with bitsandbytes, 4-bit quantization and QLoRA

Binary and Scalar Embedding Quantization for Significantly Faster & Cheaper Retrieval

quanto: a pytorch quantization toolkit