Huu-Hiep Nguyen's picture

34 506

Huu-Hiep Nguyen

hiepnh

·

AI & ML interests

None yet

Recent Activity

liked a model 3 days ago

almanach/camembert-base

liked a model 4 days ago

ibm-granite/granite-guardian-3.3-8b

liked a model 5 days ago

deepseek-ai/DeepSeek-V3.2

View all activity

Organizations

None yet

upvoted an article 8 days ago

Article

Continuous batching from first principles

+1

12 days ago

•

242

upvoted 2 articles 24 days ago

Article

Who Routes LLM Routers? RouterArena: Building the Evaluation Foundation for LLM Routing

26 days ago

•

9

Article

🌳 QAT: The Art of Growing a Bonsai Model

28 days ago

•

15

upvoted an article 25 days ago

Article

Uncensor any LLM with abliteration

Jun 13, 2024

•

733

upvoted a collection 25 days ago

abliterated-v3

Latest gen of the abliterated models I've produced • 17 items • Updated Jun 3, 2024 • 134

upvoted an article 2 months ago

Article

Cactus: High-Performance AI Inference on Any Smartphone

Oct 3

•

8

upvoted 2 articles 3 months ago

Article

Welcome EmbeddingGemma, Google's new efficient embedding model

+4

Sep 4

•

263

Article

The SOTA Text-to-speech and Zero Shot Voice cloning model that no one knows about...

Jan 20

•

74

upvoted 3 collections 3 months ago

Orpheus Multilingual Research Release

Beta Release of multilingual models. • 12 items • Updated Apr 10 • 106

Orpheus TTS

TTS Towards Human-Sounding Speech • 2 items • Updated Mar 18 • 74

FastVLM

Efficient Vision Encoding for Vision Language Models • 9 items • Updated Sep 2 • 104

upvoted a collection 6 months ago

Falcon-H1

Falcon-H1 Family of Hybrid-Head Language Models (Transformer-SSM), including 0.5B, 1.5B, 1.5B-Deep, 3B, 7B, and 34B (pretrained & instruction-tuned). • 38 items • Updated about 1 month ago • 56

upvoted a paper 8 months ago

SmolVLM: Redefining small and efficient multimodal models

Paper • 2504.05299 • Published Apr 7 • 200

upvoted a paper 9 months ago

Why Do Multi-Agent LLM Systems Fail?

Paper • 2503.13657 • Published Mar 17 • 47

upvoted an article 10 months ago

Article

Mahjong: Where Grandmas Beat The Best LLMs

Feb 18

•

9

upvoted 2 collections about 1 year ago

Llama 3.2

This collection hosts the transformers and original repos of the Llama 3.2 and Llama Guard 3 • 15 items • Updated Dec 6, 2024 • 647

DataGemma Release

A series of pioneering open models that help ground LLMs in real-world data through Data Commons. • 2 items • Updated Jul 10 • 86

upvoted 2 collections over 1 year ago

Yi-Coder

4 items • Updated Sep 4, 2024 • 31

DeepSeekCoder-V2

6 items • Updated 10 days ago • 110

upvoted a paper over 1 year ago

Your Transformer is Secretly Linear

Paper • 2405.12250 • Published May 19, 2024 • 158