Vinh Nguyen's picture

81 240

Vinh Nguyen

vinhnx90

·

https://vinhnx.github.io

AI & ML interests

Learn by doing

Recent Activity

liked a model about 14 hours ago

unsloth/Llama-4-Scout-17B-16E-Instruct-unsloth-bnb-4bit

liked a model about 14 hours ago

meta-llama/Llama-4-Scout-17B-16E-Instruct

upvoted a collection about 14 hours ago

View all activity

Organizations

vinhnx90's activity

upvoted a collection about 14 hours ago

Llama 4

Llama 4 release • 10 items • Updated about 19 hours ago • 310

upvoted an article about 16 hours ago

Article

Welcome Llama 4 Maverick & Scout on Hugging Face!

1 day ago

• 71

upvoted a collection 3 days ago

Gemma 3 QAT

Quantization Aware Trained (QAT) Gemma 3 checkpoints. The model preserves similar quality as half precision while using 3x less memory • 8 items • Updated 3 days ago • 92

upvoted a collection 9 days ago

CoRNStack

State-of-the-art code retrieval and re-ranking models and datasets • 9 items • Updated 11 days ago • 15

upvoted a paper 9 days ago

Gemma 3 Technical Report

Paper • 2503.19786 • Published 12 days ago • 43

upvoted a collection 11 days ago

🧠 Reasoning datasets

Datasets with reasoning traces for math and code released by the community • 20 items • Updated 5 days ago • 122

upvoted a collection 13 days ago

Phi GRPO Fine Tuning

1 item • Updated 14 days ago • 1

upvoted 2 collections 15 days ago

Qwen GRPO Fine Tuning

4 items • Updated 7 days ago • 1

Open-RS

Model weights & datasets in the paper "Reinforcement Learning for Reasoning in Small LLMs: What Works and What Doesn’t" • 8 items • Updated 16 days ago • 11

upvoted a paper 15 days ago

Reinforcement Learning for Reasoning in Small LLMs: What Works and What Doesn't

Paper • 2503.16219 • Published 17 days ago • 46

upvoted a collection 16 days ago

Gemma 3

All versions of Google's new multimodal models in 1B, 4B, 12B, and 27B sizes. In GGUF, dynamic 4-bit and 16-bit formats. • 29 items • Updated about 17 hours ago • 48