Jianbo Wu's picture

1 1 2

Jianbo Wu

jwu323

·

AI & ML interests

None yet

Recent Activity

Reacted to qq8933's post with 🔥 19 days ago

LLaMA-O1: Open Large Reasoning Model Frameworks For Training, Inference and Evaluation With PyTorch and HuggingFace Large Reasoning Models powered by Monte Carlo Tree Search (MCTS), Self-Play Reinforcement Learning, PPO, AlphaGo Zero's dua policy paradigm and Large Language Models! https://github.com/SimpleBerry/LLaMA-O1/ What will happen when you compound MCTS ❤ LLM ❤ Self-Play ❤RLHF? Just a little bite of strawberry!🍓 Past related works: https://huggingface.co/papers/2410.02884 https://huggingface.co/papers/2406.07394

Reacted to qq8933's post with 👍 22 days ago

LLaMA-O1: Open Large Reasoning Model Frameworks For Training, Inference and Evaluation With PyTorch and HuggingFace Large Reasoning Models powered by Monte Carlo Tree Search (MCTS), Self-Play Reinforcement Learning, PPO, AlphaGo Zero's dua policy paradigm and Large Language Models! https://github.com/SimpleBerry/LLaMA-O1/ What will happen when you compound MCTS ❤ LLM ❤ Self-Play ❤RLHF? Just a little bite of strawberry!🍓 Past related works: https://huggingface.co/papers/2410.02884 https://huggingface.co/papers/2406.07394

upvoted a paper about 2 months ago

LLaMA-Berry: Pairwise Optimization for O1-like Olympiad-Level Mathematical Reasoning

View all activity

Organizations

Papers 1

arxiv:2410.02884

models 2

jwu323/origin-llama-13b

Updated Jul 17, 2023

jwu323/origin-llama-7b

Text Generation • Updated Jul 11, 2023 • 10

datasets

None public yet