Pre2Post-Chess Open-sourced models and datasets for training the chess reasoning models. pavelslab-nyu/pretrain_v1_54B Updated Jul 20 • 768 • 1 pavelslab-nyu/chess_puzzle_benchmark Viewer • Updated Jul 20 • 2.36k • 83 pre-to-post-olmo/Math-Models Text Generation • Updated Jul 19 pavelslab-nyu/chess_puzzle_training_datasets Preview • Updated 20 days ago • 96
rlvr-weak-supervision Models from "When Can LLMs Learn to Reason with Weak Supervision?" — Llama-3.2-3B with continual pre-training and Thinking SFT. pavelslab-nyu/Llama-3.2-3B-ThinkSFT 3B • Updated Apr 20 • 759 pavelslab-nyu/Llama-3.2-3B-CPT-Math-ThinkSFT 3B • Updated Apr 20 • 110 pavelslab-nyu/Llama-3.2-3B-CPT-Math 3B • Updated Apr 20 • 8
Pre2Post-Chess Open-sourced models and datasets for training the chess reasoning models. pavelslab-nyu/pretrain_v1_54B Updated Jul 20 • 768 • 1 pavelslab-nyu/chess_puzzle_benchmark Viewer • Updated Jul 20 • 2.36k • 83 pre-to-post-olmo/Math-Models Text Generation • Updated Jul 19 pavelslab-nyu/chess_puzzle_training_datasets Preview • Updated 20 days ago • 96
rlvr-weak-supervision Models from "When Can LLMs Learn to Reason with Weak Supervision?" — Llama-3.2-3B with continual pre-training and Thinking SFT. pavelslab-nyu/Llama-3.2-3B-ThinkSFT 3B • Updated Apr 20 • 759 pavelslab-nyu/Llama-3.2-3B-CPT-Math-ThinkSFT 3B • Updated Apr 20 • 110 pavelslab-nyu/Llama-3.2-3B-CPT-Math 3B • Updated Apr 20 • 8
