*.7z filter=lfs diff=lfs merge=lfs -text *.arrow filter=lfs diff=lfs merge=lfs -text *.bin filter=lfs diff=lfs merge=lfs -text *.bz2 filter=lfs diff=lfs merge=lfs -text *.ckpt filter=lfs diff=lfs merge=lfs -text *.ftz filter=lfs diff=lfs merge=lfs -text *.gz filter=lfs diff=lfs merge=lfs -text *.h5 filter=lfs diff=lfs merge=lfs -text *.joblib filter=lfs diff=lfs merge=lfs -text *.lfs.* filter=lfs diff=lfs merge=lfs -text *.mlmodel filter=lfs diff=lfs merge=lfs -text *.model filter=lfs diff=lfs merge=lfs -text *.msgpack filter=lfs diff=lfs merge=lfs -text *.npy filter=lfs diff=lfs merge=lfs -text *.npz filter=lfs diff=lfs merge=lfs -text *.onnx filter=lfs diff=lfs merge=lfs -text *.ot filter=lfs diff=lfs merge=lfs -text *.parquet filter=lfs diff=lfs merge=lfs -text *.pb filter=lfs diff=lfs merge=lfs -text *.pickle filter=lfs diff=lfs merge=lfs -text *.pkl filter=lfs diff=lfs merge=lfs -text *.pt filter=lfs diff=lfs merge=lfs -text *.pth filter=lfs diff=lfs merge=lfs -text *.rar filter=lfs diff=lfs merge=lfs -text *.safetensors filter=lfs diff=lfs merge=lfs -text saved_model/**/* filter=lfs diff=lfs merge=lfs -text *.tar.* filter=lfs diff=lfs merge=lfs -text *.tar filter=lfs diff=lfs merge=lfs -text *.tflite filter=lfs diff=lfs merge=lfs -text *.tgz filter=lfs diff=lfs merge=lfs -text *.wasm filter=lfs diff=lfs merge=lfs -text *.xz filter=lfs diff=lfs merge=lfs -text *.zip filter=lfs diff=lfs merge=lfs -text *.zst filter=lfs diff=lfs merge=lfs -text *tfevents* filter=lfs diff=lfs merge=lfs -text Qwen2.5-7B-LLM-sft-free-think-step300/tokenizer.json filter=lfs diff=lfs merge=lfs -text Qwen2.5-7B-LLM-sft-free-think-step400/tokenizer.json filter=lfs diff=lfs merge=lfs -text Qwen2.5-7B-LLM-sft-no-think-step300/tokenizer.json filter=lfs diff=lfs merge=lfs -text Qwen2.5-7B-LLM-sft-no-think-step400/tokenizer.json filter=lfs diff=lfs merge=lfs -text Qwen2.5-VL-7B-VLM-sft-free-think-step600/tokenizer.json.backup filter=lfs diff=lfs merge=lfs -text Qwen2.5-VL-7B-VLM-sft-free-think-step800/tokenizer.json.backup filter=lfs diff=lfs merge=lfs -text Qwen2.5-VL-7B-VLM-sft-no-think-step200/tokenizer.json.backup filter=lfs diff=lfs merge=lfs -text Qwen2.5-VL-7B-VLM-sft-no-think-step400/tokenizer.json.backup filter=lfs diff=lfs merge=lfs -text Qwen2.5-VL-7B-VLM-sft-no-think-step600/tokenizer.json.backup filter=lfs diff=lfs merge=lfs -text Qwen2.5-VL-7B-VLM-sft-no-think-step800/tokenizer.json.backup filter=lfs diff=lfs merge=lfs -text Qwen2.5-VL-7B-Overcooked-large-new-free-think-step100/tokenizer.json.backup filter=lfs diff=lfs merge=lfs -text Qwen2.5-VL-7B-Overcooked-large-new-free-think-step200/tokenizer.json.backup filter=lfs diff=lfs merge=lfs -text Qwen2.5-VL-7B-Overcooked-large-new-free-think-step300/tokenizer.json.backup filter=lfs diff=lfs merge=lfs -text Qwen2.5-VL-7B-Overcooked-large-new-free-think-step400/tokenizer.json.backup filter=lfs diff=lfs merge=lfs -text Qwen2.5-VL-7B-Overcooked-large-new-free-think-step500/tokenizer.json.backup filter=lfs diff=lfs merge=lfs -text Qwen2.5-VL-7B-Overcooked-large-new-free-think-step600/tokenizer.json.backup filter=lfs diff=lfs merge=lfs -text Qwen2.5-VL-7B-Overcooked-large-new-free-think-step700/tokenizer.json.backup filter=lfs diff=lfs merge=lfs -text Qwen2.5-VL-7B-Overcooked-large-new-free-think-step800/tokenizer.json.backup filter=lfs diff=lfs merge=lfs -text Qwen2.5-7B-LLM-Overcooked-free-think-step100/tokenizer.json filter=lfs diff=lfs merge=lfs -text Qwen2.5-7B-LLM-Overcooked-free-think-step200/tokenizer.json filter=lfs diff=lfs merge=lfs -text Qwen2.5-7B-LLM-Overcooked-free-think-step300/tokenizer.json filter=lfs diff=lfs merge=lfs -text Qwen2.5-7B-LLM-Overcooked-free-think-step400/tokenizer.json filter=lfs diff=lfs merge=lfs -text Qwen2.5-7B-LLM-Overcooked-no-think-step100/tokenizer.json filter=lfs diff=lfs merge=lfs -text Qwen2.5-7B-LLM-Overcooked-no-think-step200/tokenizer.json filter=lfs diff=lfs merge=lfs -text Qwen2.5-7B-LLM-Overcooked-no-think-step300/tokenizer.json filter=lfs diff=lfs merge=lfs -text Qwen2.5-7B-LLM-Overcooked-no-think-step400/tokenizer.json filter=lfs diff=lfs merge=lfs -text Qwen2.5-VL-7B-Overcooked-no-think-step100/tokenizer.json filter=lfs diff=lfs merge=lfs -text Qwen2.5-VL-7B-Overcooked-no-think-step200/tokenizer.json filter=lfs diff=lfs merge=lfs -text Qwen2.5-VL-7B-Overcooked-no-think-step300/tokenizer.json filter=lfs diff=lfs merge=lfs -text Qwen2.5-VL-7B-Overcooked-no-think-step400/tokenizer.json filter=lfs diff=lfs merge=lfs -text Qwen2.5-3B-LLM-Overcooked-free-think-step50/tokenizer.json filter=lfs diff=lfs merge=lfs -text Qwen2.5-3B-LLM-Overcooked-free-think-step100/tokenizer.json filter=lfs diff=lfs merge=lfs -text Qwen2.5-3B-LLM-Overcooked-free-think-step150/tokenizer.json filter=lfs diff=lfs merge=lfs -text Qwen2.5-3B-LLM-Overcooked-free-think-step200/tokenizer.json filter=lfs diff=lfs merge=lfs -text Qwen2.5-3B-LLM-Overcooked-free-think-step250/tokenizer.json filter=lfs diff=lfs merge=lfs -text Qwen2.5-3B-LLM-Overcooked-free-think-step300/tokenizer.json filter=lfs diff=lfs merge=lfs -text Qwen2.5-3B-LLM-Overcooked-free-think-step350/tokenizer.json filter=lfs diff=lfs merge=lfs -text Qwen2.5-3B-LLM-Overcooked-free-think-step400/tokenizer.json filter=lfs diff=lfs merge=lfs -text Qwen2.5-3B-LLM-Overcooked-no-think-step50/tokenizer.json filter=lfs diff=lfs merge=lfs -text Qwen2.5-3B-LLM-Overcooked-no-think-step100/tokenizer.json filter=lfs diff=lfs merge=lfs -text Qwen2.5-3B-LLM-Overcooked-no-think-step150/tokenizer.json filter=lfs diff=lfs merge=lfs -text Qwen2.5-3B-LLM-Overcooked-no-think-step200/tokenizer.json filter=lfs diff=lfs merge=lfs -text Qwen2.5-3B-LLM-Overcooked-no-think-step250/tokenizer.json filter=lfs diff=lfs merge=lfs -text Qwen2.5-3B-LLM-Overcooked-no-think-step300/tokenizer.json filter=lfs diff=lfs merge=lfs -text Qwen2.5-3B-LLM-Overcooked-no-think-step350/tokenizer.json filter=lfs diff=lfs merge=lfs -text Qwen2.5-3B-LLM-Overcooked-no-think-step400/tokenizer.json filter=lfs diff=lfs merge=lfs -text Qwen2.5-3B-LLM-Sokoban-free-think-step50/tokenizer.json filter=lfs diff=lfs merge=lfs -text Qwen2.5-3B-LLM-Sokoban-free-think-step100/tokenizer.json filter=lfs diff=lfs merge=lfs -text Qwen2.5-3B-LLM-Sokoban-free-think-step150/tokenizer.json filter=lfs diff=lfs merge=lfs -text Qwen2.5-3B-LLM-Sokoban-free-think-step200/tokenizer.json filter=lfs diff=lfs merge=lfs -text Qwen2.5-3B-LLM-Sokoban-free-think-step250/tokenizer.json filter=lfs diff=lfs merge=lfs -text Qwen2.5-3B-LLM-Sokoban-free-think-step300/tokenizer.json filter=lfs diff=lfs merge=lfs -text Qwen2.5-3B-LLM-Sokoban-free-think-step350/tokenizer.json filter=lfs diff=lfs merge=lfs -text Qwen2.5-3B-LLM-Sokoban-free-think-step400/tokenizer.json filter=lfs diff=lfs merge=lfs -text Qwen2.5-3B-LLM-Sokoban-free-think-step450/tokenizer.json filter=lfs diff=lfs merge=lfs -text Qwen2.5-3B-LLM-Sokoban-free-think-step500/tokenizer.json filter=lfs diff=lfs merge=lfs -text Qwen2.5-3B-LLM-Sokoban-free-think-step550/tokenizer.json filter=lfs diff=lfs merge=lfs -text Qwen2.5-3B-LLM-Sokoban-free-think-step600/tokenizer.json filter=lfs diff=lfs merge=lfs -text Qwen2.5-3B-LLM-Sokoban-free-think-step650/tokenizer.json filter=lfs diff=lfs merge=lfs -text Qwen2.5-3B-LLM-Sokoban-free-think-step700/tokenizer.json filter=lfs diff=lfs merge=lfs -text Qwen2.5-3B-LLM-Sokoban-free-think-step750/tokenizer.json filter=lfs diff=lfs merge=lfs -text Qwen2.5-3B-LLM-Sokoban-free-think-step800/tokenizer.json filter=lfs diff=lfs merge=lfs -text Qwen2.5-3B-LLM-Sokoban-no-think-step50/tokenizer.json filter=lfs diff=lfs merge=lfs -text Qwen2.5-3B-LLM-Sokoban-no-think-step100/tokenizer.json filter=lfs diff=lfs merge=lfs -text Qwen2.5-3B-LLM-Sokoban-no-think-step150/tokenizer.json filter=lfs diff=lfs merge=lfs -text Qwen2.5-3B-LLM-Sokoban-no-think-step200/tokenizer.json filter=lfs diff=lfs merge=lfs -text Qwen2.5-3B-LLM-Sokoban-no-think-step250/tokenizer.json filter=lfs diff=lfs merge=lfs -text Qwen2.5-3B-LLM-Sokoban-no-think-step300/tokenizer.json filter=lfs diff=lfs merge=lfs -text Qwen2.5-3B-LLM-Sokoban-no-think-step350/tokenizer.json filter=lfs diff=lfs merge=lfs -text Qwen2.5-3B-LLM-Sokoban-no-think-step400/tokenizer.json filter=lfs diff=lfs merge=lfs -text Qwen2.5-3B-LLM-Sokoban-no-think-step450/tokenizer.json filter=lfs diff=lfs merge=lfs -text Qwen2.5-3B-LLM-Sokoban-no-think-step500/tokenizer.json filter=lfs diff=lfs merge=lfs -text Qwen2.5-3B-LLM-Sokoban-no-think-step550/tokenizer.json filter=lfs diff=lfs merge=lfs -text Qwen2.5-3B-LLM-Sokoban-no-think-step600/tokenizer.json filter=lfs diff=lfs merge=lfs -text Qwen2.5-3B-LLM-Sokoban-no-think-step650/tokenizer.json filter=lfs diff=lfs merge=lfs -text Qwen2.5-3B-LLM-Sokoban-no-think-step700/tokenizer.json filter=lfs diff=lfs merge=lfs -text Qwen2.5-3B-LLM-Sokoban-no-think-step750/tokenizer.json filter=lfs diff=lfs merge=lfs -text Qwen2.5-3B-LLM-Sokoban-no-think-step800/tokenizer.json filter=lfs diff=lfs merge=lfs -text Qwen2.5-VL-3B-Overcooked-free-think-step50/tokenizer.json filter=lfs diff=lfs merge=lfs -text Qwen2.5-VL-3B-Overcooked-free-think-step100/tokenizer.json filter=lfs diff=lfs merge=lfs -text Qwen2.5-VL-3B-Overcooked-free-think-step150/tokenizer.json filter=lfs diff=lfs merge=lfs -text Qwen2.5-VL-3B-Overcooked-free-think-step200/tokenizer.json filter=lfs diff=lfs merge=lfs -text Qwen2.5-VL-3B-Overcooked-free-think-step250/tokenizer.json filter=lfs diff=lfs merge=lfs -text Qwen2.5-VL-3B-Overcooked-free-think-step300/tokenizer.json filter=lfs diff=lfs merge=lfs -text Qwen2.5-VL-3B-Overcooked-free-think-step350/tokenizer.json filter=lfs diff=lfs merge=lfs -text Qwen2.5-VL-3B-Overcooked-free-think-step400/tokenizer.json filter=lfs diff=lfs merge=lfs -text Qwen2.5-VL-3B-Overcooked-no-think-step50/tokenizer.json filter=lfs diff=lfs merge=lfs -text Qwen2.5-VL-3B-Overcooked-no-think-step100/tokenizer.json filter=lfs diff=lfs merge=lfs -text Qwen2.5-VL-3B-Overcooked-no-think-step150/tokenizer.json filter=lfs diff=lfs merge=lfs -text Qwen2.5-VL-3B-Overcooked-no-think-step200/tokenizer.json filter=lfs diff=lfs merge=lfs -text Qwen2.5-VL-3B-Overcooked-no-think-step250/tokenizer.json filter=lfs diff=lfs merge=lfs -text Qwen2.5-VL-3B-Overcooked-no-think-step300/tokenizer.json filter=lfs diff=lfs merge=lfs -text Qwen2.5-VL-3B-Overcooked-no-think-step350/tokenizer.json filter=lfs diff=lfs merge=lfs -text Qwen2.5-VL-3B-Overcooked-no-think-step400/tokenizer.json filter=lfs diff=lfs merge=lfs -text Qwen2.5-VL-3B-Sokoban-free-think-step50/tokenizer.json filter=lfs diff=lfs merge=lfs -text Qwen2.5-VL-3B-Sokoban-free-think-step100/tokenizer.json filter=lfs diff=lfs merge=lfs -text Qwen2.5-VL-3B-Sokoban-free-think-step150/tokenizer.json filter=lfs diff=lfs merge=lfs -text Qwen2.5-VL-3B-Sokoban-free-think-step200/tokenizer.json filter=lfs diff=lfs merge=lfs -text Qwen2.5-VL-3B-Sokoban-free-think-step250/tokenizer.json filter=lfs diff=lfs merge=lfs -text Qwen2.5-VL-3B-Sokoban-free-think-step300/tokenizer.json filter=lfs diff=lfs merge=lfs -text Qwen2.5-VL-3B-Sokoban-free-think-step350/tokenizer.json filter=lfs diff=lfs merge=lfs -text Qwen2.5-VL-3B-Sokoban-free-think-step400/tokenizer.json filter=lfs diff=lfs merge=lfs -text Qwen2.5-VL-3B-Sokoban-free-think-step450/tokenizer.json filter=lfs diff=lfs merge=lfs -text Qwen2.5-VL-3B-Sokoban-free-think-step500/tokenizer.json filter=lfs diff=lfs merge=lfs -text Qwen2.5-VL-3B-Sokoban-no-think-step50/tokenizer.json filter=lfs diff=lfs merge=lfs -text Qwen2.5-VL-3B-Sokoban-no-think-step100/tokenizer.json filter=lfs diff=lfs merge=lfs -text Qwen2.5-VL-3B-Sokoban-no-think-step150/tokenizer.json filter=lfs diff=lfs merge=lfs -text Qwen2.5-VL-3B-Sokoban-no-think-step200/tokenizer.json filter=lfs diff=lfs merge=lfs -text Qwen2.5-VL-3B-Sokoban-no-think-step250/tokenizer.json filter=lfs diff=lfs merge=lfs -text Qwen2.5-VL-3B-Sokoban-no-think-step300/tokenizer.json filter=lfs diff=lfs merge=lfs -text Qwen2.5-VL-3B-Sokoban-no-think-step350/tokenizer.json filter=lfs diff=lfs merge=lfs -text Qwen2.5-VL-3B-Sokoban-no-think-step400/tokenizer.json filter=lfs diff=lfs merge=lfs -text Qwen2.5-VL-3B-Sokoban-no-think-step450/tokenizer.json filter=lfs diff=lfs merge=lfs -text Qwen2.5-VL-3B-Sokoban-no-think-step500/tokenizer.json filter=lfs diff=lfs merge=lfs -text Qwen2.5-VL-3B-Sokoban-no-think-step550/tokenizer.json filter=lfs diff=lfs merge=lfs -text Qwen2.5-VL-3B-Sokoban-no-think-step600/tokenizer.json filter=lfs diff=lfs merge=lfs -text Qwen2.5-VL-3B-Sokoban-no-think-step650/tokenizer.json filter=lfs diff=lfs merge=lfs -text Qwen2.5-VL-3B-Sokoban-no-think-step700/tokenizer.json filter=lfs diff=lfs merge=lfs -text Qwen2.5-VL-3B-Sokoban-no-think-step750/tokenizer.json filter=lfs diff=lfs merge=lfs -text Qwen2.5-VL-3B-Sokoban-no-think-step800/tokenizer.json filter=lfs diff=lfs merge=lfs -text RL-3B/Sokoban-LLM-free-think/step6/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text RL-3B/Sokoban-LLM-no-think/step3/tokenizer.json filter=lfs diff=lfs merge=lfs -text RL-3B/Sokoban-LLM-free-think/step3/tokenizer.json filter=lfs diff=lfs merge=lfs -text RL-3B/Sokoban-LLM-no-think/step6/tokenizer.json filter=lfs diff=lfs merge=lfs -text RL-3B/Sokoban-LLM-free-think/step6/tokenizer.json filter=lfs diff=lfs merge=lfs -text RL-3B/Sokoban-LLM-no-think/step25/tokenizer.json filter=lfs diff=lfs merge=lfs -text RL-3B/Sokoban-LLM-free-think/step25/tokenizer.json filter=lfs diff=lfs merge=lfs -text RL-3B/Sokoban-LLM-no-think/step50/tokenizer.json filter=lfs diff=lfs merge=lfs -text RL-3B/Sokoban-LLM-free-think/step50/tokenizer.json filter=lfs diff=lfs merge=lfs -text RL-3B/Sokoban-LLM-no-think/step75/tokenizer.json filter=lfs diff=lfs merge=lfs -text RL-3B/Sokoban-VLM-free-think/step25/tokenizer.json filter=lfs diff=lfs merge=lfs -text RL-3B/Sokoban-LLM-free-think/step75/tokenizer.json filter=lfs diff=lfs merge=lfs -text RL-3B/Sokoban-VLM-no-think/step25/tokenizer.json filter=lfs diff=lfs merge=lfs -text RL-3B/Sokoban-LLM-free-think/step100/tokenizer.json filter=lfs diff=lfs merge=lfs -text RL-3B/Sokoban-LLM-no-think/step100/tokenizer.json filter=lfs diff=lfs merge=lfs -text RL-3B/Sokoban-LLM-no-think/step125/tokenizer.json filter=lfs diff=lfs merge=lfs -text RL-3B/Overcooked-LLM-no-think/step3/tokenizer.json filter=lfs diff=lfs merge=lfs -text RL-3B/Overcooked-LLM-no-think/step6/tokenizer.json filter=lfs diff=lfs merge=lfs -text SFT/3B/Overcooked-LLM-free-think/step100/tokenizer.json filter=lfs diff=lfs merge=lfs -text SFT/3B/Overcooked-LLM-free-think/step150/tokenizer.json filter=lfs diff=lfs merge=lfs -text SFT/3B/Overcooked-LLM-free-think/step200/tokenizer.json filter=lfs diff=lfs merge=lfs -text SFT/3B/Overcooked-LLM-free-think/step250/tokenizer.json filter=lfs diff=lfs merge=lfs -text SFT/3B/Overcooked-LLM-free-think/step300/tokenizer.json filter=lfs diff=lfs merge=lfs -text SFT/3B/Overcooked-LLM-free-think/step350/tokenizer.json filter=lfs diff=lfs merge=lfs -text SFT/3B/Overcooked-LLM-free-think/step400/tokenizer.json filter=lfs diff=lfs merge=lfs -text SFT/3B/Overcooked-LLM-free-think/step50/tokenizer.json filter=lfs diff=lfs merge=lfs -text SFT/3B/Overcooked-LLM-no-think/step100/tokenizer.json filter=lfs diff=lfs merge=lfs -text SFT/3B/Overcooked-LLM-no-think/step150/tokenizer.json filter=lfs diff=lfs merge=lfs -text SFT/3B/Overcooked-LLM-no-think/step200/tokenizer.json filter=lfs diff=lfs merge=lfs -text SFT/3B/Overcooked-LLM-no-think/step250/tokenizer.json filter=lfs diff=lfs merge=lfs -text SFT/3B/Overcooked-LLM-no-think/step300/tokenizer.json filter=lfs diff=lfs merge=lfs -text SFT/3B/Overcooked-LLM-no-think/step350/tokenizer.json filter=lfs diff=lfs merge=lfs -text SFT/3B/Overcooked-LLM-no-think/step400/tokenizer.json filter=lfs diff=lfs merge=lfs -text SFT/3B/Overcooked-LLM-no-think/step50/tokenizer.json filter=lfs diff=lfs merge=lfs -text SFT/3B/Sokoban-LLM-free-think/step100/tokenizer.json filter=lfs diff=lfs merge=lfs -text SFT/3B/Sokoban-LLM-free-think/step150/tokenizer.json filter=lfs diff=lfs merge=lfs -text SFT/3B/Sokoban-LLM-free-think/step200/tokenizer.json filter=lfs diff=lfs merge=lfs -text SFT/3B/Sokoban-LLM-free-think/step250/tokenizer.json filter=lfs diff=lfs merge=lfs -text SFT/3B/Sokoban-LLM-free-think/step300/tokenizer.json filter=lfs diff=lfs merge=lfs -text SFT/3B/Sokoban-LLM-free-think/step350/tokenizer.json filter=lfs diff=lfs merge=lfs -text SFT/3B/Sokoban-LLM-free-think/step400/tokenizer.json filter=lfs diff=lfs merge=lfs -text SFT/3B/Sokoban-LLM-free-think/step450/tokenizer.json filter=lfs diff=lfs merge=lfs -text SFT/3B/Sokoban-LLM-free-think/step50/tokenizer.json filter=lfs diff=lfs merge=lfs -text SFT/3B/Sokoban-LLM-free-think/step500/tokenizer.json filter=lfs diff=lfs merge=lfs -text SFT/3B/Sokoban-LLM-free-think/step550/tokenizer.json filter=lfs diff=lfs merge=lfs -text SFT/3B/Sokoban-LLM-free-think/step600/tokenizer.json filter=lfs diff=lfs merge=lfs -text SFT/3B/Sokoban-LLM-free-think/step650/tokenizer.json filter=lfs diff=lfs merge=lfs -text SFT/3B/Sokoban-LLM-free-think/step700/tokenizer.json filter=lfs diff=lfs merge=lfs -text SFT/3B/Sokoban-LLM-free-think/step750/tokenizer.json filter=lfs diff=lfs merge=lfs -text SFT/3B/Sokoban-LLM-free-think/step800/tokenizer.json filter=lfs diff=lfs merge=lfs -text SFT/3B/Sokoban-LLM-no-think/step100/tokenizer.json filter=lfs diff=lfs merge=lfs -text SFT/3B/Sokoban-LLM-no-think/step150/tokenizer.json filter=lfs diff=lfs merge=lfs -text SFT/3B/Sokoban-LLM-no-think/step200/tokenizer.json filter=lfs diff=lfs merge=lfs -text SFT/3B/Sokoban-LLM-no-think/step250/tokenizer.json filter=lfs diff=lfs merge=lfs -text SFT/3B/Sokoban-LLM-no-think/step300/tokenizer.json filter=lfs diff=lfs merge=lfs -text SFT/3B/Sokoban-LLM-no-think/step350/tokenizer.json filter=lfs diff=lfs merge=lfs -text SFT/3B/Sokoban-LLM-no-think/step400/tokenizer.json filter=lfs diff=lfs merge=lfs -text SFT/3B/Sokoban-LLM-no-think/step450/tokenizer.json filter=lfs diff=lfs merge=lfs -text SFT/3B/Sokoban-LLM-no-think/step50/tokenizer.json filter=lfs diff=lfs merge=lfs -text SFT/3B/Sokoban-LLM-no-think/step500/tokenizer.json filter=lfs diff=lfs merge=lfs -text SFT/3B/Sokoban-LLM-no-think/step550/tokenizer.json filter=lfs diff=lfs merge=lfs -text SFT/3B/Sokoban-LLM-no-think/step600/tokenizer.json filter=lfs diff=lfs merge=lfs -text SFT/3B/Sokoban-LLM-no-think/step650/tokenizer.json filter=lfs diff=lfs merge=lfs -text SFT/3B/Sokoban-LLM-no-think/step700/tokenizer.json filter=lfs diff=lfs merge=lfs -text SFT/3B/Sokoban-LLM-no-think/step750/tokenizer.json filter=lfs diff=lfs merge=lfs -text SFT/3B/Sokoban-LLM-no-think/step800/tokenizer.json filter=lfs diff=lfs merge=lfs -text SFT/7B/Overcooked-LLM-free-think/step100/tokenizer.json filter=lfs diff=lfs merge=lfs -text SFT/7B/Overcooked-LLM-free-think/step200/tokenizer.json filter=lfs diff=lfs merge=lfs -text SFT/7B/Overcooked-LLM-free-think/step300/tokenizer.json filter=lfs diff=lfs merge=lfs -text SFT/7B/Overcooked-LLM-free-think/step400/tokenizer.json filter=lfs diff=lfs merge=lfs -text SFT/7B/Overcooked-LLM-no-think/step100/tokenizer.json filter=lfs diff=lfs merge=lfs -text SFT/7B/Overcooked-LLM-no-think/step200/tokenizer.json filter=lfs diff=lfs merge=lfs -text SFT/7B/Overcooked-LLM-no-think/step300/tokenizer.json filter=lfs diff=lfs merge=lfs -text SFT/7B/Overcooked-LLM-no-think/step400/tokenizer.json filter=lfs diff=lfs merge=lfs -text SFT/7B/sft-LLM-free-think/step300/tokenizer.json filter=lfs diff=lfs merge=lfs -text SFT/7B/sft-LLM-free-think/step400/tokenizer.json filter=lfs diff=lfs merge=lfs -text SFT/7B/sft-LLM-no-think/step300/tokenizer.json filter=lfs diff=lfs merge=lfs -text SFT/7B/sft-LLM-no-think/step400/tokenizer.json filter=lfs diff=lfs merge=lfs -text SFT/3B/Overcooked-VLM-free-think/step100/tokenizer.json filter=lfs diff=lfs merge=lfs -text SFT/3B/Overcooked-VLM-free-think/step150/tokenizer.json filter=lfs diff=lfs merge=lfs -text SFT/3B/Overcooked-VLM-free-think/step200/tokenizer.json filter=lfs diff=lfs merge=lfs -text SFT/3B/Overcooked-VLM-free-think/step250/tokenizer.json filter=lfs diff=lfs merge=lfs -text SFT/3B/Overcooked-VLM-free-think/step300/tokenizer.json filter=lfs diff=lfs merge=lfs -text SFT/3B/Overcooked-VLM-free-think/step350/tokenizer.json filter=lfs diff=lfs merge=lfs -text SFT/3B/Overcooked-VLM-free-think/step400/tokenizer.json filter=lfs diff=lfs merge=lfs -text SFT/3B/Overcooked-VLM-free-think/step50/tokenizer.json filter=lfs diff=lfs merge=lfs -text SFT/3B/Overcooked-VLM-no-think/step100/tokenizer.json filter=lfs diff=lfs merge=lfs -text SFT/3B/Overcooked-VLM-no-think/step150/tokenizer.json filter=lfs diff=lfs merge=lfs -text SFT/3B/Overcooked-VLM-no-think/step200/tokenizer.json filter=lfs diff=lfs merge=lfs -text SFT/3B/Overcooked-VLM-no-think/step250/tokenizer.json filter=lfs diff=lfs merge=lfs -text SFT/3B/Overcooked-VLM-no-think/step300/tokenizer.json filter=lfs diff=lfs merge=lfs -text SFT/3B/Overcooked-VLM-no-think/step350/tokenizer.json filter=lfs diff=lfs merge=lfs -text SFT/3B/Overcooked-VLM-no-think/step400/tokenizer.json filter=lfs diff=lfs merge=lfs -text SFT/3B/Overcooked-VLM-no-think/step50/tokenizer.json filter=lfs diff=lfs merge=lfs -text SFT/3B/Sokoban-VLM-free-think/step100/tokenizer.json filter=lfs diff=lfs merge=lfs -text SFT/3B/Sokoban-VLM-free-think/step150/tokenizer.json filter=lfs diff=lfs merge=lfs -text SFT/3B/Sokoban-VLM-free-think/step200/tokenizer.json filter=lfs diff=lfs merge=lfs -text SFT/3B/Sokoban-VLM-free-think/step250/tokenizer.json filter=lfs diff=lfs merge=lfs -text SFT/3B/Sokoban-VLM-free-think/step300/tokenizer.json filter=lfs diff=lfs merge=lfs -text SFT/3B/Sokoban-VLM-free-think/step350/tokenizer.json filter=lfs diff=lfs merge=lfs -text SFT/3B/Sokoban-VLM-free-think/step400/tokenizer.json filter=lfs diff=lfs merge=lfs -text SFT/3B/Sokoban-VLM-free-think/step450/tokenizer.json filter=lfs diff=lfs merge=lfs -text SFT/3B/Sokoban-VLM-free-think/step50/tokenizer.json filter=lfs diff=lfs merge=lfs -text SFT/3B/Sokoban-VLM-free-think/step500/tokenizer.json filter=lfs diff=lfs merge=lfs -text SFT/3B/Sokoban-VLM-no-think/step100/tokenizer.json filter=lfs diff=lfs merge=lfs -text SFT/3B/Sokoban-VLM-no-think/step150/tokenizer.json filter=lfs diff=lfs merge=lfs -text SFT/3B/Sokoban-VLM-no-think/step200/tokenizer.json filter=lfs diff=lfs merge=lfs -text SFT/3B/Sokoban-VLM-no-think/step250/tokenizer.json filter=lfs diff=lfs merge=lfs -text SFT/3B/Sokoban-VLM-no-think/step300/tokenizer.json filter=lfs diff=lfs merge=lfs -text SFT/3B/Sokoban-VLM-no-think/step350/tokenizer.json filter=lfs diff=lfs merge=lfs -text SFT/3B/Sokoban-VLM-no-think/step400/tokenizer.json filter=lfs diff=lfs merge=lfs -text SFT/3B/Sokoban-VLM-no-think/step450/tokenizer.json filter=lfs diff=lfs merge=lfs -text SFT/3B/Sokoban-VLM-no-think/step50/tokenizer.json filter=lfs diff=lfs merge=lfs -text SFT/3B/Sokoban-VLM-no-think/step500/tokenizer.json filter=lfs diff=lfs merge=lfs -text SFT/3B/Sokoban-VLM-no-think/step550/tokenizer.json filter=lfs diff=lfs merge=lfs -text SFT/3B/Sokoban-VLM-no-think/step600/tokenizer.json filter=lfs diff=lfs merge=lfs -text SFT/3B/Sokoban-VLM-no-think/step650/tokenizer.json filter=lfs diff=lfs merge=lfs -text SFT/3B/Sokoban-VLM-no-think/step700/tokenizer.json filter=lfs diff=lfs merge=lfs -text SFT/3B/Sokoban-VLM-no-think/step750/tokenizer.json filter=lfs diff=lfs merge=lfs -text SFT/3B/Sokoban-VLM-no-think/step800/tokenizer.json filter=lfs diff=lfs merge=lfs -text SFT/7B/Overcooked-VLM-large-new-free-think/step100/tokenizer.json.backup filter=lfs diff=lfs merge=lfs -text SFT/7B/Overcooked-VLM-large-new-free-think/step200/tokenizer.json.backup filter=lfs diff=lfs merge=lfs -text SFT/7B/Overcooked-VLM-large-new-free-think/step300/tokenizer.json.backup filter=lfs diff=lfs merge=lfs -text SFT/7B/Overcooked-VLM-large-new-free-think/step400/tokenizer.json.backup filter=lfs diff=lfs merge=lfs -text SFT/7B/Overcooked-VLM-large-new-free-think/step500/tokenizer.json.backup filter=lfs diff=lfs merge=lfs -text SFT/7B/Overcooked-VLM-large-new-free-think/step600/tokenizer.json.backup filter=lfs diff=lfs merge=lfs -text SFT/7B/Overcooked-VLM-large-new-free-think/step700/tokenizer.json.backup filter=lfs diff=lfs merge=lfs -text SFT/7B/Overcooked-VLM-large-new-free-think/step800/tokenizer.json.backup filter=lfs diff=lfs merge=lfs -text SFT/7B/Overcooked-VLM-no-think/step100/tokenizer.json filter=lfs diff=lfs merge=lfs -text SFT/7B/Overcooked-VLM-no-think/step200/tokenizer.json filter=lfs diff=lfs merge=lfs -text SFT/7B/Overcooked-VLM-no-think/step300/tokenizer.json filter=lfs diff=lfs merge=lfs -text SFT/7B/Overcooked-VLM-no-think/step400/tokenizer.json filter=lfs diff=lfs merge=lfs -text SFT/7B/VLM-sft-free-think/step600/tokenizer.json.backup filter=lfs diff=lfs merge=lfs -text SFT/7B/VLM-sft-free-think/step800/tokenizer.json.backup filter=lfs diff=lfs merge=lfs -text SFT/7B/VLM-sft-no-think/step200/tokenizer.json.backup filter=lfs diff=lfs merge=lfs -text SFT/7B/VLM-sft-no-think/step400/tokenizer.json.backup filter=lfs diff=lfs merge=lfs -text SFT/7B/VLM-sft-no-think/step600/tokenizer.json.backup filter=lfs diff=lfs merge=lfs -text SFT/7B/VLM-sft-no-think/step800/tokenizer.json.backup filter=lfs diff=lfs merge=lfs -text SFT/7B/Sokoban-LLM-free-think/step300/tokenizer.json filter=lfs diff=lfs merge=lfs -text SFT/7B/Sokoban-LLM-free-think/step400/tokenizer.json filter=lfs diff=lfs merge=lfs -text SFT/7B/Sokoban-LLM-no-think/step300/tokenizer.json filter=lfs diff=lfs merge=lfs -text SFT/7B/Sokoban-LLM-no-think/step400/tokenizer.json filter=lfs diff=lfs merge=lfs -text SFT/7B/Sokoban-VLM-free-think/step600/tokenizer.json.backup filter=lfs diff=lfs merge=lfs -text SFT/7B/Sokoban-VLM-free-think/step800/tokenizer.json.backup filter=lfs diff=lfs merge=lfs -text SFT/7B/Sokoban-VLM-no-think/step200/tokenizer.json.backup filter=lfs diff=lfs merge=lfs -text SFT/7B/Sokoban-VLM-no-think/step400/tokenizer.json.backup filter=lfs diff=lfs merge=lfs -text SFT/7B/Sokoban-VLM-no-think/step600/tokenizer.json.backup filter=lfs diff=lfs merge=lfs -text SFT/7B/Sokoban-VLM-no-think/step800/tokenizer.json.backup filter=lfs diff=lfs merge=lfs -text RL-3B/Overcooked-LLM-no-think/step25/tokenizer.json filter=lfs diff=lfs merge=lfs -text RL-3B/Overcooked-LLM-free-think/step25/tokenizer.json filter=lfs diff=lfs merge=lfs -text RL-3B/Overcooked-LLM-no-think/step50/tokenizer.json filter=lfs diff=lfs merge=lfs -text RL-3B/Overcooked-VLM-no-think/step25/tokenizer.json filter=lfs diff=lfs merge=lfs -text RL-3B/Overcooked-LLM-free-think/step50/tokenizer.json filter=lfs diff=lfs merge=lfs -text RL-3B/Overcooked-LLM-no-think/step75/tokenizer.json filter=lfs diff=lfs merge=lfs -text RL-3B/Overcooked-VLM-free-think/step25/tokenizer.json filter=lfs diff=lfs merge=lfs -text RL-3B/Overcooked-LLM-no-think/step100/tokenizer.json filter=lfs diff=lfs merge=lfs -text RL-3B/Sokoban-LLM-no-think/step150/tokenizer.json filter=lfs diff=lfs merge=lfs -text RL-3B/Overcooked-LLM-free-think/step75/tokenizer.json filter=lfs diff=lfs merge=lfs -text RL-3B/Overcooked-VLM-no-think/step50/tokenizer.json filter=lfs diff=lfs merge=lfs -text RL-3B/Overcooked-LLM-no-think/step125/tokenizer.json filter=lfs diff=lfs merge=lfs -text RL-3B/Sokoban-LLM-no-think/step175/tokenizer.json filter=lfs diff=lfs merge=lfs -text RL-3B/Overcooked-LLM-no-think/step150/tokenizer.json filter=lfs diff=lfs merge=lfs -text RL-3B/Sokoban-LLM-no-think/step200/tokenizer.json filter=lfs diff=lfs merge=lfs -text RL-3B/Overcooked-LLM-free-think/step100/tokenizer.json filter=lfs diff=lfs merge=lfs -text RL-3B/Overcooked-VLM-free-think/step50/tokenizer.json filter=lfs diff=lfs merge=lfs -text RL-3B/Overcooked-LLM-no-think/step175/tokenizer.json filter=lfs diff=lfs merge=lfs -text RL-3B/Overcooked-VLM-no-think/step75/tokenizer.json filter=lfs diff=lfs merge=lfs -text RL-3B/Sokoban-LLM-free-think/step125/tokenizer.json filter=lfs diff=lfs merge=lfs -text RL-3B/Overcooked-LLM-no-think/step200/tokenizer.json filter=lfs diff=lfs merge=lfs -text RL-3B/Overcooked-LLM-free-think/step125/tokenizer.json filter=lfs diff=lfs merge=lfs -text RL-3B/Sokoban-LLM-free-think/step150/tokenizer.json filter=lfs diff=lfs merge=lfs -text RL-3B/Sokoban-LLM-free-think/step175/tokenizer.json filter=lfs diff=lfs merge=lfs -text RL-3B/Sokoban-LLM-free-think/step200/tokenizer.json filter=lfs diff=lfs merge=lfs -text RL-3B/Overcooked-VLM-no-think/step100/tokenizer.json filter=lfs diff=lfs merge=lfs -text RL-3B/Overcooked-LLM-free-think/step150/tokenizer.json filter=lfs diff=lfs merge=lfs -text RL-3B/Overcooked-VLM-free-think/step75/tokenizer.json filter=lfs diff=lfs merge=lfs -text RL-3B/Overcooked-LLM-free-think/step175/tokenizer.json filter=lfs diff=lfs merge=lfs -text RL-3B/Overcooked-VLM-no-think/step125/tokenizer.json filter=lfs diff=lfs merge=lfs -text RL-3B/Sokoban-VLM-no-think/step50/tokenizer.json filter=lfs diff=lfs merge=lfs -text RL-3B/Overcooked-LLM-free-think/step200/tokenizer.json filter=lfs diff=lfs merge=lfs -text RL-3B/Sokoban-VLM-free-think/step50/tokenizer.json filter=lfs diff=lfs merge=lfs -text RL-3B/Overcooked-VLM-free-think/step100/tokenizer.json filter=lfs diff=lfs merge=lfs -text RL-3B/Overcooked-VLM-no-think/step150/tokenizer.json filter=lfs diff=lfs merge=lfs -text RL-3B/Sokoban-VLM-no-think/step75/tokenizer.json filter=lfs diff=lfs merge=lfs -text RL-3B/Overcooked-VLM-no-think/step175/tokenizer.json filter=lfs diff=lfs merge=lfs -text RL-3B/Sokoban-VLM-no-think/step100/tokenizer.json filter=lfs diff=lfs merge=lfs -text RL-3B/Overcooked-VLM-free-think/step125/tokenizer.json filter=lfs diff=lfs merge=lfs -text RL-3B/Overcooked-VLM-no-think/step200/tokenizer.json filter=lfs diff=lfs merge=lfs -text RL-3B/Sokoban-VLM-no-think/step125/tokenizer.json filter=lfs diff=lfs merge=lfs -text RL-7B/Sokoban-LLM-no-think/step25/tokenizer.json filter=lfs diff=lfs merge=lfs -text RL-7B/Sokoban-LLM-free-think/step25/tokenizer.json filter=lfs diff=lfs merge=lfs -text RL-7B/Sokoban-LLM-no-think/step50/tokenizer.json filter=lfs diff=lfs merge=lfs -text RL-7B/Sokoban-LLM-free-think/step50/tokenizer.json filter=lfs diff=lfs merge=lfs -text RL-7B/Overcooked-LLM-no-think/step25/tokenizer.json filter=lfs diff=lfs merge=lfs -text RL-3B/Overcooked-VLM-free-think/step150/tokenizer.json filter=lfs diff=lfs merge=lfs -text RL-3B/Sokoban-VLM-free-think/step75/tokenizer.json filter=lfs diff=lfs merge=lfs -text RL-7B/Overcooked-LLM-no-think/step50/tokenizer.json filter=lfs diff=lfs merge=lfs -text RL-7B/Overcooked-LLM-no-think/step75/tokenizer.json filter=lfs diff=lfs merge=lfs -text RL-3B/Sokoban-VLM-free-think/step100/tokenizer.json filter=lfs diff=lfs merge=lfs -text RL-7B/Overcooked-LLM-no-think/step100/tokenizer.json filter=lfs diff=lfs merge=lfs -text RL-3B/Sokoban-VLM-free-think/step125/tokenizer.json filter=lfs diff=lfs merge=lfs -text RL-3B/Overcooked-VLM-free-think/step175/tokenizer.json filter=lfs diff=lfs merge=lfs -text RL-7B/Overcooked-LLM-no-think/step125/tokenizer.json filter=lfs diff=lfs merge=lfs -text RL-3B/Sokoban-VLM-free-think/step150/tokenizer.json filter=lfs diff=lfs merge=lfs -text RL-3B/Sokoban-VLM-free-think/step175/tokenizer.json filter=lfs diff=lfs merge=lfs -text RL-7B/Overcooked-LLM-no-think/step150/tokenizer.json filter=lfs diff=lfs merge=lfs -text RL-3B/Overcooked-VLM-free-think/step200/tokenizer.json filter=lfs diff=lfs merge=lfs -text RL-3B/Sokoban-VLM-free-think/step200/tokenizer.json filter=lfs diff=lfs merge=lfs -text RL-7B/Overcooked-LLM-no-think/step175/tokenizer.json filter=lfs diff=lfs merge=lfs -text RL-7B/Overcooked-LLM-no-think/step200/tokenizer.json filter=lfs diff=lfs merge=lfs -text backup/magen/sft-rl-ragen/checkpoints/sokoban_sft/global_step_5/tokenizer.json filter=lfs diff=lfs merge=lfs -text backup/magen-vlm/checkpoints/magen_vlm/curriculum_learning_Jitter-0303_balanced_Distance_1313_free_think_7B_RL_FROM_E_M_H_V_sft_free_think_checkpoint-100_noexample_nopos/global_step_100/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text backup/magen-vlm/checkpoints/magen_vlm/curriculum_learning_Jitter-0303_balanced_Distance_1313_free_think_7B_RL_FROM_E_M_H_V_sft_free_think_checkpoint-100_noexample_nopos/global_step_150/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text backup/magen-vlm/checkpoints/magen_vlm/curriculum_learning_Jitter-0303_balanced_Distance_1313_free_think_7B_RL_FROM_E_M_H_V_sft_free_think_checkpoint-100_noexample_nopos/global_step_200/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text backup/magen-vlm/checkpoints/magen_vlm/curriculum_learning_Jitter-0303_balanced_Distance_1313_free_think_7B_RL_FROM_E_M_H_V_sft_free_think_checkpoint-100_noexample_nopos/global_step_250/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text backup/magen-vlm/checkpoints/magen_vlm/curriculum_learning_Jitter-0303_balanced_Distance_1313_free_think_7B_RL_FROM_E_M_H_V_sft_free_think_checkpoint-100_noexample_nopos/global_step_300/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text backup/magen-vlm/checkpoints/magen_vlm/curriculum_learning_Jitter-0303_balanced_Distance_1313_free_think_7B_RL_FROM_E_M_H_V_sft_free_think_checkpoint-100_noexample_nopos/global_step_50/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text backup/magen-vlm/checkpoints/magen_vlm/curriculum_learning_Jitter-0303_balanced_Distance_1313_free_think_7B_RL_FROM_E_M_H_V_sft_free_think_checkpoint-400_noexample_nopos/global_step_100/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text backup/magen-vlm/checkpoints/magen_vlm/curriculum_learning_Jitter-0303_balanced_Distance_1313_free_think_7B_RL_FROM_E_M_H_V_sft_free_think_checkpoint-400_noexample_nopos/global_step_150/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text backup/magen-vlm/checkpoints/magen_vlm/curriculum_learning_Jitter-0303_balanced_Distance_1313_free_think_7B_RL_FROM_E_M_H_V_sft_free_think_checkpoint-400_noexample_nopos/global_step_200/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text backup/magen-vlm/checkpoints/magen_vlm/curriculum_learning_Jitter-0303_balanced_Distance_1313_free_think_7B_RL_FROM_E_M_H_V_sft_free_think_checkpoint-400_noexample_nopos/global_step_50/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text backup/magen-vlm/checkpoints/magen_vlm/curriculum_learning_Jitter-0303_balanced_Distance_1313_no_think_7B_RL_FROM_E_M_H_V_sft_no_think_checkpoint-100_noexample_nopos/global_step_100/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text backup/magen-vlm/checkpoints/magen_vlm/curriculum_learning_Jitter-0303_balanced_Distance_1313_no_think_7B_RL_FROM_E_M_H_V_sft_no_think_checkpoint-100_noexample_nopos/global_step_150/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text backup/magen-vlm/checkpoints/magen_vlm/curriculum_learning_Jitter-0303_balanced_Distance_1313_no_think_7B_RL_FROM_E_M_H_V_sft_no_think_checkpoint-100_noexample_nopos/global_step_200/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text backup/magen-vlm/checkpoints/magen_vlm/curriculum_learning_Jitter-0303_balanced_Distance_1313_no_think_7B_RL_FROM_E_M_H_V_sft_no_think_checkpoint-100_noexample_nopos/global_step_250/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text backup/magen-vlm/checkpoints/magen_vlm/curriculum_learning_Jitter-0303_balanced_Distance_1313_no_think_7B_RL_FROM_E_M_H_V_sft_no_think_checkpoint-100_noexample_nopos/global_step_300/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text backup/magen-vlm/checkpoints/magen_vlm/curriculum_learning_Jitter-0303_balanced_Distance_1313_no_think_7B_RL_FROM_E_M_H_V_sft_no_think_checkpoint-100_noexample_nopos/global_step_50/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text backup/magen-vlm/checkpoints/magen_vlm/curriculum_learning_Jitter-0303_balanced_Distance_1313_no_think_7B_RL_FROM_E_M_H_V_sft_no_think_checkpoint-400_noexample_nopos/global_step_50/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text backup/LLaMA-Factory/saves/internvl3-8b-hf/E_M_H_V_sft_free_think/checkpoint-200/tokenizer.json filter=lfs diff=lfs merge=lfs -text backup/LLaMA-Factory/saves/internvl3-8b-hf/E_M_H_V_sft_free_think/checkpoint-400/tokenizer.json filter=lfs diff=lfs merge=lfs -text backup/LLaMA-Factory/saves/internvl3-8b-hf/E_M_H_V_sft_free_think/tokenizer.json filter=lfs diff=lfs merge=lfs -text backup/LLaMA-Factory/saves/llama3_1-8b-instruct/E_M_H_V_sft_free_think/checkpoint-100/tokenizer.json filter=lfs diff=lfs merge=lfs -text backup/LLaMA-Factory/saves/llama3_1-8b-instruct/E_M_H_V_sft_free_think/checkpoint-200/tokenizer.json filter=lfs diff=lfs merge=lfs -text backup/LLaMA-Factory/saves/llama3_1-8b-instruct/E_M_H_V_sft_no_think/checkpoint-100/tokenizer.json filter=lfs diff=lfs merge=lfs -text backup/LLaMA-Factory/saves/llava-llama3-8b-v1_1/E_M_H_V_sft_free_think/checkpoint-300/tokenizer.json filter=lfs diff=lfs merge=lfs -text backup/LLaMA-Factory/saves/llava-llama3-8b-v1_1/E_M_H_V_sft_free_think/checkpoint-400/tokenizer.json filter=lfs diff=lfs merge=lfs -text backup/LLaMA-Factory/saves/llava-llama3-8b-v1_1/E_M_H_V_sft_free_think/tokenizer.json filter=lfs diff=lfs merge=lfs -text backup/LLaMA-Factory/saves/qwen2_5-3b/E_M_H_V_sft_free_think/checkpoint-300/tokenizer.json filter=lfs diff=lfs merge=lfs -text backup/LLaMA-Factory/saves/qwen2_5-3b/E_M_H_V_sft_free_think/tokenizer.json filter=lfs diff=lfs merge=lfs -text backup/LLaMA-Factory/saves/qwen2_5-3b/E_M_H_V_sft_no_think/checkpoint-200/tokenizer.json filter=lfs diff=lfs merge=lfs -text backup/LLaMA-Factory/saves/qwen2_5-3b/E_M_H_V_sft_no_think/checkpoint-300/tokenizer.json filter=lfs diff=lfs merge=lfs -text backup/LLaMA-Factory/saves/qwen2_5-3b/E_M_H_V_sft_no_think/tokenizer.json filter=lfs diff=lfs merge=lfs -text backup/LLaMA-Factory/saves/qwen2_5-3b/overcooked_sft_large_free_think/checkpoint-400/tokenizer.json filter=lfs diff=lfs merge=lfs -text backup/LLaMA-Factory/saves/qwen2_5-3b/overcooked_sft_large_free_think/tokenizer.json filter=lfs diff=lfs merge=lfs -text backup/LLaMA-Factory/saves/qwen2_5-3b/overcooked_sft_large_no_think/checkpoint-400/tokenizer.json filter=lfs diff=lfs merge=lfs -text backup/LLaMA-Factory/saves/qwen2_5-3b/overcooked_sft_large_no_think/tokenizer.json filter=lfs diff=lfs merge=lfs -text backup/LLaMA-Factory/saves/qwen2_5-3b/sokoban_sft_free_think/checkpoint-800/tokenizer.json filter=lfs diff=lfs merge=lfs -text backup/LLaMA-Factory/saves/qwen2_5-3b/sokoban_sft_free_think/tokenizer.json filter=lfs diff=lfs merge=lfs -text backup/LLaMA-Factory/saves/qwen2_5-3b/sokoban_sft_no_think/checkpoint-800/tokenizer.json filter=lfs diff=lfs merge=lfs -text backup/LLaMA-Factory/saves/qwen2_5-3b/sokoban_sft_no_think/tokenizer.json filter=lfs diff=lfs merge=lfs -text backup/LLaMA-Factory/saves/qwen2_5-7b/E_M_H_V_sft_free_think/checkpoint-300/tokenizer.json filter=lfs diff=lfs merge=lfs -text backup/LLaMA-Factory/saves/qwen2_5-7b/E_M_H_V_sft_free_think/checkpoint-400/tokenizer.json filter=lfs diff=lfs merge=lfs -text backup/LLaMA-Factory/saves/qwen2_5-7b/E_M_H_V_sft_free_think/tokenizer.json filter=lfs diff=lfs merge=lfs -text backup/LLaMA-Factory/saves/qwen2_5-7b/E_M_H_V_sft_no_think/checkpoint-300/tokenizer.json filter=lfs diff=lfs merge=lfs -text backup/LLaMA-Factory/saves/qwen2_5-7b/E_M_H_V_sft_no_think/checkpoint-400/tokenizer.json filter=lfs diff=lfs merge=lfs -text backup/LLaMA-Factory/saves/qwen2_5-7b/E_M_H_V_sft_no_think/tokenizer.json filter=lfs diff=lfs merge=lfs -text backup/LLaMA-Factory/saves/qwen2_5-7b/overcooked_sft_large_new_free_think/checkpoint-400/tokenizer.json filter=lfs diff=lfs merge=lfs -text backup/LLaMA-Factory/saves/qwen2_5-7b/overcooked_sft_large_new_free_think/tokenizer.json filter=lfs diff=lfs merge=lfs -text backup/LLaMA-Factory/saves/qwen2_5-7b/overcooked_sft_large_new_no_think/tokenizer.json filter=lfs diff=lfs merge=lfs -text backup/LLaMA-Factory/saves/qwen2_5vl-3b/overcooked_sft_large_free_think/checkpoint-400/tokenizer.json filter=lfs diff=lfs merge=lfs -text backup/LLaMA-Factory/saves/qwen2_5vl-3b/overcooked_sft_large_free_think/tokenizer.json filter=lfs diff=lfs merge=lfs -text backup/LLaMA-Factory/saves/qwen2_5vl-3b/overcooked_sft_large_no_think/checkpoint-400/tokenizer.json filter=lfs diff=lfs merge=lfs -text backup/LLaMA-Factory/saves/qwen2_5vl-3b/overcooked_sft_large_no_think/tokenizer.json filter=lfs diff=lfs merge=lfs -text backup/LLaMA-Factory/saves/qwen2_5vl-3b/sokoban_sft_free_think/checkpoint-500/tokenizer.json filter=lfs diff=lfs merge=lfs -text backup/LLaMA-Factory/saves/qwen2_5vl-3b/sokoban_sft_no_think/checkpoint-800/tokenizer.json filter=lfs diff=lfs merge=lfs -text backup/LLaMA-Factory/saves/qwen2_5vl-3b/sokoban_sft_no_think/tokenizer.json filter=lfs diff=lfs merge=lfs -text backup/LLaMA-Factory/saves/qwen3-4b-instruct-2507/E_M_H_V_sft_free_think/checkpoint-300/tokenizer.json filter=lfs diff=lfs merge=lfs -text backup/LLaMA-Factory/saves/qwen3-4b-instruct-2507/E_M_H_V_sft_free_think/checkpoint-400/tokenizer.json filter=lfs diff=lfs merge=lfs -text backup/LLaMA-Factory/saves/qwen3-4b-instruct-2507/E_M_H_V_sft_free_think/tokenizer.json filter=lfs diff=lfs merge=lfs -text backup/magen-merge/checkpoints/magen_text/dual_sokoban_main_free_think_with_reasoning_reward_text_7B_TEXT_FROMSFT_E_M_H_V_sft_free_think_CKPT400/global_step_50/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text backup/magen/sft-rl-ragen/checkpoints/ragen_comparison/instruct_sft_to_rl_qwen_0.5b/global_step_50/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text backup/magen/sft-rl-ragen/checkpoints/ragen_comparison/instruct_sft_to_rl_qwen_0.5b/global_step_50/critic/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text backup/magen/sft-rl-ragen/checkpoints/ragen_latest/test/global_step_200/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text backup/magen/sft-rl-ragen/checkpoints/ragen_latest/test/global_step_200/actor/huggingface_converted/tokenizer.json filter=lfs diff=lfs merge=lfs -text backup/magen/sft-rl-ragen/checkpoints/ragen_latest/test/global_step_200/critic/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text backup/magen/sft-rl-ragen/checkpoints/ragen_latest/test/global_step_300/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text backup/magen/sft-rl-ragen/checkpoints/ragen_latest/test/global_step_300/critic/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text backup/magen/sft-rl-ragen/checkpoints/ragen_latest/test/global_step_301/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text backup/magen/sft-rl-ragen/checkpoints/ragen_latest/test/global_step_301/critic/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text backup/magen/sft-rl-ragen/checkpoints/ragen_latest/test/global_step_302/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text backup/magen/sft-rl-ragen/checkpoints/ragen_latest/test/global_step_302/critic/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text backup/magen/sft-rl-ragen/checkpoints/ragen_latest/test_with_thinking/global_step_200/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text backup/magen/sft-rl-ragen/checkpoints/ragen_latest/test_with_thinking/global_step_200/actor_hf/tokenizer.json filter=lfs diff=lfs merge=lfs -text backup/magen/sft-rl-ragen/checkpoints/ragen_latest/test_with_thinking/global_step_200/critic/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text backup/magen/sft-rl-ragen/checkpoints/sokoban_sft/global_step_100/tokenizer.json filter=lfs diff=lfs merge=lfs -text backup/magen/sft-rl-ragen/checkpoints/sokoban_sft/global_step_200/tokenizer.json filter=lfs diff=lfs merge=lfs -text backup/magen/sft-rl-ragen/checkpoints/sokoban_sft/global_step_50/tokenizer.json filter=lfs diff=lfs merge=lfs -text backup/magen/sft-rl-ragen/checkpoints/sokoban_sft_improved/global_step_100/tokenizer.json filter=lfs diff=lfs merge=lfs -text backup/magen/sft-rl-ragen/checkpoints/sokoban_sft_improved/global_step_150/tokenizer.json filter=lfs diff=lfs merge=lfs -text backup/magen/sft-rl-ragen/checkpoints/sokoban_sft_improved/global_step_200/tokenizer.json filter=lfs diff=lfs merge=lfs -text backup/magen/sft-rl-ragen/checkpoints/sokoban_sft_improved/global_step_300/tokenizer.json filter=lfs diff=lfs merge=lfs -text backup/magen/sft-rl-ragen/checkpoints/sokoban_sft_improved/global_step_400/tokenizer.json filter=lfs diff=lfs merge=lfs -text backup/magen/sft-rl-ragen/checkpoints/sokoban_sft_improved/global_step_50/tokenizer.json filter=lfs diff=lfs merge=lfs -text backup/magen/sft-rl-ragen/checkpoints/sokoban_sft_single_step/global_step_100/tokenizer.json filter=lfs diff=lfs merge=lfs -text backup/magen/sft-rl-ragen/checkpoints/sokoban_sft_single_step/global_step_150/tokenizer.json filter=lfs diff=lfs merge=lfs -text backup/magen/sft-rl-ragen/checkpoints/sokoban_sft_single_step/global_step_200/tokenizer.json filter=lfs diff=lfs merge=lfs -text backup/magen/sft-rl-ragen/checkpoints/sokoban_sft_single_step/global_step_50/tokenizer.json filter=lfs diff=lfs merge=lfs -text backup/LLaMA-Factory/saves/qwen2_5vl-7b/overcooked_sft_large_new_no_think/tokenizer.json filter=lfs diff=lfs merge=lfs -text backup/LLaMA-Factory/saves/qwen2_5vl-7b/overcooked_sft_large_new_no_think/checkpoint-400/tokenizer.json filter=lfs diff=lfs merge=lfs -text backup/magen-merge/checkpoints/magen_text/dual_sokoban_main_free_think_with_reasoning_reward_text_7B_TEXT_FROMSFT_E_M_H_V_sft_free_think_CKPT100/global_step_100/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text backup/magen-merge/checkpoints/magen_text/dual_sokoban_main_free_think_with_reasoning_reward_text_7B_TEXT_FROMSFT_E_M_H_V_sft_free_think_CKPT100/global_step_50/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text backup/magen-merge/checkpoints/magen_text/dual_sokoban_main_free_think_with_reasoning_reward_text_7B_TEXT_FROMSFT_E_M_H_V_sft_free_think_CKPT400/global_step_100/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text