3.89 TB

Ctrl+K

1 contributor

backup: 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/vocab.json

e2d89de verified 3 months ago

RL-3B
Upload RL checkpoint: RL-3B/Sokoban-VLM-free-think/step200 5 months ago
RL-7B
Upload RL checkpoint: RL-7B/Overcooked-LLM-no-think/step200 5 months ago
SFT
Rename SFT/7B/VLM-sft-no-think to SFT/7B/Sokoban-VLM-no-think 6 months ago
backup
backup: 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/vocab.json 3 months ago
.gitattributes

46.1 kB
backup: 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 3 months ago