limmin33
/

sciW

Model card Files Files and versions

1 TB

Ctrl+K

Ctrl+K

1 contributor

History: 18 commits

limmin33's picture

Add graphgpo_belief_skip seed0 Qwen2.5-1.5B-Instruct latest_checkpointed_iteration.txt

df7fbdc verified 2 months ago

gigpo_seed0
Add GiGPO Qwen2.5-7B-Instruct sciworld seed0 (global_step_100,150) 3 months ago
graphgpo_belief_skip_seed0
Add graphgpo_belief_skip seed0 Qwen2.5-1.5B-Instruct latest_checkpointed_iteration.txt 2 months ago
graphgpo_seed0
Add graphgpo 1.5b sciworld seed0 checkpoints (steps 50/100/150) 2 months ago
grpo_seed0
Add files using upload-large-folder tool 3 months ago
rewardflow_seed0
Add RewardFlow Qwen2.5-7B-Instruct sciworld seed0 (global_step_100,150) 3 months ago
.gitattributes

4.13 kB
Add graphgpo_belief_skip seed0 Qwen2.5-1.5B-Instruct global_step_100 2 months ago