JLiangHe
/

sci-llm-ckpt

Model card Files Files and versions

198 GB

Ctrl+K

Ctrl+K

1 contributor

History: 12 commits

JLiangHe's picture

Publish V2 SFT RL step 150 checkpoint with complete evaluation trajectories and judgments

b27c3ea verified 17 days ago

qwen35-4b-synthetic-qa-grpo-step120
Add files using upload-large-folder tool about 2 months ago
qwen35-9b-base-mixed-sft-epoch2-rl-step-50
Upload Qwen3.5-9B mixed SFT epoch-2 RL step-50 model about 2 months ago
qwen35-9b-base-mixed-sft-epoch2
Upload Qwen3.5-9B mixed SFT epoch-2 model about 2 months ago
qwen35-9b-base-sci-training-data-v2-sft-epoch2-rl-step100
Upload Qwen3.5-9B v2 RL step 100 about 1 month ago
qwen35-9b-base-sci-training-data-v2-sft-epoch2
Upload Qwen3.5-9B v2 SFT epoch 2 about 1 month ago
qwen35-9b-v2sft-hard-mix-rl-step100
Upload Qwen3.5-9B hard-mix RL step 100 checkpoint 29 days ago
qwen35-9b-v2sft-new-rl-step120
Rename step-120 checkpoint to identify v2 SFT initialization 19 days ago
qwen35-9b-v2sft-new-rl-step150
Publish V2 SFT RL step 150 checkpoint with complete evaluation trajectories and judgments 17 days ago
.gitattributes
4.5 kB
Publish V2 SFT RL step 150 checkpoint with complete evaluation trajectories and judgments 17 days ago