CASE-Bench
/

CASE-8B-RSFT

Model card Files Files and versions

Vinyeh commited on 6 days ago

Commit

6dbfd83

·

verified ·

1 Parent(s): 2d70c17

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -15,7 +15,7 @@ SFT-initialized agent (40% of the training split) - already tool-calling capable
 this is the initialization that the RL models continue from.
 - **Training**: mixed single-turn SFT over the three agent roles, assistant-only loss
-- **Step**: final = 1515
 - **Base model**: Qwen3-VL-8B-Instruct
 - **Format**: merged HF checkpoint (single `model.safetensors` + tokenizer/processor)
 - **Serving tip**: run with a tool backend (the released mock-tool replay configs,

 this is the initialization that the RL models continue from.
 - **Training**: mixed single-turn SFT over the three agent roles, assistant-only loss
+- **Step**: final = 1515（1 epoch）
 - **Base model**: Qwen3-VL-8B-Instruct
 - **Format**: merged HF checkpoint (single `model.safetensors` + tokenizer/processor)
 - **Serving tip**: run with a tool backend (the released mock-tool replay configs,