初始化项目,由ModelHub XC社区提供模型

Model: lihaoxin2020/qwen3-4b-sft-gpt54-ep2-evolving-rubric-gem3-flash-step150
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-05-09 20:11:25 +08:00
commit f7f666b03b
14 changed files with 152294 additions and 0 deletions

10
README.md Normal file
View File

@@ -0,0 +1,10 @@
---
library_name: transformers
---
# sft-gpt54-ep2-evolving-rubric-gem3-flash-answer_only — step 150
GRPO checkpoint.
## Training run
- W&B: https://wandb.ai/lihaoxin2020-yale-university/refiner-sft-grpo/runs/fxscpf8a