7de5fe0997b27953d28d933caa388292107245b8
Model: lihaoxin2020/qwen3-4b-sft-gpt54-ep2-instance-rubric-gpt54-step300 Source: Original Platform
library_name
| library_name |
|---|
| transformers |
sft-gpt54-ep2-instance-rubric-gpt54-answer_only — step 300
GRPO checkpoint.
Training run
Description
Model synced from source: lihaoxin2020/qwen3-4b-sft-gpt54-ep2-instance-rubric-gpt54-step300
Languages
Jinja
100%