kangdawei
/

Open-RS-DR_GRPO-7B

Text Generation

Generated from Trainer

text-generation-inference

Model card Files Files and versions

Open-RS-DR_GRPO-7B / tokenizer.json

Commit History

Add merged model for training step 50 (adapter revision: 9ea7bdcb)

3ed87a8
verified

kangdawei commited on Nov 23, 2025

Training in progress, step 50

9ea7bdc
verified

kangdawei commited on Nov 20, 2025