zerg2187
/

GRPO_structeval_t_qwen3_v1

Reinforcement Learning

text-generation

structured-output

text-generation-inference

4-bit precision

Model card Files Files and versions

GRPO_structeval_t_qwen3_v1 / tokenizer.json

Commit History

Upload GRPO fine-tuned merged model

a49ffcb
verified

zerg2187 commited on 27 days ago