shubhamprshr
/

Qwen2.5-3B-Instruct_math_sgrpo_gaussian_0.5_0.5_True_1200

Text Generation

Generated from Trainer

text-generation-inference

Model card Files Files and versions Community

Qwen2.5-3B-Instruct_math_sgrpo_gaussian_0.5_0.5_True_1200

Commit History

End of training

28f9cc5
verified

shubhamprshr commited on 10 days ago

Model save

4801008
verified

shubhamprshr commited on 10 days ago

Training in progress, step 1200

16db05b
verified

shubhamprshr commited on 10 days ago

initial commit

d5b81cd
verified

shubhamprshr commited on 11 days ago