CharlesLi
/

mistral_rlhf_safe_llama_3_8B_reflect_1000_full

Text Generation

alignment-handbook

Generated from Trainer

text-generation-inference

Inference Endpoints

Model card Files Files and versions Metrics Training metrics Community

mistral_rlhf_safe_llama_3_8B_reflect_1000_full / runs

Commit History

End of training

4f08948
verified

CharlesLi commited on Jan 14

Model save

7f26397
verified

CharlesLi commited on Jan 14