RLHF-And-Friends
/

Llama-3.1-8B-Instruct-Reward-Ultrafeedback

Generated from Trainer

Inference Endpoints

Model card Files Files and versions Community

arqa39 commited on 22 days ago

Commit

c648f03

·

verified ·

1 Parent(s): 6530abc

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -2,7 +2,7 @@
 base_model: meta-llama/Meta-Llama-3.1-8B-Instruct
 datasets: trl-lib/ultrafeedback_binarized
 library_name: transformers
-model_name: Meta-Llama-3.1-8B-Instruct-Reward-ultrafeedback_binarized-max_length-1024-LoRA-8r
 tags:
 - generated_from_trainer
 - trl

 base_model: meta-llama/Meta-Llama-3.1-8B-Instruct
 datasets: trl-lib/ultrafeedback_binarized
 library_name: transformers
+model_name: Llama-3.1-8B-Instruct-Reward-Ultrafeedback
 tags:
 - generated_from_trainer
 - trl