clembench-playpen
/

meta-llama-Meta-Llama-3.1-8B-Instruct_SFT_E1_D20002

Generated from Trainer

Model card Files Files and versions Metrics Training metrics Community

Nicohst commited on 26 days ago

Commit

952ffff

•

1 Parent(s): 13b0db8

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -23,7 +23,7 @@ This model is a fine-tuned version of [unsloth/meta-llama-3.1-8b-instruct-bnb-4b
 ## Model description
 This model is finetuned on all successful episodes of the top 3 models from benchmark versoions 0.9 and 1.0.
-Approximatedly 350 episodes are in the dataset.
 The dataset id is D20002

 ## Model description
 This model is finetuned on all successful episodes of the top 3 models from benchmark versoions 0.9 and 1.0.
+Approximatedly 920 episodes are in the dataset.
 The dataset id is D20002