Upload

README.md

@@ -3,9 +3,12 @@ library_name: transformers
 license: llama3
 base_model: Dynosaur/llama3-8b-math-sft
 tags:
+- alignment-handbook
 - trl
 - sft
 - generated_from_trainer
+datasets:
+- Dynosaur/math-sft-subtask-6-subset
 model-index:
 - name: llama3-8b-math-sft-subtask-6-subset
   results: []
@@ -16,7 +19,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # llama3-8b-math-sft-subtask-6-subset
 
-This model is a fine-tuned version of [Dynosaur/llama3-8b-math-sft](https://huggingface.co/Dynosaur/llama3-8b-math-sft) on an unknown dataset.
+This model is a fine-tuned version of [Dynosaur/llama3-8b-math-sft](https://huggingface.co/Dynosaur/llama3-8b-math-sft) on the Dynosaur/math-sft-subtask-6-subset dataset.
 
 ## Model description