Update README.md

README.md

@@ -5,8 +5,12 @@ tags:
 - generated_from_trainer
 base_model: meta-llama/Meta-Llama-3-8B-Instruct
 model-index:
-- name: outputs/llama-3-8b-claudstruct-v2/
+- name: llama-3-8b-claudstruct-v2
   results: []
+datasets:
+- Norquinal/claude_multi_instruct_30k
+language:
+- en
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -103,9 +107,9 @@ special_tokens:
 
 </details><br>
 
-# outputs/llama-3-8b-claudstruct-v2/
+# llama-3-8b-claudstruct-v2
 
-This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) on the None dataset.
+This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) on the [Norquinal/claude_multi_instruct_30k](https://huggingface.co/datasets/Norquinal/claude_multi_instruct_30k) dataset.
 It achieves the following results on the evaluation set:
 - Loss: 1.6839