Update README.md

README.md

@@ -1,12 +1,17 @@
 ---
 base_model: huggyllama/llama-7b
 library_name: peft
-license: other
+license: mit
 tags:
-- generated_from_trainer
+- peft
+- lora
+- dora
 model-index:
 - name: llama-3-8-fine-tuned-dora
   results: []
+datasets:
+- timdettmers/openassistant-guanaco
+pipeline_tag: text-generation
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -14,7 +19,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 # llama-3-8-fine-tuned-dora
 
-This model is a fine-tuned version of [huggyllama/llama-7b](https://huggingface.co/huggyllama/llama-7b) on an unknown dataset.
+This model is a fine-tuned version of [huggyllama/llama-7b](https://huggingface.co/huggyllama/llama-7b) on on [openassistant-guanaco](https://huggingface.co/datasets/timdettmers/openassistant-guanaco) dataset.
+For LoraConfig we set the `use_dora=True` for the Dora decomposition and comparison with Lora. 
 
 ## Model description