Update README.md

README.md

@@ -1,4 +1,5 @@
 ---
+base_model: meta-llama/Meta-Llama-3-8B-Instruct
 library_name: transformers
 tags:
 - 4-bit
@@ -6,8 +7,23 @@ tags:
 - text-generation
 - autotrain_compatible
 - endpoints_compatible
+- axolotl
+- finetune
+- dpo
+- facebook
+- meta
+- pytorch
+- llama
+- llama-3
 pipeline_tag: text-generation
+license: llama3
+license_name: llama3
+license_link: LICENSE
 inference: false
+model_creator: MaziyarPanahi
+model_name: Llama-3-8B-Instruct-DPO-v0.3
+datasets:
+- Intel/orca_dpo_pairs
 quantized_by: Suparious
 ---
 # MaziyarPanahi/Llama-3-8B-Instruct-DPO-v0.3 AWQ
@@ -15,7 +31,11 @@ quantized_by: Suparious
 - Model creator: [MaziyarPanahi](https://huggingface.co/MaziyarPanahi)
 - Original model: [Llama-3-8B-Instruct-DPO-v0.3](https://huggingface.co/MaziyarPanahi/Llama-3-8B-Instruct-DPO-v0.3)
 
+<img src="./llama-3-merges.webp" alt="Llama-3 DPO Logo" width="500" style="margin-left:'auto' margin-right:'auto' display:'block'"/>
 
+## Model Summary
+
+This model is a fine-tune (DPO) of `meta-llama/Meta-Llama-3-8B-Instruct` model. I have used `rope_theta` to extend the context length up to 32K safely.
 
 ## How to use