Update README.md

README.md

@@ -7,7 +7,9 @@ model_name: Mistral-7B-Instruct-v0.2
 quantized_by: Leliuga
 pipeline_tag: text-generation
 tags:
-  - mistral 
+- mistral
+- arxiv:2310.06825
+- arxiv:1910.09700
 ---
 # Mistral-7B-Instruct-v0.2 - bnb 4bit
 - Model creator: [Mistral AI_](https://huggingface.co/mistralai)
@@ -15,5 +17,4 @@ tags:
 
 ## Description
 
-This model is 4bit quantized version of [Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) using bitsandbytes. It's designed for fine-tuning! The PAD token is set as UNK.
-
+This model is 4bit quantized version of [Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) using bitsandbytes. It's designed for fine-tuning! The PAD token is set as UNK.