Update README.md

README.md

@@ -1,5 +1,5 @@
 ---
-base_model: checkpoints/Mistral-7B-Instruct-EI-Iter3
+base_model: UCLA-AGI/Mistral7B-PairRM-SPPO-Iter3
 datasets:
 - synthetic_data_mistral-7b-instruct-expert-iteration-iter3_score
 tags:
@@ -8,7 +8,7 @@ tags:
 - autoquant
 - gptq
 model-index:
-- name: Mistral-7B-Instruct-EI-Iter3
+- name: Mistral7B-PairRM-SPPO-Iter3
   results: []
 ---
 
@@ -17,7 +17,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # Mistral-7B-Instruct-EI-Iter3
 
-This model is a GPTQ version of [checkpoints/Mistral-7B-Instruct-EI-Iter3](https://huggingface.co/checkpoints/Mistral-7B-Instruct-EI-Iter3) 
+This model is a GPTQ version of [UCLA-AGI/Mistral7B-PairRM-SPPO-Iter3](UCLA-AGI/Mistral7B-PairRM-SPPO-Iter3) 
 
 Created with [AutoQuant](https://colab.research.google.com/drive/1b6nqC7UZVt8bx4MksX7s656GXPM-eWw4?usp=sharing)