Update README.md

README.md

@@ -1,7 +1,7 @@
 ---
 library_name: transformers
 license: other
-base_model: hon9kon9ize/Qwen2.5-7B-cpt
+base_model: hon9kon9ize/CantoneseLLM-7B-sft
 tags:
 - llama-factory
 - full
@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # CantoneseLLMChat-v1.0
 
-This model is a fine-tuned version of [hon9kon9ize/Qwen2.5-7B-cpt](https://huggingface.co/hon9kon9ize/Qwen2.5-7B-cpt) on the dpo_v1 dataset.
+This model is a fine-tuned version of [hon9kon9ize/CantoneseLLM-7B-sft](https://huggingface.co/hon9kon9ize/CantoneseLLM-7B-sft) on the dpo_v1 dataset.
 It achieves the following results on the evaluation set:
 - Loss: 0.3170
 - Rewards/chosen: -0.7307