Update README.md

README.md

@@ -225,7 +225,7 @@ print(tokenizer.decode(response, skip_special_tokens=True))
 ## Training Details
 
 ### Supervised fine-tuning
-SFT on top of Qwen2.5-7B using axolotl (https://github.com/axolotl-ai-cloud/axolotl).
+SFT on top of Qwen2.5-72B using axolotl (https://github.com/axolotl-ai-cloud/axolotl).
 
 We used Deepspeed's Zero-3 distributed training using the following hardware:
 
@@ -276,7 +276,7 @@ The training set consists of around 1.8B tokens, having 3 different types of dat
 - Gradient accumulation steps: 4
 
 ### Model Merging
-The model trained was merged with the Qwen2.5-7B-Instruct model using the DARE_TIES technique. [Mergekit](https://github.com/arcee-ai/mergekit) was used to conduct the merging.
+The model trained was merged with the Qwen2.5-72-Instruct model using the DARE_TIES technique. [Mergekit](https://github.com/arcee-ai/mergekit) was used to conduct the merging.
 
 ### Model Alignment
 The model is aligned using the Direct Preference Optimization (DPO) technique through a two-step process: