s1.1 replication
					Collection
				
Replication of fine-tuning the Qwen2.5 family of models on the S1 and S1.1 datasets, as described in the S1 work (https://arxiv.org/abs/2501.19393)
					• 
				10 items
				• 
				Updated
					
				
Qwen2.5-32B-Instruct finetuned on s1.1K.