vwxyzjn
		
		
				
				·
				 
		
		
		
			AI & ML interests
		
		None yet
		
		
			Organizations
		
		
	
		
	 
				vwxyzjn/ppo_async
				
				
			 
				vwxyzjn/ppo_sync
				
				
			
		
	
				Updated
					
				
				
				
	
				
				
 
				vwxyzjn/online_dpo_sync
				
				
			
		
	
				Updated
					
				
				
				
	
				
				
 
				vwxyzjn/online_dpo_async
				
				
			
		
	
				Updated
					
				
				
				
	
				
				
 
				vwxyzjn/rm_zephyr_new
				
				
			
			Text Classification
			
• 
		
				7B
			• 
	
				Updated
					
				
				
				
	
				
				 
				vwxyzjn/online_dpo_vllm_thread_beta_0.03__allenai_open_instruct_dev
				
				
			
		
	
				Updated
					
				
				
				
	
				
				
 
				vwxyzjn/reward_modeling__EleutherAI_pythia-14m
				
				
			
		
	
				Updated
					
				
				
				
	
				
				
 
				vwxyzjn/online_dpo_vllm__vwxyzjn_btulu
				
				
			
		
	
				Updated
					
				
				
				
	
				
				
 
				vwxyzjn/online_dpo_vllm__allenai_llama-3-tulu-2-8b
				
				
			 
				vwxyzjn/btulu
				
				
			
			Text Generation
			
• 
		
				8B
			• 
	
				Updated
					
				
				
				
	
				
				 
				vwxyzjn/online_dpo_tulu_2
				
				
			
			Text Generation
			
• 
		
	
				Updated
					
				
				
				
	
				
				 
				vwxyzjn/gkd-model
				
				
			
		
	
				Updated
					
				
				
				
	
				
				
 
				vwxyzjn/reward_modeling__allenai_llama-3-tulu-2-8b
				
				
			
		
	
				Updated
					
				
				
				
	
				
				
 
				vwxyzjn/online_dpo__cleanrl_EleutherAI_pythia-1b-deduped__sft__tldr
				
				
			
		
	
				Updated
					
				
				
				
	
				
				
 
				vwxyzjn/online_dpo__EleutherAI_pythia-14m
				
				
			
		
	
				Updated
					
				
				
				
	
				
				
 
				vwxyzjn/online_dpo__EleutherAI_pythia-1b-deduped
				
				
			
		
	
				Updated
					
				
				
				
	
				
				
 
				vwxyzjn/tulu3_7b_llama3
				
				
			
		
	
				Updated
					
				
				
				
	
				
				
 
				vwxyzjn/tulu3_7b_llama3-10000-max-samples
				
				
			 
				vwxyzjn/reward_modeling__EleutherAI_pythia-1b-deduped
				
				
			
		
	
				Updated
					
				
				
				
	
				
				
 
				vwxyzjn/EleutherAI_pythia-14m__reward_modeling__tldr
				
				
			
		
	
				Updated
					
				
				
				
	
				
				
 
				vwxyzjn/rejection_sampling_23251
				
				
			
		
	
				Updated
					
				
				
				
	
				
				
 
				vwxyzjn/online_sft_test1
				
				
			
		
	
				Updated
					
				
				
				
	
				
				
 
				vwxyzjn/online_sft_test
				
				
			
		
	
				Updated
					
				
				
				
	
				
				
 
				vwxyzjn/online_dpo_test
				
				
			
		
	
				Updated
					
				
				
				
	
				
				
 
				vwxyzjn/summarize_from_feedback_details
				
				
			
		
	
				Updated
					
				
				
				
	
				
				
 
				vwxyzjn/online_dpo_llmjudge_tldr_6.9b
				
				
			
			Text Generation
			
• 
		
				7B
			• 
	
				Updated
					
				
				
				
	
				
				 
				vwxyzjn/online_dpo_llmjudge
				
				
			
			Text Generation
			
• 
		
				1B
			• 
	
				Updated
					
				
				
				
	
				
				 
				vwxyzjn/online_dpo_llmjudge_tldr
				
				
			
		
	
				Updated
					
				
				
				
	
				
				
 
				vwxyzjn/online_dpo_tldr_6.9b
				
				
			
			Text Generation
			
• 
		
				7B
			• 
	
				Updated
					
				
				
				
	
				
				 
				vwxyzjn/online_dpo_tldr
				
				
			
			Text Generation
			
• 
		
				1B
			• 
	
				Updated