The *RLMT* collection. Coming soon!
			
	
	Princeton NLP group
princeton-nlp
		AI & ML interests
None yet
		Recent Activity
						updated 
								a collection
							
						about 1 month ago
						
					RLMT Experiments
						
						updated 
								a collection
							
						about 1 month ago
						
					RLMT Experiments
						
						updated 
								a collection
							
						about 1 month ago
						
					RLMT Experiments
						Organizations
SimPO
			This collections contains a list of SimPO and baseline models.
			
	
	- 
	
	
	  princeton-nlp/gemma-2-9b-it-SimPOText Generation • 9B • Updated • 2.19k • • 171
- 
	
	
	  princeton-nlp/gemma-2-9b-it-DPOText Generation • 9B • Updated • 9 • • 9
- 
	
	
	  princeton-nlp/Llama-3-Base-8B-SFT-IPOText Generation • 8B • Updated • 7 • • 1
- 
	
	
	  princeton-nlp/Llama-3-Base-8B-SFT-DPOText Generation • 8B • Updated • 75 •
RLMT Experiments
			The *RLMT* collection. Coming soon!
			
	
	SimPO
			This collections contains a list of SimPO and baseline models.
			
	
	- 
	
	
	  princeton-nlp/gemma-2-9b-it-SimPOText Generation • 9B • Updated • 2.19k • • 171
- 
	
	
	  princeton-nlp/gemma-2-9b-it-DPOText Generation • 9B • Updated • 9 • • 9
- 
	
	
	  princeton-nlp/Llama-3-Base-8B-SFT-IPOText Generation • 8B • Updated • 7 • • 1
- 
	
	
	  princeton-nlp/Llama-3-Base-8B-SFT-DPOText Generation • 8B • Updated • 75 •
			models
			306
		
			
	
	
	
	
	 
				princeton-nlp/warm-start__grpo__nothink__Qwen2.5-7B-Instruct
		
				8B
			• 
	
				Updated
					
				
				• 
					
					116
				
	
				
				
 
				princeton-nlp/warm-start__grpo__nothink__Llama-3.1-8B-Instruct
		
				8B
			• 
	
				Updated
					
				
				• 
					
					2
				
	
				
				
 
				princeton-nlp/warm-start__grpo__nothink__Qwen2.5-7B
		
				8B
			• 
	
				Updated
					
				
				• 
					
					2
				
	
				
				
 
				princeton-nlp/warm-start__grpo__nothink__Llama-3.1-8B
		
				8B
			• 
	
				Updated
					
				
				• 
					
					2
				
	
				
				
 
				princeton-nlp/warm-start__grpo__think__Qwen2.5-7B-Instruct
		
				8B
			• 
	
				Updated
					
				
				• 
					
					8
				
	
				
				
 
				princeton-nlp/warm-start__grpo__think__Llama-3.1-8B-Instruct
		
				8B
			• 
	
				Updated
					
				
				• 
					
					2
				
	
				
				
 
				princeton-nlp/warm-start__grpo__think__Qwen2.5-7B
		
				8B
			• 
	
				Updated
					
				
				• 
					
					5
				
	
				
				
 
				princeton-nlp/warm-start__grpo__think__Llama-3.1-8B
		
				8B
			• 
	
				Updated
					
				
				• 
					
					2
				
	
				
				
 
				princeton-nlp/zero__grpo__nothink__Qwen2.5-7B
		
				8B
			• 
	
				Updated
					
				
				• 
					
					2
				
	
				
				
 
				princeton-nlp/zero__grpo__nothink__Llama-3.1-8B
		
				8B
			• 
	
				Updated
					
				
				• 
					
					1
				
	
				
				
			datasets
			47
		
			
	
	
	
	
	princeton-nlp/rl_tulu3_wildchat-if_prompts
			Viewer
			• 
	
				Updated
					
				• 
			
			7.79k
	
				• 
					
					99
				
				• 
					
					3
				
princeton-nlp/gemini_2.5_flash_0417_sft-data
			Viewer
			• 
	
				Updated
					
				• 
			
			6k
	
				• 
					
					121
				
				• 
					
					1
				
princeton-nlp/prolong-data-512K
	
				Updated
					
				
	
				• 
					
					11.2k
				
				• 
					
					10
				
princeton-nlp/SWE-bench_Lite
			Viewer
			• 
	
				Updated
					
				• 
			
			323
	
				• 
					
					26.6k
				
				• 
					
					49
				
princeton-nlp/SWE-bench
			Viewer
			• 
	
				Updated
					
				• 
			
			21.5k
	
				• 
					
					18.7k
				
				• 
					
					124
				
princeton-nlp/SWE-bench_Verified
			Viewer
			• 
	
				Updated
					
				• 
			
			500
	
				• 
					
					968k
				
				• 
					
					224
				
princeton-nlp/TextbooksBySubject
			Viewer
			• 
	
				Updated
					
				• 
			
			129
	
				• 
					
					18
				
				
				
princeton-nlp/TextbookChapters
			Viewer
			• 
	
				Updated
					
				• 
			
			77.9k
	
				• 
					
					99
				
				• 
					
					10
				
princeton-nlp/SWE-bench_Multimodal
			Viewer
			• 
	
				Updated
					
				• 
			
			612
	
				• 
					
					472
				
				• 
					
					21
				
princeton-nlp/fineweb_edu-swahili-translated
			Viewer
			• 
	
				Updated
					
				• 
			
			137k
	
				• 
					
					24
				
				• 
					
					2
				
 
								 
								 
								





