|  Matthias Reso | cf678b9bf0
							
							Adjust imports to package structure + cleaned up imports | 2 år sedan | 
				
					
						|  Matthias Reso | 02428c992a
							
							Adding vllm as dependency; fix dep install with hatchling | 2 år sedan | 
				
					
						|  Matthias Reso | c8522eb0ff
							
							Remove peft install from src | 2 år sedan | 
				
					
						|  Matthias Reso | 4c9cc7d223
							
							Move modules into separate src folder | 2 år sedan | 
				
					
						|  Geeta Chauhan | fbc513ec47
							
							adding notes how to get the HF models (#151) | 2 år sedan | 
				
					
						|  Hamid Shojanazeri | bcfafd9a0b
							
							adding notes how to get the HF models | 2 år sedan | 
				
					
						|  Geeta Chauhan | cfba150311
							
							adding llama code inference (#144) | 2 år sedan | 
				
					
						|  Hamid Shojanazeri | 6105a3f886
							
							clarifying the infilling use-case | 2 år sedan | 
				
					
						|  Hamid Shojanazeri | 8b0008433c
							
							fix typos | 2 år sedan | 
				
					
						|  Hamid Shojanazeri | 564ef2f628
							
							remove padding logic | 2 år sedan | 
				
					
						|  Hamid Shojanazeri | 277a292fbc
							
							adding autotokenizer | 2 år sedan | 
				
					
						|  Hamid Shojanazeri | 3f2fb9167e
							
							adding notes to model not supporting infilling | 2 år sedan | 
				
					
						|  Hamid Shojanazeri | c62428b99c
							
							setting defaults of temp and top_p | 2 år sedan | 
				
					
						|  Hamid Shojanazeri | c014ae7cb8
							
							setting BT option to true | 2 år sedan | 
				
					
						|  Hamid Shojanazeri | 4fa44e16d9
							
							add note for python llama not suited for llama infilling | 2 år sedan | 
				
					
						|  Hamid Shojanazeri | b18a186385
							
							removing the option to take prompt from cli | 2 år sedan | 
				
					
						|  Hamid Shojanazeri | 75991d8795
							
							fix the extra line added and remove take prompt from cli | 2 år sedan | 
				
					
						|  Hamid Shojanazeri | d28fc9898a
							
							addressing doc comments | 2 år sedan | 
				
					
						|  Hamid Shojanazeri | a234d1fe0c
							
							fix typos | 2 år sedan | 
				
					
						|  Hamid Shojanazeri | 2d9f4796e8
							
							fixing the output format | 2 år sedan | 
				
					
						|  Hamid Shojanazeri | 1e8ea70b26
							
							adding llama code inference | 2 år sedan | 
				
					
						|  Geeta Chauhan | 82e05c46e0
							
							fix a bug in the config for use_fast_kernels (#121) | 2 år sedan | 
				
					
						|  Hamid Shojanazeri | 971c079aa6
							
							bugfix: remove duplicate load_peft_model (#124) | 2 år sedan | 
				
					
						|  hongbo.mo | fcc817e923
							
							bugfix: remove duplicate load_peft_model | 2 år sedan | 
				
					
						|  Brian Vaughan | 3faf005226
							
							fix a bug in the config for use_fast_kernels | 2 år sedan | 
				
					
						|  Geeta Chauhan | 03faba661f
							
							Update paddings  (#85) | 2 år sedan | 
				
					
						|  Geeta Chauhan | 205e5a4b81
							
							save cpu mem by leveraging FSDP rank0 broadcasting (#77) | 2 år sedan | 
				
					
						|  Hamid Shojanazeri | 85a4ed1b65
							
							Merge branch 'main' into update_paddings | 2 år sedan | 
				
					
						|  lchu | feaa344af3
							
							resolve conflicts | 2 år sedan | 
				
					
						|  Geeta Chauhan | 3f1fef7a00
							
							adding flash attention and xformer memory efficient through PT SDPA (#97) | 2 år sedan |