himanshushukla12
							
						 | 
						
							
							
								3170c2785d
							
							Changed readme for usage of multimodal inferencing of gradio UI by passsing hugigng-face token from the arguments
						 | 
						1 rok pred | 
					
				
					
						
							
								   himanshushukla12
							
						 | 
						
							
							
								750b499d14
							
							Added passing of Hugging-face token from the arguments
						 | 
						1 rok pred | 
					
				
					
						
							
								   himanshushukla12
							
						 | 
						
							
							
								c609a442b0
							
							Change Gradio -> gradio
						 | 
						1 rok pred | 
					
				
					
						
							
								   Himanshu Shukla
							
						 | 
						
							
							
								b94a3402d5
							
							Merge branch 'meta-llama:main' into main
						 | 
						1 rok pred | 
					
				
					
						
							
								   himanshushukla12
							
						 | 
						
							
							
								19938dded9
							
							Added instructions in README.md for using the Gradio UI
						 | 
						1 rok pred | 
					
				
					
						
							
								   Huang Zhihong
							
						 | 
						
							
							
								a620831762
							
							Fix the bug when continue the peft. (#717)
						 | 
						1 rok pred | 
					
				
					
						
							
								   himanshushukla12
							
						 | 
						
							
							
								b2f96557da
							
							Modified requirements.txt by adding the gradio dependency
						 | 
						1 rok pred | 
					
				
					
						
							
								   himanshushukla12
							
						 | 
						
							
							
								22be586773
							
							Implemented memory management to release GPU resources after inference
						 | 
						1 rok pred | 
					
				
					
						
							
								   himanshushukla12
							
						 | 
						
							
							
								405371288b
							
							Added basic LlamaInference class structure, model loading functionality, image processing and text generation
						 | 
						1 rok pred | 
					
				
					
						
							
								   himanshushukla12
							
						 | 
						
							
							
								0c985d873c
							
							added a file to start with Inferencing on llama3.2 vision using gradio UI
						 | 
						1 rok pred | 
					
				
					
						
							
								   Ethan
							
						 | 
						
							
							
								288ac90e4a
							
							Removed unused files and cleaned up terraform.
						 | 
						1 rok pred | 
					
				
					
						
							
								   Ethan
							
						 | 
						
							
							
								059f0a4ca1
							
							Initial commit for Crusoe recipes, beginning with vLLM tutorial on benchmarking fp8.
						 | 
						1 rok pred | 
					
				
					
						
							
								   Sanyam Bhutani
							
						 | 
						
							
							
								9a56c4199a
							
							added missing word and corrected spelling (#707)
						 | 
						1 rok pred | 
					
				
					
						
							
								   Jannik Malte Meissner
							
						 | 
						
							
							
								3f883f6ce2
							
							added missing word and corrected spelling
						 | 
						1 rok pred | 
					
				
					
						
							
								   erik-dunteman
							
						 | 
						
							
							
								ea9dbe1404
							
							add docs headers
						 | 
						1 rok pred | 
					
				
					
						
							
								   Erik Dunteman
							
						 | 
						
							
							
								8967fa87b9
							
							Update README.md
						 | 
						1 rok pred | 
					
				
					
						
							
								   erik-dunteman
							
						 | 
						
							
							
								9b77803689
							
							add modal many llama human eval example
						 | 
						1 rok pred | 
					
				
					
						
							
								   Sanyam Bhutani
							
						 | 
						
							
							
								cc84da2db6
							
							Update requirements.txt (#664)
						 | 
						1 rok pred | 
					
				
					
						
							
								   Sanyam Bhutani
							
						 | 
						
							
							
								5fdeb55058
							
							chore: update train_utils.py (#690)
						 | 
						1 rok pred | 
					
				
					
						
							
								   Sanyam Bhutani
							
						 | 
						
							
							
								ad5ce807df
							
							[Fixed] RuntimeError: probability tensor contains either inf, nan or element < 0 (#704)
						 | 
						1 rok pred | 
					
				
					
						
							
								   himanshushukla12
							
						 | 
						
							
							
								625860d3db
							
							removed dependency of singly GPU using accelerate
						 | 
						1 rok pred | 
					
				
					
						
							
								   himanshushukla12
							
						 | 
						
							
							
								5c3fe5b477
							
							[Fixed]RuntimeError: probability tensor contains either inf, nan or element < 0
						 | 
						1 rok pred | 
					
				
					
						
							
								   Kai Wu
							
						 | 
						
							
							
								d9aab4606f
							
							Delete cookie (#700)
						 | 
						1 rok pred | 
					
				
					
						
							
								   Sanyam Bhutani
							
						 | 
						
							
							
								44f19d6d0e
							
							Delete .watchman-cookie-devgpu003.cco3.facebook.com-3137776-2746
						 | 
						1 rok pred | 
					
				
					
						
							
								   Lucas Ventura
							
						 | 
						
							
							
								2774065891
							
							Improve model checkpoint saving logic (#691)
						 | 
						1 rok pred | 
					
				
					
						
							
								   Sanyam Bhutani
							
						 | 
						
							
							
								c77394bbea
							
							Fix llama-cli call
						 | 
						1 rok pred | 
					
				
					
						
							
								   Sanyam Bhutani
							
						 | 
						
							
							
								386092cf84
							
							Added 3.2 Example
						 | 
						1 rok pred | 
					
				
					
						
							
								   Sanyam Bhutani
							
						 | 
						
							
							
								cd74e9be12
							
							DLAI Move
						 | 
						1 rok pred | 
					
				
					
						
							
								   Sanyam Bhutani
							
						 | 
						
							
							
								5bc4b2727e
							
							Move Tool Notebooks
						 | 
						1 rok pred | 
					
				
					
						
							
								   Kai Wu
							
						 | 
						
							
							
								2501f519c7
							
							Updates to accommodate OpenLLM leaderboard v2 tasks and change Meta Llama 3.1 to Llama 3.1 (#639)
						 | 
						1 rok pred |