|  Joone Hur | e2efc79eae
							
							Disable markdown link check in cloud-api README.md | il y a 1 an | 
				
					
						|  Joone Hur | 83efccb22b
							
							Add gradio library for user interface in inference.py | il y a 1 an | 
				
					
						|  Hamid Shojanazeri | 5edd1a2cc4
							
							Fix `load_model` missing argument (#377) | il y a 1 an | 
				
					
						|  Hamid Shojanazeri | 1c7b49fda2
							
							[Demos] Adding OctoAI API Examples (Hosted Llama solution) (#379) | il y a 1 an | 
				
					
						|  Thierry Moreau | ede3860aea
							
							hyperlink fix | il y a 1 an | 
				
					
						|  Thierry Moreau | 409f4b5401
							
							added update for this PR | il y a 1 an | 
				
					
						|  Thierry Moreau | 34399ad8e3
							
							fix path | il y a 1 an | 
				
					
						|  Thierry Moreau | 621195a8ab
							
							md fix | il y a 1 an | 
				
					
						|  Thierry Moreau | 92166acc02
							
							documentation update ++ | il y a 1 an | 
				
					
						|  Thierry Moreau | b7d0941045
							
							documentation update | il y a 1 an | 
				
					
						|  Thierry Moreau | 5e777e137a
							
							simplifying the model names | il y a 1 an | 
				
					
						|  Guocheng | a73108704c
							
							Fix load_model missing argument | il y a 1 an | 
				
					
						|  Thierry Moreau | c68c044efd
							
							authorship update | il y a 1 an | 
				
					
						|  Thierry Moreau | 47ccf9be73
							
							adding the getting to know llama starter guide | il y a 1 an | 
				
					
						|  Thierry Moreau | d57354af23
							
							Merge branch 'tmoreau-octoai' of github.com:octoml/llama-recipes into tmoreau-octoai | il y a 1 an | 
				
					
						|  Thierry Moreau | bd23f8b8f1
							
							updated examples to (1) use OctoAI embeddings, and (2) not state the decommissioned int4 models | il y a 1 an | 
				
					
						|  Thierry Moreau | 26d7b34889
							
							adding purple llama to the mix | il y a 1 an | 
				
					
						|  Thierry Moreau | 635923e066
							
							update to use OctoAI embedding | il y a 1 an | 
				
					
						|  Thierry Moreau | 0a57c802d1
							
							pinning RAG chatbot requirements | il y a 1 an | 
				
					
						|  Thierry Moreau | 993fea0708
							
							naming tweaks | il y a 1 an | 
				
					
						|  Thierry Moreau | 1ca4a9c523
							
							update index | il y a 1 an | 
				
					
						|  Thierry Moreau | 5f2855e5cf
							
							adding RAG chatbot example | il y a 1 an | 
				
					
						|  Thierry Moreau | 961660f46f
							
							rename examples | il y a 1 an | 
				
					
						|  Thierry Moreau | 0db941413b
							
							adding video summary OctoAI example | il y a 1 an | 
				
					
						|  Thierry Moreau | 525128828d
							
							remove space | il y a 1 an | 
				
					
						|  Thierry Moreau | 813a99e278
							
							adding OctoAI gradio example | il y a 1 an | 
				
					
						|  Thierry Moreau | e79e5a7e3a
							
							octoai live data example, tested | il y a 1 an | 
				
					
						|  Thierry Moreau | b8fd519e04
							
							adding OctoAI hello llama cloud example | il y a 1 an | 
				
					
						|  Thierry Moreau | 3f462cb13d
							
							updated examples to (1) use OctoAI embeddings, and (2) not state the decommissioned int4 models | il y a 1 an | 
				
					
						|  Thierry Moreau | 2c338d2616
							
							adding purple llama to the mix | il y a 1 an |