555 commits

Author	SHA1	Message	Date
Krrish Dholakia	e62b584439	adding support for cohere, anthropic, llama2 tokenizers	2023-09-22 14:03:52 -07:00
ishaan-jaff	2b9e3434ff	fix async import error	2023-09-21 11:16:50 -07:00
ishaan-jaff	ac90c5286f	conditional import async_generator	2023-09-21 11:09:57 -07:00
ishaan-jaff	35bb6f5a50	support acompletion + stream for ollama	2023-09-21 10:39:48 -07:00
Krrish Dholakia	9ec8ea89bb	fixing huggingface tgi index issue for best of	2023-09-21 10:05:22 -07:00
Krrish Dholakia	a8711dc5c2	fix hf tgi best of bug	2023-09-20 20:53:32 -07:00
Krrish Dholakia	c63db48652	return all best of sequences	2023-09-20 14:43:25 -07:00
ishaan-jaff	b81f8d2ddd	remove cuda from petals	2023-09-20 09:23:39 -07:00
Krrish Dholakia	ecad921b01	add oobabooga text web api support	2023-09-19 18:56:53 -07:00
ishaan-jaff	85862c1066	petals remove print statement	2023-09-19 10:56:30 -07:00
ishaan-jaff	946c81626d	fix petals imports	2023-09-19 09:27:40 -07:00
ishaan-jaff	bee1224aa2	dev4	2023-09-19 09:24:34 -07:00
ishaan-jaff	385640b743	petals fixes	2023-09-19 09:24:34 -07:00
ishaan-jaff	f6ccadabc8	fix petals import	2023-09-19 09:24:34 -07:00
ishaan-jaff	a107b7b3ec	add petals file for completion	2023-09-19 09:24:34 -07:00
Krrish Dholakia	45293613ba	fix meta llama prompt template mapping bug	2023-09-18 21:24:41 -07:00
Krrish Dholakia	633e36de42	handle llama 2 eos tokens in streaming	2023-09-18 13:44:19 -07:00
Krrish Dholakia	5b294c704e	fix hf conversational task bug	2023-09-18 11:46:36 -07:00
ishaan-jaff	0bee6e0d38	cleanup	2023-09-18 10:43:44 -07:00
ishaan-jaff	e7f4e8b4a4	allow non tgi llms	2023-09-18 10:26:57 -07:00
Phodaie	35b5d773c8	code typo in falcon related prompt factory	2023-09-17 15:40:36 +00:00
ishaan-jaff	c714372b9d	streaming for amazon titan bedrock	2023-09-16 09:57:16 -07:00
ishaan-jaff	29e3b4fdd2	support optional params for bedrock amazon	2023-09-16 09:19:07 -07:00
ishaan-jaff	96dbbf7422	remove tg ai print	2023-09-15 09:29:39 -07:00
ishaan-jaff	7f46cfcb22	bump version with bedrock	2023-09-14 14:54:36 -07:00
ishaan-jaff	489260b24b	fix sagemaker test	2023-09-14 14:49:46 -07:00
ishaan-jaff	4a61b8e380	linting fix bedrock	2023-09-14 14:26:23 -07:00
ishaan-jaff	83c8d8576b	bedrock.py fixes	2023-09-14 14:15:39 -07:00
ishaan-jaff	38bdb9335c	add bedrock to main and init	2023-09-14 13:51:09 -07:00
Krrish Dholakia	3b4064a58f	move cohere to http endpoint	2023-09-14 11:17:38 -07:00
Krrish Dholakia	f98da9f13c	adding support for nlp cloud	2023-09-14 09:19:34 -07:00
Krrish Dholakia	fef2a39843	adding finish reason mapping for aleph alpha and baseten	2023-09-13 19:39:11 -07:00
Krrish Dholakia	aaa57abddd	map finish reason	2023-09-13 19:22:38 -07:00
Krrish Dholakia	5b6b9a9fab	huggingface conversational task support	2023-09-13 13:45:23 -07:00
Krrish Dholakia	bab36c2c6f	work for hf inference endpoint	2023-09-11 18:37:55 -07:00
ishaan-jaff	56bd8c1c52	olla upgrades, fix streaming, add non streaming resp	2023-09-09 14:07:13 -07:00
ishaan-jaff	599be6a374	raise vllm error	2023-09-08 15:27:01 -07:00
Krrish Dholakia	6b3cb18983	fix linting issues	2023-09-06 20:43:59 -07:00
Krrish Dholakia	35cf6ef0a1	batch completions for vllm now works too	2023-09-06 19:26:19 -07:00
ishaan-jaff	8b3b682000	add replicate pricing	2023-09-06 18:14:34 -07:00
Krrish Dholakia	4cfcabd919	adding support for vllm	2023-09-06 18:07:44 -07:00
ishaan-jaff	04f8b20651	fix linting errors @krrishdholakia	2023-09-06 16:38:42 -07:00
Krrish Dholakia	0ace48d719	update custom prompt template function	2023-09-06 13:14:36 -07:00
Krrish Dholakia	44f71aa321	logging replicate response logs	2023-09-06 11:28:40 -07:00
ishaan-jaff	1da6026622	add flan + vicuna + fix replicate errors	2023-09-06 11:23:58 -07:00
Krrish Dholakia	48ee4a08ac	updates	2023-09-06 11:21:48 -07:00
ishaan-jaff	d4c4a138ca	add replicate support for max_tokens	2023-09-06 10:38:21 -07:00
ishaan-jaff	bc9b629726	add Replicate Error class	2023-09-06 10:25:40 -07:00
ishaan-jaff	1c61b7b229	add replicate streaming	2023-09-06 10:23:13 -07:00
ishaan-jaff	c45b132675	use replicate http requests instead	2023-09-06 09:43:05 -07:00