2244 commits

Author	SHA1	Message	Date
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
Krrish Dholakia	3d6836417e	adding prompt template for falcon 180b	2023-09-06 08:44:13 -07:00
Krrish Dholakia	074f6dbfaf	fixing linting errors	2023-09-05 14:52:57 -07:00
Krrish Dholakia	af33a85043	only use tgai's prompt template for llama2 instruct models	2023-09-05 12:25:52 -07:00
Krrish Dholakia	64f3d3c56e	prompt formatting for together ai llama2 models	2023-09-05 11:57:13 -07:00
ishaan-jaff	fe4caf5c3d	baseten client mapping	2023-09-04 15:41:37 -07:00
ishaan-jaff	79acfb4dab	fix aleph alpha client init	2023-09-04 15:14:09 -07:00
Krrish Dholakia	2384806cfd	adding first-party + custom prompt templates for huggingface	2023-09-04 14:54:09 -07:00
ishaan-jaff	a474b89779	clean up hugging face completion()	2023-09-04 14:41:06 -07:00
ishaan-jaff	2bf9ee4ecf	v0 bedrock support	2023-09-04 12:40:40 -07:00
ishaan-jaff	126830f08a	allow users to set AWS_REGION_NAME	2023-09-04 11:57:22 -07:00
ishaan-jaff	e03d442e8f	add optional params for llama-2	2023-09-04 11:41:20 -07:00