Commit graph

68 commits

Author SHA1 Message Date
Krrish Dholakia
e6a65695eb fix linting issues 2023-09-06 20:43:59 -07:00
Krrish Dholakia
14fa57c185 batch completions for vllm now works too 2023-09-06 19:26:19 -07:00
ishaan-jaff
1eed36eb1d add replicate pricing 2023-09-06 18:14:34 -07:00
Krrish Dholakia
7290a972e5 adding support for vllm 2023-09-06 18:07:44 -07:00
ishaan-jaff
cd091ad844 fix linting errors @krrishdholakia 2023-09-06 16:38:42 -07:00
Krrish Dholakia
021512c60f update custom prompt template function 2023-09-06 13:14:36 -07:00
Krrish Dholakia
311bfb7bb7 logging replicate response logs 2023-09-06 11:28:40 -07:00
ishaan-jaff
a2d425f7de add flan + vicuna + fix replicate errors 2023-09-06 11:23:58 -07:00
Krrish Dholakia
8189a16188 updates 2023-09-06 11:21:48 -07:00
ishaan-jaff
89ebdab2b3 add replicate support for max_tokens 2023-09-06 10:38:21 -07:00
ishaan-jaff
d8dfa2d80d add Replicate Error class 2023-09-06 10:25:40 -07:00
ishaan-jaff
74e0e90620 add replicate streaming 2023-09-06 10:23:13 -07:00
ishaan-jaff
6fb01ec257 use replicate http requests instead 2023-09-06 09:43:05 -07:00
Krrish Dholakia
c85465a398 adding prompt template for falcon 180b 2023-09-06 08:44:13 -07:00
Krrish Dholakia
aa5d44dccb fixing linting errors 2023-09-05 14:52:57 -07:00
Krrish Dholakia
4661f3dab9 only use tgai's prompt template for llama2 instruct models 2023-09-05 12:25:52 -07:00
Krrish Dholakia
090ec35a4d prompt formatting for together ai llama2 models 2023-09-05 11:57:13 -07:00
ishaan-jaff
db4f4c0191 baseten client mapping 2023-09-04 15:41:37 -07:00
ishaan-jaff
b8b7d9bf44 fix aleph alpha client init 2023-09-04 15:14:09 -07:00
Krrish Dholakia
5ae420317e adding first-party + custom prompt templates for huggingface 2023-09-04 14:54:09 -07:00
ishaan-jaff
c1fb3f19f5 clean up hugging face completion() 2023-09-04 14:41:06 -07:00
ishaan-jaff
f5931a7235 v0 bedrock support 2023-09-04 12:40:40 -07:00
ishaan-jaff
f156733ed3 allow users to set AWS_REGION_NAME 2023-09-04 11:57:22 -07:00
ishaan-jaff
44f44ad5a3 add optional params for llama-2 2023-09-04 11:41:20 -07:00
ishaan-jaff
746001e32a working sagemaker support 2023-09-04 11:30:34 -07:00
ishaan-jaff
022c632ce4 v0 add sagemaker 2023-09-04 11:02:20 -07:00
ishaan-jaff
c0c499f7db clean out AI21 Init Client calls 2023-09-04 10:08:53 -07:00
ishaan-jaff
31ebbf5208 remove init for together_ai completion calls 2023-09-04 09:59:24 -07:00
ishaan-jaff
898df9a9d3 remove init AnthropicClient for completion calls 2023-09-04 09:34:15 -07:00
ishaan-jaff
4a994dc498 use api_base instead of custom_api_base 2023-09-02 17:11:30 -07:00
Krrish Dholakia
a972676655 adding support for aleph alpha 2023-09-02 13:15:41 -07:00
Krrish Dholakia
4927e5879f update baseten handler to handle TGI calls 2023-08-30 19:14:48 -07:00
Krrish Dholakia
8be55744ad clean up print statements 2023-08-30 16:11:49 -07:00
Krrish Dholakia
5cd98965e0 updates 2023-08-30 16:05:42 -07:00
Krrish Dholakia
fd7b7b998b add huggingface 2023-08-30 16:05:33 -07:00
Krrish Dholakia
1385c26aff return logprobs for hf models 2023-08-30 15:16:26 -07:00
Krrish Dholakia
259de2d117 adding context window exceeded error to huggingface 2023-08-29 16:46:04 -07:00
Krrish Dholakia
c00cb299fc add context window exceeded error for anthropic 2023-08-29 16:28:07 -07:00
Krrish Dholakia
9646c03fe5 adding coverage for ai21 2023-08-29 13:32:20 -07:00
Krrish Dholakia
342fece93d add coverage for rate limit errors to togetherai 2023-08-29 12:54:56 -07:00
Krrish Dholakia
a0f882d507 new logger client 2023-08-28 14:59:00 -07:00
Krrish Dholakia
3087c904eb fixes to streaming for ai21, baseten, and openai text completions 2023-08-28 09:42:51 -07:00
ishaan-jaff
a69b7ffcfa formatting improvements 2023-08-28 09:20:50 -07:00
ishaan-jaff
3e0a16acf4 anthropic fixes 2023-08-28 09:17:29 -07:00
ishaan-jaff
f8cfae034c anthropic py fixes 2023-08-28 09:15:29 -07:00
Ishaan Jaff
f9ea5e70c5 Merge branch 'main' into fix-streaming-anthropic-2 2023-08-28 09:05:51 -07:00
Krrish Dholakia
95ce560f6d fix anthropic streaming 2023-08-26 18:54:51 -07:00
Krrish Dholakia
574ed99cd9 adding coverage for additional baseten output formats 2023-08-24 18:20:43 -07:00
Krrish Dholakia
f7f108d230 move baseten to a REST endpoint call 2023-08-24 14:43:49 -07:00
adriensas
a52eb7dcf4 fix linting 2023-08-23 11:07:45 +02:00