| .. |
|
huggingface_llms_metadata
|
add hf tgi and conversational models
|
2023-09-27 15:56:45 -07:00 |
|
prompt_templates
|
(fix): llama-2 non-chat models prompt template
|
2023-11-07 21:33:54 -08:00 |
|
tokenizers
|
adding support for cohere, anthropic, llama2 tokenizers
|
2023-09-22 14:03:52 -07:00 |
|
__init__.py
|
add linting
|
2023-08-18 11:05:05 -07:00 |
|
ai21.py
|
fix(main.py): fix caching for router
|
2023-11-11 17:45:23 -08:00 |
|
aleph_alpha.py
|
(feat) use usage class for model responses for cohere, hf, tg ai, cohere
|
2023-10-27 09:58:47 -07:00 |
|
anthropic.py
|
refactor(huggingface,-anthropic,-replicate,-sagemaker): making huggingface, anthropic, replicate, sagemaker compatible openai v1 sdk
|
2023-11-11 17:38:15 -08:00 |
|
azure.py
|
refactor(azure.py): working azure completion calls with openai v1 sdk
|
2023-11-11 16:44:39 -08:00 |
|
base.py
|
refactor(openai.py): making it compatible for openai v1
|
2023-11-11 15:33:02 -08:00 |
|
baseten.py
|
(feat) use usage class for model responses for cohere, hf, tg ai, cohere
|
2023-10-27 09:58:47 -07:00 |
|
bedrock.py
|
refactor(bedrock.py-+-cohere.py): making bedrock and cohere compatible with openai v1 sdk
|
2023-11-11 17:33:19 -08:00 |
|
cohere.py
|
refactor(bedrock.py-+-cohere.py): making bedrock and cohere compatible with openai v1 sdk
|
2023-11-11 17:33:19 -08:00 |
|
huggingface_restapi.py
|
refactor(huggingface,-anthropic,-replicate,-sagemaker): making huggingface, anthropic, replicate, sagemaker compatible openai v1 sdk
|
2023-11-11 17:38:15 -08:00 |
|
maritalk.py
|
feat(main.py): add support for maritalk api
|
2023-10-30 17:36:51 -07:00 |
|
nlp_cloud.py
|
(feat) use usage class for model responses for cohere, hf, tg ai, cohere
|
2023-10-27 09:58:47 -07:00 |
|
ollama.py
|
(feat) completion ollama raise exception when ollama resp != 200
|
2023-11-10 08:54:05 -08:00 |
|
oobabooga.py
|
(feat) use usage class for model responses for cohere, hf, tg ai, cohere
|
2023-10-27 09:58:47 -07:00 |
|
openai.py
|
refactor(azure.py): working azure completion calls with openai v1 sdk
|
2023-11-11 16:44:39 -08:00 |
|
palm.py
|
(feat) add model_response.usage.completion_tokens for bedrock, palm, petals, sagemaker
|
2023-10-27 09:51:50 -07:00 |
|
petals.py
|
(feat) add model_response.usage.completion_tokens for bedrock, palm, petals, sagemaker
|
2023-10-27 09:51:50 -07:00 |
|
replicate.py
|
refactor(huggingface,-anthropic,-replicate,-sagemaker): making huggingface, anthropic, replicate, sagemaker compatible openai v1 sdk
|
2023-11-11 17:38:15 -08:00 |
|
sagemaker.py
|
refactor(huggingface,-anthropic,-replicate,-sagemaker): making huggingface, anthropic, replicate, sagemaker compatible openai v1 sdk
|
2023-11-11 17:38:15 -08:00 |
|
together_ai.py
|
(fix) tg ai raise errors on non 200 responses
|
2023-11-11 11:21:12 -08:00 |
|
vertex_ai.py
|
(fix) vertex ai streaming
|
2023-11-03 12:54:36 -07:00 |
|
vllm.py
|
(feat) use usage class for model responses for cohere, hf, tg ai, cohere
|
2023-10-27 09:58:47 -07:00 |
