Spaces:
Sleeping
Sleeping
Commit History
-
:boom: [Fix] slow tokenizer issue, and finish by stop_sequences
8697de8 -
:zap: [Enhance] Add new model yi-1.5-34b, and remove unavailable models
b9a642a
-
:zap: [Enhance] Use nous-mixtral-8x7b as default model
214fb7b -
:zap: [Enhance] Quieter openai auth, use cffi to request hf-chat id, and console token count for exceeds
0f710a2 -
:gem: [Feature] Moduralize TokenChecker, and fix gated model repos with alternatives
8df3985 -
:gem: [Feature] MessageCompoer: decompose to system and input prompt
0b6e0c9
-
:zap: [Enhance] Upgrade gemma-7b to 1.1
3b00a19
-
:gem: [Feature] New model supported: command-r-plus (CohereForai/c4ai-command-r-plus)
3965e1f
-
:gem: [Feature] Enable gpt-3.5 in chat_api
cd6b52a -
:recycle: [Refactor] Use tclogger, and configure envs better
babcd78
-
:boom: [Fix] Revert chat templates with mannual version as nous-mixtral-8x7b behaves weirdly
dc3b7a9 -
:recycle: [Refactor] Use official chat_template to replace mannual parses for several models, and remove unused message split functions
4a9e46f -
:recycle: [Refactor] Move AVAILABLE_MODELS(_DICTS) to constants
40ba0ea -
:gem: [Feature] Support new model: openchat-3.5-0106
9f5d69c
-
:gem: [Feature] New model enabled: gemma-7b
77b5a47
-
:boom: [Fix] Missing system message for original mistral models
395e196 -
:gem: [Feature] New model enabled: nous-mixtral-8-7b
4a28ca5
-
:gem: [Feature] MessageComposer: Support openchat-3.5, and generalize preprocessing stages
30421b7
-
:gem: [Feature] Support no-stream mode with dict response
d2b20f2
-
:gem: [Feature] New MessageOutputer: Support Openai Stream format
eb3e513 -
:gem: [Feature] New MessageComposer: Merge and split messages in mixtral-instruct format
9e62d8e