Spaces:
Runtime error
Runtime error
Commit History
-
:boom: [Fix] Remove whole token which ends with stop_sequences
2d7c092 -
:boom: [Fix] Remove stop_sequences from content
8a167b0 -
:boom: [Fix] slow tokenizer issue, and finish by stop_sequences
8697de8
-
:zap: [Enhance] Remove pycrypto requirements, and prettify log
24cceb8 -
:zap: [Enhance] Replace Crypto with hashlib
0616d17 -
:gem: [Feature] Enable gpt-3.5-turbo by adding proof_of_work step
3061fdd -
:gem: [Feature] New ProofWorker: Used in openai auth
c59b13c -
:gem: [Feature] New HfApiException: INVALID_API_KEY_ERROR
a1d960f
-
:zap: [Enhance] HuggingchatStreamer: logger auth messages
862427b -
:zap: [Enhance] Use chrome impoersonate for cffi_requests, and upgrade to v1.2.5
0618e58 -
: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 -
:boom: [Fix] Value of (delta_)content or content_type not assigned
b40b5fc -
:gem: [Feature] Moduralize TokenChecker, and fix gated model repos with alternatives
8df3985 -
:gem: [Feature] HuggingchatStreamer: Support no-stream mode
caedafb -
:gem: [Feature] HuggingchatStreamer: Enable chat_return_generator
62d5db7 -
:gem: [Feature] New TokenChecker: count tokens and check token limit
64105c5 -
:gem: [Feature] Split to Requester and Streamer, and mock chat history with messages
c43287d -
:gem: [Feature] Enable chat response with get_message_id
e4d11b8 -
:hammer: [WIP] Enabling get_message_id
a5ac953 -
:gem: [Feature] HuggingchatStreamer: Build pipeline of chat_response
55b0c51 -
:gem: [Feature] HuggingchatStreamer: New log request and response
c706328 -
:gem: [Feature] HuggingchatStreamer: New get_hf_chat_id, and improve get_conversation_id
391cdfe -
:gem: [Feature] New HuggingchatStreamer: get_conversation_id
f1218fc
-
:gem: [Feature] Enable non-stream return, and prettify logger
397529a -
:boom: [Fix] Set default model
5dc8ebf -
:recycle: [Refactor] Rename gpt-3.5 to gpt-3.5-turbo
d36d623 -
:gem: [Feature] Enable gpt-3.5 in chat_api
cd6b52a -
:recycle: [Refactor] Rename message_streamer to huggingface_streamer
3125c87 -
:recycle: [Refactor] Use tclogger, and configure envs better
babcd78
-
:recycle: [Refactor] Move STOP_SEQUENCES_MAP and TOKEN_LIMIT_MAP to constants
bf8c5bd -
:recycle: [Refactor] Move MODELS_MAP to constants
3f608c6 -
:gem: [Feature] Support new model: openchat-3.5-0106
9f5d69c
-
:gem: [Feature] New model enabled: gemma-7b
77b5a47
-
:zap: [Enhance] Set min and max for top_p
64645f0 -
:gem: [Feature] Add top_p and set 0.95 as default
403b8cf -
:gem: [Feature] Add use_cache parameter, and set default temperature to 0.5
e2b245b
-
:gem: [Feature] New model enabled: nous-mixtral-8-7b
4a28ca5
-
:zap: [Enhance] Remove openchat-3.5 from available models
06c8d58
-
:boom: [Fix] inputs_tokens + max_new_tokens must <= 32768
fa3bfb0 -
:boom: [Fix] temperature must be strictly positive
eb00725
-
:boom: [Fix] Error 500 when temperature is null
8ba223c -
:zap: [Enhance] Auto calculate max_tokens if not set
1b9f698
-
:zap: [Enhance] Remove leading whitespaces of first response
c95d47e -
:pencil: [Doc] Available models: More comments on dropped models
85354a9
-
:gem: [Feature] MessageStreamer: Support stop sequence and auto removal
4ba2ca6 -
:gem: [Feature] Support call hf api with api_key via HTTP Bearer
2da6968
-
:gem: [Feature] Support no-stream mode with dict response
d2b20f2
-
:pencil: [Doc] Readme for features, and comments for references
e820e51 -
:zap: [Enhance] Cleaner logger output
b96cef7