Hugging Face's logo

Spaces:
ColamanAI
/
hf-llm-api
Running

App Files Community
hf-llm-api

Commit History

:zap: [Enhance] Display schema of /api/v1 for user-friendly compatibility
a2d3414

Hansimov commited on

:gem: [Feature] ChatAPIApp: New /readme route
6e2fad5

Hansimov commited on

:pencil: [Doc] New model, and prettify formats
37be019

Hansimov commited on

:zap: [Enhance] ChatAPIApp: Only include schema for non-prefix route
06a233d

Hansimov commited on

:gem: [Feature] New model enabled: nous-mixtral-8-7b
4a28ca5

Hansimov commited on

:zap: [Enhance] Align /models response with openai format
245d9fd

Hansimov commited on

:pencil: [Doc] Update available models
acbd8bf

Hansimov commited on

:zap: [Enhance] add /api/v1 prefix for hf banning and ui compatability
6d3fdc0

Hansimov commited on

:zap: [Enhance] Remove openchat-3.5 from available models
06c8d58

Hansimov commited on

:boom: [Fix] inputs_tokens + max_new_tokens must <= 32768
fa3bfb0

Hansimov commited on

:boom: [Fix] temperature must be strictly positive
eb00725

Hansimov commited on

:boom: [Fix] Error 500 when temperature is null
8ba223c

Hansimov commited on

:boom: [Fix] Error 422 when max_tokens is null
a54e7a6

Hansimov commited on

:zap: [Enhance] Auto calculate max_tokens if not set
1b9f698

Hansimov commited on

:zap: [Enhance] Remove leading whitespaces of first response
c95d47e

Hansimov commited on

:boom: [Fix] Ignore invalid HF Token
8ab8ca6

Hansimov commited on

:pencil: [Doc] Available models: More comments on dropped models
85354a9

Hansimov commited on

:pencil: [Doc] Readme: New models, api key and no-stream mode, and models to support
cec776f

Hansimov commited on

:gem: [Feature] MessageComposer: Support openchat-3.5, and generalize preprocessing stages
30421b7

Hansimov commited on

:gem: [Feature] MessageStreamer: Support stop sequence and auto removal
4ba2ca6

Hansimov commited on

:zap: [Enhance] Update available models description
c769be6

Hansimov commited on

:zap: [Enhance] Support provide api_key with os env HF_TOKEN
bc384a3

Hansimov commited on

:gem: [Feature] Support call hf api with api_key via HTTP Bearer
2da6968

Hansimov commited on

:gem: [Feature] Support no-stream mode with dict response
d2b20f2

Hansimov commited on

:boom: [Fix] Suppress ping message by increasing ping interval
489b65b

Hansimov commited on

:pencil: [Doc] Readme for features, and comments for references
e820e51

Hansimov commited on

:zap: [Enhance] Cleaner logger output
b96cef7

Hansimov commited on

:zap: [Enhance] New models: mistral-7b and openchat-3.5
e916990

Hansimov commited on

:zap: [Enhance] OSLogger: Re-wrap for better syntax check, and move stream log to debug
047008b

Hansimov commited on

:pencil: [Comment] References of requests params
395ee29

Hansimov commited on

:zap: [Enhance] Default models and max_new_tokens
6aa8b86

Hansimov commited on

:zap: [Enhance] API: Ensure temperature to be positive
3dfcb72

Hansimov commited on

:gem: [Feature] New ArgParser: Specify server ip, port and running mode
e28221f

Hansimov commited on

:boom: [Fix] Module apis not found
937bc45

Hansimov commited on

:gem: [Feature] New Github Actions: Sync to huggingface hub spaces
b1de8a0

Hansimov commited on

:pencil: [Doc] Readme: Features, deployment, api usage examples, and huggingface space configs
a16695d

Hansimov commited on

:gem: [Feature] New examples: chat with openai and post
f3b1386

Hansimov commited on

:gem: [Feature] Enable Docker deployment, and add requirements
5a836c3

Hansimov commited on

:gem: [Feature] New ChatAPIApp: Enable fastapi for openai format api call
3a09006

Hansimov commited on

:gem: [Feature] New MessageOutputer: Support Openai Stream format
eb3e513

Hansimov commited on

:gem: [Feature] New MessageStreamer: Enable requests inference api with requests
9f341cc

Hansimov commited on

:gem: [Feature] New enver: set_envs()
9bc229a

Hansimov commited on

:gem: [Feature] New MessageComposer: Merge and split messages in mixtral-instruct format
9e62d8e

Hansimov commited on

:gem: [Feature] New enver and logger system
5b642ff

Hansimov commited on