Commit History

  1. :hammer: [Test] Enable deployment in vercel Running

    fdc9940

  1. :zap: [Enhance] Set min and max for top_p

    64645f0
  2. :gem: [Feature] Add top_p and set 0.95 as default

    403b8cf
  3. :gem: [Feature] Add use_cache parameter, and set default temperature to 0.5

    e2b245b

  1. :boom: [Fix] Missing system message for original mistral models

    395e196
  2. :zap: [Enhance] Display schema of /api/v1 for user-friendly compatibility

    a2d3414
  3. :gem: [Feature] ChatAPIApp: New /readme route

    6e2fad5
  4. :pencil: [Doc] New model, and prettify formats

    37be019
  5. :zap: [Enhance] ChatAPIApp: Only include schema for non-prefix route

    06a233d
  6. :gem: [Feature] New model enabled: nous-mixtral-8-7b

    4a28ca5

  1. :zap: [Enhance] Align /models response with openai format

    245d9fd

  1. :pencil: [Doc] Update available models

    acbd8bf
  2. :zap: [Enhance] add /api/v1 prefix for hf banning and ui compatability

    6d3fdc0
  3. :zap: [Enhance] Remove openchat-3.5 from available models

    06c8d58

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

    fa3bfb0
  2. :boom: [Fix] temperature must be strictly positive

    eb00725

  1. :boom: [Fix] Error 500 when temperature is null

    8ba223c
  2. :boom: [Fix] Error 422 when max_tokens is null

    a54e7a6
  3. :zap: [Enhance] Auto calculate max_tokens if not set

    1b9f698

  1. :zap: [Enhance] Remove leading whitespaces of first response

    c95d47e
  2. :boom: [Fix] Ignore invalid HF Token

    8ab8ca6
  3. :pencil: [Doc] Available models: More comments on dropped models

    85354a9

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

    cec776f
  2. :gem: [Feature] MessageComposer: Support openchat-3.5, and generalize preprocessing stages

    30421b7
  3. :gem: [Feature] MessageStreamer: Support stop sequence and auto removal

    4ba2ca6
  4. :zap: [Enhance] Update available models description

    c769be6
  5. :zap: [Enhance] Support provide api_key with os env HF_TOKEN

    bc384a3
  6. :gem: [Feature] Support call hf api with api_key via HTTP Bearer

    2da6968

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

    d2b20f2

  1. :boom: [Fix] Suppress ping message by increasing ping interval

    489b65b

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

    e820e51
  2. :zap: [Enhance] Cleaner logger output

    b96cef7
  3. :zap: [Enhance] New models: mistral-7b and openchat-3.5

    e916990
  4. :zap: [Enhance] OSLogger: Re-wrap for better syntax check, and move stream log to debug

    047008b
  5. :pencil: [Comment] References of requests params

    395ee29
  6. :zap: [Enhance] Default models and max_new_tokens

    6aa8b86

  1. :zap: [Enhance] API: Ensure temperature to be positive

    3dfcb72
  2. :gem: [Feature] New ArgParser: Specify server ip, port and running mode

    e28221f
  3. :boom: [Fix] Module apis not found

    937bc45
  4. :gem: [Feature] New Github Actions: Sync to huggingface hub spaces

    b1de8a0
  5. :pencil: [Doc] Readme: Features, deployment, api usage examples, and huggingface space configs

    a16695d
  6. :gem: [Feature] New examples: chat with openai and post

    f3b1386
  7. :gem: [Feature] Enable Docker deployment, and add requirements

    5a836c3
  8. :gem: [Feature] New ChatAPIApp: Enable fastapi for openai format api call

    3a09006
  9. :gem: [Feature] New MessageOutputer: Support Openai Stream format

    eb3e513
  10. :gem: [Feature] New MessageStreamer: Enable requests inference api with requests

    9f341cc
  11. :gem: [Feature] New enver: set_envs()

    9bc229a
  12. :gem: [Feature] New MessageComposer: Merge and split messages in mixtral-instruct format

    9e62d8e
  13. :gem: [Feature] New enver and logger system

    5b642ff