hf-llm-api / apis /chat_api.py

Commit History

  1. :gem: [Feature] Add top_p and set 0.95 as default

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

    e2b245b

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

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

    6e2fad5
  3. :zap: [Enhance] ChatAPIApp: Only include schema for non-prefix route

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

    4a28ca5

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

    245d9fd

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

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

    06c8d58

  1. :boom: [Fix] Error 422 when max_tokens is null

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

    1b9f698

  1. :boom: [Fix] Ignore invalid HF Token

    8ab8ca6

  1. :zap: [Enhance] Update available models description

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

    bc384a3
  3. :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. :zap: [Enhance] New models: mistral-7b and openchat-3.5

    e916990
  2. :zap: [Enhance] Default models and max_new_tokens

    6aa8b86

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

    e28221f
  2. :gem: [Feature] New ChatAPIApp: Enable fastapi for openai format api call

    3a09006