mirror of
https://github.com/nomic-ai/gpt4all.git
synced 2025-09-30 01:08:47 +00:00
8aba2c9009
* feat: local inference server * fix: source to use bash + vars * chore: isort and black * fix: make file + inference mode * chore: logging * refactor: remove old links * fix: add new env vars * feat: hf inference server * refactor: remove old links * test: batch and single response * chore: black + isort * separate gpu and cpu dockerfiles * moved gpu to separate dockerfile * Fixed test endpoints * Edits to API. server won't start due to failed instantiation error * Method signature * fix: gpu_infer * tests: fix tests --------- Co-authored-by: Andriy Mulyar <andriy.mulyar@gmail.com>
19 lines
394 B
Python
19 lines
394 B
Python
from pydantic import BaseSettings
|
|
|
|
|
|
class Settings(BaseSettings):
|
|
app_environment = 'dev'
|
|
model: str = 'ggml-mpt-7b-chat.bin'
|
|
gpt4all_path: str = '/models'
|
|
inference_mode: str = "cpu"
|
|
hf_inference_server_host: str = "http://gpt4all_gpu:80/generate"
|
|
|
|
temp: float = 0.18
|
|
top_p: float = 1.0
|
|
top_k: int = 50
|
|
repeat_penalty: float = 1.18
|
|
|
|
|
|
|
|
settings = Settings()
|