Skip to content

Environment

Environment Dependencies

Dependencies and Use Cases

  • Fine-tuning (based on alpaca-lora): datasets, deepspeed, faiss-cpu, fire, gradio, numpy, peft, torch, transformers
  • Fine-tuning (based on collie): collie-lm, numpy, peft, torch, transformers, datasets, deepspeed, fire
  • Fine-tuning (based on lightllm): lightllm
  • Fine-tuning (based on vllm): vllm

Basic Dependencies

  • fastapi: FastAPI is a modern, fast (high-performance) web framework for building APIs, used in conjunction with Python 3.6+ type hints.
  • loguru: Loguru is a Python logging library aimed at providing flexible logging capabilities through a concise and easy-to-use API.
  • pydantic: Pydantic is a data validation and settings management tool that uses Python's type annotations to validate data.
  • Requests: Requests is a Python HTTP library for sending HTTP requests. It is simple and easy to use, making it a common choice for making web requests in Python.
  • uvicorn: Uvicorn is a lightweight and fast ASGI server used for running web applications in Python 3.6+.
  • cloudpickle: Cloudpickle is a Python serialization library capable of serializing Python objects into byte streams for transmission across Python programs and interpreters.
  • flake8: Flake8 is a code style checking tool used to detect errors in Python code and ensure compliance with PEP 8 coding standards.
  • gradio: Gradio is a library for quickly creating simple web interfaces, allowing users to interact with Python models.
  • gradio_client: The Gradio client library allows users to load and use Gradio interfaces from a remote server.
  • protobuf: Google's Protocol Buffers Python implementation, used for serializing structured data.
  • setuptools: A Python package installation and distribution tool, used for packaging and distributing Python applications and libraries.