geoffrey-llm 0.0.2

A lightweight toolkit for LLM fine-tuning, inference optimization, and agent development

geoffrey-llm

A lightweight toolkit for LLM fine-tuning, inference optimization, and agent development.

⚠️ Note: This package is currently in early development (v0.0.1). APIs will change frequently.

Planned Features

• Simplified LoRA/QLoRA fine-tuning interface
• Unified inference backend (vLLM, llama.cpp, TensorRT)
• GraphRAG-lite for knowledge graph RAG
• Log analysis Agent toolkit
• Model quantization utilities (AWQ, GPTQ)

Installation

pip install geoffrey-llm

Optional dependencies

# For fine-tuning capabilities
pip install geoffrey-llm[finetune]

# For optimized inference
pip install geoffrey-llm[inference]

# Development install
pip install geoffrey-llm[dev]

Quick Start

from geoffrey_llm import placeholder

print(placeholder())
# Output: geoffrey-llm is under development. Stay tuned!

License

MIT License