sshh12/llm_optimize
LLM Optimize is a proof-of-concept library for doing LLM (large language model) guided blackbox optimization.
This project helps machine learning engineers and data scientists automatically improve their model's performance or other code metrics. You provide an initial piece of Python code (like a model training script) and a natural language description of what you want to optimize (e.g., "increase test score"). The system uses a large language model to iteratively suggest code changes, providing an improved version of your code and explanations for each step.
No commits in the last 6 months.
Use this if you are a machine learning engineer or developer looking to automate and guide the optimization of Python code, such as refining model architectures, improving generalization, or reducing code length, through natural language instructions.
Not ideal if you need highly efficient numerical optimization for functions with well-defined mathematical properties, as this method is less efficient for simple numerical problems.
Stars
61
Forks
8
Language
Python
License
MIT
Category
Last pushed
May 01, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/sshh12/llm_optimize"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
jncraton/languagemodels
Explore large language models in 512MB of RAM
microsoft/unilm
Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities
haizelabs/verdict
Inference-time scaling for LLMs-as-a-judge.
albertan017/LLM4Decompile
Reverse Engineering: Decompiling Binary Code with Large Language Models
bytedance/Sa2VA
Official Repo For Pixel-LLM Codebase