Airmomo/tpo-llm-webui
TPO 是一个优化 LLM 输出文本的框架，通过迭代反馈和优化提示的方式来“微调模型”，而非直接调整模型的参数，使模型在推理过程中与人类偏好对齐以生成更好的结果。本项目提供了一个友好的 WebUI 来加载模型，实时优化基础模型并展示最佳结果。
This tool helps improve the quality of text generated by large language models (LLMs) without needing to retrain them. You input a prompt or question, and the system interactively refines the LLM's output to better match human preferences, providing more useful, safe, and truthful results. It's designed for anyone using LLMs who needs their outputs to be more aligned with specific human expectations.
No commits in the last 6 months.
Use this if you are working with large language models and need to ensure their text outputs are consistently high-quality, relevant, and aligned with human values or specific requirements without complex model retraining.
Not ideal if you need to deeply customize or fine-tune an LLM's core behavior by modifying its internal parameters.
Stars
13
Forks
1
Language
Jupyter Notebook
License
MIT
Category
Last pushed
Feb 22, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/Airmomo/tpo-llm-webui"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
ParisNeo/lollms-webui
Lord of Large Language and Multi modal Systems Web User Interface
ggozad/oterm
the terminal client for Ollama
owndev/Open-WebUI-Functions
Open-WebUI-Functions is a collection of custom pipelines, filters, and integrations designed to...
hand-e-fr/OpenHosta
A lightweight library integrating LLM natively into Python
lmg-anon/mikupad
LLM Frontend in a single html file