Cluster 456896

5 repos

Jupyter Notebook · 2

Python · 2

llm ·13

llm-training ·13

tpo ·13

web-ui ·13

gradio ·0

Related clusters

CatoG/LLM-DPO

LLM Direct Preference Optimization: Huggingface Space

Python

12 commits

CatoG/DPO_Demo

No description

12 commits

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…

Jupyter Notebook

11 commits

deep-diver/LLM-Pref-Mark-UI

No description

Python

7 commits

Phylliida/ModelPreferences

Learning Preferences of LLMs

Jupyter Notebook

76 commits