kaistAI/Janus
[NeurIPS 2024] Train LLMs with diverse system messages reflecting individualized preferences to generalize to unseen system messages
This project helps large language models (LLMs) better understand and respond to individual user preferences. By inputting diverse system messages that specify unique values and styles, the model learns to generate outputs tailored to that specific guidance, rather than a general public standard. This is ideal for developers creating highly personalized AI applications or virtual assistants.
No commits in the last 6 months.
Use this if you need an LLM that can accurately adopt a wide range of specific personas, tones, or instruction sets defined in system messages.
Not ideal if you're looking for a simple, off-the-shelf LLM for general conversational AI without specific personalization needs.
Stars
53
Forks
5
Language
Python
License
Apache-2.0
Category
Last pushed
Aug 10, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/kaistAI/Janus"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
agentscope-ai/Trinity-RFT
Trinity-RFT is a general-purpose, flexible and scalable framework designed for reinforcement...
OpenRLHF/OpenRLHF
An Easy-to-use, Scalable and High-performance Agentic RL Framework based on Ray (PPO & DAPO &...
zjunlp/EasyEdit
[ACL 2024] An Easy-to-use Knowledge Editing Framework for LLMs.
huggingface/alignment-handbook
Robust recipes to align language models with human and AI preferences
hyunwoongko/nanoRLHF
nanoRLHF: from-scratch journey into how LLMs and RLHF really work.