hank0316/AdaSearch
This includes the original implementation of "AdaSearch: Balancing Parametric Knowledge and Search in Large Language Models via Reinforcement Learning".
This project helps AI developers create large language models that can decide when to use their internal knowledge versus when to search for external information. You input a trained LLM and get back an enhanced model that makes smarter, more transparent decisions about when to search for answers, improving accuracy and awareness of its own knowledge. This is for machine learning engineers and AI researchers building advanced language models.
Use this if you are developing LLMs and want them to make more informed and auditable decisions about when to perform an external search.
Not ideal if you are looking for a ready-to-use LLM for end-user applications, as this is a framework for model development.
Stars
10
Forks
—
Language
—
License
MIT
Category
Last pushed
Dec 29, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/hank0316/AdaSearch"
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