xrsrke/toolformer
Implementation of Toolformer: Language Models Can Teach Themselves to Use Tools
This project helps developers augment their large language models (LLMs) with the ability to use external tools, like calculators or search engines. It takes an existing LLM and text data as input, then automatically inserts API calls into the text so the model learns when and how to use tools to improve its responses. The primary users are machine learning engineers and researchers working on natural language processing.
144 stars. No commits in the last 6 months. Available on PyPI.
Use this if you want to empower your language models to perform calculations or look up information directly, rather than hallucinating answers.
Not ideal if you are a non-developer seeking a ready-to-use application, as this requires programming knowledge to implement and customize.
Stars
144
Forks
15
Language
Jupyter Notebook
License
MIT
Category
Last pushed
Apr 05, 2023
Commits (30d)
0
Dependencies
7
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/xrsrke/toolformer"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related models
MozerWang/AMPO
[ICLR 2026] Adaptive Social Learning via Mode Policy Optimization for Language Agents
real-stanford/reflect
[CoRL 2023] REFLECT: Summarizing Robot Experiences for Failure Explanation and Correction
nsidn98/LLaMAR
Code for our paper LLaMAR: LM-based Long-Horizon Planner for Multi-Agent Robotics
BatsResearch/planetarium
Dataset and benchmark for assessing LLMs in translating natural language descriptions of...
WayneMao/RoboMatrix
The Official Implementation of RoboMatrix