xLAM
Active·★ 637·APACHE·Updated 2026-06-02
★ Trending
xLAM is a research repository for Large Action Models (LAMs), which aggregates and unifies agent trajectories from diverse environments into a consistent format. It streamlines the creation of a generic data loader optimized for agent training, enabling robust model development across various scenarios.
#Large Action Models#Function Calling#Agent Training#Multi-turn Conversation#LLM
01
Features
01Aggregates agent trajectories from distinct environments
02Standardizes and unifies trajectories into a consistent format
03Optimized generic data loader for agent training
04Maintains equilibrium across different data sources during training
05Supports efficient inference with Transformers and vLLM
02
Compatibility
Transformers
Native
Verified via docs
vLLM
Supported
Verified via docs
FastChat
Supported
Verified via docs
Python 3.9+
Native
Verified via docs
03
Quick start
1
$ pip install -e .
04
Use cases
↳Function calling in LLMs
↳Training autonomous agents
↳Multi-turn conversation processing
05
Alternatives
Comments
Log in to leave a comment
No comments yet. Be the first!