xLAM
Research on Intelligent Agents Based on Large Language Models
- Support aggregation and unification of intelligent agent trajectories in multiple environments
- Optimized universal data loader designed specifically for intelligent agent training
- Maintain balance between different data sources and maintain independent randomness between devices
- Compatibility with VLLM and FastChat platforms
- Model fine-tuning to adapt to a wide range of intelligent agent tasks and scenarios
- Provide detailed installation and training guidelines for researchers to quickly get started
Product Details
XLAM is an intelligent agent research project based on Large Language Models (LLMs) developed by the Salesforce AI Research team. It aggregates intelligent agent trajectories from different environments, standardizes and unifies these trajectories into a consistent format to create an optimized universal data loader specifically designed for intelligent agent training. XLAM-v0.1-r is the 0.1 version of this model series, designed specifically for research purposes and compatible with VLLM and FastChat platforms.
