LLaMA-Factory is a fine-tuning and training framework for Meta's LLaMA language models. It enables researchers and developers to train and customize LLaMA models efficiently using advanced optimization techniques.
Features
- Supports fine-tuning of LLaMA models for specific tasks
- Optimized training with LoRA and QLoRA to reduce resource usage
- Provides pre-configured training scripts for faster setup
- Multi-GPU and distributed training support for scalability
- Integrates seamlessly with Hugging Face Transformers
- Compatible with FP16 and BF16 precision for efficient computation
License
Apache License V2.0Follow LLaMA-Factory
Other Useful Business Software
Custom VMs From 1 to 96 vCPUs With 99.95% Uptime
Live migration and automatic failover keep workloads online through maintenance. One free e2-micro VM every month.
Rate This Project
Login To Rate This Project
User Reviews
Be the first to post a review of LLaMA-Factory!