AIPython★ 71,186
hiyouga/LlamaFactory
LlamaFactory: Unified LLM Tuning
LlamaFactory offers a unified library for efficient fine‑tuning of 100+ LLMs and VLMs, with support for LoRA, QLoRA and distributed multi‑GPU training.
// KEY FEATURES
- Supports 100+ LLMs and VLMs with ready‑to‑use configs for quick experimentation.
- Unified API for LoRA, QLoRA, AdaLoRA and full fine‑tuning of language and vision models.
- Provides distributed training scripts across multiple GPUs with mixed‑precision support.
- Compatible with Hugging Face Transformers, DeepSpeed, and FSDP for seamless integration.
#agent#ai#deepseek#fine-tuning#gemma#gpt#instruction-tuning#large-language-models#llama#llama3#llm#lora
Open on GitHub →New repositories every 30 minutes
REDDYX AI scans GitHub 24/7 and ships the best AI/ML/Web3 projects to Telegram.
Join on Telegram