Get the latest tech news

Llama-Factory: Unified, Efficient Fine-Tuning for 100 Open LLMs


Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024) - hiyouga/LLaMA-Factory

Advanced algorithms: GaLore, BAdam, APOLLO, Adam-mini, Muon, OFT, DoRA, LongLoRA, LLaMA Pro, Mixture-of-Depths, LoRA+, LoftQ and PiSSA. Extra dependencies available: torch, torch-npu, metrics, deepspeed, liger-kernel, bitsandbytes, hqq, eetq, gptq, aqlm, vllm, sglang, galore, apollo, badam, adam-mini, qwen, minicpm_v, openmind, swanlab, dev [arxiv] Yi et al. Generation Meets Verification: Accelerating Large Language Model Inference with Smart Parallel Auto-Correct Decoding.

Get the Android app

Or read this on Hacker News

Read more on:

Photo of Factory

Factory

Photo of tuning

tuning

Photo of open LLMs

open LLMs

Related news:

News photo

Parts shortage is the latest problem to hit General Motors production | There will be temporary layoffs at a factory in Missouri from September 29-October 19.

News photo

Foxconn says EV sales are so slow it's converting a factory to build AI servers instead

News photo

Foxconn says EV sales are so slow it's converting a factory to build AI servers instead