Technology · LLMs → Fine-tuning · Open Source · wiki:stub
This pack is still a wiki stub. Opening text below if present; full article bands appear after deepen (`Wiki-status: deep`).
LlamaFactory is a unified efficient fine-tuning toolkit for 100+ LLMs and VLMs (LoRA/QLoRA and related methods). It is a practical model-factory companion to Axolotl/Unsloth. Use when the OS needs domain-adapted models (estimating language, invoice fields) and you want one harness across many base models. Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024). In this catalog, LlamaFactory is treated as a first-class stack choice: read the primary sources and evidence table before wiring it into a corridor, and prefer measured fit over fashion when peers cover the same job.
9 tags · 6 out · 7 in · 3 artifacts · 1 gaps · 12 corpus docs
map_edge · 4
tech_features · 1
tech_quote · 6
tech_readme · 1