TUDB-Labs/mLoRA
An Efficient "Factory" to Build Multiple LoRA Adapters
This framework helps machine learning practitioners efficiently customize Large Language Models (LLMs) for many specific tasks. You provide a base LLM and several datasets, and it produces multiple specialized LoRA adapters that can be used to tailor the LLM's behavior. This is ideal for AI product developers or researchers who need to fine-tune many LLMs concurrently.
373 stars. No commits in the last 6 months.
Use this if you need to create multiple customized versions of a Large Language Model (LLM) quickly and efficiently, sharing a single base model across all adaptations.
Not ideal if you only need to fine-tune a single LLM, or if you prefer to manage each fine-tuning process independently without shared resources.
Stars
373
Forks
66
Language
Python
License
Apache-2.0
Category
Last pushed
Feb 13, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/TUDB-Labs/mLoRA"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
unslothai/unsloth
Fine-tuning & Reinforcement Learning for LLMs. 🦥 Train OpenAI gpt-oss, DeepSeek, Qwen, Llama,...
huggingface/peft
🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.
modelscope/ms-swift
Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs (Qwen3.5, DeepSeek-R1, GLM-5,...
oumi-ai/oumi
Easily fine-tune, evaluate and deploy gpt-oss, Qwen3, DeepSeek-R1, or any open source LLM / VLM!
linkedin/Liger-Kernel
Efficient Triton Kernels for LLM Training