doem97/ICLR26_mtLoRA
[ICLR 2026] Official implementation (Claude Agent reproduce supported) of paper "mtLoRA: Scalable Multi-Task Low-Rank Model Adaptation" +2.3% over SOTA with 47% fewer parameters
This project helps AI researchers and machine learning engineers fine-tune large language models for many different tasks more efficiently. It takes a base language model and training data for 15-25+ tasks, then outputs a specialized model that performs better across all tasks with fewer parameters and less training time. Researchers working on advanced multi-task learning for large AI models will find this useful.
Use this if you are trying to adapt large language models to a wide range of tasks and are encountering performance degradation or high computational costs with existing methods.
Not ideal if you are working with a single task or a small number of tasks, as the benefits of this scalable multi-task adaptation approach might not be fully realized.
Stars
12
Forks
—
Language
Python
License
—
Category
Last pushed
Mar 04, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/doem97/ICLR26_mtLoRA"
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