iboing/CorDA
CorDA: Context-Oriented Decomposition Adaptation of Large Language Models for task-aware parameter-efficient fine-tuning(NeurIPS 2024)
This tool helps AI engineers efficiently adapt large language models (LLMs) to new tasks. It takes a pre-trained LLM and a task-specific dataset as input, then produces a fine-tuned LLM that performs better on the target task while preserving existing knowledge. AI/ML practitioners working with LLMs will find this useful for customizing models without extensive retraining.
No commits in the last 6 months.
Use this if you need to fine-tune a Llama-2-7b model for specific tasks like answering questions, solving math problems, or generating code, and want to improve performance while reducing computational cost compared to full fine-tuning.
Not ideal if you are not working with large language models or require a solution that supports a broader range of LLM architectures beyond Llama-2 without manual configuration.
Stars
55
Forks
3
Language
Python
License
Apache-2.0
Category
Last pushed
Jan 13, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/iboing/CorDA"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
scaleapi/llm-engine
Scale LLM Engine public repository
AGI-Arena/MARS
The official implementation of MARS: Unleashing the Power of Variance Reduction for Training Large Models
modelscope/easydistill
a toolkit on knowledge distillation for large language models
AGI-Edgerunners/LLM-Adapters
Code for our EMNLP 2023 Paper: "LLM-Adapters: An Adapter Family for Parameter-Efficient...
Wang-ML-Lab/bayesian-peft
Bayesian Low-Rank Adaptation of LLMs: BLoB [NeurIPS 2024] and TFB [NeurIPS 2025]