---
tags:
  - sketchtune
  - sketch to adapt
library_name: transformers
---

# Base Models for Fine-tuning in *(ICML 2025) Sketch to Adapt: Fine-Tunable Sketches for Efficient LLM Adaptation*

This repository hosts the compressed base models used in the fine-tuning experiments from our ICML 2025 paper: **Sketch to Adapt: Fine-Tunable Sketches for Efficient LLM Adaptation**. The available models and formats are as follows.

| Model         | Bits | GPR (Groups Per Row)     |
|---------------|--------|--------------------|
| Llama-3-8B     | INT4   | 1/2/4/8       |
| Llama-2-7B     | INT4   | 1/2/4/8       |
| Llama-7B       | INT4   | 1/2/4/8       |
| Llama-13B      | INT4   | 1/2/4/8       |

For full details on how to reproduce the experiments, please refer to our GitHub repository:

👉 [https://github.com/LeanModels/SketchTune](https://github.com/LeanModels/SketchTune).

### What is SketchTune?

SketchTune is a novel method for adapting large language models (LLMs) that focuses on reducing memory usage and improving speed while fine-tuning. Instead of adding low-rank adapters like LoRA or DoRA, it compresses the model's weights into compact, trainable "sketches" for downstream adaptation.

**Key benefits:**

* **Combines compression and adaptation** - SketchTune trains directly on compressed representations, removing the need for separate adapters. This saves memory, improves model performance and speed.
* **Avoids low-rank limits** - Low-rank adapters assume weight updates follow a low rank structure. SketchTune skips this assumption, using sketching to better capture complex changes in model weights.

**Performance highlights:**

* Even with base models that are **2.6–3.5× smaller**, SketchTune **outperforms LoRA, DoRA, and S2FT** on commonsense and math reasoning benchmarks.
* On the GSM8K math dataset, SketchTune achieves a **14.48% higher accuracy than LoftQ**, while training **7.3× fewer parameters**.

For a deep dive into how sketching works, including math details and extensive test results, check out our full paper: [https://arxiv.org/abs/2410.06364](https://arxiv.org/abs/2410.06364).

### Citation

If you find this work helpful, please consider citing our paper:
```bibtex
@inproceedings{
  zhang2025sketch,
  title={Sketch to Adapt: Fine-Tunable Sketches for Efficient {LLM} Adaptation},
  author={Tianyi Zhang and Junda Su and Aditya Desai and Oscar Wu and Zhaozhuo Xu and Anshumali Shrivastava},
  booktitle={Forty-second International Conference on Machine Learning},
  year={2025},
  url={https://openreview.net/forum?id=zZXOXhxO6I}
}
```