FuguReport

Fine-Tuning Low-Bit Models with Gradient in Quantized Code Space

Authors Shiguang Wu, Zhouchen Lin, Quanming Yao
Affiliations Tsinghua University / Peking University
Categories Method / Quantization / Consistent low-bit fine-tuning, Task / Model Compression / Applying quantized models, Evaluation / Optimization Techniques / Improvement across quantized data types
License CC BY 4.0

Abstract Overview

This paper studies strict fully low-bit fine-tuning, where the adapted model must remain in the same quantized format at deployment, so optimization is performed over quantization codes and scales rather than a continuous weight space. The authors propose GradCodeS, which constructs a geometry-aware code surrogate gradient and uses it to guide a discrete guide-sample-evaluate-select search over valid low-bit candidates. The method separates proposal construction from update acceptance: gradients shape where to search, but the accepted state is chosen only by the realized loss of deployable low-bit checkpoints. Experiments cover arithmetic reasoning, instruction following, and structured semantic parsing on Qwen3-0.6B and Llama-3.2 1B/3B models, with evaluations across multiple 4-bit baselines and quantization datatypes.

Novelty

The main novelty is a first-order optimization signal defined directly in quantized code space, rather than reusing ordinary weight gradients or relying purely on zeroth-order search. The paper also combines this code-space surrogate gradient with deployment-faithful discrete candidate selection, and provides local theoretical results linking the surrogate to steepest descent and one-step code updates.

Results

Across the reported tasks and backbones, GradCodeS is the strongest fully 4-bit method, consistently improving over direct 4-bit quantization and other fully low-bit baselines such as PV-Tuning, QuZO, QZO, and QES. The method also shows robustness across NF4, INT4, and MXFP4, and its guided sampler yields higher candidate selection probability under the same budget than Gaussian, one-hop, or ordinary weight-gradient-guided sampling.

Key Points

  1. GradCodeS targets deployment-faithful low-bit fine-tuning by optimizing directly over quantized codes and scales, avoiding a mismatch between the trained state and the deployed checkpoint.
  2. Its core technical idea is a code surrogate gradient that accounts for quantization geometry, including codebook gaps and group scales, and then uses that signal to guide discrete candidate search.
  3. Empirically, the method delivers the best reported fully 4-bit results across reasoning, instruction-following, and structured prediction benchmarks, while also improving candidate-search efficiency and remaining compatible with multiple quantization datatypes.

References

This page was created using generative AI such as GPT-5, Claude Opus 4, Gemini 3, Gemini 3.1 Flash Image, and their higher-end successor versions. No guarantee can be made regarding its contents.