SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2410.01623 · NeurIPS · 2025

Fira: Can We Achieve Full-rank Training of LLMs under Low-rank Constraint?

Xiangyu Yue, Ye Yuan, Xi Chen, Guoren Wang, Kaituo Feng, Changsheng Li, Xunhao Lai

arXiv · PDF · Open in the Atlas

Code that ran

2 of 2 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (1 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 1 has no contract verdict; 1 failure of our instrument; 0 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2410.01623.json · badge: /api/ran/2410.01623.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
xichen-fy/Fira canonical (classifier label)
classifier basis: classifier_2025
1 ran · 0 no recorded run
xichen-fy/fira marked official in Papers with Code
Papers with Code archive
1 ran · 0 no recorded run
FunctionStatusWhere it lives
GradientProjector Ran
ran on a synthesized input · constructed an object; no result was computed
xichen-fy/fira/optimizer_torch/gradient_projection.py
code served (permissive licence) · get_code("33ca766ca389525b")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned an instance of its own class, GradientProjector: the run constructed the object and did not call it, so no result was computed. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch

torch.manual_seed(0)

ARGS = {
    'rank': 2,
    'verbose': False,
    'update_proj_gap': 200,
    'alpha': 1.0,
    'proj_type': 'std'
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type GradientProjector — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a GradientProjector output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
generate_prompt Ran
ran; our contract draft was wrong, not the code
xichen-fy/Fira/fine_tuning/finetune.py
code served (permissive licence) · get_code("56e674752db00649")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1) and returned str. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch

torch.manual_seed(0)

# The function expects a dict with 'input', 'instruction', and 'output' keys
data_point = {
    'instruction': 'Translate the following text to French.',
    'input': 'Hello, how are you?',
    'output': 'Bonjour, comment allez-vous?'
}

ARGS = {
    'data_point': data_point
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block

Also present in other papers' code

Of 2 samples lifted from this paper's linked repositories, 2 carry a function identity and 0 do not. Of the 2 distinct functions with an identity, 1 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 1 the same month, 1 later) and 1 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
generate_prompt 15 other papers
7 dated earlier, 3 the same month, 4 later, 1 same year, order not determinable
2304.01933 (2023-04)
LLM-Adapters: An Adapter Family for Parameter-Efficient Fine-Tuning of Large Language Models
2307.08072 (2023-07)
Do Emergent Abilities Exist in Quantized Large Language Models: An Empirical Study
2024.naacl-long.132 (2024 (year only))
LLM-based Medical Assistant Personalization with Short-and Long-Term Memory Coordination
and 12 more not named here

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Low-rank training has emerged as a promising approach for reducing memory usage in training Large Language Models (LLMs). Previous methods either rely on decomposing weight matrices (e.g., LoRA), or seek to decompose gradient matrices (e.g., GaLore) to ensure reduced memory consumption. However, both of them constrain the training in a low-rank subspace, thus inevitably leading to sub-optimal performance. To resolve this, we propose a new plug-and-play training framework for LLMs called Fira, as the first attempt to consistently preserve the low-rank constraint for memory efficiency, while achieving full-rank training (i.e., training with full-rank gradients of full-rank weights) to avoid inferior outcomes. First, we observe an interesting phenomenon during LLM training: the scaling impact of adaptive optimizers (e.g., Adam) on the gradient norm remains similar from low-rank to full-rank training. In light of this, we propose a norm-based scaling method, which utilizes the scaling impact of low-rank optimizers as substitutes for that of original full-rank optimizers to achieve this goal. Moreover, we find that low-rank optimizers may lead to potential loss spikes during training. To address this, we further put forward a norm-growth limiter to smooth the gradient. Extensive experiments on the pre-training and fine-tuning of LLMs show that Fira outperforms both LoRA and GaLore. Notably, for pre-training LLaMA 7B, our Fira uses 8× smaller memory of optimizer states than Galore, yet outperforms it by a large margin.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2410.01623")
get_code_for_paper("2410.01623")
have("2410.01623")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2410.01623.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2410.01623.svg)](https://syntology.ai/paper/2410.01623)

Connect an agent — have() is free.