SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2006.10518 · 2020

Improving Post Training Neural Quantization: Layer-wise Calibration and Integer Programming

arXiv · PDF · Open in the Atlas

Code that ran

2 of 7 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 2 have no contract verdict; 0 failures of our instrument; 5 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/2006.10518.json · badge: /api/ran/2006.10518.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
itayhubara/CalibTIP canonical (classifier label)
classifier basis: census
2 ran · 5 no recorded run
FunctionStatusWhere it lives
nearby_int Ran
ran on a synthesized input
itayhubara/CalibTIP/models/mobilenet_v2_old.py
code served (permissive licence) · get_code("f0e3c7e07f4ec4a8")
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 int, ndim 0, dtype family int, shape () as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape 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
import numpy as np

torch.manual_seed(0)

ARGS = {
    "n": 3.7
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type int, ndim 0, dtype family int, shape () — shape () as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
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
weight_decay_config Ran
ran on a synthesized input
itayhubara/CalibTIP/models/mobilenet_v2_old.py
code served (permissive licence) · get_code("318278bbb49c6d02")
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 dict. 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
import torch.nn as nn

torch.manual_seed(0)

# Define QConv2d since it's referenced in the function
class QConv2d(nn.Module):
    def __init__(self, in_channels, out_channels, kernel_size=3, groups=1):
        super().__init__()
        self.in_channels = in_channels
        self.out_channels = out_channels
        self.groups = groups
        self.weight = nn.Parameter(torch.randn(out_channels, in_channels // groups, kernel_size, kernel_size))
        self.bias = nn.Parameter(torch.randn(out_channels))
    
    def forward(self, x):
        return x

ARGS = {
    'value': 0.0001,
    'log': False,
}
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 dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict 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
conv Not yet run
unverified (harvested, no recorded run)
itayhubara/CalibTIP/models/mobilenet_v2_old.py
code served (permissive licence) · get_code("9c78f4848d2df0cb")
How it ran

no invocation recorded.

conv3x3 Not yet run
unverified (harvested, no recorded run)
itayhubara/CalibTIP/models/resnet.py
code served (permissive licence) · get_code("1775197fd615680a")
How it ran

no invocation recorded.

depBatchNorm2d Not yet run
unverified (harvested, no recorded run)
itayhubara/CalibTIP/models/inception.py
code served (permissive licence) · get_code("9ee14cbba4386d2e")
How it ran

no invocation recorded.

inception_v3 Not yet run
unverified (harvested, no recorded run)
itayhubara/CalibTIP/models/inception.py
code served (permissive licence) · get_code("7be99c438ebdedf8")
How it ran

no invocation recorded.

mpip_compression Not yet run
unverified (harvested, no recorded run)
itayhubara/CalibTIP/mpip_compression_pytorch_multi.py
code served (permissive licence) · get_code("800fc61832114933")
How it ran

no invocation recorded.

Also present in other papers' code

Of 7 samples lifted from this paper's linked repositories, 7 carry a function identity and 0 do not. Of the 7 distinct functions with an identity, 1 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 0 the same month, 0 later) and 6 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
nearby_int 1 other paper
1 dated earlier
1805.11046 (2018-05)
Scalable Methods for 8-bit Training of Neural Networks

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

Lately, post-training quantization methods have gained considerable attention, as they are simple to use, and require only a small unlabeled calibration set. This small dataset cannot be used to fine-tune the model without significant over-fitting. Instead, these methods only use the calibration set to set the activations' dynamic ranges. However, such methods always resulted in significant accuracy degradation, when used below 8-bits (except on small datasets). Here we aim to break the 8-bit barrier. To this end, we minimize the quantization errors of each layer separately by optimizing its parameters over the calibration set. We empirically demonstrate that this approach is: (1) much less susceptible to over-fitting than the standard fine-tuning approaches, and can be used even on a very small calibration set; and (2) more powerful than previous methods, which only set the activations' dynamic ranges. Furthermore, we demonstrate how to optimally allocate the bit-widths for each layer, while constraining accuracy degradation or model compression by proposing a novel integer programming formulation. Finally, we suggest model global statistics tuning, to correct biases introduced during quantization. Together, these methods yield state-of-the-art results for both vision and text models. For instance, on ResNet50, we obtain less than 1\% accuracy degradation --- with 4-bit weights and activations in all layers, but the smallest two. We open-sourced our code.

For agents

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

get_harvested_code_for_paper("2006.10518")
get_code_for_paper("2006.10518")
have("2006.10518")

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

curl https://syntology.ai/api/ran/2006.10518.json

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

[![Syntology run record](https://syntology.ai/api/ran/2006.10518.svg)](https://syntology.ai/paper/2006.10518)

Connect an agent — have() is free.