SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2502.19261 · ICLR · 2025

Drop-Upcycling: Training Sparse Mixture of Experts with Partial Re-initialization

Jun Suzuki, Rio Yokota, Taishi Nakamura, Takuya Akiba, Kazuki Fujii, Yusuke Oda

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 (0 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 2 failures of our instrument; 0 no recorded run), measured 2026-11-22; 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/2502.19261.json · badge: /api/ran/2502.19261.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
Taishi-N324/Drop-Upcycling community
Papers with Code archive
2 ran · 0 no recorded run
FunctionStatusWhere it lives
initialize_weights Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
Taishi-N324/Drop-Upcycling/conversions/drop_upcycling.py
code served (permissive licence) · get_code("8785e020e9ec2081")
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 Tensor, ndim 2, dtype family float, shape (2, 4) 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 logging
import torch

logger = logging.getLogger(__name__)

torch.manual_seed(0)

ARGS = {
    'size': (2, 4),
    'method': 'torch_normal',
    'std': 0.02,
    'mean': 0
}
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 Tensor, ndim 2, dtype family float, shape (2, 4) — shape (2, 4) 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
shuffle_and_partially_initialize Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
Taishi-N324/Drop-Upcycling/conversions/drop_upcycling.py
code served (permissive licence) · get_code("3a72ee8840583353")
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 Tensor. 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 logging
import torch

# Set up logging
logging.basicConfig(level=logging.INFO)

# Set seed for reproducibility
torch.manual_seed(0)

# Create a small tensor for testing
# Shape: (hidden_size=5, intermediate_size=4) for down_proj case
# or (intermediate_size=4, hidden_size=5) for up_proj/gate_proj case
tensor = torch.randn(5, 4, dtype=torch.bfloat16)

# Create a permutation for shuffling
perm = torch.randperm(4)

# Define arguments
ARGS = {
    'tensor': tensor,
    'perm': perm,
    'target_size': 3,
    'is_down_proj': True,
    'layer_idx': 0,
    'expert_idx': 0,
    'ffn_init_ratio': 0.5
}
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 Tensor, shape (5, 3) — shape (5, 3) as a later run recorded it
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, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 2 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.

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

The Mixture of Experts (MoE) architecture reduces the training and inference cost significantly compared to a dense model of equivalent capacity. Upcycling is an approach that initializes and trains an MoE model using a pre-trained dense model. While upcycling leads to initial performance gains, the training progresses slower than when trained from scratch, leading to suboptimal performance in the long term. We propose Drop-Upcycling -a method that effectively addresses this problem. Drop-Upcycling combines two seemingly contradictory approaches: utilizing the knowledge of pre-trained dense models while statistically re-initializing some parts of the weights. This approach strategically promotes expert specialization, significantly enhancing the MoE model's efficiency in knowledge acquisition. Extensive large-scale experiments demonstrate that Drop-Upcycling significantly outperforms previous MoE construction methods in the long term, specifically when training on hundreds of billions of tokens or more. As a result, our MoE model with 5.9B active parameters achieves comparable performance to a 13B dense model in the same model family, while requiring approximately 1/4 of the training FLOPs. All experimental resources, including source code, training data, model checkpoints and logs, are publicly available to promote reproducibility and future research on MoE. Weights huggingface.co/collections/llm-jp/ drop-upcycling-674dc5be7bbb45e12a476b80 Data gitlab.llm-jp.nii.ac.jp/ datasets/llm-jp-corpus-v3 Code github.com/Taishi-N324/Drop-Upcycling Logs wandb.ai/taishi-nakamura/Drop-Upcycling

For agents

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

get_harvested_code_for_paper("2502.19261")
get_code_for_paper("2502.19261")
have("2502.19261")

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

curl https://syntology.ai/api/ran/2502.19261.json

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

[![Syntology run record](https://syntology.ai/api/ran/2502.19261.svg)](https://syntology.ai/paper/2502.19261)

Connect an agent — have() is free.