Papers › Model-GLUE: Democratized LLM Scaling for A Large Model Zoo in the Wild

Model-GLUE: Democratized LLM Scaling for A Large Model Zoo in the Wild

7 Oct 2024arXiv:2410.05357archive 2025-07-28

Xinyu Zhao, Guoheng Sun, Ruisi Cai, Yukun Zhou, Pingzhi Li, Peihao Wang, Bowen Tan, Yexiao He, Li Chen, Yi Liang, Beidi Chen, Binhang Yuan, Hongyi Wang, Ang Li, Zhangyang Wang, Tianlong Chen

As Large Language Models (LLMs) excel across tasks and specialized domains, scaling LLMs based on existing models has garnered significant attention, which faces the challenge of decreasing performance when combining disparate models. Various techniques have been proposed for the aggregation of pre-trained LLMs, including model merging, Mixture-of-Experts, and stacking. Despite their merits, a comprehensive comparison and synergistic application of them to a diverse model zoo is yet to be adequately addressed. In light of this research gap, this paper introduces Model-GLUE, a holistic LLM scaling guideline. First, our work starts with a benchmarking of existing LLM scaling techniques, especially selective merging, and variants of mixture. Utilizing the insights from the benchmark results, we formulate an optimal strategy for the selection and aggregation of a heterogeneous model zoo characterizing different architectures and initialization.Our methodology involves the clustering of mergeable models and optimal merging strategy selection, and the integration of clusters through a model mixture. Finally, evidenced by our experiments on a diverse Llama-2-based model zoo, Model-GLUE shows an average performance enhancement of 5.61%, achieved without additional training. Codes are available at: https://github.com/Model-GLUE/Model-GLUE.

PaperPDFCodeCode Syntology ranMethod as code

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 16 code samples harvested from 1 repository linked to this paper: 10 ran (of which 4 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 5 where Syntology's instrument failed) · 6 unverified. Where Syntology's instrument failed: 3 where our contract draft was wrong; 2 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 16 samples from 1 repository, 10 ran (5 with no instrument failure; 5 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written between 2026-09-22 and 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 4 of the 10 samples that ran have no recorded date.

model-glue/model-glue officialmentioned in paperMITSyntology: 16 samples, 10 ran (5 instrument-failed) · 6 unverified report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

16 samples harvested: 10 ran (of which 4 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 5 where Syntology's instrument failed) · 6 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

3ran · our draft was wrong
2ran; the contract check could not run
5ran
6unverified

Licence: 0 of the 16 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from model-glue/model-glue. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. For 2 samples that ran, the graph records a signature this page does not show: for a class the fixture built without calling, the harness called the object with inputs it made up itself, so the recorded signature is the harness's probe, not the fixture's arguments. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

model-glue/model-glue official repository 16 samples, 10 ran (5 instrument-failed) · 6 unverified
repeat_kv in 244 papers
census: 15 implementations from 60 papers, 2 distinct outputs on one shared input this sample: bucket 1 of 1, arg 1: rank 4, kind float, dtype float32
mixture/mixtral_model_level/modeling_mixtral_model_level_hybrid.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted MIT (permissive) · 30d7eec482ebf6b1 · report fixture: signature hidden_states:Tensor/4/float, n_rep:int/0/int · returned Tensor · level recorded, date not recorded
MixtralModelLevelHybridConfig mixture/mixtral_model_level/modeling_mixtral_model_level_hybrid.py ran MIT (permissive) · 5f809614ad45d87e · report fixture: returned MixtralModelLevelHybridConfig · level recorded 2026-09-22
MixtralModelLevelHybridMLP mixture/mixtral_model_level/modeling_mixtral_model_level_hybrid.py ran · metamorphic tier: deterministic fingerprinted MIT (permissive) · 168afe1c35dcbf7a · report fixture: returned MixtralModelLevelHybridMLP · level recorded 2026-09-22
MixtralModelLevelHybridRMSNorm mixture/mixtral_model_level/modeling_mixtral_model_level_hybrid.py ran · metamorphic tier: deterministic MIT (permissive) · 61211405adf0232e · report fixture: returned MixtralModelLevelHybridRMSNorm · level recorded 2026-09-22
MixtralModelLevelHybridRotaryEmbedding mixture/mixtral_model_level/modeling_mixtral_model_level_hybrid.py ran · metamorphic tier: deterministic MIT (permissive) · 2af3f93fb1f05187 · report fixture: returned MixtralModelLevelHybridRotaryEmbedding · level recorded 2026-09-22
apply_rotary_pos_emb in 393 papers
census: 14 implementations from 15 papers, 8 distinct outputs across 7 buckets, one shared input per bucket
mixture/mixtral_model_level/modeling_mixtral_model_level_hybrid.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant MIT (permissive) · d61c483a3c2b3156 · report fixture: signature q:Tensor/4/float, k:Tensor/4/float, cos:Tensor/2/float, sin:Tensor/2/float, position_ids:Tensor/2/int, unsqueeze_dim:int/0/int · returned tuple · level recorded, date not recorded
hash_args in 46 papers lm_eval/api/model.py ran · our draft was wrong fingerprinted MIT (permissive) · 20a7cc804eb22661 · report fixture: signature attr:str/0/str, args:tuple/1/str · returned str · level recorded, date not recorded
remove_after_return in 5 papers bigcode_eval/utils.py ran · our draft was wrong fingerprinted MIT (permissive) · 29ee1d8c120f674a · report fixture: signature code:str/0/str · returned str · level recorded 2026-09-24
rotate_half in 424 papers
census: 24 implementations from 96 papers, 4 distinct outputs across 2 buckets, one shared input per bucket this sample: bucket 1 of 2, arg 1: rank 2, kind float, dtype float32
mixture/mixtral_model_level/modeling_mixtral_model_level_hybrid.py ran · our draft was wrong fingerprinted MIT (permissive) · b99eea6376d1e212 · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded, date not recorded
update_code_gens bigcode_eval/utils.py ran MIT (permissive) · ac86a6f136bea277 · report fixture: signature task:MockTask/0/?, tokenizer:MockTokenizer/0/?, limit_start:int/0/int, prefix:str/0/str, instruction_tokens:list/1/str, postprocess:bool/0/bool, code_gens:dict/0/?, gen_token_dict:dict/0/? · returned dict · level recorded 2026-09-24
MixtralModelLevelHybridAttention mixture/mixtral_model_level/modeling_mixtral_model_level_hybrid.py unverified MIT (permissive) · b7a56ddb57bcb75d · report
MixtralModelLevelHybridDenseDecoderLayer mixture/mixtral_model_level/modeling_mixtral_model_level_hybrid.py unverified MIT (permissive) · 10f90dfc6066b0b8 · report
MixtralModelLevelHybridFlashAttention2 mixture/mixtral_model_level/modeling_mixtral_model_level_hybrid.py unverified MIT (permissive) · c81e094f251fdc6a · report
MixtralModelLevelHybridSdpaAttention mixture/mixtral_model_level/modeling_mixtral_model_level_hybrid.py unverified MIT (permissive) · 2315328e9bcd8f59 · report
MixtralModelLevelHybridSparseDecoderLayer mixture/mixtral_model_level/modeling_mixtral_model_level_hybrid.py unverified MIT (permissive) · 3cc021576be7867c · report
complete_code in 7 papers bigcode_eval/utils.py unverified MIT (permissive) · 59f94e66fd20d85d · report

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it.

1 assembly on this paper: 1 harvested, 0 generated.

harvested Assembly for Model-GLUE (graph method: Model-GLUE). 13 bricks; individually on a fixture: 8 ran (of which 4 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 4 where Syntology's instrument failed) · 5 unverified. The assembly has not been run end-to-end.

  1. MixtralModelLevelHybridSparseDecoderLayer entry · level 0 · unverified · 3cc021576be7867c
  2. MixtralModelLevelHybridConfig helper · level 1 · ran · 5f809614ad45d87e
  3. MixtralModelLevelHybridDenseDecoderLayer helper · level 0 · unverified · 10f90dfc6066b0b8
  4. MixtralModelLevelHybridMLP helper · level 1 · ran · 168afe1c35dcbf7a
  5. MixtralModelLevelHybridRMSNorm model · level 1 · ran · 61211405adf0232e
  6. MixtralModelLevelHybridRotaryEmbedding helper · level 1 · ran · 2af3f93fb1f05187
  7. _get_unpad_data helper · level 1 · ran · our draft was wrong · 180b7fb4f14752ec
  8. apply_rotary_pos_emb helper · level 1 · ran; the contract check could not run · 0fe82a947dc39b42
  9. repeat_kv helper · level 2 · ran; the contract check could not run · 3c76e52815c5401d
  10. rotate_half helper · level 1 · ran · our draft was wrong · e03d53ba9d4f9ae5
  11. MixtralModelLevelHybridAttention model · level 0 · unverified · b7a56ddb57bcb75d
  12. MixtralModelLevelHybridFlashAttention2 model · level 0 · unverified · c81e094f251fdc6a
  13. MixtralModelLevelHybridSdpaAttention model · level 0 · unverified · 2315328e9bcd8f59

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2410.05357") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

BenchmarkingMixture-of-Expertsmodel

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections