Home › Code › load_model_and_tokenizer

load_model_and_tokenizer

Syntologyentry name in harvested coderead from the graph 2026-09-24

load_model_and_tokenizer appears in the code Syntology harvested for 61 papers, as 64 distinct code bodies found in 66 places (a place is one code body under one paper). At least one of them ran in 10 of the papers; 0 of the code bodies carry a behaviour fingerprint.

What this page is not. Routines are grouped here by the exact string of their function or class name. Nothing asserts that two samples named load_model_and_tokenizer do the same thing, share code, or are comparable; the name is a string, not an identity. Behaviour outputs (what a fingerprinted sample returned on the shared battery) are not in this export and are not shown here; the graph at syntology.ai holds them. "Ran" means executed on a synthesized fixture, not that the code is correct or reproduces a paper.

Samples Syntology

Syntology ran 10 of the 64 distinct code bodies named load_model_and_tokenizer; 54 are unverified. One tile per status, in the site's fixed vocabulary, each code body counted once:

0ran · honoured contract
0ran · violated contract
0ran · our draft was wrong
0ran · fixture could not drive it
10ran
54unverified
0fingerprinted

Licence is a property of each copy, so it is counted per place: 30 of the 66 places are pointer only (Syntology does not serve that copy's text). This site shows no code text for any sample; every row below links to the file in its repository where the record names one.

“Ran” means the sample executed on a synthesized input; it does not mean the output is correct. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code, and those samples did run. The ran count above is every status except unverified, the same rule as each paper page.

Papers

61 papers shown of 61, newest first; 66 places in the table. A paper with no recorded date is placed by the month its arXiv id encodes, shown in the Date column as YYYY-MM (from id). One row per place: a paper whose repository defines the name more than once appears more than once, and the same code body held for several papers appears once under each, with the same status. Titles and dates are the archive's archive 2025-07-28 for papers in the archive, and the graph's for 19 papers added by Syntology; 2 papers have no page here and are shown by arXiv id only. Status and fingerprint are Syntology's record of each code body; licence is recorded for each place. The File cell ends with the code body's code_sha256, Syntology's identity for that exact code: an agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

PaperDateFileStatus SyntologyLicence
IDEEA: training-free Input-Dependent stEEring via Activation cluster matching added by Syntology 2026-09 (from id) DSL-Lab/IDEEA/common/modeling.py e3f80c2ee531022c unverified no licence file found · pointer only
StateSwap: Probing Support-Elimination Hidden States in Multiple-Choice Questions added by Syntology 2026-09 (from id) Cha0Ga0/SWAPSTATE/src/hs_swap/models.py b88b122f84c5cb80 unverified no licence file found · pointer only
Latent Fact-Checking: Detecting Misinformation through Activation Engineering added by Syntology 2026-08 (from id) Malta-Lab/LaFaCt/methods/base.py 6c2fa8a910a6e5fe unverified no licence file found · pointer only
When Correct Solutions Repeat: Rarity-Aware Credit Redistribution for GRPO added by Syntology 2026-08 (from id) CzZ12/When-Correct-Solutions-Repeat-Rarity-Aware-Credit-Redistribution-for-GRPO/grpo_trainer_utils.py 9ac32f5a2f8c738c unverified MIT (permissive)
Can Induced Emotion Bias LLM Behaviors in Sequential Decision Making? added by Syntology 2026-07 (from id) costa-nus/llm-emotion-decision/utils/hf.py 9bcca6a41327a4e1 unverified no licence file found · pointer only
Why Struggle with Continuous Latents? Interpretable Discrete Latent Reasoning via Rendered Compression added by Syntology 2026-06 (from id) Miraclecsc/Discrete-Latent-Reasoning/deepseek_codebook/visualize_latent_ids.py 8e067d12bb78f5b8 unverified no licence file found · pointer only
SlotGCG: Exploiting the Positional Vulnerability in LLMs for Jailbreak Attacks added by Syntology 2026-06 (from id) youai058/SlotGCG/baselines/model_utils.py 419da37a5e7e4f3a unverified no licence file found · pointer only
A Measure-Theoretic Analysis of Reasoning: Structural Generalization and Approximation Limits added by Syntology 2026-05 (from id) Yyuzrah/AMTA4R/MTA4R/src/eval_flexible.py 865ff8f8286bfd35 unverified no licence file found · pointer only
SAGE: Shaping Anchors for Guided Exploration in RLVR of LLMs added by Syntology 2026-05 (from id) tally0818/SAGE/src/train/common.py f62f00e1e077e5a1 unverified no licence file found · pointer only
Nudging Beyond the Comfort Zone: Efficient Strategy-Guided Exploration for RLVR added by Syntology 2026-05 (from id) tally0818/NudgeRL/src/train/train_nudgerl.py 4238d2cfcafc21b0 ran no licence file found · pointer only
Multi-Rollout On-Policy Distillation via Peer Successes and Failures added by Syntology 2026-05 (from id) viviable/mopd_code/analysis/score_teacher_contexts.py 1a52c3aa3027b3fe unverified Apache-2.0 (permissive)
LLM-Agnostic Semantic Representation Attack added by Syntology 2026-05 (from id) JiaweiLian/SRA/baselines/model_utils.py 090eed81a24d4b32 unverified MIT (permissive)
Latent Planning Emerges with Scale added by Syntology 2026-04 (from id) hannamw/model-planning-public/animal_stories/probing.py fcdffa1e12fc52ec unverified MIT (permissive)
Same Geometry, Opposite Noise: Transformer Magnitude Representations Lack Scalar Variability added by Syntology 2026-04 (from id) synthiumjp/weber/m3_pilot/m3_extract.py 6e731249ef09bbf4 unverified no licence file found · pointer only
Parameter-Efficient Fine-Tuning for Medical Text Summarization: A Comparative Study of Lora, Prompt Tuning, and Full Fine-Tuning added by Syntology 2026-03 (from id) eracoding/llm-medical-summarization/src/models/model_loader.py ca3dd3a359eeb3eb unverified no licence file found · pointer only
VIGiA: Instructional Video Guidance via Dialogue Reasoning and Retrieval added by Syntology 2026-02 (from id) dmgcsilva/vigia/inference/vigia/dialogue_sim.py 72ca0249eb720e57 unverified no licence file found · pointer only
Rethinking Hallucinations: Correctness, Consistency, and Prompt Multiplicity added by Syntology 2026-02 (from id) AI21Labs/in-context-ralm/ralm/model_utils.py 93181488645fbb58 unverified Apache-2.0 (permissive)
Activation Oracles: Training and Evaluating LLMs as General-Purpose Activation Explainers added by Syntology 2025-12 (from id) cywinski/eliciting-secret-knowledge/sampling/utils.py 7c099df440884000 unverified MIT (permissive)
Addressing Tokenization Inconsistency in Steganography and Watermarking Based on Large Language Models added by Syntology 2025-08 (from id) ryehr/Consistency/src/tokenization_consistency/models.py e037ac1be5c9f57f unverified MIT (permissive)
LongWriter-Zero: Mastering Ultra-Long Text Generation via Reinforcement Learning 23 Jun 2025 thudm/longwriter/trans_web_demo.py b966ffef888e5413 unverified Apache-2.0 (permissive)
Reasoning-to-Defend: Safety-Aware Reasoning Can Defend Large Language Models from Jailbreaking 18 Feb 2025 chuhac/Reasoning-to-Defend/HarmBench/baselines/model_utils.py 090eed81a24d4b32 unverified MIT (permissive)
Adversarial Reasoning at Jailbreaking Time 3 Feb 2025 helloworld10011/adversarial-reasoning/utils.py c46ed68c0b1d6f03 unverified Apache-2.0 (permissive)
LLM Safety Alignment is Divergence Estimation in Disguise 2 Feb 2025 rhaldarpurdue/kldo/eval_utils.py 63fd436cd288e12f unverified Apache-2.0 (permissive)
LLM Safety Alignment is Divergence Estimation in Disguise 2 Feb 2025 rhaldarpurdue/kldo/dataset_generation/compare.py d690eaa700e23094 unverified Apache-2.0 (permissive)
LLM Safety Alignment is Divergence Estimation in Disguise 2 Feb 2025 rhaldarpurdue/kldo/dataset_generation/generate.py b95843089da1efe9 unverified Apache-2.0 (permissive)
Turning Logic Against Itself : Probing Model Defenses Through Contrastive Questions 3 Jan 2025 UKPLab/emnlp2025-poate-attack/poate_attack/attacks/utils/models.py 090eed81a24d4b32 unverified Apache-2.0 (permissive)
AttriBoT: A Bag of Tricks for Efficiently Approximating Leave-One-Out Context Attribution 22 Nov 2024 r-three/AttriBoT/context_attribution/model_utils.py 4c63c74cb872e812 unverified no licence file found · pointer only
Squeezed Attention: Accelerating Long Context Length LLM Inference 14 Nov 2024 SqueezeAILab/SqueezedAttention/LongBench/pred.py 71856fc92741e6f7 unverified no licence file found · pointer only
Controllable Context Sensitivity and the Knob Behind It 11 Nov 2024 kdu4108/context-vs-prior-finetuning/model_utils/utils.py 63070f500d814722 unverified no licence file found · pointer only
A Common Pitfall of Margin-based Language Model Alignment: Gradient Entanglement 17 Oct 2024 humainlab/understand_marginpo/analysis/grad_heatmap_1.py 2b221536391e6a55 unverified no licence file found · pointer only
Functional Homotopy: Smoothing Discrete Optimization via Continuous Parameters for LLM Jailbreak Attacks 5 Oct 2024 danshumaan/functional_homotopy/fhautodan/utils/opt_utils.py 576ee553d5cff992 ran no licence file found · pointer only
Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents 3 Oct 2024 agiresearch/ASB/memory_defense/ppl_utils.py faabedfe90d4f114 unverified MIT (permissive)
A Controlled Study on Long Context Extension and Generalization in LLMs 18 Sep 2024 leooyii/lceg/longbench/pred.py 2b06c68ea29c8f3b ran no licence file found · pointer only
Advancing Adversarial Suffix Transfer Learning on Aligned Large Language Models 27 Aug 2024 Waffle-Liu/DeGCG/baselines/model_utils.py 5949ab432e811362 unverified MIT (permissive)
Knowledge in Superposition: Unveiling the Failures of Lifelong Knowledge Editing for Large Language Models 14 Aug 2024 chenhuihu/knowledge_in_superposition/Cache_Cov.py 411e60fba7b021a5 ran no licence file found · pointer only
Knowledge in Superposition: Unveiling the Failures of Lifelong Knowledge Editing for Large Language Models 14 Aug 2024 chenhuihu/knowledge_in_superposition/Compute_Activation_Cos.py f8698e8cdcb6e36c unverified no licence file found · pointer only
OriGen:Enhancing RTL Code Generation with Code-to-Code Augmentation and Self-Reflection 23 Jul 2024 pku-liang/origen/evaluation/generate_lora.py ab078cc050d0eb8a unverified no licence file found · pointer only
PreAlign: Boosting Cross-Lingual Transfer by Early Establishment of Multilingual Alignment 23 Jul 2024 saltychtao/prealign/src/utils.py c6ea57e16ccfac13 unverified no licence file found · pointer only
Open (Clinical) LLMs are Sensitive to Instruction Phrasings 12 Jul 2024 alceballosa/clin-robust/modules/utils.py 19adfb763485b0b5 unverified no licence file found · pointer only
From Loops to Oops: Fallback Behaviors of Language Models Under Uncertainty 8 Jul 2024 mivg/fallbacks/utils/utils.py 03f72536317546c1 ran MIT (permissive)
ChatGLM: A Family of Large Language Models from GLM-130B to GLM-4 All Tools 18 Jun 2024 thudm/chatglm/finetune_demo/inference_hf.py 91958a6f1719c4f7 unverified Apache-2.0 (permissive)
ChatGLM: A Family of Large Language Models from GLM-130B to GLM-4 All Tools 18 Jun 2024 thudm/chatglm/basic_demo/web_demo_gradio.py bb6e915ee912453d unverified Apache-2.0 (permissive)
GUICourse: From General Vision Language Models to Versatile GUI Agents 17 Jun 2024 yiye3/guicourse/Qwen-SFT&Infer/infer.py baaebe9658032c54 ran no licence file found · pointer only
Probing the Decision Boundaries of In-context Learning in Large Language Models 17 Jun 2024 siyan-zhao/ICL_decision_boundary/get_llm_decision_boundary.py 7d229e134c72cc58 unverified no licence file found · pointer only
Probing the Decision Boundaries of In-context Learning in Large Language Models 17 Jun 2024 siyan-zhao/ICL_decision_boundary/finetune_icl.py fa6cb2e5730316a9 unverified no licence file found · pointer only
Designing a Dashboard for Transparency and Control of Conversational AI 12 Jun 2024 yc015/talktuner-chatbot-llm-dashboard/dashboard_v1/probing/train_probes.py d0a8ad2ed431e1b5 unverified MIT (permissive)
Why Don't Prompt-Based Fairness Metrics Correlate? 9 Jun 2024 chandar-lab/CAIRO/model/model_load.py 58913a7b3b43bf05 ran MIT (permissive)
Improving Alignment and Robustness with Circuit Breakers 6 Jun 2024 blackswan-ai/circuit-breakers/evaluation/utils.py 2671d81aefc6945e unverified MIT (permissive)
Efficient Adversarial Training in LLMs with Continuous Attacks 24 May 2024 sophie-xhonneux/continuous-advtrain/src/model_utils.py 06cd66993d331abf unverified MIT (permissive)
Studying Large Language Model Behaviors Under Context-Memory Conflicts With Real Documents 24 Apr 2024 kortukov/realistic_knowledge_conflicts/src/model_utils.py b70e091f78d4e3ac ran no licence file found · pointer only
Massive Activations in Large Language Models 27 Feb 2024 bluorion-com/refine_massive_activations/utils/model.py f9134816cda05113 unverified MIT (permissive)
REAR: A Relevance-Aware Retrieval-Augmented Framework for Open-Domain Question Answering 27 Feb 2024 RUCAIBox/REAR/rear/src/load_model.py f0ed5a58b6a31117 unverified no licence file found · pointer only
Defending LLMs against Jailbreaking Attacks via Backtranslation 26 Feb 2024 yihanwang617/llm-jailbreaking-defense-backtranslation/attacks/autodan.py 3bcc8e42ea5e457e ran BSD-3-Clause (permissive)
Coercing LLMs to do and reveal (almost) anything 21 Feb 2024 jonasgeiping/carving/carving/model_interface.py 832c4bb5405dc600 unverified MIT (permissive)
Attacking Large Language Models with Projected Gradient Descent 14 Feb 2024 sigeisler/reinforce-attacks-llms/baselines/model_utils.py 0313a63291b892b7 unverified MIT (permissive)
Soft Prompt Threats: Attacking Safety Alignment and Unlearning in Open-Source LLMs through the Embedding Space 14 Feb 2024 schwinnl/llm_embedding_attack/embedding_attack_toxic.py 067aa4bb86ba8911 unverified MIT (permissive)
COLD-Attack: Jailbreaking LLMs with Stealthiness and Controllability 13 Feb 2024 Yu-Fangxu/COLD-Attack/opt_util.py 886d1670186fba06 ran no licence file found · pointer only
PiCO: Peer Review in LLMs based on the Consistency Optimization 2 Feb 2024 PKU-YuanGroup/Peer-review-in-LLMs/llm_judge/common.py 8feea35ea433b832 unverified no licence file found · pointer only
Large Language Models Can Learn Temporal Reasoning 12 Jan 2024 xiongsiheng/tg-llm/src/SFT_TG_Reasoning_ppl.py e9cff349000673db unverified MIT (permissive)
LLM Lies: Hallucinations are not Bugs, but Features as Adversarial Examples 2 Oct 2023 pku-yuangroup/hallucination-attack/utils.py 8afcadff70823ad7 unverified MIT (permissive)
Graph of Thoughts: Solving Elaborate Problems with Large Language Models 18 Aug 2023 chiral-carbon/kg-for-science/src/utils/utils.py 786ad935afe1d784 unverified MIT (permissive)
OUTFOX: LLM-Generated Essay Detection Through In-Context Learning with Adversarially Generated Examples 21 Jul 2023 ryuryukke/OUTFOX/utils/utils.py 59ab6a8438c40917 unverified Apache-2.0 (permissive)
A Survey of Large Language Models 31 Mar 2023 xusenlinzy/api-for-open-llm/api/adapter/loader.py 37c3d7ab0a5f9367 unverified Apache-2.0 (permissive)
ContraCLM: Contrastive Learning For Causal Language Model 3 Oct 2022 amazon-science/contraclm/utils.py 0770c863fd59b11f unverified Apache-2.0 (permissive)
arXiv:2025.emnlp-main.326 cl-tohoku/ca-multi-ptn/sft/src/inference.py 6e98cbfbcd92571a unverified MIT (permissive)
arXiv:2023.emnlp-main.771 Patrick-Ni/KnowEE/src/load_models_and_datasets.py bb16cfebf07908c0 unverified MIT (permissive)

This site shows no code text; each File cell links to the file on GitHub at the repository's current default branch, which may have changed since the harvest. "Pointer only" means Syntology does not serve that copy's text, for one of four 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; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). 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 cell for the reason. Per-sample records for a paper are on its paper page under "Code Syntology ran".

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