Home › Code › load_tf_weights_in_gpt2

load_tf_weights_in_gpt2

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

load_tf_weights_in_gpt2 appears in the code Syntology harvested for 68 papers, as 14 distinct code bodies found in 69 places (a place is one code body under one paper). At least one of them ran in 0 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_tf_weights_in_gpt2 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 0 of the 14 distinct code bodies named load_tf_weights_in_gpt2; 14 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
0ran
14unverified
0fingerprinted

Licence is a property of each copy, so it is counted per place: 14 of the 69 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

68 papers shown of 68, newest first; 69 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; 4 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
Utilizing Evolution Strategies to Train Transformers in Reinforcement Learning 23 Jan 2025 mafi412/evolution-strategies-and-decision-transformers/codebase/components/decision_transformer/gym/models/trajectory_gpt2.py 00a33466c69c5705 unverified MIT (permissive)
Moto: Latent Motion Token as the Bridging Language for Learning Robot Manipulation from Videos 5 Dec 2024 tencentarc/moto/moto_gpt/src/models/trajectory_gpt2.py 00a33466c69c5705 unverified licence not identified · pointer only
Continual Task Learning through Adaptive Policy Self-Composition 18 Nov 2024 charleshsc/CompoFormer/dt/trajectory_gpt2.py 00a33466c69c5705 unverified Apache-2.0 (permissive)
DeeR-VLA: Dynamic Inference of Multimodal Large Language Models for Efficient Robot Execution 4 Nov 2024 yueyang130/DeeR-VLA/robot_flamingo/models/trajectory_gpt2.py 00a33466c69c5705 unverified Apache-2.0 (permissive)
The LLM Language Network: A Neuroscientific Approach for Identifying Causally Task-Relevant Units 4 Nov 2024 bkhmsi/llm-localization/models/modeling_gpt2.py eae14ebac1cd9c52 unverified no licence file found · pointer only
Task-Aware Harmony Multi-Task Decision Transformer for Offline Reinforcement Learning 2 Nov 2024 charleshsc/HarmoDT/prompt_dt/trajectory_gpt2.py 00a33466c69c5705 unverified Apache-2.0 (permissive)
Teaching Embodied Reinforcement Learning Agents: Informativeness and Diversity of Language Use 31 Oct 2024 sled-group/teachable_rl/alfworld/decision_transformer/models/trajectory_gpt2.py 00a33466c69c5705 unverified no licence file found · pointer only
Reinforcement Learning Gradients as Vitamin for Online Finetuning Decision Transformers 31 Oct 2024 kaiyan289/rl_as_vitamin_for_online_decision_transformers/decision_transformer/models/trajectory_gpt2.py 00a33466c69c5705 unverified no licence file found · pointer only
Value Residual Learning For Alleviating Attention Concentration In Transformers 23 Oct 2024 Zcchill/Value-Residual-Learning/src/modeling/modeling_gpt2_baseline.py eae14ebac1cd9c52 unverified MIT (permissive)
Meta-DT: Offline Meta-RL as Conditional Sequence Modeling with World Model Disentanglement 15 Oct 2024 NJU-RL/Meta-DT/meta_dt/trajectory_gpt2.py 00a33466c69c5705 unverified no licence file found · pointer only
CLIBE: Detecting Dynamic Backdoors in Transformer-based NLP Models 2 Sep 2024 raytsang123/clibe/generative_backdoors/detection/modeling_gpt2.py 3665fea6427d655d unverified Apache-2.0 (permissive)
GR-MG: Leveraging Partially Annotated Data via Multi-Modal Goal-Conditioned Policy 26 Aug 2024 bytedance/GR-MG/policy/model/gpt2.py 3665fea6427d655d unverified Apache-2.0 (permissive)
Adversarially Robust Decision Transformer 25 Jul 2024 xiaohangt/ardt/decision_transformer/decision_transformer/models/trajectory_gpt2.py bc9fb74e483fb901 unverified MIT (permissive)
Train-Attention: Meta-Learning Where to Focus in Continual Knowledge Learning 24 Jul 2024 ybseo-academy/TAALM/utils/kadapter/Llama2_Model_Kadapter.py cb4e99dd4b50f69d unverified no licence file found · pointer only
From Instance Training to Instruction Learning: Task Adapters Generation from Instructions 18 Jun 2024 Xnhyacinth/TAGI/src/modeling_gpt2.py bc9fb74e483fb901 unverified Apache-2.0 (permissive)
GOMAA-Geo: GOal Modality Agnostic Active Geo-localization 4 Jun 2024 mvrl/gomaa-geo/models/model_gpt.py 3665fea6427d655d unverified MIT (permissive)
Q-value Regularized Transformer for Offline Reinforcement Learning 27 May 2024 charleshsc/qt/decision_transformer/models/trajectory_gpt2.py 00a33466c69c5705 unverified Apache-2.0 (permissive)
RepEval: Effective Text Evaluation with LLM Representation 30 Apr 2024 shikib/usr/transformers/modeling_gpt2.py 654e91efc679fe84 unverified Apache-2.0 (permissive)
DESTEIN: Navigating Detoxification of Language Models via Universal Steering Pairs and Head-wise Activation Fusion 16 Apr 2024 lizlizli/destein/modeling/modeling_gpt2.py 3665fea6427d655d unverified no licence file found · pointer only
Decision Mamba: Reinforcement Learning via Sequence Modeling with Selective State Spaces 29 Mar 2024 toshihiro-ota/decision-mamba/gym/models/trajectory_gpt2.py 00a33466c69c5705 unverified MIT (permissive)
Keyformer: KV Cache Reduction through Key Tokens Selection for Efficient Generative Inference 14 Mar 2024 d-matrix-ai/keyformer-llm/models/cerebras-keyformer-lib/modeling_gpt2.py bc9fb74e483fb901 unverified Apache-2.0 (permissive)
Generative Pretrained Structured Transformers: Unsupervised Syntactic Language Models at Scale 13 Mar 2024 alipay/StructuredLM_RTDT/model/gpt2_flash_attn.py 3665fea6427d655d unverified Apache-2.0 (permissive)
Reinforced Sequential Decision-Making for Sepsis Treatment: The POSNEGDM Framework with Mortality Classifier and Transformer 12 Mar 2024 dipeshtamboli/posnegdm-reinforced-sequential-decision-making-for-sepsis-treatment/dualsight/models/trajectory_gpt2.py 00a33466c69c5705 unverified MIT (permissive)
EdgeQAT: Entropy and Distribution Guided Quantization-Aware Training for the Acceleration of Lightweight LLMs on the Edge 16 Feb 2024 shawnricecake/edgeqat/distill_train/models/modeling_gpt2_fp16.py 3665fea6427d655d unverified no licence file found · pointer only
Multi-Patch Prediction: Adapting LLMs for Time Series Representation Learning 7 Feb 2024 yxbian23/aLLM4TS/models/modeling_gpt2.py 3665fea6427d655d unverified no licence file found · pointer only
Some things are more CRINGE than others: Iterative Preference Optimization with the Pairwise Cringe Loss 27 Dec 2023 facebookresearch/RAM/projects/cocomix/models/modeling_gpt2_cocomix.py 9a0a23caa628b0b9 unverified MIT (permissive)
Critic-Guided Decision Transformer for Offline Reinforcement Learning 21 Dec 2023 sharkwyf/cgdt/decision_transformer/models/trajectory_gpt2.py 00a33466c69c5705 unverified MIT (permissive)
Free from Bellman Completeness: Trajectory Stitching via Model-based Return-conditioned Supervised Learning 30 Oct 2023 zhaoyizhou1123/mbrcsl/offlinerlkit/modules/trajectory_gpt2.py bc9fb74e483fb901 unverified MIT (permissive)
When can transformers reason with abstract symbols? 15 Oct 2023 eboix/relational-reasoning/train_gpt2/gpt2_with_identity.py 3665fea6427d655d unverified no licence file found · pointer only
Self-Detoxifying Language Models via Toxification Reversal 14 Oct 2023 cooperleong00/toxificationreversal/models/gpt2/modeling_gpt2.py bc9fb74e483fb901 unverified no licence file found · pointer only
Self-Detoxifying Language Models via Toxification Reversal 14 Oct 2023 cooperleong00/toxificationreversal/models/gpt2/modeling_gpt2_innerdetox.py c87b238769f13efb unverified no licence file found · pointer only
Fine-Tune Language Models as Multi-Modal Differential Equation Solvers 9 Aug 2023 liuyangmage/in-context-operator-networks/icon-lm/models_gpt2_source.py c4bac98236c1fc2c unverified MIT (permissive)
Diffusion Model is an Effective Planner and Data Synthesizer for Multi-Task Reinforcement Learning 29 May 2023 tinnerhrhe/MTDiff/diffuser/models/GPT2.py 00a33466c69c5705 unverified MIT (permissive)
Future-conditioned Unsupervised Pretraining for Decision Transformer 26 May 2023 fffffarmer/pdt/src/models/trajectory_gpt2.py 00a33466c69c5705 unverified MIT (permissive)
When should we prefer Decision Transformers for Offline Reinforcement Learning? 23 May 2023 prajjwal1/rl_paradigm/exorl/models/trajectory_gpt2.py 00a33466c69c5705 unverified MIT (permissive)
In-Context Operator Learning with Data Prompts for Differential Equation Problems 17 Apr 2023 LiuYangMage/in-context-operator-networks/icon-lm/models_gpt2_source.py c4bac98236c1fc2c unverified MIT (permissive)
Merging Decision Transformers: Weight Averaging for Forming Multi-Task Policies 14 Mar 2023 daniellawson9999/merging-decision-transformers/decision-transformer/decision_transformer/models/trajectory_gpt2.py cb4e99dd4b50f69d unverified MIT (permissive)
Learning Video Representations from Large Language Models 8 Dec 2022 facebookresearch/lavila/lavila/models/gpt2_gated.py bc9fb74e483fb901 unverified MIT recorded; this copy not marked cleared · pointer only
WIDER & CLOSER: Mixture of Short-channel Distillers for Zero-shot Cross-lingual Named Entity Recognition 7 Dec 2022 mckysse/msd/transformers/modeling_gpt2.py 654e91efc679fe84 unverified Apache-2.0 (permissive)
How Crucial is Transformer in Decision Transformer? 26 Nov 2022 max7born/decision-lstm/src/decision_transformer/models/trajectory_gpt2.py 00a33466c69c5705 unverified MIT (permissive)
Exploring Discrete Diffusion Models for Image Captioning 21 Nov 2022 buxiangzhiren/ddcap/tf_adpt.py cb4e99dd4b50f69d unverified MIT (permissive)
On the Effect of Pre-training for Transformer in Different Modality on Offline Reinforcement Learning 17 Nov 2022 machelreid/can-wikipedia-help-offline-rl/code/decision_transformer/models/trajectory_gpt2.py cb4e99dd4b50f69d unverified MIT (permissive)
Benchmarking Reinforcement Learning Techniques for Autonomous Navigation 10 Oct 2022 Daffan/ros_jackal/rl_algos/trajectory_gpt2.py 00a33466c69c5705 unverified MIT (permissive)
Offline RL for Natural Language Generation with Implicit Language Q Learning 5 Jun 2022 sea-snell/implicit-language-q-learning/src/models/gpt2_optional_final_ln.py cb4e99dd4b50f69d unverified MIT (permissive)
Towards Understanding How Machines Can Learn Causal Overhypotheses 16 Jun 2022 cannylab/casual_overhypotheses/models/decision-transformer/models/trajectory_gpt2.py 00a33466c69c5705 unverified MIT (permissive)
Human Language Modeling 10 May 2022 humanlab/hart/src/model/modeling_hart.py 5235fb1d3272245b unverified Apache-2.0 (permissive)
COLD Decoding: Energy-based Constrained Text Generation with Langevin Dynamics 23 Feb 2022 qkaren/COLD_decoding/GPT2ForwardBackward/modeling_opengpt2.py 00a33466c69c5705 unverified Apache-2.0 (permissive)
Evidence-aware Fake News Detection with Graph Neural Networks 18 Jan 2022 CRIPAC-DIG/GET/pytorch_transformers/modeling_gpt2.py 654e91efc679fe84 unverified MIT (permissive)
StARformer: Transformer with State-Action-Reward Representations for Visual Reinforcement Learning 12 Oct 2021 elicassion/StARformer/gym/models/trajectory_gpt2.py 00a33466c69c5705 unverified MIT (permissive)
Decision Transformer: Reinforcement Learning via Sequence Modeling 2 Jun 2021 Amadeus979/decision-transformer/gym/decision_transformer/models/trajectory_gpt2.py 00a33466c69c5705 unverified MIT (permissive)
Plug-and-Blend: A Framework for Controllable Story Generation with Blended Control Codes 23 Mar 2021 xxbidiao/plug-and-blend/gedi_helpers/modeling_gpt2.py c4bac98236c1fc2c unverified MIT (permissive)
The elephant in the interpretability room: Why use attention as explanation when we have saliency methods? 12 Oct 2020 jessevig/bertviz/bertviz/transformers_neuron_view/modeling_gpt2.py 654e91efc679fe84 unverified Apache-2.0 (permissive)
Stylized Dialogue Response Generation Using Stylized Unpaired Texts 27 Sep 2020 silverriver/Stylized_Dialog/TCFC/bt_beam/model/gpt2.py c4bac98236c1fc2c unverified MIT (permissive)
GeDi: Generative Discriminator Guided Sequence Generation 14 Sep 2020 salesforce/GeDi/modeling_gpt2.py c4bac98236c1fc2c unverified BSD-3-Clause (permissive)
Contextualizing Hate Speech Classifiers with Post-hoc Explanation 5 May 2020 owaisCS/TestHateSpeech/bert/modeling_gpt2.py a62604f618a8cc82 unverified MIT (permissive)
A Simple Language Model for Task-Oriented Dialogue 2 May 2020 salesforce/simpletod/models/modeling_gpt2.py c4bac98236c1fc2c unverified BSD-3-Clause (permissive)
POINTER: Constrained Progressive Text Generation via Insertion-based Generative Pre-training 1 May 2020 dreasysnail/POINTER/pytorch_transformers/modeling_gpt2.py 07bb0220eb5b609f unverified MIT (permissive)
VGCN-BERT: Augmenting BERT with Graph Embedding for Text Classification 12 Apr 2020 Louis-udm/VGCN-BERT/old_version/pytorch_pretrained_bert/modeling_gpt2.py 8a9df506fe60a0cd unverified MIT (permissive)
Exploring Versatile Generative Language Model Via Parameter-Efficient Transfer Learning 8 Apr 2020 zlinao/VGLM/pytorch_transformers/modeling_gpt2.py 654e91efc679fe84 unverified MIT (permissive)
K-Adapter: Infusing Knowledge into Pre-Trained Models with Adapters 5 Feb 2020 microsoft/K-Adapter/pytorch_transformers/modeling_gpt2.py 654e91efc679fe84 unverified MIT (permissive)
ZEN: Pre-training Chinese Text Encoder Enhanced by N-gram Representations 2 Nov 2019 SVAIGBA/TwASP/pytorch_pretrained_bert/modeling_gpt2.py a62604f618a8cc82 unverified MIT (permissive)
Graph-Based Reasoning over Heterogeneous External Knowledge for Commonsense Question Answering 9 Sep 2019 DecstionBack/AAAI_2020_CommonsenseQA/pytorch_transformers/modeling_gpt2.py 07bb0220eb5b609f unverified Apache-2.0 (permissive)
Patient Knowledge Distillation for BERT Model Compression 25 Aug 2019 Daniel-H-99/Patient-Knowledge-Distillation/BERT/pytorch_pretrained_bert/modeling_gpt2.py a62604f618a8cc82 unverified MIT recorded; this copy not marked cleared · pointer only
XLNet: Generalized Autoregressive Pretraining for Language Understanding 19 Jun 2019 samwisegamjeee/pytorch-transformers/pytorch_transformers/modeling_gpt2.py 07bb0220eb5b609f unverified Apache-2.0 (permissive)
Open Sesame: Getting Inside BERT's Linguistic Knowledge 4 Jun 2019 yongjie-lin/bert-opensesame/bertviz/bertviz/pytorch_pretrained_bert/modeling_gpt2.py a62604f618a8cc82 unverified Apache-2.0 (permissive)
arXiv:aaai_33874 txsun1997/Black-Box-Tuning/models/deep_modeling_gpt2.py 00a33466c69c5705 unverified MIT (permissive)
arXiv:2025.emnlp-main.688 yueen-ma/Astra/model/trajectory_transformer.py 3665fea6427d655d unverified MIT (permissive)
arXiv:2024.findings-naacl.32 SnowYJ/sem_syn_separation/optimus_separate_graph_sem_syntax_fuse_gpt2/pytorch_transformers/modeling_gpt2.py 654e91efc679fe84 unverified MIT (permissive)
arXiv:2023.findings-acl.765 qtli/EIB/code/EIB_model/modeling_gpt2.py 59e7bfe60606f53b unverified Apache-2.0 (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