{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/code/load-tf-weights-in-t5","entry":"load_tf_weights_in_t5","source":"Syntology graph, per-sample; not an archive number","read_at":"2026-09-24T18:15:14+00:00","claim":"Names are grouped by exact entry-name string. Same-named routines are NOT asserted to be equivalent; 'ran' means executed on a synthesized fixture, not correctness. n_samples_ran = sum of by_status over every status except 'unverified' (ran_draft_wrong and ran_fixture are failures of Syntology's instrument, not of the code); n_papers_ran = papers with at least one such sample.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"n_papers":28,"n_papers_ran":0,"units":"n_samples, n_samples_ran, n_samples_fingerprinted and by_status count distinct code bodies (code_sha256); n_places and n_places_pointer_only count places, one per (paper, code body) pair, which is also the unit of the samples list","n_samples":10,"n_samples_ran":0,"n_samples_fingerprinted":0,"n_places":28,"n_places_pointer_only":11,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":0,"unverified":10},"syntology":{"atlas_url":null,"mcp":null,"mcp_per_sample":{"tool":"get_code","arguments_in":"samples[].mcp_get_code"},"developers":"https://syntology.ai/developers"},"samples":[{"arxiv_id":"2501.08453","paper":"/paper/vchitect-2-0-parallel-transformer-for-scaling","title":"Vchitect-2.0: Parallel Transformer for Scaling Up Video Diffusion Models","date":"2025-01-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Vchitect/Vchitect-2.0","path":"models/modeling_t5.py","file_url":"https://github.com/Vchitect/Vchitect-2.0/blob/HEAD/models/modeling_t5.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"f383d81f62012649","mcp_get_code":{"code_sha256":"f383d81f62012649"}},{"arxiv_id":"2407.21633","paper":"/paper/2407-21633","title":"Zero-Shot Cross-Domain Dialogue State Tracking via Dual Low-Rank Adaptation","date":"2024-07-31","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"suntea233/DualLoRA","path":"copy_t5.py","file_url":"https://github.com/suntea233/DualLoRA/blob/HEAD/copy_t5.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"136abfa3e8ce028d","mcp_get_code":{"code_sha256":"136abfa3e8ce028d"}},{"arxiv_id":"2406.18847","paper":"/paper/learning-retrieval-augmentation-for","title":"Learning Retrieval Augmentation for Personalized Dialogue Generation","date":"2024-06-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hqsiswiliam/lapdog","path":"src/modeling_t5.py","file_url":"https://github.com/hqsiswiliam/lapdog/blob/HEAD/src/modeling_t5.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"230899b7dd1ea8a1","mcp_get_code":{"code_sha256":"230899b7dd1ea8a1"}},{"arxiv_id":"2406.12382","paper":"/paper/from-instance-training-to-instruction","title":"From Instance Training to Instruction Learning: Task Adapters Generation from Instructions","date":"2024-06-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Xnhyacinth/TAGI","path":"src/modeling_t5.py","file_url":"https://github.com/Xnhyacinth/TAGI/blob/HEAD/src/modeling_t5.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"bfbc7746415f3426","mcp_get_code":{"code_sha256":"bfbc7746415f3426"}},{"arxiv_id":"2405.17427","paper":"/paper/reason3d-searching-and-reasoning-3d","title":"Reason3D: Searching and Reasoning 3D Segmentation via Large Language Model","date":"2024-05-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"kuanchihhuang/reason3d","path":"lavis/models/reason3d_models/modeling_t5.py","file_url":"https://github.com/kuanchihhuang/reason3d/blob/HEAD/lavis/models/reason3d_models/modeling_t5.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"bfbc7746415f3426","mcp_get_code":{"code_sha256":"bfbc7746415f3426"}},{"arxiv_id":"2403.12499","paper":"/paper/listwise-generative-retrieval-models-via-a","title":"Listwise Generative Retrieval Models via a Sequential Learning Process","date":"2024-03-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lightningtyb/listgr","path":"code/model.py","file_url":"https://github.com/lightningtyb/listgr/blob/HEAD/code/model.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"136abfa3e8ce028d","mcp_get_code":{"code_sha256":"136abfa3e8ce028d"}},{"arxiv_id":"2402.07398","paper":"/paper/vislinginstruct-elevating-zero-shot-learning","title":"VisLingInstruct: Elevating Zero-Shot Learning in Multi-Modal Language Models with Autonomous Instruction Optimization","date":"2024-02-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zhudongsheng75/vislinginstruct","path":"vislinginstruct/models/modeling_t5.py","file_url":"https://github.com/zhudongsheng75/vislinginstruct/blob/HEAD/vislinginstruct/models/modeling_t5.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"bfbc7746415f3426","mcp_get_code":{"code_sha256":"bfbc7746415f3426"}},{"arxiv_id":"2402.02503","paper":"/paper/gerea-question-aware-prompt-captions-for","title":"GeReA: Question-Aware Prompt Captions for Knowledge-based Visual Question Answering","date":"2024-02-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"upper9527/gerea","path":"src/modeling_t5.py","file_url":"https://github.com/upper9527/gerea/blob/HEAD/src/modeling_t5.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"52fdf83141474e49","mcp_get_code":{"code_sha256":"52fdf83141474e49"}},{"arxiv_id":"2401.07105","paper":"/paper/graph-language-models","title":"Graph Language Models","date":"2024-01-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"heidelberg-nlp/graphlanguagemodels","path":"models/graph_T5/graph_t5/modeling_t5.py","file_url":"https://github.com/heidelberg-nlp/graphlanguagemodels/blob/HEAD/models/graph_T5/graph_t5/modeling_t5.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"7112073cf1646198","mcp_get_code":{"code_sha256":"7112073cf1646198"}},{"arxiv_id":"2311.11860","paper":"/paper/lion-empowering-multimodal-large-language","title":"LION : Empowering Multimodal Large Language Model with Dual-Level Visual Knowledge","date":"2023-11-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"rshaojimmy/jiutian","path":"models/modeling_t5.py","file_url":"https://github.com/rshaojimmy/jiutian/blob/HEAD/models/modeling_t5.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"bfbc7746415f3426","mcp_get_code":{"code_sha256":"bfbc7746415f3426"}},{"arxiv_id":"2311.08106","paper":"/paper/carpe-diem-on-the-evaluation-of-world","title":"Carpe Diem: On the Evaluation of World Knowledge in Lifelong Language Models","date":"2023-11-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"kimyuji/evolvingqa_benchmark","path":"models/T5_Model_Kadapter.py","file_url":"https://github.com/kimyuji/evolvingqa_benchmark/blob/HEAD/models/T5_Model_Kadapter.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"136abfa3e8ce028d","mcp_get_code":{"code_sha256":"136abfa3e8ce028d"}},{"arxiv_id":"2311.03057","paper":"/paper/glen-generative-retrieval-via-lexical-index","title":"GLEN: Generative Retrieval via Lexical Index Learning","date":"2023-11-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"skleee/GLEN","path":"src/tevatron/modeling/glen_t5_modeling.py","file_url":"https://github.com/skleee/GLEN/blob/HEAD/src/tevatron/modeling/glen_t5_modeling.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"33fcca2adb353b5f","mcp_get_code":{"code_sha256":"33fcca2adb353b5f"}},{"arxiv_id":"2310.15896","paper":"/paper/bianque-balancing-the-questioning-and","title":"BianQue: Balancing the Questioning and Suggestion Ability of Health LLMs with Multi-turn Health Conversations Polished by ChatGPT","date":"2023-10-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"scutcyr/bianque","path":"models/t5/modeling_t5.py","file_url":"https://github.com/scutcyr/bianque/blob/HEAD/models/t5/modeling_t5.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"bfbc7746415f3426","mcp_get_code":{"code_sha256":"bfbc7746415f3426"}},{"arxiv_id":"2310.07815","paper":"/paper/language-models-as-semantic-indexers","title":"Language Models As Semantic Indexers","date":"2023-10-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"petergriffinjin/lmindexer","path":"SemanticID/src/IDGen/reconstruct_decoder.py","file_url":"https://github.com/petergriffinjin/lmindexer/blob/HEAD/SemanticID/src/IDGen/reconstruct_decoder.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"bfbc7746415f3426","mcp_get_code":{"code_sha256":"bfbc7746415f3426"}},{"arxiv_id":"2309.13952","paper":"/paper/vidchapters-7m-video-chapters-at-scale","title":"VidChapters-7M: Video Chapters at Scale","date":"2023-09-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"antoyang/VidChapters","path":"model/modeling_t5.py","file_url":"https://github.com/antoyang/VidChapters/blob/HEAD/model/modeling_t5.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"bfbc7746415f3426","mcp_get_code":{"code_sha256":"bfbc7746415f3426"}},{"arxiv_id":"2308.09936","paper":"/paper/bliva-a-simple-multimodal-llm-for-better","title":"BLIVA: A Simple Multimodal LLM for Better Handling of Text-Rich Visual Questions","date":"2023-08-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mlpc-ucsd/bliva","path":"bliva/models/modeling_t5.py","file_url":"https://github.com/mlpc-ucsd/bliva/blob/HEAD/bliva/models/modeling_t5.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"code_sha256_prefix":"bfbc7746415f3426","mcp_get_code":{"code_sha256":"bfbc7746415f3426"}},{"arxiv_id":"2308.07922","paper":"/paper/raven-in-context-learning-with-retrieval","title":"RAVEN: In-Context Learning with Retrieval-Augmented Encoder-Decoder Language Models","date":"2023-08-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jeffhj/raven","path":"src/modeling_t5.py","file_url":"https://github.com/jeffhj/raven/blob/HEAD/src/modeling_t5.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"136abfa3e8ce028d","mcp_get_code":{"code_sha256":"136abfa3e8ce028d"}},{"arxiv_id":"2307.04349","paper":"/paper/rltf-reinforcement-learning-from-unit-test","title":"RLTF: Reinforcement Learning from Unit Test Feedback","date":"2023-07-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zyq-scut/rltf","path":"trainers/modeling_t5.py","file_url":"https://github.com/zyq-scut/rltf/blob/HEAD/trainers/modeling_t5.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"code_sha256_prefix":"136abfa3e8ce028d","mcp_get_code":{"code_sha256":"136abfa3e8ce028d"}},{"arxiv_id":"2306.07285","paper":"/paper/transcoder-towards-unified-transferable-code","title":"TransCoder: Towards Unified Transferable Code Representation Learning Inspired by Human Skills","date":"2023-05-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"qiushisun/transcoder","path":"models_list/T5ForConditionalGeneration_Prefix_2.py","file_url":"https://github.com/qiushisun/transcoder/blob/HEAD/models_list/T5ForConditionalGeneration_Prefix_2.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"bfbc7746415f3426","mcp_get_code":{"code_sha256":"bfbc7746415f3426"}},{"arxiv_id":"2210.14102","paper":"/paper/exploring-mode-connectivity-for-pre-trained","title":"Exploring Mode Connectivity for Pre-trained Language Models","date":"2022-10-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"thunlp/mode-connectivity-plm","path":"T5_model/modeling_t5.py","file_url":"https://github.com/thunlp/mode-connectivity-plm/blob/HEAD/T5_model/modeling_t5.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"136abfa3e8ce028d","mcp_get_code":{"code_sha256":"136abfa3e8ce028d"}},{"arxiv_id":"2209.14627","paper":"/paper/an-equal-size-hard-em-algorithm-for-diverse","title":"An Equal-Size Hard EM Algorithm for Diverse Dialogue Generation","date":"2022-09-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"anonymous-1759/eqhard-em","path":"model/adapter_t5.py","file_url":"https://github.com/anonymous-1759/eqhard-em/blob/HEAD/model/adapter_t5.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"136abfa3e8ce028d","mcp_get_code":{"code_sha256":"136abfa3e8ce028d"}},{"arxiv_id":"2205.06983","paper":"/paper/rasat-integrating-relational-structures-into","title":"RASAT: Integrating Relational Structures into Pretrained Seq2Seq Model for Text-to-SQL","date":"2022-05-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lumia-group/rasat","path":"seq2seq/model/t5_original_model.py","file_url":"https://github.com/lumia-group/rasat/blob/HEAD/seq2seq/model/t5_original_model.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"136abfa3e8ce028d","mcp_get_code":{"code_sha256":"136abfa3e8ce028d"}},{"arxiv_id":"2204.07705","paper":"/paper/benchmarking-generalization-via-in-context","title":"Super-NaturalInstructions: Generalization via Declarative Instructions on 1600+ NLP Tasks","date":"2022-04-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"renzelou/pick-rank","path":"src/modeling_pointer.py","file_url":"https://github.com/renzelou/pick-rank/blob/HEAD/src/modeling_pointer.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"edfe67269d5fa277","mcp_get_code":{"code_sha256":"edfe67269d5fa277"}},{"arxiv_id":"2201.05966","paper":"/paper/unifiedskg-unifying-and-multi-tasking","title":"UnifiedSKG: Unifying and Multi-Tasking Structured Knowledge Grounding with Text-to-Text Language Models","date":"2022-01-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hkunlp/unifiedskg","path":"models/adapter/modeling_t5.py","file_url":"https://github.com/hkunlp/unifiedskg/blob/HEAD/models/adapter/modeling_t5.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"136abfa3e8ce028d","mcp_get_code":{"code_sha256":"136abfa3e8ce028d"}},{"arxiv_id":"aaai_33874","paper":null,"title":"arXiv:aaai_33874","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"txsun1997/Black-Box-Tuning","path":"models/deep_modeling_t5.py","file_url":"https://github.com/txsun1997/Black-Box-Tuning/blob/HEAD/models/deep_modeling_t5.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"247ce015d4375b22","mcp_get_code":{"code_sha256":"247ce015d4375b22"}},{"arxiv_id":"aaai_27999","paper":null,"title":"arXiv:aaai_27999","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"mlpc-ucsd/BLIVA","path":"bliva/models/modeling_t5.py","file_url":"https://github.com/mlpc-ucsd/BLIVA/blob/HEAD/bliva/models/modeling_t5.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"code_sha256_prefix":"bfbc7746415f3426","mcp_get_code":{"code_sha256":"bfbc7746415f3426"}},{"arxiv_id":"2025.acl-long.1300","paper":null,"title":"arXiv:2025.acl-long.1300","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"weijieliu-cs/QuASAR","path":"core/modeling_t5.py","file_url":"https://github.com/weijieliu-cs/QuASAR/blob/HEAD/core/modeling_t5.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"593e83d56ed7c9a4","mcp_get_code":{"code_sha256":"593e83d56ed7c9a4"}},{"arxiv_id":"2023.findings-emnlp.672","paper":null,"title":"arXiv:2023.findings-emnlp.672","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"guihuzhang/FactSpotter","path":"g2t_gen_code/code/modeling_t5.py","file_url":"https://github.com/guihuzhang/FactSpotter/blob/HEAD/g2t_gen_code/code/modeling_t5.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"52fdf83141474e49","mcp_get_code":{"code_sha256":"52fdf83141474e49"}}]}