{"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-transfo-xl","entry":"load_tf_weights_in_transfo_xl","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":12,"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":3,"n_samples_ran":0,"n_samples_fingerprinted":0,"n_places":12,"n_places_pointer_only":1,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":0,"unverified":3},"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":"2010.05607","paper":"/paper/the-elephant-in-the-interpretability-room-why","title":"The elephant in the interpretability room: Why use attention as explanation when we have saliency methods?","date":"2020-10-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jessevig/bertviz","path":"bertviz/transformers_neuron_view/modeling_transfo_xl.py","file_url":"https://github.com/jessevig/bertviz/blob/HEAD/bertviz/transformers_neuron_view/modeling_transfo_xl.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":"23d246e59ef9447b","mcp_get_code":{"code_sha256":"23d246e59ef9447b"}},{"arxiv_id":"2005.02439","paper":"/paper/contextualizing-hate-speech-classifiers-with","title":"Contextualizing Hate Speech Classifiers with Post-hoc Explanation","date":"2020-05-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"owaisCS/TestHateSpeech","path":"bert/modeling_transfo_xl.py","file_url":"https://github.com/owaisCS/TestHateSpeech/blob/HEAD/bert/modeling_transfo_xl.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"1ebc2bf2c3cddc4d","mcp_get_code":{"code_sha256":"1ebc2bf2c3cddc4d"}},{"arxiv_id":"2005.00558","paper":"/paper/pointer-constrained-text-generation-via","title":"POINTER: Constrained Progressive Text Generation via Insertion-based Generative Pre-training","date":"2020-05-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"dreasysnail/POINTER","path":"pytorch_transformers/modeling_transfo_xl.py","file_url":"https://github.com/dreasysnail/POINTER/blob/HEAD/pytorch_transformers/modeling_transfo_xl.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"23d246e59ef9447b","mcp_get_code":{"code_sha256":"23d246e59ef9447b"}},{"arxiv_id":"2004.03829","paper":"/paper/exploring-versatile-generative-language-model","title":"Exploring Versatile Generative Language Model Via Parameter-Efficient Transfer Learning","date":"2020-04-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zlinao/VGLM","path":"pytorch_transformers/modeling_transfo_xl.py","file_url":"https://github.com/zlinao/VGLM/blob/HEAD/pytorch_transformers/modeling_transfo_xl.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"23d246e59ef9447b","mcp_get_code":{"code_sha256":"23d246e59ef9447b"}},{"arxiv_id":"2002.01808","paper":"/paper/k-adapter-infusing-knowledge-into-pre-trained","title":"K-Adapter: Infusing Knowledge into Pre-Trained Models with Adapters","date":"2020-02-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"microsoft/K-Adapter","path":"pytorch_transformers/modeling_transfo_xl.py","file_url":"https://github.com/microsoft/K-Adapter/blob/HEAD/pytorch_transformers/modeling_transfo_xl.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"23d246e59ef9447b","mcp_get_code":{"code_sha256":"23d246e59ef9447b"}},{"arxiv_id":"1911.00720","paper":"/paper/zen-pre-training-chinese-text-encoder","title":"ZEN: Pre-training Chinese Text Encoder Enhanced by N-gram Representations","date":"2019-11-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"cuhksz-nlp/het-mc","path":"pytorch_pretrained_bert/modeling_transfo_xl.py","file_url":"https://github.com/cuhksz-nlp/het-mc/blob/HEAD/pytorch_pretrained_bert/modeling_transfo_xl.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"1ebc2bf2c3cddc4d","mcp_get_code":{"code_sha256":"1ebc2bf2c3cddc4d"}},{"arxiv_id":"1909.05311","paper":"/paper/graph-based-reasoning-over-heterogeneous","title":"Graph-Based Reasoning over Heterogeneous External Knowledge for Commonsense Question Answering","date":"2019-09-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"DecstionBack/AAAI_2020_CommonsenseQA","path":"pytorch_transformers/modeling_transfo_xl.py","file_url":"https://github.com/DecstionBack/AAAI_2020_CommonsenseQA/blob/HEAD/pytorch_transformers/modeling_transfo_xl.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":"23d246e59ef9447b","mcp_get_code":{"code_sha256":"23d246e59ef9447b"}},{"arxiv_id":"1908.09355","paper":"/paper/patient-knowledge-distillation-for-bert-model","title":"Patient Knowledge Distillation for BERT Model Compression","date":"2019-08-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"eunanomist/PKD_BERT","path":"BERT/pytorch_pretrained_bert/modeling_transfo_xl.py","file_url":"https://github.com/eunanomist/PKD_BERT/blob/HEAD/BERT/pytorch_pretrained_bert/modeling_transfo_xl.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"code_sha256_prefix":"1ebc2bf2c3cddc4d","mcp_get_code":{"code_sha256":"1ebc2bf2c3cddc4d"}},{"arxiv_id":"1906.08237","paper":"/paper/xlnet-generalized-autoregressive-pretraining","title":"XLNet: Generalized Autoregressive Pretraining for Language Understanding","date":"2019-06-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"samwisegamjeee/pytorch-transformers","path":"pytorch_transformers/modeling_transfo_xl.py","file_url":"https://github.com/samwisegamjeee/pytorch-transformers/blob/HEAD/pytorch_transformers/modeling_transfo_xl.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":"23d246e59ef9447b","mcp_get_code":{"code_sha256":"23d246e59ef9447b"}},{"arxiv_id":"1901.02860","paper":"/paper/transformer-xl-attentive-language-models","title":"Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context","date":"2019-01-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"cedrickchee/pytorch-pretrained-BERT","path":"pytorch_pretrained_bert/modeling_transfo_xl.py","file_url":"https://github.com/cedrickchee/pytorch-pretrained-BERT/blob/HEAD/pytorch_pretrained_bert/modeling_transfo_xl.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":"1ebc2bf2c3cddc4d","mcp_get_code":{"code_sha256":"1ebc2bf2c3cddc4d"}},{"arxiv_id":"2024.findings-naacl.32","paper":null,"title":"arXiv:2024.findings-naacl.32","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"SnowYJ/sem_syn_separation","path":"optimus_separate_graph_sem_syntax_fuse_gpt2/pytorch_transformers/modeling_transfo_xl.py","file_url":"https://github.com/SnowYJ/sem_syn_separation/blob/HEAD/optimus_separate_graph_sem_syntax_fuse_gpt2/pytorch_transformers/modeling_transfo_xl.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"23d246e59ef9447b","mcp_get_code":{"code_sha256":"23d246e59ef9447b"}},{"arxiv_id":"2023.findings-emnlp.331","paper":null,"title":"arXiv:2023.findings-emnlp.331","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"lwaekfjlk/TRAMS","path":"utils/modeling_transfo_xl.py","file_url":"https://github.com/lwaekfjlk/TRAMS/blob/HEAD/utils/modeling_transfo_xl.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":"d2404e268e31107c","mcp_get_code":{"code_sha256":"d2404e268e31107c"}}]}