{"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/quick-gelu","entry":"quick_gelu","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":43,"n_papers_ran":26,"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":4,"n_samples_ran":3,"n_samples_fingerprinted":3,"n_places":43,"n_places_pointer_only":24,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":3,"unverified":1},"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":"2606.03066","paper":"/paper/arxiv-2606-03066","title":"CORE: Conflict-Oriented Reasoning for General Multimodal Manipulation Detection","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"shen8424/CORE","path":"libs/transformers/modeling_flax_utils.py","file_url":"https://github.com/shen8424/CORE/blob/HEAD/libs/transformers/modeling_flax_utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"a66d2b78670c85e1","mcp_get_code":{"code_sha256":"a66d2b78670c85e1"}},{"arxiv_id":"2510.13183","paper":"/paper/arxiv-2510-13183","title":"DSCD: Large Language Model Detoxification with Self-Constrained Decoding","date":null,"month_inferred_from_arxiv_id":"2025-10","title_source":"syntology","repo":"ZHANGJINKUI/DSCD","path":"transformers/modeling_flax_utils.py","file_url":"https://github.com/ZHANGJINKUI/DSCD/blob/HEAD/transformers/modeling_flax_utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a66d2b78670c85e1","mcp_get_code":{"code_sha256":"a66d2b78670c85e1"}},{"arxiv_id":"2507.03038","paper":"/paper/cautious-next-token-prediction","title":"Cautious Next Token Prediction","date":"2025-07-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"wyzjack/CNTP","path":"custom_transformers_packages/gsm8k_strategyqa/transformers/modeling_flax_utils.py","file_url":"https://github.com/wyzjack/CNTP/blob/HEAD/custom_transformers_packages/gsm8k_strategyqa/transformers/modeling_flax_utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a66d2b78670c85e1","mcp_get_code":{"code_sha256":"a66d2b78670c85e1"}},{"arxiv_id":"2505.19235","paper":"/paper/corematching-a-co-adaptive-sparse-inference","title":"CoreMatching: A Co-adaptive Sparse Inference Framework with Token and Neuron Pruning for Comprehensive Acceleration of Vision-Language Models","date":"2025-05-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"wangqinsi1/2025-ICML-CoreMatching","path":"transformers/modeling_flax_utils.py","file_url":"https://github.com/wangqinsi1/2025-ICML-CoreMatching/blob/HEAD/transformers/modeling_flax_utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"a66d2b78670c85e1","mcp_get_code":{"code_sha256":"a66d2b78670c85e1"}},{"arxiv_id":"2502.13963","paper":"/paper/mudaf-long-context-multi-document-attention","title":"MuDAF: Long-Context Multi-Document Attention Focusing through Contrastive Learning on Attention Heads","date":"2025-02-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"NeosKnight233/MuDAF","path":"transformers/modeling_flax_utils.py","file_url":"https://github.com/NeosKnight233/MuDAF/blob/HEAD/transformers/modeling_flax_utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"a66d2b78670c85e1","mcp_get_code":{"code_sha256":"a66d2b78670c85e1"}},{"arxiv_id":"2410.19123","paper":"/paper/read-me-refactorizing-llms-as-router","title":"Read-ME: Refactorizing LLMs as Router-Decoupled Mixture of Experts with System Co-Design","date":"2024-10-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"VITA-Group/READ-ME","path":"src/transformers/activations_tf.py","file_url":"https://github.com/VITA-Group/READ-ME/blob/HEAD/src/transformers/activations_tf.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"e2d56cb91f999bef","mcp_get_code":{"code_sha256":"e2d56cb91f999bef"}},{"arxiv_id":"2410.12178","paper":"/paper/model-balancing-helps-low-data-training-and","title":"Model Balancing Helps Low-data Training and Fine-tuning","date":"2024-10-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zihanghliu/modelbalancing","path":"transformers/src/transformers/activations_tf.py","file_url":"https://github.com/zihanghliu/modelbalancing/blob/HEAD/transformers/src/transformers/activations_tf.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"e2d56cb91f999bef","mcp_get_code":{"code_sha256":"e2d56cb91f999bef"}},{"arxiv_id":"2409.15647","paper":"/paper/looped-transformers-for-length-generalization","title":"Looped Transformers for Length Generalization","date":"2024-09-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"UW-Madison-Lee-Lab/looped-tf","path":"src/transformers/activations_tf.py","file_url":"https://github.com/UW-Madison-Lee-Lab/looped-tf/blob/HEAD/src/transformers/activations_tf.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"e2d56cb91f999bef","mcp_get_code":{"code_sha256":"e2d56cb91f999bef"}},{"arxiv_id":"2407.07071","paper":"/paper/lookback-lens-detecting-and-mitigating","title":"Lookback Lens: Detecting and Mitigating Contextual Hallucinations in Large Language Models Using Only Attention Maps","date":"2024-07-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"voidism/lookback-lens","path":"transformers-4.32.0/src/transformers/activations_tf.py","file_url":"https://github.com/voidism/lookback-lens/blob/HEAD/transformers-4.32.0/src/transformers/activations_tf.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"e2d56cb91f999bef","mcp_get_code":{"code_sha256":"e2d56cb91f999bef"}},{"arxiv_id":"2407.01320","paper":"/paper/increasing-model-capacity-for-free-a-simple","title":"Increasing Model Capacity for Free: A Simple Strategy for Parameter Efficient Fine-tuning","date":"2024-07-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"LINs-lab/CapaBoost","path":"src/transformers/activations_tf.py","file_url":"https://github.com/LINs-lab/CapaBoost/blob/HEAD/src/transformers/activations_tf.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":"e2d56cb91f999bef","mcp_get_code":{"code_sha256":"e2d56cb91f999bef"}},{"arxiv_id":"2406.08332","paper":"/paper/udon-universal-dynamic-online-distillation","title":"UDON: Universal Dynamic Online distillatioN for generic image representations","date":"2024-06-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"nikosips/UDON","path":"universal_embedding/udon_clip_vit_with_embedding.py","file_url":"https://github.com/nikosips/UDON/blob/HEAD/universal_embedding/udon_clip_vit_with_embedding.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"387ba0de72d89d99","mcp_get_code":{"code_sha256":"387ba0de72d89d99"}},{"arxiv_id":"2406.02900","paper":"/paper/scaling-laws-for-reward-model-1","title":"Scaling Laws for Reward Model Overoptimization in Direct Alignment Algorithms","date":"2024-06-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"openai/summarize-from-feedback","path":"summarize_from_feedback/models/ops.py","file_url":"https://github.com/openai/summarize-from-feedback/blob/HEAD/summarize_from_feedback/models/ops.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"e21f72f1a9834aef","mcp_get_code":{"code_sha256":"e21f72f1a9834aef"}},{"arxiv_id":"2406.02395","paper":"/paper/grootvl-tree-topology-is-all-you-need-in","title":"GrootVL: Tree Topology is All You Need in State Space Model","date":"2024-06-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"easonxiao-888/grootvl","path":"GrootL/transformers/modeling_flax_utils.py","file_url":"https://github.com/easonxiao-888/grootvl/blob/HEAD/GrootL/transformers/modeling_flax_utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"a66d2b78670c85e1","mcp_get_code":{"code_sha256":"a66d2b78670c85e1"}},{"arxiv_id":"2404.19245","paper":"/paper/hydralora-an-asymmetric-lora-architecture-for","title":"HydraLoRA: An Asymmetric LoRA Architecture for Efficient Fine-Tuning","date":"2024-04-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"clin0212/hydralora","path":"HydraLoRA/transformers/modeling_flax_utils.py","file_url":"https://github.com/clin0212/hydralora/blob/HEAD/HydraLoRA/transformers/modeling_flax_utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"a66d2b78670c85e1","mcp_get_code":{"code_sha256":"a66d2b78670c85e1"}},{"arxiv_id":"2404.16367","paper":"/paper/learning-syntax-without-planting-trees","title":"Learning Syntax Without Planting Trees: Understanding When and Why Transformers Generalize Hierarchically","date":"2024-04-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"kabirahuja2431/transformers-hg","path":"transformers/src/transformers/activations_tf.py","file_url":"https://github.com/kabirahuja2431/transformers-hg/blob/HEAD/transformers/src/transformers/activations_tf.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"e2d56cb91f999bef","mcp_get_code":{"code_sha256":"e2d56cb91f999bef"}},{"arxiv_id":"2403.13263","paper":"/paper/sc-tune-unleashing-self-consistent","title":"SC-Tune: Unleashing Self-Consistent Referential Comprehension in Large Vision Language Models","date":"2024-03-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ivattyue/SC-Tune","path":"transformers/modeling_flax_utils.py","file_url":"https://github.com/ivattyue/SC-Tune/blob/HEAD/transformers/modeling_flax_utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a66d2b78670c85e1","mcp_get_code":{"code_sha256":"a66d2b78670c85e1"}},{"arxiv_id":"2403.10942","paper":"/paper/scantalk-3d-talking-heads-from-unregistered","title":"ScanTalk: 3D Talking Heads from Unregistered Scans","date":"2024-03-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"miccunifi/ScanTalk","path":"src/hubert/activations.py","file_url":"https://github.com/miccunifi/ScanTalk/blob/HEAD/src/hubert/activations.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"e21f72f1a9834aef","mcp_get_code":{"code_sha256":"e21f72f1a9834aef"}},{"arxiv_id":"2403.09766","paper":"/paper/an-image-is-worth-1000-lies-adversarial","title":"An Image Is Worth 1000 Lies: Adversarial Transferability across Prompts on Vision-Language Models","date":"2024-03-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Haochen-Luo/CroPA","path":"transformers/modeling_flax_utils.py","file_url":"https://github.com/Haochen-Luo/CroPA/blob/HEAD/transformers/modeling_flax_utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"a66d2b78670c85e1","mcp_get_code":{"code_sha256":"a66d2b78670c85e1"}},{"arxiv_id":"2402.18223","paper":"/paper/improving-open-ended-text-generation-via","title":"Improving Open-Ended Text Generation via Adaptive Decoding","date":"2024-02-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zwhong714/adaptive_decoding","path":"transformers-main/src/transformers/activations_tf.py","file_url":"https://github.com/zwhong714/adaptive_decoding/blob/HEAD/transformers-main/src/transformers/activations_tf.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"e2d56cb91f999bef","mcp_get_code":{"code_sha256":"e2d56cb91f999bef"}},{"arxiv_id":"2402.14789","paper":"/paper/self-guided-masked-autoencoders-for-domain","title":"Self-Guided Masked Autoencoders for Domain-Agnostic Self-Supervised Learning","date":"2024-02-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"johnathan-xie/sma","path":"src/transformers/activations_tf.py","file_url":"https://github.com/johnathan-xie/sma/blob/HEAD/src/transformers/activations_tf.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":"e2d56cb91f999bef","mcp_get_code":{"code_sha256":"e2d56cb91f999bef"}},{"arxiv_id":"2402.12656","paper":"/paper/hypermoe-towards-better-mixture-of-experts","title":"HyperMoE: Towards Better Mixture of Experts via Transferring Among Experts","date":"2024-02-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"bumble666/hypermoe_early_version","path":"gpt-2-moe/transformers/modeling_flax_utils.py","file_url":"https://github.com/bumble666/hypermoe_early_version/blob/HEAD/gpt-2-moe/transformers/modeling_flax_utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"a66d2b78670c85e1","mcp_get_code":{"code_sha256":"a66d2b78670c85e1"}},{"arxiv_id":"2402.05827","paper":"/paper/is-it-possible-to-edit-large-language-models","title":"On the Robustness of Editing Large Language Models","date":"2024-02-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"xbmxb/edit_analysis","path":"code/transformers/modeling_flax_utils.py","file_url":"https://github.com/xbmxb/edit_analysis/blob/HEAD/code/transformers/modeling_flax_utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"a66d2b78670c85e1","mcp_get_code":{"code_sha256":"a66d2b78670c85e1"}},{"arxiv_id":"2312.09979","paper":"/paper/the-art-of-balancing-revolutionizing-mixture","title":"LoRAMoE: Alleviate World Knowledge Forgetting in Large Language Models via MoE-Style Plugin","date":"2023-12-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ablustrund/loramoe","path":"transformers/modeling_flax_utils.py","file_url":"https://github.com/ablustrund/loramoe/blob/HEAD/transformers/modeling_flax_utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"a66d2b78670c85e1","mcp_get_code":{"code_sha256":"a66d2b78670c85e1"}},{"arxiv_id":"2311.07468","paper":"/paper/are-we-falling-in-a-middle-intelligence-trap","title":"An Analysis and Mitigation of the Reversal Curse","date":"2023-11-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"trestad/mitigating-reversal-curse","path":"transformers/src/transformers/activations_tf.py","file_url":"https://github.com/trestad/mitigating-reversal-curse/blob/HEAD/transformers/src/transformers/activations_tf.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"e2d56cb91f999bef","mcp_get_code":{"code_sha256":"e2d56cb91f999bef"}},{"arxiv_id":"2311.06761","paper":"/paper/learning-knowledge-enhanced-contextual","title":"Learning Knowledge-Enhanced Contextual Language Representations for Domain Natural Language Understanding","date":"2023-11-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"alibaba/EasyNLP","path":"easynlp/modelzoo/activations.py","file_url":"https://github.com/alibaba/EasyNLP/blob/HEAD/easynlp/modelzoo/activations.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"e21f72f1a9834aef","mcp_get_code":{"code_sha256":"e21f72f1a9834aef"}},{"arxiv_id":"2310.18738","paper":"/paper/tlm-token-level-masking-for-transformers","title":"TLM: Token-Level Masking for Transformers","date":"2023-10-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Young1993/tlm","path":"transformers/modeling_flax_utils.py","file_url":"https://github.com/Young1993/tlm/blob/HEAD/transformers/modeling_flax_utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"a66d2b78670c85e1","mcp_get_code":{"code_sha256":"a66d2b78670c85e1"}},{"arxiv_id":"2310.09832","paper":"/paper/merging-experts-into-one-improving","title":"Merging Experts into One: Improving Computational Efficiency of Mixture of Experts","date":"2023-10-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"shwai-he/meo","path":"transformers/modeling_flax_utils.py","file_url":"https://github.com/shwai-he/meo/blob/HEAD/transformers/modeling_flax_utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"a66d2b78670c85e1","mcp_get_code":{"code_sha256":"a66d2b78670c85e1"}},{"arxiv_id":"2310.05107","paper":"/paper/ov-parts-towards-open-vocabulary-part","title":"OV-PARTS: Towards Open-Vocabulary Part Segmentation","date":"2023-10-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"openrobotlab/ov_parts","path":"transformers/modeling_flax_utils.py","file_url":"https://github.com/openrobotlab/ov_parts/blob/HEAD/transformers/modeling_flax_utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"a66d2b78670c85e1","mcp_get_code":{"code_sha256":"a66d2b78670c85e1"}},{"arxiv_id":"2305.15756","paper":"/paper/unitrec-a-unified-text-to-text-transformer","title":"UniTRec: A Unified Text-to-Text Transformer and Joint Contrastive Learning Framework for Text-based Recommendation","date":"2023-05-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"veason-silverbullet/unitrec","path":"transformers/modeling_flax_utils.py","file_url":"https://github.com/veason-silverbullet/unitrec/blob/HEAD/transformers/modeling_flax_utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a66d2b78670c85e1","mcp_get_code":{"code_sha256":"a66d2b78670c85e1"}},{"arxiv_id":"2305.10614","paper":"/paper/token-wise-decomposition-of-autoregressive","title":"Token-wise Decomposition of Autoregressive Language Model Hidden States for Analyzing Model Predictions","date":"2023-05-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"byungdoh/llm_decomposition","path":"huggingface/src/transformers/activations_tf.py","file_url":"https://github.com/byungdoh/llm_decomposition/blob/HEAD/huggingface/src/transformers/activations_tf.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":"e2d56cb91f999bef","mcp_get_code":{"code_sha256":"e2d56cb91f999bef"}},{"arxiv_id":"2303.14582","paper":"/paper/identification-of-negative-transfers-in","title":"Identification of Negative Transfers in Multitask Learning Using Surrogate Models","date":"2023-03-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"neu-statsml-research/task-modeling","path":"transformers/modeling_flax_utils.py","file_url":"https://github.com/neu-statsml-research/task-modeling/blob/HEAD/transformers/modeling_flax_utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a66d2b78670c85e1","mcp_get_code":{"code_sha256":"a66d2b78670c85e1"}},{"arxiv_id":"2301.12132","paper":"/paper/autopeft-automatic-configuration-search-for","title":"AutoPEFT: Automatic Configuration Search for Parameter-Efficient Fine-Tuning","date":"2023-01-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"cambridgeltl/autopeft","path":"adapter-transformers-adapters3.1.0/src/transformers/activations_tf.py","file_url":"https://github.com/cambridgeltl/autopeft/blob/HEAD/adapter-transformers-adapters3.1.0/src/transformers/activations_tf.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":false,"code_sha256_prefix":"e2d56cb91f999bef","mcp_get_code":{"code_sha256":"e2d56cb91f999bef"}},{"arxiv_id":"2212.11185","paper":"/paper/entropy-and-distance-based-predictors-from","title":"Entropy- and Distance-Based Predictors From GPT-2 Attention Patterns Predict Reading Times Over and Above GPT-2 Surprisal","date":"2022-12-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"byungdoh/attn_dist","path":"huggingface/src/transformers/activations_tf.py","file_url":"https://github.com/byungdoh/attn_dist/blob/HEAD/huggingface/src/transformers/activations_tf.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":"e2d56cb91f999bef","mcp_get_code":{"code_sha256":"e2d56cb91f999bef"}},{"arxiv_id":"2212.00921","paper":"/paper/agro-adversarial-discovery-of-error-prone","title":"AGRO: Adversarial Discovery of Error-prone groups for Robust Optimization","date":"2022-12-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"bhargaviparanjape/robust-transformers","path":"src/transformers/activations_tf.py","file_url":"https://github.com/bhargaviparanjape/robust-transformers/blob/HEAD/src/transformers/activations_tf.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":false,"code_sha256_prefix":"e2d56cb91f999bef","mcp_get_code":{"code_sha256":"e2d56cb91f999bef"}},{"arxiv_id":"2211.05392","paper":"/paper/events-realm-event-reasoning-of-entity-states","title":"EvEntS ReaLM: Event Reasoning of Entity States via Language Models","date":"2022-11-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"spilioeve/eventsrealm","path":"transformers-single-all-attribute-prompt-experiments/src/transformers/activations_tf.py","file_url":"https://github.com/spilioeve/eventsrealm/blob/HEAD/transformers-single-all-attribute-prompt-experiments/src/transformers/activations_tf.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e2d56cb91f999bef","mcp_get_code":{"code_sha256":"e2d56cb91f999bef"}},{"arxiv_id":"2202.00666","paper":"/paper/typical-decoding-for-natural-language","title":"Locally Typical Sampling","date":"2022-02-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"cimeister/typical-sampling","path":"src/transformers/activations_tf.py","file_url":"https://github.com/cimeister/typical-sampling/blob/HEAD/src/transformers/activations_tf.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":false,"code_sha256_prefix":"e2d56cb91f999bef","mcp_get_code":{"code_sha256":"e2d56cb91f999bef"}},{"arxiv_id":"2111.05498","paper":"/paper/attention-approximates-sparse-distributed","title":"Attention Approximates Sparse Distributed Memory","date":"2021-11-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"trentbrick/attention-approximates-sdm","path":"HugFace/src/transformers/activations.py","file_url":"https://github.com/trentbrick/attention-approximates-sdm/blob/HEAD/HugFace/src/transformers/activations.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e21f72f1a9834aef","mcp_get_code":{"code_sha256":"e21f72f1a9834aef"}},{"arxiv_id":"2111.00160","paper":"/paper/dsee-dually-sparsity-embedded-efficient-1","title":"DSEE: Dually Sparsity-embedded Efficient Tuning of Pre-trained Language Models","date":"2021-10-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"vita-group/dsee","path":"non-GPT-2/src/transformers/activations.py","file_url":"https://github.com/vita-group/dsee/blob/HEAD/non-GPT-2/src/transformers/activations.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e21f72f1a9834aef","mcp_get_code":{"code_sha256":"e21f72f1a9834aef"}},{"arxiv_id":"2110.04366","paper":"/paper/towards-a-unified-view-of-parameter-efficient-1","title":"Towards a Unified View of Parameter-Efficient Transfer Learning","date":"2021-10-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jxhe/unify-parameter-efficient-tuning","path":"src/transformers/activations.py","file_url":"https://github.com/jxhe/unify-parameter-efficient-tuning/blob/HEAD/src/transformers/activations.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":false,"code_sha256_prefix":"e21f72f1a9834aef","mcp_get_code":{"code_sha256":"e21f72f1a9834aef"}},{"arxiv_id":"2007.07779","paper":"/paper/adapterhub-a-framework-for-adapting","title":"AdapterHub: A Framework for Adapting Transformers","date":"2020-07-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"adapter-hub/adapter-transformers-legacy","path":"src/transformers/activations_tf.py","file_url":"https://github.com/adapter-hub/adapter-transformers-legacy/blob/HEAD/src/transformers/activations_tf.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":false,"code_sha256_prefix":"e2d56cb91f999bef","mcp_get_code":{"code_sha256":"e2d56cb91f999bef"}},{"arxiv_id":"2024.findings-naacl.117","paper":null,"title":"arXiv:2024.findings-naacl.117","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"qqplot/dcpmi","path":"transformers/src/transformers/activations_tf.py","file_url":"https://github.com/qqplot/dcpmi/blob/HEAD/transformers/src/transformers/activations_tf.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e2d56cb91f999bef","mcp_get_code":{"code_sha256":"e2d56cb91f999bef"}},{"arxiv_id":"2022.naacl-main.130","paper":null,"title":"arXiv:2022.naacl-main.130","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"parovicm/BADX","path":"src/transformers/activations.py","file_url":"https://github.com/parovicm/BADX/blob/HEAD/src/transformers/activations.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"e21f72f1a9834aef","mcp_get_code":{"code_sha256":"e21f72f1a9834aef"}},{"arxiv_id":"2022.findings-emnlp.427","paper":null,"title":"arXiv:2022.findings-emnlp.427","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"kgarg8/FullTextKP","path":"transformers/modeling_flax_utils.py","file_url":"https://github.com/kgarg8/FullTextKP/blob/HEAD/transformers/modeling_flax_utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a66d2b78670c85e1","mcp_get_code":{"code_sha256":"a66d2b78670c85e1"}}]}