{"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/flax-shard-checkpoint","entry":"flax_shard_checkpoint","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":15,"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":2,"n_samples_ran":0,"n_samples_fingerprinted":0,"n_places":15,"n_places_pointer_only":8,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":0,"unverified":2},"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":"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":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e3ce70ca9258800e","mcp_get_code":{"code_sha256":"e3ce70ca9258800e"}},{"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":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"80d41fe6d81de3dd","mcp_get_code":{"code_sha256":"80d41fe6d81de3dd"}},{"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":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"e3ce70ca9258800e","mcp_get_code":{"code_sha256":"e3ce70ca9258800e"}},{"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":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"80d41fe6d81de3dd","mcp_get_code":{"code_sha256":"80d41fe6d81de3dd"}},{"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":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"e3ce70ca9258800e","mcp_get_code":{"code_sha256":"e3ce70ca9258800e"}},{"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":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"e3ce70ca9258800e","mcp_get_code":{"code_sha256":"e3ce70ca9258800e"}},{"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":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e3ce70ca9258800e","mcp_get_code":{"code_sha256":"e3ce70ca9258800e"}},{"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":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"e3ce70ca9258800e","mcp_get_code":{"code_sha256":"e3ce70ca9258800e"}},{"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":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"e3ce70ca9258800e","mcp_get_code":{"code_sha256":"e3ce70ca9258800e"}},{"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":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"e3ce70ca9258800e","mcp_get_code":{"code_sha256":"e3ce70ca9258800e"}},{"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":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"e3ce70ca9258800e","mcp_get_code":{"code_sha256":"e3ce70ca9258800e"}},{"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":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"e3ce70ca9258800e","mcp_get_code":{"code_sha256":"e3ce70ca9258800e"}},{"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":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"e3ce70ca9258800e","mcp_get_code":{"code_sha256":"e3ce70ca9258800e"}},{"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":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"e3ce70ca9258800e","mcp_get_code":{"code_sha256":"e3ce70ca9258800e"}},{"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":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e3ce70ca9258800e","mcp_get_code":{"code_sha256":"e3ce70ca9258800e"}}]}