{"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/rmsnorm-func","entry":"rmsnorm_func","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":9,"n_papers_ran":2,"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":1,"n_samples_fingerprinted":1,"n_places":9,"n_places_pointer_only":2,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":1,"ran_fixture":0,"ran":0,"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":"2604.07394","paper":"/paper/arxiv-2604-07394","title":"Flux Attention: Context-Aware Hybrid Attention for Efficient LLMs Inference","date":null,"month_inferred_from_arxiv_id":"2026-04","title_source":"syntology","repo":"qqtang-code/FluxAttention","path":"fluxattn/training/eval/modeling_flash_llama.py","file_url":"https://github.com/qqtang-code/FluxAttention/blob/HEAD/fluxattn/training/eval/modeling_flash_llama.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"349dce8e37362617","mcp_get_code":{"code_sha256":"349dce8e37362617"}},{"arxiv_id":"2602.05258","paper":"/paper/arxiv-2602-05258","title":"CoPE: Clipped RoPE as A Scalable Free Lunch for Long Context LLMs","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"hrlics/CoPE","path":"train/training/modeling_flash_llama_cope.py","file_url":"https://github.com/hrlics/CoPE/blob/HEAD/train/training/modeling_flash_llama_cope.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"ab6fba34dd3815d7","mcp_get_code":{"code_sha256":"ab6fba34dd3815d7"}},{"arxiv_id":"2410.05076","paper":"/paper/tidaldecode-fast-and-accurate-llm-decoding","title":"TidalDecode: Fast and Accurate LLM Decoding with Position Persistent Sparse Attention","date":"2024-10-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"DerrickYLJ/TidalDecode","path":"src/models/yarn_tidaldecoding.py","file_url":"https://github.com/DerrickYLJ/TidalDecode/blob/HEAD/src/models/yarn_tidaldecoding.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":"ab6fba34dd3815d7","mcp_get_code":{"code_sha256":"ab6fba34dd3815d7"}},{"arxiv_id":"2410.02660","paper":"/paper/how-to-train-long-context-language-models","title":"How to Train Long-Context Language Models (Effectively)","date":"2024-10-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"princeton-nlp/prolong","path":"training/modeling_flash_llama.py","file_url":"https://github.com/princeton-nlp/prolong/blob/HEAD/training/modeling_flash_llama.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"ab6fba34dd3815d7","mcp_get_code":{"code_sha256":"ab6fba34dd3815d7"}},{"arxiv_id":"2402.09739","paper":"/paper/qurating-selecting-high-quality-data-for","title":"QuRating: Selecting High-Quality Data for Training Language Models","date":"2024-02-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"princeton-nlp/qurating","path":"modeling/modeling_flash_llama.py","file_url":"https://github.com/princeton-nlp/qurating/blob/HEAD/modeling/modeling_flash_llama.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"ab6fba34dd3815d7","mcp_get_code":{"code_sha256":"ab6fba34dd3815d7"}},{"arxiv_id":"2312.15166","paper":"/paper/solar-10-7b-scaling-large-language-models","title":"SOLAR 10.7B: Scaling Large Language Models with Simple yet Effective Depth Up-Scaling","date":"2023-12-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jquesnelle/scaled-rope","path":"scaled_rope/modeling_llama_together_yarn.py","file_url":"https://github.com/jquesnelle/scaled-rope/blob/HEAD/scaled_rope/modeling_llama_together_yarn.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"ab6fba34dd3815d7","mcp_get_code":{"code_sha256":"ab6fba34dd3815d7"}},{"arxiv_id":"2310.03668","paper":"/paper/gollie-annotation-guidelines-improve-zero","title":"GoLLIE: Annotation Guidelines improve Zero-Shot Information-Extraction","date":"2023-10-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hitz-zentroa/gollie","path":"src/model/patch_models/modeling_flash_llama.py","file_url":"https://github.com/hitz-zentroa/gollie/blob/HEAD/src/model/patch_models/modeling_flash_llama.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"349dce8e37362617","mcp_get_code":{"code_sha256":"349dce8e37362617"}},{"arxiv_id":"openreview_trSWJ99WzS","paper":null,"title":"arXiv:openreview_trSWJ99WzS","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"DerrickYLJ/LessIsMore","path":"src/models/yarn_tidaldecoding.py","file_url":"https://github.com/DerrickYLJ/LessIsMore/blob/HEAD/src/models/yarn_tidaldecoding.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":"ab6fba34dd3815d7","mcp_get_code":{"code_sha256":"ab6fba34dd3815d7"}},{"arxiv_id":"2025.acl-long.366","paper":null,"title":"arXiv:2025.acl-long.366","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"princeton-nlp/ProLong","path":"training/modeling_flash_llama.py","file_url":"https://github.com/princeton-nlp/ProLong/blob/HEAD/training/modeling_flash_llama.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"ab6fba34dd3815d7","mcp_get_code":{"code_sha256":"ab6fba34dd3815d7"}}]}