{"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/llamadynamicntkscalingrotaryembedding","entry":"LlamaDynamicNTKScalingRotaryEmbedding","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":6,"n_papers_ran":6,"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":6,"n_samples_ran":6,"n_samples_fingerprinted":3,"n_places":6,"n_places_pointer_only":3,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":6,"unverified":0},"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":"2412.00876","paper":"/paper/dynamic-llava-efficient-multimodal-large","title":"Dynamic-LLaVA: Efficient Multimodal Large Language Models via Dynamic Vision-language Context Sparsification","date":"2024-12-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"osilly/dynamic_llava","path":"llava/model/language_model/dynamic_modeling_llama.py","file_url":"https://github.com/osilly/dynamic_llava/blob/HEAD/llava/model/language_model/dynamic_modeling_llama.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"68bd42b9c09a9dd1","mcp_get_code":{"code_sha256":"68bd42b9c09a9dd1"}},{"arxiv_id":"2407.03157","paper":"/paper/let-the-code-llm-edit-itself-when-you-edit","title":"Let the Code LLM Edit Itself When You Edit the Code","date":"2024-07-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zhenyuhe00/PIE","path":"my_modeling_llama_recomputedynamic.py","file_url":"https://github.com/zhenyuhe00/PIE/blob/HEAD/my_modeling_llama_recomputedynamic.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"67620ba8e35fd76d","mcp_get_code":{"code_sha256":"67620ba8e35fd76d"}},{"arxiv_id":"2406.12335","paper":"/paper/attention-score-is-not-all-you-need-for-token","title":"Attention Score is not All You Need for Token Importance Indicator in KV Cache Reduction: Value Also Matters","date":"2024-06-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"guozhiyu/vatp","path":"utils_hh/modify_llama.py","file_url":"https://github.com/guozhiyu/vatp/blob/HEAD/utils_hh/modify_llama.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"3613d71443ec2450","mcp_get_code":{"code_sha256":"3613d71443ec2450"}},{"arxiv_id":"2402.14905","paper":"/paper/mobilellm-optimizing-sub-billion-parameter","title":"MobileLLM: Optimizing Sub-billion Parameter Language Models for On-Device Use Cases","date":"2024-02-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"facebookresearch/mobilellm","path":"utils/modeling_llama.py","file_url":"https://github.com/facebookresearch/mobilellm/blob/HEAD/utils/modeling_llama.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"a70d6d3c2afe50fe","mcp_get_code":{"code_sha256":"a70d6d3c2afe50fe"}},{"arxiv_id":"2402.01469","paper":"/paper/amor-a-recipe-for-building-adaptable-modular","title":"AMOR: A Recipe for Building Adaptable Modular Knowledge Agents Through Process Feedback","date":"2024-02-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jianguanthu/amor","path":"code/manager.py","file_url":"https://github.com/jianguanthu/amor/blob/HEAD/code/manager.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"572dde6105d00036","mcp_get_code":{"code_sha256":"572dde6105d00036"}},{"arxiv_id":"2203.08913","paper":"/paper/memorizing-transformers-1","title":"Memorizing Transformers","date":"2022-03-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"normal-computing/extended-mind-transformers","path":"src/llama/modeling.py","file_url":"https://github.com/normal-computing/extended-mind-transformers/blob/HEAD/src/llama/modeling.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":"b90643346c166065","mcp_get_code":{"code_sha256":"b90643346c166065"}}]}