{"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/llamarotaryembedding","entry":"LlamaRotaryEmbedding","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":13,"n_papers_ran":12,"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":13,"n_samples_ran":12,"n_samples_fingerprinted":7,"n_places":13,"n_places_pointer_only":5,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":12,"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":"2601.21444","paper":"/paper/arxiv-2601-21444","title":"APB-V: Accelerating Long-Video Understanding via Sequence-Parallelism-aware Approximate Attention","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"thunlp/APB","path":"experiments_apb/APB/modeling_llama_locret.py","file_url":"https://github.com/thunlp/APB/blob/HEAD/experiments_apb/APB/modeling_llama_locret.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"c547d4b763b0772a","mcp_get_code":{"code_sha256":"c547d4b763b0772a"}},{"arxiv_id":"2507.01900","paper":null,"title":"arXiv:2507.01900","date":null,"month_inferred_from_arxiv_id":"2025-07","title_source":null,"repo":"SongtaoLiu0823/HARP","path":"models/modeling_llama_drop_qk.py","file_url":"https://github.com/SongtaoLiu0823/HARP/blob/HEAD/models/modeling_llama_drop_qk.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"e6fa61d9471c6f8f","mcp_get_code":{"code_sha256":"e6fa61d9471c6f8f"}},{"arxiv_id":"2503.12340","paper":"/paper/svd-llm-v2-optimizing-singular-value","title":"SVD-LLM V2: Optimizing Singular Value Truncation for Large Language Model Compression","date":"2025-03-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"aiot-mlsys-lab/svd-llm","path":"SVDLLM.py","file_url":"https://github.com/aiot-mlsys-lab/svd-llm/blob/HEAD/SVDLLM.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"c4daf2f7ed4b51f9","mcp_get_code":{"code_sha256":"c4daf2f7ed4b51f9"}},{"arxiv_id":"2502.13533","paper":"/paper/train-small-infer-large-memory-efficient-lora","title":"Train Small, Infer Large: Memory-Efficient LoRA Training for Large Language Models","date":"2025-02-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"junzhang-zj/LoRAM","path":"loram/2_pruned_low_rank_matrix_training.py","file_url":"https://github.com/junzhang-zj/LoRAM/blob/HEAD/loram/2_pruned_low_rank_matrix_training.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"c9f2757f0827b802","mcp_get_code":{"code_sha256":"c9f2757f0827b802"}},{"arxiv_id":"2502.12623","paper":"/paper/deepresonance-enhancing-multimodal-music","title":"DeepResonance: Enhancing Multimodal Music Understanding via Music-centric Multi-way Instruction Tuning","date":"2025-02-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"sony/DeepResonance","path":"code/model/deepresonance.py","file_url":"https://github.com/sony/DeepResonance/blob/HEAD/code/model/deepresonance.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"5f256ecadc2081af","mcp_get_code":{"code_sha256":"5f256ecadc2081af"}},{"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":"7541f97d86797bda","mcp_get_code":{"code_sha256":"7541f97d86797bda"}},{"arxiv_id":"2410.03115","paper":"/paper/x-alma-plug-play-modules-and-adaptive","title":"X-ALMA: Plug & Play Modules and Adaptive Rejection for Quality Translation at Scale","date":"2024-10-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"fe1ixxu/ALMA","path":"modeling_xalma.py","file_url":"https://github.com/fe1ixxu/ALMA/blob/HEAD/modeling_xalma.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"18df0f479941cc0b","mcp_get_code":{"code_sha256":"18df0f479941cc0b"}},{"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":"a847c3e201c31fbe","mcp_get_code":{"code_sha256":"a847c3e201c31fbe"}},{"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":"5151d2a6b2115e55","mcp_get_code":{"code_sha256":"5151d2a6b2115e55"}},{"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":"deterministic","behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"29fb31107100b259","mcp_get_code":{"code_sha256":"29fb31107100b259"}},{"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":"88c615c48b7dd37b","mcp_get_code":{"code_sha256":"88c615c48b7dd37b"}},{"arxiv_id":"2307.09288","paper":"/paper/llama-2-open-foundation-and-fine-tuned-chat","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","date":"2023-07-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"meetyou-ai-lab/can-mc-evaluate-llms","path":"Embeddings/src/llama/modeling_llama.py","file_url":"https://github.com/meetyou-ai-lab/can-mc-evaluate-llms/blob/HEAD/Embeddings/src/llama/modeling_llama.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"26ec53f064adbca5","mcp_get_code":{"code_sha256":"26ec53f064adbca5"}},{"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":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"580c588511c469d9","mcp_get_code":{"code_sha256":"580c588511c469d9"}}]}