{"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/llamaattention","entry":"LlamaAttention","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":4,"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":16,"n_samples_ran":4,"n_samples_fingerprinted":2,"n_places":16,"n_places_pointer_only":6,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":4,"unverified":12},"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":"2604.21649","paper":"/paper/arxiv-2604-21649","title":"GS-Quant: Granular Semantic and Generative Structural Quantization for Knowledge Graph Completion","date":null,"month_inferred_from_arxiv_id":"2026-04","title_source":"syntology","repo":"mikumifa/GS-Quant","path":"codebook/rqvae.py","file_url":"https://github.com/mikumifa/GS-Quant/blob/HEAD/codebook/rqvae.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":"de06c2e189aa7a3f","mcp_get_code":{"code_sha256":"de06c2e189aa7a3f"}},{"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":"f73e0032142662c6","mcp_get_code":{"code_sha256":"f73e0032142662c6"}},{"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":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"da27c3489fa94e64","mcp_get_code":{"code_sha256":"da27c3489fa94e64"}},{"arxiv_id":"2503.13108","paper":"/paper/lifting-the-veil-on-visual-information-flow","title":"Lifting the Veil on Visual Information Flow in MLLMs: Unlocking Pathways to Faster Inference","date":"2025-03-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ustc-hyin/HiMAP","path":"src/LLaVA/llava/model/language_model/himap.py","file_url":"https://github.com/ustc-hyin/HiMAP/blob/HEAD/src/LLaVA/llava/model/language_model/himap.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"b782c56a6374b40d","mcp_get_code":{"code_sha256":"b782c56a6374b40d"}},{"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":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"9dee9df76b1fdd21","mcp_get_code":{"code_sha256":"9dee9df76b1fdd21"}},{"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":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"586f7e54af865636","mcp_get_code":{"code_sha256":"586f7e54af865636"}},{"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":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"64c5b45fc73cecfd","mcp_get_code":{"code_sha256":"64c5b45fc73cecfd"}},{"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":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"2f90acc30c03054d","mcp_get_code":{"code_sha256":"2f90acc30c03054d"}},{"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":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"02658020404dcd81","mcp_get_code":{"code_sha256":"02658020404dcd81"}},{"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":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"f7eec176aae368de","mcp_get_code":{"code_sha256":"f7eec176aae368de"}},{"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/LLM-QAT","path":"models/modeling_llama_quant.py","file_url":"https://github.com/facebookresearch/LLM-QAT/blob/HEAD/models/modeling_llama_quant.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"ae14385b5684f28e","mcp_get_code":{"code_sha256":"ae14385b5684f28e"}},{"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":"6bfe6fa28a5de901","mcp_get_code":{"code_sha256":"6bfe6fa28a5de901"}},{"arxiv_id":"2401.16421","paper":"/paper/two-stones-hit-one-bird-bilevel-positional","title":"Two Stones Hit One Bird: Bilevel Positional Encoding for Better Length Extrapolation","date":"2024-01-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zhenyuhe00/bipe","path":"my_modeling_llama_bipe_alibi.py","file_url":"https://github.com/zhenyuhe00/bipe/blob/HEAD/my_modeling_llama_bipe_alibi.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"f550f6737f3c0ff4","mcp_get_code":{"code_sha256":"f550f6737f3c0ff4"}},{"arxiv_id":"2401.07159","paper":"/paper/quantized-side-tuning-fast-and-memory","title":"Quantized Side Tuning: Fast and Memory-Efficient Tuning of Quantized Large Language Models","date":"2024-01-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"youarespecialtome/qst","path":"modeling_llama_qst.py","file_url":"https://github.com/youarespecialtome/qst/blob/HEAD/modeling_llama_qst.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":"49bff92fc40bac47","mcp_get_code":{"code_sha256":"49bff92fc40bac47"}},{"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":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"04267dd6afc2cfd2","mcp_get_code":{"code_sha256":"04267dd6afc2cfd2"}},{"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":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"1104581ac75ea9c6","mcp_get_code":{"code_sha256":"1104581ac75ea9c6"}}]}