{"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/llamaconfig","entry":"LlamaConfig","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":0,"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":"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":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"f9a174e38fa49463","mcp_get_code":{"code_sha256":"f9a174e38fa49463"}},{"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":"4607ba91049415cf","mcp_get_code":{"code_sha256":"4607ba91049415cf"}},{"arxiv_id":"2502.17599","paper":"/paper/meda-dynamic-kv-cache-allocation-for","title":"MEDA: Dynamic KV Cache Allocation for Efficient Multimodal Long-Context Inference","date":"2025-02-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"aiot-mlsys-lab/meda","path":"Dynamic-MLLMs/LLaVA-mix_merge_v1/llava/model/kv_token_merge/modify_llama.py","file_url":"https://github.com/aiot-mlsys-lab/meda/blob/HEAD/Dynamic-MLLMs/LLaVA-mix_merge_v1/llava/model/kv_token_merge/modify_llama.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"2e14541ab89507cc","mcp_get_code":{"code_sha256":"2e14541ab89507cc"}},{"arxiv_id":"2402.15220","paper":"/paper/chunkattention-efficient-self-attention-with","title":"ChunkAttention: Efficient Self-Attention with Prefix-Aware KV Cache and Two-Phase Partition","date":"2024-02-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"microsoft/chunk-attention","path":"src/chunk_attn/models/llama_hf/modeling_llama.py","file_url":"https://github.com/microsoft/chunk-attention/blob/HEAD/src/chunk_attn/models/llama_hf/modeling_llama.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"72f120426b530e6b","mcp_get_code":{"code_sha256":"72f120426b530e6b"}},{"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":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"eae5ddb4e89f48a1","mcp_get_code":{"code_sha256":"eae5ddb4e89f48a1"}},{"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":"1bcd8d227ad19b17","mcp_get_code":{"code_sha256":"1bcd8d227ad19b17"}}]}