{"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/llamarmsnorm","entry":"LlamaRMSNorm","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":9,"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":9,"n_samples_ran":9,"n_samples_fingerprinted":0,"n_places":9,"n_places_pointer_only":3,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":9,"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":"2602.19113","paper":"/paper/arxiv-2602-19113","title":"Learning from Complexity: Exploring Dynamic Sample Pruning of Spatio-Temporal Training","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"HKUDS/OpenCity","path":"model/OpenCity/OpenCity.py","file_url":"https://github.com/HKUDS/OpenCity/blob/HEAD/model/OpenCity/OpenCity.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"3e97aa6dae556601","mcp_get_code":{"code_sha256":"3e97aa6dae556601"}},{"arxiv_id":"2505.18853","paper":"/paper/smoothie-smoothing-diffusion-on-token","title":"Smoothie: Smoothing Diffusion on Token Embeddings for Text Generation","date":"2025-05-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ashaba1in/smoothie","path":"model/score_estimator.py","file_url":"https://github.com/ashaba1in/smoothie/blob/HEAD/model/score_estimator.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"cdb9860741882c48","mcp_get_code":{"code_sha256":"cdb9860741882c48"}},{"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":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"9f7bd959c5fde990","mcp_get_code":{"code_sha256":"9f7bd959c5fde990"}},{"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":"ef0f3d688eac1213","mcp_get_code":{"code_sha256":"ef0f3d688eac1213"}},{"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":"b601acb1c084205e","mcp_get_code":{"code_sha256":"b601acb1c084205e"}},{"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":"50ff7976d78544ac","mcp_get_code":{"code_sha256":"50ff7976d78544ac"}},{"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","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"3e5e1a1a6ae02184","mcp_get_code":{"code_sha256":"3e5e1a1a6ae02184"}},{"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":"98b6bb174c074dae","mcp_get_code":{"code_sha256":"98b6bb174c074dae"}},{"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":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"90915865fd797169","mcp_get_code":{"code_sha256":"90915865fd797169"}}]}