{"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/write-model","entry":"write_model","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":0,"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":11,"n_samples_ran":0,"n_samples_fingerprinted":0,"n_places":17,"n_places_pointer_only":9,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":0,"unverified":11},"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":"2503.06881","paper":"/paper/resmoe-space-efficient-compression-of-mixture","title":"ResMoE: Space-efficient Compression of Mixture of Experts LLMs via Residual Restoration","date":"2025-03-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"idea-isail-lab-uiuc/resmoe","path":"mixtral/resmoe_mixtral/convert_mixtral_weights_to_hf.py","file_url":"https://github.com/idea-isail-lab-uiuc/resmoe/blob/HEAD/mixtral/resmoe_mixtral/convert_mixtral_weights_to_hf.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"ee2001e1c7496dc4","mcp_get_code":{"code_sha256":"ee2001e1c7496dc4"}},{"arxiv_id":"2410.02184","paper":"/paper/codejudge-evaluating-code-generation-with","title":"CodeJudge: Evaluating Code Generation with Large Language Models","date":"2024-10-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"VichyTong/CodeJudge","path":"evaluation/model/convert_llama_weights_to_hf.py","file_url":"https://github.com/VichyTong/CodeJudge/blob/HEAD/evaluation/model/convert_llama_weights_to_hf.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":"5f56e1f4e5b6ba8c","mcp_get_code":{"code_sha256":"5f56e1f4e5b6ba8c"}},{"arxiv_id":"2409.17504","paper":"/paper/haloscope-harnessing-unlabeled-llm","title":"HaloScope: Harnessing Unlabeled LLM Generations for Hallucination Detection","date":"2024-09-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"deeplearning-wisc/haloscope","path":"llama_iti/convert_llama_weights_to_hf.py","file_url":"https://github.com/deeplearning-wisc/haloscope/blob/HEAD/llama_iti/convert_llama_weights_to_hf.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"4681d3d61616d9e0","mcp_get_code":{"code_sha256":"4681d3d61616d9e0"}},{"arxiv_id":"2406.18200","paper":"/paper/seed-accelerating-reasoning-tree-construction","title":"SEED: Accelerating Reasoning Tree Construction via Scheduled Speculative Decoding","date":"2024-06-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Linking-ai/SEED","path":"src/llama_tree_attn/convert_llama_weights_to_hf.py","file_url":"https://github.com/Linking-ai/SEED/blob/HEAD/src/llama_tree_attn/convert_llama_weights_to_hf.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"731285361b7dea0e","mcp_get_code":{"code_sha256":"731285361b7dea0e"}},{"arxiv_id":"2406.05317","paper":"/paper/lococo-dropping-in-convolutions-for-long","title":"LoCoCo: Dropping In Convolutions for Long Context Compression","date":"2024-06-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"VITA-Group/LoCoCo","path":"llama/convert_llama_weights_to_hf.py","file_url":"https://github.com/VITA-Group/LoCoCo/blob/HEAD/llama/convert_llama_weights_to_hf.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"b91ba72f3b013e76","mcp_get_code":{"code_sha256":"b91ba72f3b013e76"}},{"arxiv_id":"2405.19298","paper":"/paper/adaptive-image-quality-assessment-via","title":"Adaptive Image Quality Assessment via Teaching Large Multimodal Model to Compare","date":"2024-05-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Q-Future/Compare2Score","path":"q_align/model/convert_mplug_owl2_weight_to_hf.py","file_url":"https://github.com/Q-Future/Compare2Score/blob/HEAD/q_align/model/convert_mplug_owl2_weight_to_hf.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"c40b2d63fc02cac4","mcp_get_code":{"code_sha256":"c40b2d63fc02cac4"}},{"arxiv_id":"2405.13053","paper":"/paper/meteora-multiple-tasks-embedded-lora-for","title":"MeteoRA: Multiple-tasks Embedded LoRA for Large Language Models","date":"2024-05-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"paragonlight/meteor-of-lora","path":"base_model/llama/convert_llama_meteor_weights_to_hf.py","file_url":"https://github.com/paragonlight/meteor-of-lora/blob/HEAD/base_model/llama/convert_llama_meteor_weights_to_hf.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"b91ba72f3b013e76","mcp_get_code":{"code_sha256":"b91ba72f3b013e76"}},{"arxiv_id":"2404.03196","paper":"/paper/okay-let-s-do-this-modeling-event-coreference","title":"Okay, Let's Do This! Modeling Event Coreference with Generated Rationales and Knowledge Distillation","date":"2024-04-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"csu-signal/llama_cdcr","path":"convert_llama_weights_to_hf.py","file_url":"https://github.com/csu-signal/llama_cdcr/blob/HEAD/convert_llama_weights_to_hf.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"4b597d1b6e00be58","mcp_get_code":{"code_sha256":"4b597d1b6e00be58"}},{"arxiv_id":"2402.16061","paper":"/paper/how-large-language-models-encode-context","title":"How Large Language Models Encode Context Knowledge? A Layer-Wise Probing Study","date":"2024-02-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jometeorie/probing_llama","path":"code/llama/convert_llama_weights_to_hf.py","file_url":"https://github.com/jometeorie/probing_llama/blob/HEAD/code/llama/convert_llama_weights_to_hf.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"731285361b7dea0e","mcp_get_code":{"code_sha256":"731285361b7dea0e"}},{"arxiv_id":"2402.16061","paper":"/paper/how-large-language-models-encode-context","title":"How Large Language Models Encode Context Knowledge? A Layer-Wise Probing Study","date":"2024-02-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jometeorie/probing_llama","path":"code/custom_llama/convert_llama_weights_to_hf.py","file_url":"https://github.com/jometeorie/probing_llama/blob/HEAD/code/custom_llama/convert_llama_weights_to_hf.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"cfeea96bf995824a","mcp_get_code":{"code_sha256":"cfeea96bf995824a"}},{"arxiv_id":"2402.01618","paper":"/paper/style-vectors-for-steering-generative-large","title":"Style Vectors for Steering Generative Large Language Model","date":"2024-02-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"dlr-sc/style-vectors-for-steering-llms","path":"utils/convert_llama_weights_to_hf.py","file_url":"https://github.com/dlr-sc/style-vectors-for-steering-llms/blob/HEAD/utils/convert_llama_weights_to_hf.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"cfeea96bf995824a","mcp_get_code":{"code_sha256":"cfeea96bf995824a"}},{"arxiv_id":"2401.06706","paper":"/paper/multi-candidate-speculative-decoding","title":"Multi-Candidate Speculative Decoding","date":"2024-01-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"njunlp/mcsd","path":"MCSD/model/llama_tree_attn/convert_llama_weights_to_hf.py","file_url":"https://github.com/njunlp/mcsd/blob/HEAD/MCSD/model/llama_tree_attn/convert_llama_weights_to_hf.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"731285361b7dea0e","mcp_get_code":{"code_sha256":"731285361b7dea0e"}},{"arxiv_id":"2308.16137","paper":"/paper/lm-infinite-simple-on-the-fly-length","title":"LM-Infinite: Zero-Shot Extreme Length Generalization for Large Language Models","date":"2023-08-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Glaciohound/LM-Infinite","path":"models/get_llama2/convert_llama_weights_to_hf.py","file_url":"https://github.com/Glaciohound/LM-Infinite/blob/HEAD/models/get_llama2/convert_llama_weights_to_hf.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"25ab7cdc2eb3c237","mcp_get_code":{"code_sha256":"25ab7cdc2eb3c237"}},{"arxiv_id":"2307.08072","paper":"/paper/do-emergent-abilities-exist-in-quantized","title":"Do Emergent Abilities Exist in Quantized Large Language Models: An Empirical Study","date":"2023-07-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"rucaibox/quantizedempirical","path":"convert_llama_weights_to_hf.py","file_url":"https://github.com/rucaibox/quantizedempirical/blob/HEAD/convert_llama_weights_to_hf.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"25ab7cdc2eb3c237","mcp_get_code":{"code_sha256":"25ab7cdc2eb3c237"}},{"arxiv_id":"2307.08072","paper":"/paper/do-emergent-abilities-exist-in-quantized","title":"Do Emergent Abilities Exist in Quantized Large Language Models: An Empirical Study","date":"2023-07-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"rucaibox/quantizedempirical","path":"models/convert_llama_weights_to_hf.py","file_url":"https://github.com/rucaibox/quantizedempirical/blob/HEAD/models/convert_llama_weights_to_hf.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"57f5bf024e9e6eb0","mcp_get_code":{"code_sha256":"57f5bf024e9e6eb0"}},{"arxiv_id":"2305.13718","paper":"/paper/logicllm-exploring-self-supervised-logic","title":"Exploring Self-supervised Logic-enhanced Training for Large Language Models","date":"2023-05-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"sparkjiao/logicllm","path":"convert_llama_weights_to_hf.py","file_url":"https://github.com/sparkjiao/logicllm/blob/HEAD/convert_llama_weights_to_hf.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"de4478ea1dfdf42d","mcp_get_code":{"code_sha256":"de4478ea1dfdf42d"}},{"arxiv_id":"2025.findings-emnlp.435","paper":null,"title":"arXiv:2025.findings-emnlp.435","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"nguyenngocbaocmt02/OT-Intervention","path":"lofit_models/convert_llama_weights_to_hf.py","file_url":"https://github.com/nguyenngocbaocmt02/OT-Intervention/blob/HEAD/lofit_models/convert_llama_weights_to_hf.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"25ab7cdc2eb3c237","mcp_get_code":{"code_sha256":"25ab7cdc2eb3c237"}}]}