{"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/load-tokenizer-and-model","entry":"load_tokenizer_and_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":8,"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":6,"n_samples_ran":0,"n_samples_fingerprinted":0,"n_places":10,"n_places_pointer_only":0,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":0,"unverified":6},"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":"2508.01191","paper":"/paper/arxiv-2508-01191","title":"Is Chain-of-Thought Reasoning of LLMs a Mirage? A Data Distribution Lens","date":null,"month_inferred_from_arxiv_id":"2025-08","title_source":"syntology","repo":"ChengshuaiZhao0/DataAlchemy","path":"src/models.py","file_url":"https://github.com/ChengshuaiZhao0/DataAlchemy/blob/HEAD/src/models.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"122613e13bcc1d7e","mcp_get_code":{"code_sha256":"122613e13bcc1d7e"}},{"arxiv_id":"2410.20745","paper":"/paper/shopping-mmlu-a-massive-multi-task-online","title":"Shopping MMLU: A Massive Multi-Task Online Shopping Benchmark for Large Language Models","date":"2024-10-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"KL4805/ShoppingMMLU","path":"skill_wise_eval/utils.py","file_url":"https://github.com/KL4805/ShoppingMMLU/blob/HEAD/skill_wise_eval/utils.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":"6cad10d0763d137f","mcp_get_code":{"code_sha256":"6cad10d0763d137f"}},{"arxiv_id":"2410.20745","paper":"/paper/shopping-mmlu-a-massive-multi-task-online","title":"Shopping MMLU: A Massive Multi-Task Online Shopping Benchmark for Large Language Models","date":"2024-10-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"KL4805/ShoppingMMLU","path":"task_wise_eval/utils.py","file_url":"https://github.com/KL4805/ShoppingMMLU/blob/HEAD/task_wise_eval/utils.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":"f2b76d01892e989d","mcp_get_code":{"code_sha256":"f2b76d01892e989d"}},{"arxiv_id":"2408.16500","paper":"/paper/cogvlm2-visual-language-models-for-image-and","title":"CogVLM2: Visual Language Models for Image and Video Understanding","date":"2024-08-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"thudm/glm-4","path":"finetune/finetune_vision.py","file_url":"https://github.com/thudm/glm-4/blob/HEAD/finetune/finetune_vision.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":"a000febbe236a229","mcp_get_code":{"code_sha256":"a000febbe236a229"}},{"arxiv_id":"2406.12793","paper":"/paper/chatglm-a-family-of-large-language-models","title":"ChatGLM: A Family of Large Language Models from GLM-130B to GLM-4 All Tools","date":"2024-06-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"thudm/chatglm","path":"finetune_demo/finetune_hf.py","file_url":"https://github.com/thudm/chatglm/blob/HEAD/finetune_demo/finetune_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":"632dd3e505d6e594","mcp_get_code":{"code_sha256":"632dd3e505d6e594"}},{"arxiv_id":"2406.12793","paper":"/paper/chatglm-a-family-of-large-language-models","title":"ChatGLM: A Family of Large Language Models from GLM-130B to GLM-4 All Tools","date":"2024-06-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"thudm/chatglm4","path":"finetune/finetune_vision.py","file_url":"https://github.com/thudm/chatglm4/blob/HEAD/finetune/finetune_vision.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":"a000febbe236a229","mcp_get_code":{"code_sha256":"a000febbe236a229"}},{"arxiv_id":"2406.05925","paper":"/paper/hello-again-llm-powered-personalized-agent","title":"Hello Again! LLM-powered Personalized Agent for Long-term Dialogue","date":"2024-06-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"leolee99/ld-agent","path":"Trainer/lora_tune.py","file_url":"https://github.com/leolee99/ld-agent/blob/HEAD/Trainer/lora_tune.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"632dd3e505d6e594","mcp_get_code":{"code_sha256":"632dd3e505d6e594"}},{"arxiv_id":"2312.08914","paper":"/paper/cogagent-a-visual-language-model-for-gui","title":"CogAgent: A Visual Language Model for GUI Agents","date":"2023-12-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"THUDM/CogAgent","path":"finetune/finetune.py","file_url":"https://github.com/THUDM/CogAgent/blob/HEAD/finetune/finetune.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":"459bb9214094ea8f","mcp_get_code":{"code_sha256":"459bb9214094ea8f"}},{"arxiv_id":"2210.02414","paper":"/paper/glm-130b-an-open-bilingual-pre-trained-model","title":"GLM-130B: An Open Bilingual Pre-trained Model","date":"2022-10-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"thudm/chatglm3","path":"finetune_demo/finetune_hf.py","file_url":"https://github.com/thudm/chatglm3/blob/HEAD/finetune_demo/finetune_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":"632dd3e505d6e594","mcp_get_code":{"code_sha256":"632dd3e505d6e594"}},{"arxiv_id":"2025.naacl-long.272","paper":null,"title":"arXiv:2025.naacl-long.272","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"leolee99/LD-Agent","path":"Trainer/lora_tune.py","file_url":"https://github.com/leolee99/LD-Agent/blob/HEAD/Trainer/lora_tune.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"632dd3e505d6e594","mcp_get_code":{"code_sha256":"632dd3e505d6e594"}}]}