{"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":"/paper/glm-130b-an-open-bilingual-pre-trained-model","title":"GLM-130B: An Open Bilingual Pre-trained Model","arxiv_id":"2210.02414","date":"2022-10-05","proceeding":null,"authors":["Aohan Zeng","Xiao Liu","Zhengxiao Du","Zihan Wang","Hanyu Lai","Ming Ding","Zhuoyi Yang","Yifan Xu","Wendi Zheng","Xiao Xia","Weng Lam Tam","Zixuan Ma","Yufei Xue","Jidong Zhai","WenGuang Chen","Peng Zhang","Yuxiao Dong","Jie Tang"],"abstract":"We introduce GLM-130B, a bilingual (English and Chinese) pre-trained language model with 130 billion parameters. It is an attempt to open-source a 100B-scale model at least as good as GPT-3 (davinci) and unveil how models of such a scale can be successfully pre-trained. Over the course of this effort, we face numerous unexpected technical and engineering challenges, particularly on loss spikes and divergence. In this paper, we introduce the training process of GLM-130B including its design choices, training strategies for both efficiency and stability, and engineering efforts. The resultant GLM-130B model offers significant outperformance over GPT-3 175B (davinci) on a wide range of popular English benchmarks while the performance advantage is not observed in OPT-175B and BLOOM-176B. It also consistently and significantly outperforms ERNIE TITAN 3.0 260B -- the largest Chinese language model -- across related benchmarks. Finally, we leverage a unique scaling property of GLM-130B to reach INT4 quantization without post training, with almost no performance loss, making it the first among 100B-scale models and more importantly, allowing its effective inference on 4$\\times$RTX 3090 (24G) or 8$\\times$RTX 2080 Ti (11G) GPUs, the most affordable GPUs required for using 100B-scale models. The GLM-130B model weights are publicly accessible and its code, training logs, related toolkit, and lessons learned are open-sourced at \\url{https://github.com/THUDM/GLM-130B/}.","url_abs":"https://arxiv.org/abs/2210.02414v2","url_pdf":"https://arxiv.org/pdf/2210.02414v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"glm-130b-an-open-bilingual-pre-trained-model","repo_url":"https://github.com/thudm/glm-130b","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"glm-130b-an-open-bilingual-pre-trained-model","repo_url":"https://github.com/thudm/chatglm","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"glm-130b-an-open-bilingual-pre-trained-model","repo_url":"https://github.com/thudm/chatglm2-6b","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"glm-130b-an-open-bilingual-pre-trained-model","repo_url":"https://github.com/thudm/chatglm3","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"glm-130b-an-open-bilingual-pre-trained-model","repo_url":"https://github.com/2023-MindSpore-4/Code12/tree/main/MindFormers/glm","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"glm-130b-an-open-bilingual-pre-trained-model","repo_url":"https://github.com/2023-MindSpore-4/Code12/tree/main/MindFormers/glm3","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"glm-130b-an-open-bilingual-pre-trained-model","repo_url":"https://github.com/THUDM/GLM","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"glm-130b-an-open-bilingual-pre-trained-model","repo_url":"https://github.com/jackaduma/ChatGLM-LoRA-RLHF-PyTorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"glm-130b-an-open-bilingual-pre-trained-model","repo_url":"https://github.com/modelscope/modelscope","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"long-context-understanding","task_name":"Long-Context Understanding"},{"task_slug":"multi-task-language-understanding","task_name":"Multi-task Language Understanding"},{"task_slug":"quantization","task_name":"Quantization"},{"task_slug":"model","task_name":"model"}],"methods":[{"method_slug":"aware","method_name":"AWARE"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"attention-dropout","method_name":"Attention Dropout"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"cosine-annealing","method_name":"Cosine Annealing"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"ernie","method_name":"ERNIE"},{"method_slug":"glm","method_name":"GLM"},{"method_slug":"gpt-3","method_name":"GPT-3"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"linear-warmup-with-cosine-annealing","method_name":"Linear Warmup With Cosine Annealing"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"weight-decay","method_name":"Weight Decay"}],"datasets_introduced":[],"methods_introduced":[{"slug":"glm","name":"GLM","full_name":"GLM"}],"results":[{"leaderboard":"/sota/language-modelling-on-big-bench-lite","task":"Language Modelling","dataset":"BIG-bench-lite","model":"GLM-130B (3-shot)","rank_in_archive_order":1,"of":3,"metrics":{"Accuracy":"15.11"},"uses_additional_data":false},{"leaderboard":"/sota/language-modelling-on-big-bench-lite","task":"Language Modelling","dataset":"BIG-bench-lite","model":"GLM-130B (1-shot)","rank_in_archive_order":2,"of":3,"metrics":{"Accuracy":"14.91"},"uses_additional_data":false},{"leaderboard":"/sota/language-modelling-on-big-bench-lite","task":"Language Modelling","dataset":"BIG-bench-lite","model":"GLM-130B (0-shot)","rank_in_archive_order":3,"of":3,"metrics":{"Accuracy":"13.31"},"uses_additional_data":false},{"leaderboard":"/sota/language-modelling-on-clue-afqmc","task":"Language Modelling","dataset":"CLUE (AFQMC)","model":"GLM-130B","rank_in_archive_order":1,"of":2,"metrics":{"Accuracy":"71.2"},"uses_additional_data":false},{"leaderboard":"/sota/language-modelling-on-clue-afqmc","task":"Language Modelling","dataset":"CLUE (AFQMC)","model":"ERNIE 3.0 Titan-260B","rank_in_archive_order":2,"of":2,"metrics":{"Accuracy":"69.0"},"uses_additional_data":false},{"leaderboard":"/sota/language-modelling-on-clue-c3","task":"Language Modelling","dataset":"CLUE (C3)","model":"GLM-130B","rank_in_archive_order":1,"of":2,"metrics":{"Accuracy":"77.5"},"uses_additional_data":false},{"leaderboard":"/sota/language-modelling-on-clue-c3","task":"Language Modelling","dataset":"CLUE (C3)","model":"ERNIE 3.0 Titan-260B","rank_in_archive_order":2,"of":2,"metrics":{"Accuracy":"54.9"},"uses_additional_data":false},{"leaderboard":"/sota/language-modelling-on-clue-cmnli","task":"Language Modelling","dataset":"CLUE (CMNLI)","model":"GLM-130B","rank_in_archive_order":1,"of":2,"metrics":{"Accuracy":"77.0"},"uses_additional_data":false},{"leaderboard":"/sota/language-modelling-on-clue-cmnli","task":"Language Modelling","dataset":"CLUE (CMNLI)","model":"ERNIE 3.0 Titan-260B","rank_in_archive_order":2,"of":2,"metrics":{"Accuracy":"51.7"},"uses_additional_data":false},{"leaderboard":"/sota/language-modelling-on-clue-cmrc2018","task":"Language Modelling","dataset":"CLUE (CMRC2018)","model":"GLM-130B","rank_in_archive_order":1,"of":2,"metrics":{"Accuracy":"55.7"},"uses_additional_data":false},{"leaderboard":"/sota/language-modelling-on-clue-cmrc2018","task":"Language Modelling","dataset":"CLUE (CMRC2018)","model":"ERNIE 3.0 Titan-260B","rank_in_archive_order":2,"of":2,"metrics":{"Accuracy":"16.6"},"uses_additional_data":false},{"leaderboard":"/sota/language-modelling-on-clue-drcd","task":"Language Modelling","dataset":"CLUE (DRCD)","model":"GLM-130B","rank_in_archive_order":1,"of":2,"metrics":{"Accuracy":"77.1"},"uses_additional_data":false},{"leaderboard":"/sota/language-modelling-on-clue-drcd","task":"Language Modelling","dataset":"CLUE (DRCD)","model":"ERNIE 3.0 Titan-260B","rank_in_archive_order":2,"of":2,"metrics":{"Accuracy":"29.5"},"uses_additional_data":false},{"leaderboard":"/sota/language-modelling-on-clue-ocnli-50k","task":"Language Modelling","dataset":"CLUE (OCNLI_50K)","model":"GLM-130B","rank_in_archive_order":1,"of":2,"metrics":{"Accuracy":"74.7"},"uses_additional_data":false},{"leaderboard":"/sota/language-modelling-on-clue-ocnli-50k","task":"Language Modelling","dataset":"CLUE (OCNLI_50K)","model":"ERNIE 3.0 Titan-260B","rank_in_archive_order":2,"of":2,"metrics":{"Accuracy":"44.6"},"uses_additional_data":false},{"leaderboard":"/sota/language-modelling-on-clue-wsc1-1","task":"Language Modelling","dataset":"CLUE (WSC1.1)","model":"GLM-130B","rank_in_archive_order":1,"of":2,"metrics":{"Accuracy":"83.9"},"uses_additional_data":false},{"leaderboard":"/sota/language-modelling-on-clue-wsc1-1","task":"Language Modelling","dataset":"CLUE (WSC1.1)","model":"ERNIE 3.0 Titan-260B","rank_in_archive_order":2,"of":2,"metrics":{"Accuracy":"81.1"},"uses_additional_data":false},{"leaderboard":"/sota/language-modelling-on-fewclue-bustm","task":"Language Modelling","dataset":"FewCLUE (BUSTM)","model":"GLM-130B","rank_in_archive_order":1,"of":2,"metrics":{"Accuracy":"77.5"},"uses_additional_data":false},{"leaderboard":"/sota/language-modelling-on-fewclue-bustm","task":"Language Modelling","dataset":"FewCLUE (BUSTM)","model":"ERNIE 3.0 Titan-260B","rank_in_archive_order":2,"of":2,"metrics":{"Accuracy":"64.4"},"uses_additional_data":false},{"leaderboard":"/sota/language-modelling-on-fewclue-chid-fc","task":"Language Modelling","dataset":"FewCLUE (CHID-FC)","model":"GLM-130B","rank_in_archive_order":1,"of":2,"metrics":{"Accuracy":"90.1"},"uses_additional_data":false},{"leaderboard":"/sota/language-modelling-on-fewclue-chid-fc","task":"Language Modelling","dataset":"FewCLUE (CHID-FC)","model":"ERNIE 3.0 Titan-260B","rank_in_archive_order":2,"of":2,"metrics":{"Accuracy":"87.1"},"uses_additional_data":false},{"leaderboard":"/sota/language-modelling-on-fewclue-cluewsc-fc","task":"Language Modelling","dataset":"FewCLUE (CLUEWSC-FC)","model":"GLM-130B","rank_in_archive_order":1,"of":2,"metrics":{"Accuracy":"77.4"},"uses_additional_data":false},{"leaderboard":"/sota/language-modelling-on-fewclue-cluewsc-fc","task":"Language Modelling","dataset":"FewCLUE (CLUEWSC-FC)","model":"ERNIE 3.0 Titan-260B","rank_in_archive_order":2,"of":2,"metrics":{"Accuracy":"53.5"},"uses_additional_data":false},{"leaderboard":"/sota/language-modelling-on-fewclue-eprstmt","task":"Language Modelling","dataset":"FewCLUE (EPRSTMT)","model":"GLM-130B","rank_in_archive_order":1,"of":2,"metrics":{"Accuracy":"92.5"},"uses_additional_data":false},{"leaderboard":"/sota/language-modelling-on-fewclue-eprstmt","task":"Language Modelling","dataset":"FewCLUE (EPRSTMT)","model":"ERNIE 3.0 Titan-260B","rank_in_archive_order":2,"of":2,"metrics":{"Accuracy":"88.8"},"uses_additional_data":false},{"leaderboard":"/sota/language-modelling-on-fewclue-ocnli-fc","task":"Language Modelling","dataset":"FewCLUE (OCNLI-FC)","model":"GLM-130B","rank_in_archive_order":1,"of":2,"metrics":{"Accuracy":"73.8"},"uses_additional_data":false},{"leaderboard":"/sota/language-modelling-on-fewclue-ocnli-fc","task":"Language Modelling","dataset":"FewCLUE (OCNLI-FC)","model":"ERNIE 3.0 Titan-260B","rank_in_archive_order":2,"of":2,"metrics":{"Accuracy":"53.8"},"uses_additional_data":false},{"leaderboard":"/sota/language-modelling-on-lambada","task":"Language Modelling","dataset":"LAMBADA","model":"GLM-130B (bidirectional attention)","rank_in_archive_order":12,"of":37,"metrics":{"Accuracy":"80.2"},"uses_additional_data":false},{"leaderboard":"/sota/language-modelling-on-the-pile","task":"Language Modelling","dataset":"The Pile","model":"GLM-130B","rank_in_archive_order":5,"of":39,"metrics":{"Bits per byte":"0.634"},"uses_additional_data":false},{"leaderboard":"/sota/language-modelling-on-the-pile","task":"Language Modelling","dataset":"The Pile","model":"Jurassic-1","rank_in_archive_order":7,"of":39,"metrics":{"Bits per byte":"0.65"},"uses_additional_data":false},{"leaderboard":"/sota/language-modelling-on-the-pile","task":"Language Modelling","dataset":"The Pile","model":"GPT-3","rank_in_archive_order":16,"of":39,"metrics":{"Bits per byte":"0.742"},"uses_additional_data":false},{"leaderboard":"/sota/long-context-understanding-on-ada-leval","task":"Long-Context Understanding","dataset":"Ada-LEval (BestAnswer)","model":"ChatGLM3-6b-32k","rank_in_archive_order":7,"of":10,"metrics":{"12k":"0.9","16k":"0.5","1k":"39.8","2k":"18.8","4k":"9.0","6k":"5.0","8k":"3.4"},"uses_additional_data":false},{"leaderboard":"/sota/long-context-understanding-on-ada-leval","task":"Long-Context Understanding","dataset":"Ada-LEval (BestAnswer)","model":"ChatGLM2-6b-32k","rank_in_archive_order":10,"of":10,"metrics":{"12k":"0.0","16k":"0.3","1k":"31.2","2k":"10.9","4k":"4.5","6k":"1.6","8k":"1.6"},"uses_additional_data":false},{"leaderboard":"/sota/long-context-understanding-on-ada-leval-tsort","task":"Long-Context Understanding","dataset":"Ada-LEval (TSort)","model":"ChatGLM3-6b-32k","rank_in_archive_order":9,"of":10,"metrics":{"16k":"0.7","2k":"2.3","4k":"2.4","8k":"2.0"},"uses_additional_data":false},{"leaderboard":"/sota/long-context-understanding-on-ada-leval-tsort","task":"Long-Context Understanding","dataset":"Ada-LEval (TSort)","model":"ChatGLM2-6b-32k","rank_in_archive_order":10,"of":10,"metrics":{"16k":"0.9","2k":"0.9","4k":"0.2","8k":"0.7"},"uses_additional_data":false},{"leaderboard":"/sota/multi-task-language-understanding-on-mmlu","task":"Multi-task Language Understanding","dataset":"MML","model":"GLM-130B","rank_in_archive_order":30,"of":44,"metrics":{"Average (%)":"44.8"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2210.02414","atlas_url":"https://app.syntology.ai/?focus=2210.02414","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.02414"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"deterministic:regex_extraction","url":"https://github.com/THUDM/GLM-130B","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/thudm/glm-130b","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/thudm/chatglm2-6b","reach":{"status":"ok","spdx":"NOASSERTION"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/modelscope/modelscope","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/jackaduma/ChatGLM-LoRA-RLHF-PyTorch","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/thudm/chatglm","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/THUDM/GLM","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/2023-MindSpore-4/Code12/tree/main/MindFormers/glm3","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/thudm/chatglm3","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/2023-MindSpore-4/Code12/tree/main/MindFormers/glm","reach":null}],"summary":{"ran":12,"ran_draft_wrong":1,"unverified":8},"by_repo_kind":{"official":{"samples":9,"ran":8,"repositories":1},"listed":{"samples":12,"ran":5,"repositories":3}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"57bdd79eeeb0d09e","entry":"F1_metric","repo":"THUDM/GLM-130B","repo_kind":"official","path":"evaluation/metrics.py","file_url":"https://github.com/THUDM/GLM-130B/blob/HEAD/evaluation/metrics.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"57bdd79eeeb0d09e"}},{"code_sha256_prefix":"184ed80cb890ac12","entry":"PromptSpell","repo":"THUDM/GLM","repo_kind":"listed","path":"model/modeling_glm.py","file_url":"https://github.com/THUDM/GLM/blob/HEAD/model/modeling_glm.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"184ed80cb890ac12"}},{"code_sha256_prefix":"1bc1a496ad4d784f","entry":"accuracy_metric","repo":"THUDM/GLM-130B","repo_kind":"official","path":"evaluation/metrics.py","file_url":"https://github.com/THUDM/GLM-130B/blob/HEAD/evaluation/metrics.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"1bc1a496ad4d784f"}},{"code_sha256_prefix":"945d1222f0c75dab","entry":"add_bminf_args","repo":"THUDM/GLM-130B","repo_kind":"official","path":"initialize.py","file_url":"https://github.com/THUDM/GLM-130B/blob/HEAD/initialize.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"945d1222f0c75dab"}},{"code_sha256_prefix":"8c1dee88ecad5be5","entry":"add_evaluation_specific_args","repo":"THUDM/GLM-130B","repo_kind":"official","path":"evaluate.py","file_url":"https://github.com/THUDM/GLM-130B/blob/HEAD/evaluate.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"8c1dee88ecad5be5"}},{"code_sha256_prefix":"1a1a6bb1bc387926","entry":"find_all_tasks","repo":"THUDM/GLM-130B","repo_kind":"official","path":"evaluate.py","file_url":"https://github.com/THUDM/GLM-130B/blob/HEAD/evaluate.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"1a1a6bb1bc387926"}},{"code_sha256_prefix":"43c9688838aff8b2","entry":"gelu","repo":"jackaduma/ChatGLM-LoRA-RLHF-PyTorch","repo_kind":"listed","path":"models/modeling_chatglm.py","file_url":"https://github.com/jackaduma/ChatGLM-LoRA-RLHF-PyTorch/blob/HEAD/models/modeling_chatglm.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"43c9688838aff8b2"}},{"code_sha256_prefix":"c8f235d13277facd","entry":"gelu_impl","repo":"jackaduma/ChatGLM-LoRA-RLHF-PyTorch","repo_kind":"listed","path":"models/modeling_chatglm.py","file_url":"https://github.com/jackaduma/ChatGLM-LoRA-RLHF-PyTorch/blob/HEAD/models/modeling_chatglm.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c8f235d13277facd"}},{"code_sha256_prefix":"5530d6c17cee956e","entry":"get_masks_and_position_ids","repo":"THUDM/GLM-130B","repo_kind":"official","path":"generate.py","file_url":"https://github.com/THUDM/GLM-130B/blob/HEAD/generate.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"5530d6c17cee956e"}},{"code_sha256_prefix":"6bcca529f47d7b8e","entry":"init_method_normal","repo":"THUDM/GLM","repo_kind":"listed","path":"model/modeling_glm.py","file_url":"https://github.com/THUDM/GLM/blob/HEAD/model/modeling_glm.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"6bcca529f47d7b8e"}},{"code_sha256_prefix":"4cd519b7c609ddfa","entry":"pad_batch","repo":"THUDM/GLM-130B","repo_kind":"official","path":"evaluation/dataset.py","file_url":"https://github.com/THUDM/GLM-130B/blob/HEAD/evaluation/dataset.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"4cd519b7c609ddfa"}},{"code_sha256_prefix":"cef36ffea76c70c8","entry":"precision_metric","repo":"THUDM/GLM-130B","repo_kind":"official","path":"evaluation/metrics.py","file_url":"https://github.com/THUDM/GLM-130B/blob/HEAD/evaluation/metrics.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"cef36ffea76c70c8"}},{"code_sha256_prefix":"2df80eb832dfdf12","entry":"preprocess","repo":"jackaduma/ChatGLM-LoRA-RLHF-PyTorch","repo_kind":"listed","path":"tokenize_dataset_rows.py","file_url":"https://github.com/jackaduma/ChatGLM-LoRA-RLHF-PyTorch/blob/HEAD/tokenize_dataset_rows.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2df80eb832dfdf12"}},{"code_sha256_prefix":"c9043275a83fa6fd","entry":"GLMModel","repo":"THUDM/GLM","repo_kind":"listed","path":"model/modeling_glm.py","file_url":"https://github.com/THUDM/GLM/blob/HEAD/model/modeling_glm.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c9043275a83fa6fd"}},{"code_sha256_prefix":"1b801af1b3425cfa","entry":"format_example","repo":"jackaduma/ChatGLM-LoRA-RLHF-PyTorch","repo_kind":"listed","path":"cover_alpaca2jsonl.py","file_url":"https://github.com/jackaduma/ChatGLM-LoRA-RLHF-PyTorch/blob/HEAD/cover_alpaca2jsonl.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"1b801af1b3425cfa"}},{"code_sha256_prefix":"294d09efc94ec53e","entry":"isEnglish","repo":"THUDM/GLM-130B","repo_kind":"official","path":"generate.py","file_url":"https://github.com/THUDM/GLM-130B/blob/HEAD/generate.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"294d09efc94ec53e"}},{"code_sha256_prefix":"25fd6233234767aa","entry":"load_tf_weights_in_chatglm_6b","repo":"jackaduma/ChatGLM-LoRA-RLHF-PyTorch","repo_kind":"listed","path":"models/modeling_chatglm.py","file_url":"https://github.com/jackaduma/ChatGLM-LoRA-RLHF-PyTorch/blob/HEAD/models/modeling_chatglm.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"25fd6233234767aa"}},{"code_sha256_prefix":"632dd3e505d6e594","entry":"load_tokenizer_and_model","repo":"thudm/chatglm3","repo_kind":"listed","path":"finetune_demo/finetune_hf.py","file_url":"https://github.com/thudm/chatglm3/blob/HEAD/finetune_demo/finetune_hf.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"632dd3e505d6e594"}},{"code_sha256_prefix":"732abe979cb6bf39","entry":"preprocess_function","repo":"jackaduma/ChatGLM-LoRA-RLHF-PyTorch","repo_kind":"listed","path":"train_reward_model.py","file_url":"https://github.com/jackaduma/ChatGLM-LoRA-RLHF-PyTorch/blob/HEAD/train_reward_model.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"732abe979cb6bf39"}},{"code_sha256_prefix":"677f282a0ca855b5","entry":"print_model_size","repo":"thudm/chatglm3","repo_kind":"listed","path":"finetune_demo/finetune_hf.py","file_url":"https://github.com/thudm/chatglm3/blob/HEAD/finetune_demo/finetune_hf.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"677f282a0ca855b5"}},{"code_sha256_prefix":"58b8c47b2ea3036c","entry":"print_rank_0","repo":"THUDM/GLM","repo_kind":"listed","path":"model/modeling_glm.py","file_url":"https://github.com/THUDM/GLM/blob/HEAD/model/modeling_glm.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"58b8c47b2ea3036c"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}