{"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/token-scaled-logit-distillation-for-ternary-1","title":"Token-Scaled Logit Distillation for Ternary Weight Generative Language Models","arxiv_id":"2308.06744","date":"2023-08-13","proceeding":"NeurIPS 2023 11","authors":["Minsoo Kim","Sihwa Lee","Janghwan Lee","Sukjin Hong","Du-Seong Chang","Wonyong Sung","Jungwook Choi"],"abstract":"Generative Language Models (GLMs) have shown impressive performance in tasks such as text generation, understanding, and reasoning. However, the large model size poses challenges for practical deployment. To solve this problem, Quantization-Aware Training (QAT) has become increasingly popular. However, current QAT methods for generative models have resulted in a noticeable loss of accuracy. To counteract this issue, we propose a novel knowledge distillation method specifically designed for GLMs. Our method, called token-scaled logit distillation, prevents overfitting and provides superior learning from the teacher model and ground truth. This research marks the first evaluation of ternary weight quantization-aware training of large-scale GLMs with less than 1.0 degradation in perplexity and achieves enhanced accuracy in tasks like common-sense QA and arithmetic reasoning as well as natural language understanding. Our code is available at https://github.com/aiha-lab/TSLD.","url_abs":"https://arxiv.org/abs/2308.06744v4","url_pdf":"https://arxiv.org/pdf/2308.06744v4.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":"token-scaled-logit-distillation-for-ternary-1","repo_url":"https://github.com/aiha-lab/tsld","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"arithmetic-reasoning","task_name":"Arithmetic Reasoning"},{"task_slug":"common-sense-reasoning","task_name":"Common Sense Reasoning"},{"task_slug":"knowledge-distillation","task_name":"Knowledge Distillation"},{"task_slug":"natural-language-understanding","task_name":"Natural Language Understanding"},{"task_slug":"quantization","task_name":"Quantization"},{"task_slug":"text-generation","task_name":"Text Generation"}],"methods":[{"method_slug":"knowledge-distillation","method_name":"Knowledge Distillation"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2308.06744","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.06744"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+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/aiha-lab/TSLD","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/aiha-lab/tsld","reach":{"status":"ok"}}],"summary":{"ran_draft_wrong":2,"ran":3},"by_repo_kind":{"official":{"samples":5,"ran":5,"repositories":1}},"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":5,"samples":[{"code_sha256_prefix":"675da8641c602b03","entry":"round_ste","repo":"aiha-lab/TSLD","repo_kind":"official","path":"utils/utils_quant.py","file_url":"https://github.com/aiha-lab/TSLD/blob/HEAD/utils/utils_quant.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":2,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"675da8641c602b03"}},{"code_sha256_prefix":"d07d04439cd1d44f","entry":"jload","repo":"aiha-lab/TSLD","repo_kind":"official","path":"utils/alpaca_dataset.py","file_url":"https://github.com/aiha-lab/TSLD/blob/HEAD/utils/alpaca_dataset.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"d07d04439cd1d44f"}},{"code_sha256_prefix":"2252427ecd077946","entry":"make_supervised_data_module","repo":"aiha-lab/TSLD","repo_kind":"official","path":"utils/alpaca_dataset.py","file_url":"https://github.com/aiha-lab/TSLD/blob/HEAD/utils/alpaca_dataset.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"2252427ecd077946"}},{"code_sha256_prefix":"6c069e538ca55d9e","entry":"preprocess","repo":"aiha-lab/TSLD","repo_kind":"official","path":"utils/alpaca_dataset.py","file_url":"https://github.com/aiha-lab/TSLD/blob/HEAD/utils/alpaca_dataset.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"6c069e538ca55d9e"}},{"code_sha256_prefix":"7012e80ddf687239","entry":"w_quantize_func","repo":"aiha-lab/TSLD","repo_kind":"official","path":"utils/utils_quant.py","file_url":"https://github.com/aiha-lab/TSLD/blob/HEAD/utils/utils_quant.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"7012e80ddf687239"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}