{"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/scaling-instruction-finetuned-language-models","title":"Scaling Instruction-Finetuned Language Models","arxiv_id":"2210.11416","date":"2022-10-20","proceeding":null,"authors":["Hyung Won Chung","Le Hou","Shayne Longpre","Barret Zoph","Yi Tay","William Fedus","Yunxuan Li","Xuezhi Wang","Mostafa Dehghani","Siddhartha Brahma","Albert Webson","Shixiang Shane Gu","Zhuyun Dai","Mirac Suzgun","Xinyun Chen","Aakanksha Chowdhery","Alex Castro-Ros","Marie Pellat","Kevin Robinson","Dasha Valter","Sharan Narang","Gaurav Mishra","Adams Yu","Vincent Zhao","Yanping Huang","Andrew Dai","Hongkun Yu","Slav Petrov","Ed H. Chi","Jeff Dean","Jacob Devlin","Adam Roberts","Denny Zhou","Quoc V. Le","Jason Wei"],"abstract":"Finetuning language models on a collection of datasets phrased as instructions has been shown to improve model performance and generalization to unseen tasks. In this paper we explore instruction finetuning with a particular focus on (1) scaling the number of tasks, (2) scaling the model size, and (3) finetuning on chain-of-thought data. We find that instruction finetuning with the above aspects dramatically improves performance on a variety of model classes (PaLM, T5, U-PaLM), prompting setups (zero-shot, few-shot, CoT), and evaluation benchmarks (MMLU, BBH, TyDiQA, MGSM, open-ended generation). For instance, Flan-PaLM 540B instruction-finetuned on 1.8K tasks outperforms PALM 540B by a large margin (+9.4% on average). Flan-PaLM 540B achieves state-of-the-art performance on several benchmarks, such as 75.2% on five-shot MMLU. We also publicly release Flan-T5 checkpoints, which achieve strong few-shot performance even compared to much larger models, such as PaLM 62B. Overall, instruction finetuning is a general method for improving the performance and usability of pretrained language models.","url_abs":"https://arxiv.org/abs/2210.11416v5","url_pdf":"https://arxiv.org/pdf/2210.11416v5.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":"scaling-instruction-finetuned-language-models","repo_url":"https://github.com/coastalcph/zeroshot_lexglue","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"scaling-instruction-finetuned-language-models","repo_url":"https://github.com/declare-lab/flan-alpaca","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"scaling-instruction-finetuned-language-models","repo_url":"https://github.com/formulamonks/llm-benchmarker-suite","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"scaling-instruction-finetuned-language-models","repo_url":"https://github.com/google-research/flan","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"scaling-instruction-finetuned-language-models","repo_url":"https://github.com/joelniklaus/lawinstruct","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"scaling-instruction-finetuned-language-models","repo_url":"https://github.com/kapllan/zeroshot_lexglue","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"scaling-instruction-finetuned-language-models","repo_url":"https://github.com/theoremone/llm-benchmarker-suite","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"scaling-instruction-finetuned-language-models","repo_url":"https://github.com/yli-z/ml4h_are_clinical_t5_models_better_for_clinical_text","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"scaling-instruction-finetuned-language-models","repo_url":"https://github.com/zchuz/timebench","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"coreference-resolution","task_name":"Coreference Resolution"},{"task_slug":"cross-lingual-question-answering","task_name":"Cross-Lingual Question Answering"},{"task_slug":"mmlu","task_name":"MMLU"},{"task_slug":"multi-task-language-understanding","task_name":"Multi-task Language Understanding"},{"task_slug":"paraphrase-identification","task_name":"Paraphrase Identification"},{"task_slug":"question-answering","task_name":"Question Answering"}],"methods":[{"method_slug":"adafactor","method_name":"Adafactor"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"attention-dropout","method_name":"Attention Dropout"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"flan-t5","method_name":"Flan-T5"},{"method_slug":"glu","method_name":"Gated Linear Unit"},{"method_slug":"inverse-square-root-schedule","method_name":"Inverse Square Root Schedule"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"palm","method_name":"PaLM"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"sentencepiece","method_name":"SentencePiece"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"t5","method_name":"T5"}],"datasets_introduced":[],"methods_introduced":[{"slug":"flan-t5","name":"Flan-T5","full_name":"Flan-T5"}],"results":[{"leaderboard":"/sota/coreference-resolution-on-winograd-schema","task":"Coreference Resolution","dataset":"Winograd Schema Challenge","model":"Flan-T5 XXL (zero -shot)","rank_in_archive_order":10,"of":82,"metrics":{"Accuracy":"89.82"},"uses_additional_data":false},{"leaderboard":"/sota/cross-lingual-question-answering-on-tydiqa","task":"Cross-Lingual Question Answering","dataset":"TyDiQA-GoldP","model":"Flan-U-PaLM 540B (direct-prompting)","rank_in_archive_order":3,"of":11,"metrics":{"EM":"68.3"},"uses_additional_data":false},{"leaderboard":"/sota/cross-lingual-question-answering-on-tydiqa","task":"Cross-Lingual Question Answering","dataset":"TyDiQA-GoldP","model":"Flan-PaLM 540B (direct-prompting)","rank_in_archive_order":4,"of":11,"metrics":{"EM":"67.8"},"uses_additional_data":false},{"leaderboard":"/sota/multi-task-language-understanding-on-bbh-alg","task":"Multi-task Language Understanding","dataset":"BBH-alg","model":"Flan-PaLM 540B (3-shot, fine-tuned, CoT + SC)","rank_in_archive_order":2,"of":7,"metrics":{"Average (%)":"66.5"},"uses_additional_data":false},{"leaderboard":"/sota/multi-task-language-understanding-on-bbh-alg","task":"Multi-task Language Understanding","dataset":"BBH-alg","model":"PaLM 540B (CoT + self-consistency)","rank_in_archive_order":3,"of":7,"metrics":{"Average (%)":"62.2"},"uses_additional_data":false},{"leaderboard":"/sota/multi-task-language-understanding-on-bbh-alg","task":"Multi-task Language Understanding","dataset":"BBH-alg","model":"Flan-PaLM 540B (3-shot, fine-tuned, CoT)","rank_in_archive_order":4,"of":7,"metrics":{"Average (%)":"61.3"},"uses_additional_data":false},{"leaderboard":"/sota/multi-task-language-understanding-on-bbh-alg","task":"Multi-task Language Understanding","dataset":"BBH-alg","model":"PaLM 540B (CoT)","rank_in_archive_order":5,"of":7,"metrics":{"Average (%)":"57.6"},"uses_additional_data":false},{"leaderboard":"/sota/multi-task-language-understanding-on-bbh-alg","task":"Multi-task Language Understanding","dataset":"BBH-alg","model":"Flan-PaLM 540B (3-shot, fine-tuned)","rank_in_archive_order":6,"of":7,"metrics":{"Average (%)":"48.2"},"uses_additional_data":false},{"leaderboard":"/sota/multi-task-language-understanding-on-bbh-alg","task":"Multi-task Language Understanding","dataset":"BBH-alg","model":"PaLM 540B","rank_in_archive_order":7,"of":7,"metrics":{"Average (%)":"38.3"},"uses_additional_data":false},{"leaderboard":"/sota/multi-task-language-understanding-on-bbh-nlp","task":"Multi-task Language Understanding","dataset":"BBH-nlp","model":"Flan-PaLM 540B (3-shot, fine-tuned, CoT + SC)","rank_in_archive_order":7,"of":15,"metrics":{"Average (%)":"78.4"},"uses_additional_data":false},{"leaderboard":"/sota/multi-task-language-understanding-on-bbh-nlp","task":"Multi-task Language Understanding","dataset":"BBH-nlp","model":"PaLM 540B (CoT + self-consistency)","rank_in_archive_order":8,"of":15,"metrics":{"Average (%)":"78.2"},"uses_additional_data":false},{"leaderboard":"/sota/multi-task-language-understanding-on-bbh-nlp","task":"Multi-task Language Understanding","dataset":"BBH-nlp","model":"Flan-PaLM 540B (3-shot, fine-tuned, CoT)","rank_in_archive_order":10,"of":15,"metrics":{"Average (%)":"72.4"},"uses_additional_data":false},{"leaderboard":"/sota/multi-task-language-understanding-on-bbh-nlp","task":"Multi-task Language Understanding","dataset":"BBH-nlp","model":"PaLM 540B (CoT)","rank_in_archive_order":11,"of":15,"metrics":{"Average (%)":"71.2"},"uses_additional_data":false},{"leaderboard":"/sota/multi-task-language-understanding-on-bbh-nlp","task":"Multi-task Language Understanding","dataset":"BBH-nlp","model":"Flan-PaLM 540B (5-shot, finetuned)","rank_in_archive_order":12,"of":15,"metrics":{"Average (%)":"70.0"},"uses_additional_data":false},{"leaderboard":"/sota/multi-task-language-understanding-on-bbh-nlp","task":"Multi-task Language Understanding","dataset":"BBH-nlp","model":"PaLM 540B","rank_in_archive_order":13,"of":15,"metrics":{"Average (%)":"62.7"},"uses_additional_data":false},{"leaderboard":"/sota/multi-task-language-understanding-on-mgsm","task":"Multi-task Language Understanding","dataset":"MGSM","model":"Flan-PaLM 540B (8-shot, fine-tuned, CoT + SC)","rank_in_archive_order":3,"of":12,"metrics":{"Average (%)":"72.0"},"uses_additional_data":false},{"leaderboard":"/sota/multi-task-language-understanding-on-mgsm","task":"Multi-task Language Understanding","dataset":"MGSM","model":"Flan-U-PaLM 540B (CoT)","rank_in_archive_order":4,"of":12,"metrics":{"Average (%)":"60.4"},"uses_additional_data":false},{"leaderboard":"/sota/multi-task-language-understanding-on-mgsm","task":"Multi-task Language Understanding","dataset":"MGSM","model":"Flan-PaLM 540B (8-shot, fine-tuned, CoT)","rank_in_archive_order":5,"of":12,"metrics":{"Average (%)":"57.0"},"uses_additional_data":false},{"leaderboard":"/sota/multi-task-language-understanding-on-mgsm","task":"Multi-task Language Understanding","dataset":"MGSM","model":"text-davinci-003","rank_in_archive_order":8,"of":12,"metrics":{"Average (%)":"36"},"uses_additional_data":false},{"leaderboard":"/sota/multi-task-language-understanding-on-mgsm","task":"Multi-task Language Understanding","dataset":"MGSM","model":"code-davinci-002","rank_in_archive_order":9,"of":12,"metrics":{"Average (%)":"35"},"uses_additional_data":false},{"leaderboard":"/sota/multi-task-language-understanding-on-mgsm","task":"Multi-task Language Understanding","dataset":"MGSM","model":"text-davinci-002","rank_in_archive_order":10,"of":12,"metrics":{"Average (%)":"23.7"},"uses_additional_data":false},{"leaderboard":"/sota/multi-task-language-understanding-on-mgsm","task":"Multi-task Language Understanding","dataset":"MGSM","model":"Flan-PaLM 540B (8-shot, fine-tuned)","rank_in_archive_order":11,"of":12,"metrics":{"Average (%)":"21.2"},"uses_additional_data":false},{"leaderboard":"/sota/multi-task-language-understanding-on-mgsm","task":"Multi-task Language Understanding","dataset":"MGSM","model":"GPT-3 Davinci 175B","rank_in_archive_order":12,"of":12,"metrics":{"Average (%)":"5.7"},"uses_additional_data":false},{"leaderboard":"/sota/multi-task-language-understanding-on-mmlu","task":"Multi-task Language Understanding","dataset":"MML","model":"llama 2(65b)","rank_in_archive_order":9,"of":44,"metrics":{"Average (%)":"73.5"},"uses_additional_data":false},{"leaderboard":"/sota/multi-task-language-understanding-on-mmlu","task":"Multi-task Language Understanding","dataset":"MML","model":"GPT-3 Davinci 175B (CoT)","rank_in_archive_order":19,"of":44,"metrics":{"Average (%)":"59.5"},"uses_additional_data":false},{"leaderboard":"/sota/multi-task-language-understanding-on-mmlu","task":"Multi-task Language Understanding","dataset":"MML","model":"Flan-T5-XL 3B (CoT)","rank_in_archive_order":27,"of":44,"metrics":{"Average (%)":"45.5"},"uses_additional_data":false},{"leaderboard":"/sota/multi-task-language-understanding-on-mmlu","task":"Multi-task Language Understanding","dataset":"MML","model":"Flan-T5-Large 780M","rank_in_archive_order":29,"of":44,"metrics":{"Average (%)":"45.1"},"uses_additional_data":false},{"leaderboard":"/sota/multi-task-language-understanding-on-mmlu","task":"Multi-task Language Understanding","dataset":"MML","model":"Flan-T5-Large 780M (CoT)","rank_in_archive_order":31,"of":44,"metrics":{"Average (%)":"40.5"},"uses_additional_data":false},{"leaderboard":"/sota/multi-task-language-understanding-on-mmlu","task":"Multi-task Language Understanding","dataset":"MML","model":"GPT-3 Davinci 175B (5-shot)","rank_in_archive_order":32,"of":44,"metrics":{"Average (%)":"39.7"},"uses_additional_data":false},{"leaderboard":"/sota/multi-task-language-understanding-on-mmlu","task":"Multi-task Language Understanding","dataset":"MML","model":"Flan-T5-Base 250M","rank_in_archive_order":38,"of":44,"metrics":{"Average (%)":"35.9"},"uses_additional_data":false},{"leaderboard":"/sota/multi-task-language-understanding-on-mmlu","task":"Multi-task Language Understanding","dataset":"MML","model":"Flan-T5-Base 250M (CoT)","rank_in_archive_order":39,"of":44,"metrics":{"Average (%)":"33.7"},"uses_additional_data":false},{"leaderboard":"/sota/multi-task-language-understanding-on-mmlu","task":"Multi-task Language Understanding","dataset":"MML","model":"Flan-T5-Small 80M","rank_in_archive_order":43,"of":44,"metrics":{"Average (%)":"28.7"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2210.11416","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.11416"}},"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":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/declare-lab/flan-alpaca","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/joelniklaus/lawinstruct","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/formulamonks/llm-benchmarker-suite","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/google-research/flan","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/theoremone/llm-benchmarker-suite","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/zchuz/timebench","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/kapllan/zeroshot_lexglue","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/yli-z/ml4h_are_clinical_t5_models_better_for_clinical_text","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/coastalcph/zeroshot_lexglue","reach":{"status":"ok"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/jasonwei20/flan-2","reach":{"status":"ok"}}],"summary":{"ran":1,"ran_draft_wrong":7,"unverified":9},"by_repo_kind":{"listed":{"samples":17,"ran":8,"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":2,"samples":[{"code_sha256_prefix":"ce7574929468c029","entry":"TextToTextSample","repo":"declare-lab/flan-alpaca","repo_kind":"listed","path":"training.py","file_url":"https://github.com/declare-lab/flan-alpaca/blob/HEAD/training.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"ce7574929468c029"}},{"code_sha256_prefix":"09b037bcbd40904b","entry":"example_list_to_batch","repo":"google-research/flan","repo_kind":"listed","path":"flan/v2/preprocessors.py","file_url":"https://github.com/google-research/flan/blob/HEAD/flan/v2/preprocessors.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":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"09b037bcbd40904b"}},{"code_sha256_prefix":"348e3fae4483828f","entry":"format_from_feature_dictionary","repo":"google-research/flan","repo_kind":"listed","path":"flan/v2/preprocessors.py","file_url":"https://github.com/google-research/flan/blob/HEAD/flan/v2/preprocessors.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":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"348e3fae4483828f"}},{"code_sha256_prefix":"965f08c21d5cd016","entry":"format_single_prompted_example","repo":"yli-z/ml4h_are_clinical_t5_models_better_for_clinical_text","repo_kind":"listed","path":"src/finetune_bc5cdr.py","file_url":"https://github.com/yli-z/ml4h_are_clinical_t5_models_better_for_clinical_text/blob/HEAD/src/finetune_bc5cdr.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"965f08c21d5cd016"}},{"code_sha256_prefix":"d9dfc4a47b45d445","entry":"get_training_keys","repo":"google-research/flan","repo_kind":"listed","path":"flan/v2/preprocessors.py","file_url":"https://github.com/google-research/flan/blob/HEAD/flan/v2/preprocessors.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":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"d9dfc4a47b45d445"}},{"code_sha256_prefix":"298d3ae7382f4e0b","entry":"preprocess_function","repo":"yli-z/ml4h_are_clinical_t5_models_better_for_clinical_text","repo_kind":"listed","path":"src/finetune_bc5cdr.py","file_url":"https://github.com/yli-z/ml4h_are_clinical_t5_models_better_for_clinical_text/blob/HEAD/src/finetune_bc5cdr.py","link_basis":"first_harvest_node","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":"298d3ae7382f4e0b"}},{"code_sha256_prefix":"945f9e10849aba5f","entry":"remove_unbatchable_items_ds","repo":"google-research/flan","repo_kind":"listed","path":"flan/v2/preprocessors.py","file_url":"https://github.com/google-research/flan/blob/HEAD/flan/v2/preprocessors.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":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"945f9e10849aba5f"}},{"code_sha256_prefix":"aed287a99a6a9c29","entry":"remove_unbatchable_items_ex","repo":"google-research/flan","repo_kind":"listed","path":"flan/v2/preprocessors.py","file_url":"https://github.com/google-research/flan/blob/HEAD/flan/v2/preprocessors.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":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"aed287a99a6a9c29"}},{"code_sha256_prefix":"fd9be101d56df782","entry":"LightningModel","repo":"declare-lab/flan-alpaca","repo_kind":"listed","path":"training.py","file_url":"https://github.com/declare-lab/flan-alpaca/blob/HEAD/training.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":"fd9be101d56df782"}},{"code_sha256_prefix":"20789a28303d52df","entry":"TextToTextData","repo":"declare-lab/flan-alpaca","repo_kind":"listed","path":"training.py","file_url":"https://github.com/declare-lab/flan-alpaca/blob/HEAD/training.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":"20789a28303d52df"}},{"code_sha256_prefix":"883e0c27ae1147a1","entry":"TextToTextDataset","repo":"declare-lab/flan-alpaca","repo_kind":"listed","path":"training.py","file_url":"https://github.com/declare-lab/flan-alpaca/blob/HEAD/training.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":"883e0c27ae1147a1"}},{"code_sha256_prefix":"826cda9a9517d6b1","entry":"TokensLengthAnalyzer","repo":"declare-lab/flan-alpaca","repo_kind":"listed","path":"training.py","file_url":"https://github.com/declare-lab/flan-alpaca/blob/HEAD/training.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":"826cda9a9517d6b1"}},{"code_sha256_prefix":"e4eeb164dc20068a","entry":"batch_apply_template","repo":"google-research/flan","repo_kind":"listed","path":"flan/v2/preprocessors.py","file_url":"https://github.com/google-research/flan/blob/HEAD/flan/v2/preprocessors.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":"e4eeb164dc20068a"}},{"code_sha256_prefix":"69440900d762a595","entry":"example_batch_to_list","repo":"google-research/flan","repo_kind":"listed","path":"flan/v2/preprocessors.py","file_url":"https://github.com/google-research/flan/blob/HEAD/flan/v2/preprocessors.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":"69440900d762a595"}},{"code_sha256_prefix":"da56567fc45532d9","entry":"get_batch_formatter","repo":"google-research/flan","repo_kind":"listed","path":"flan/v2/preprocessors.py","file_url":"https://github.com/google-research/flan/blob/HEAD/flan/v2/preprocessors.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":"da56567fc45532d9"}},{"code_sha256_prefix":"1a288d0d4efefd6a","entry":"reformat_batched_example","repo":"google-research/flan","repo_kind":"listed","path":"flan/v2/preprocessors.py","file_url":"https://github.com/google-research/flan/blob/HEAD/flan/v2/preprocessors.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":"1a288d0d4efefd6a"}},{"code_sha256_prefix":"8c6076b9e23aff01","entry":"reformat_single_example","repo":"google-research/flan","repo_kind":"listed","path":"flan/v2/preprocessors.py","file_url":"https://github.com/google-research/flan/blob/HEAD/flan/v2/preprocessors.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":"8c6076b9e23aff01"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}