{"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/sailor-open-language-models-for-south-east","title":"Sailor: Open Language Models for South-East Asia","arxiv_id":"2404.03608","date":"2024-04-04","proceeding":null,"authors":["Longxu Dou","Qian Liu","Guangtao Zeng","Jia Guo","Jiahui Zhou","Wei Lu","Min Lin"],"abstract":"We present Sailor, a family of open language models ranging from 0.5B to 7B parameters, tailored for South-East Asian (SEA) languages. These models are continually pre-trained from Qwen1.5, a great language model for multilingual use cases. From Qwen1.5, Sailor models accept 200B to 400B tokens, primarily covering the languages of English, Chinese, Vietnamese, Thai, Indonesian, Malay, and Lao. The training leverages several techniques, including BPE dropout for improving the model robustness, aggressive data cleaning and deduplication, and small proxy models to optimize data mixture. Experimental results on four typical tasks indicate that Sailor models demonstrate strong performance across different benchmarks, including commonsense reasoning, question answering, reading comprehension and examination. Embracing the open-source spirit, we share our insights through this report to spark a wider interest in developing large language models for multilingual use cases.","url_abs":"https://arxiv.org/abs/2404.03608v1","url_pdf":"https://arxiv.org/pdf/2404.03608v1.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":"sailor-open-language-models-for-south-east","repo_url":"https://github.com/epfllm/megatron-llm","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"sailor-open-language-models-for-south-east","repo_url":"https://github.com/sail-sg/sailor-llm","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"sailor-open-language-models-for-south-east","repo_url":"https://github.com/hit-scir/huozi","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"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":"question-answering","task_name":"Question Answering"},{"task_slug":"reading-comprehension","task_name":"Reading Comprehension"}],"methods":[{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dropout","method_name":"Dropout"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2404.03608","atlas_url":"https://app.syntology.ai/?focus=2404.03608","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.03608"}},"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":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/epfllm/megatron-llm","reach":{"status":"ok","spdx":"NOASSERTION"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/sail-sg/sailor-llm","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/hit-scir/huozi","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":7,"ran_honours":1,"unverified":4},"by_repo_kind":{"official":{"samples":12,"ran":8,"repositories":2}},"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":11,"samples":[{"code_sha256_prefix":"684c66f5cec0794e","entry":"all_gather_item","repo":"epfllm/megatron-llm","repo_kind":"official","path":"megatron/dist_signal_handler.py","file_url":"https://github.com/epfllm/megatron-llm/blob/HEAD/megatron/dist_signal_handler.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"684c66f5cec0794e"}},{"code_sha256_prefix":"db8deebff0d5256c","entry":"allocate_mem_buff","repo":"epfllm/megatron-llm","repo_kind":"official","path":"megatron/memory.py","file_url":"https://github.com/epfllm/megatron-llm/blob/HEAD/megatron/memory.py","link_basis":"harvester_set","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":"db8deebff0d5256c"}},{"code_sha256_prefix":"cc64b6ee963afc52","entry":"assert_viewless_tensor","repo":"epfllm/megatron-llm","repo_kind":"official","path":"megatron/core/utils.py","file_url":"https://github.com/epfllm/megatron-llm/blob/HEAD/megatron/core/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"cc64b6ee963afc52"}},{"code_sha256_prefix":"99baeb4271f72548","entry":"build_num_microbatches_calculator","repo":"epfllm/megatron-llm","repo_kind":"official","path":"megatron/microbatches.py","file_url":"https://github.com/epfllm/megatron-llm/blob/HEAD/megatron/microbatches.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"99baeb4271f72548"}},{"code_sha256_prefix":"33de97c702d46371","entry":"divide","repo":"epfllm/megatron-llm","repo_kind":"official","path":"megatron/core/utils.py","file_url":"https://github.com/epfllm/megatron-llm/blob/HEAD/megatron/core/utils.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"33de97c702d46371"}},{"code_sha256_prefix":"84fc895d549d7b93","entry":"first_option_parse","repo":"sail-sg/sailor-llm","repo_kind":"official","path":"eval/sailor_text_postprocessors.py","file_url":"https://github.com/sail-sg/sailor-llm/blob/HEAD/eval/sailor_text_postprocessors.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"84fc895d549d7b93"}},{"code_sha256_prefix":"11ee5870494a1570","entry":"get_device","repo":"epfllm/megatron-llm","repo_kind":"official","path":"megatron/dist_signal_handler.py","file_url":"https://github.com/epfllm/megatron-llm/blob/HEAD/megatron/dist_signal_handler.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"11ee5870494a1570"}},{"code_sha256_prefix":"9114f74bf4588d72","entry":"make_viewless_tensor","repo":"epfllm/megatron-llm","repo_kind":"official","path":"megatron/core/utils.py","file_url":"https://github.com/epfllm/megatron-llm/blob/HEAD/megatron/core/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"9114f74bf4588d72"}},{"code_sha256_prefix":"8a1aaa5bb993da97","entry":"get_mem_buff","repo":"epfllm/megatron-llm","repo_kind":"official","path":"megatron/memory.py","file_url":"https://github.com/epfllm/megatron-llm/blob/HEAD/megatron/memory.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"8a1aaa5bb993da97"}},{"code_sha256_prefix":"6ac246b8e8d0329c","entry":"is_pipeline_first_stage","repo":"epfllm/megatron-llm","repo_kind":"official","path":"megatron/core/parallel_state.py","file_url":"https://github.com/epfllm/megatron-llm/blob/HEAD/megatron/core/parallel_state.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"6ac246b8e8d0329c"}},{"code_sha256_prefix":"b64cb10233a3ce60","entry":"is_pipeline_last_stage","repo":"epfllm/megatron-llm","repo_kind":"official","path":"megatron/core/parallel_state.py","file_url":"https://github.com/epfllm/megatron-llm/blob/HEAD/megatron/core/parallel_state.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"b64cb10233a3ce60"}},{"code_sha256_prefix":"d6baa2c0dd7f70d7","entry":"is_rank_in_embedding_group","repo":"epfllm/megatron-llm","repo_kind":"official","path":"megatron/core/parallel_state.py","file_url":"https://github.com/epfllm/megatron-llm/blob/HEAD/megatron/core/parallel_state.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"d6baa2c0dd7f70d7"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}