{"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/airavata-introducing-hindi-instruction-tuned","title":"Airavata: Introducing Hindi Instruction-tuned LLM","arxiv_id":"2401.15006","date":"2024-01-26","proceeding":null,"authors":["Jay Gala","Thanmay Jayakumar","Jaavid Aktar Husain","Aswanth Kumar M","Mohammed Safi Ur Rahman Khan","Diptesh Kanojia","Ratish Puduppully","Mitesh M. Khapra","Raj Dabre","Rudra Murthy","Anoop Kunchukuttan"],"abstract":"We announce the initial release of \"Airavata,\" an instruction-tuned LLM for Hindi. Airavata was created by fine-tuning OpenHathi with diverse, instruction-tuning Hindi datasets to make it better suited for assistive tasks. Along with the model, we also share the IndicInstruct dataset, which is a collection of diverse instruction-tuning datasets to enable further research for Indic LLMs. Additionally, we present evaluation benchmarks and a framework for assessing LLM performance across tasks in Hindi. Currently, Airavata supports Hindi, but we plan to expand this to all 22 scheduled Indic languages. You can access all artifacts at https://ai4bharat.github.io/airavata.","url_abs":"https://arxiv.org/abs/2401.15006v2","url_pdf":"https://arxiv.org/pdf/2401.15006v2.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":"airavata-introducing-hindi-instruction-tuned","repo_url":"https://github.com/ai4bharat/indicinstruct","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2401.15006","atlas_url":"https://app.syntology.ai/?focus=2401.15006","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.15006"}},"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/ai4bharat/indicinstruct","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":8,"ran_draft_wrong":1,"unverified":5},"by_repo_kind":{"official":{"samples":14,"ran":9,"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":0,"samples":[{"code_sha256_prefix":"17d17a8f4a188a7d","entry":"convert_message","repo":"ai4bharat/indicinstruct","repo_kind":"official","path":"open_instruct/gradio_demo_chat.py","file_url":"https://github.com/ai4bharat/indicinstruct/blob/HEAD/open_instruct/gradio_demo_chat.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":"17d17a8f4a188a7d"}},{"code_sha256_prefix":"e125c6d221046882","entry":"create_prompt_with_gemma_chat_format","repo":"ai4bharat/indicinstruct","repo_kind":"official","path":"eval/templates.py","file_url":"https://github.com/ai4bharat/indicinstruct/blob/HEAD/eval/templates.py","link_basis":"first_harvest_node","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":"e125c6d221046882"}},{"code_sha256_prefix":"c2ea9b08ef7b2a43","entry":"create_prompt_with_llama2_chat_format","repo":"ai4bharat/indicinstruct","repo_kind":"official","path":"eval/templates.py","file_url":"https://github.com/ai4bharat/indicinstruct/blob/HEAD/eval/templates.py","link_basis":"first_harvest_node","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":"c2ea9b08ef7b2a43"}},{"code_sha256_prefix":"aa0185cde82ab7d0","entry":"create_prompt_with_tulu_chat_format","repo":"ai4bharat/indicinstruct","repo_kind":"official","path":"eval/templates.py","file_url":"https://github.com/ai4bharat/indicinstruct/blob/HEAD/eval/templates.py","link_basis":"first_harvest_node","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":"aa0185cde82ab7d0"}},{"code_sha256_prefix":"4967e8b8db0b2f2c","entry":"dispatch_openai_chat_requesets","repo":"ai4bharat/indicinstruct","repo_kind":"official","path":"eval/dispatch_openai_requests.py","file_url":"https://github.com/ai4bharat/indicinstruct/blob/HEAD/eval/dispatch_openai_requests.py","link_basis":"first_harvest_node","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":"4967e8b8db0b2f2c"}},{"code_sha256_prefix":"d03d79aa598e2229","entry":"dispatch_openai_prompt_requesets","repo":"ai4bharat/indicinstruct","repo_kind":"official","path":"eval/dispatch_openai_requests.py","file_url":"https://github.com/ai4bharat/indicinstruct/blob/HEAD/eval/dispatch_openai_requests.py","link_basis":"first_harvest_node","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":"d03d79aa598e2229"}},{"code_sha256_prefix":"1cb0eeb16cf04ee3","entry":"encode_with_messages_format","repo":"ai4bharat/indicinstruct","repo_kind":"official","path":"open_instruct/finetune.py","file_url":"https://github.com/ai4bharat/indicinstruct/blob/HEAD/open_instruct/finetune.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":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"1cb0eeb16cf04ee3"}},{"code_sha256_prefix":"661419d69a095bfe","entry":"encode_with_prompt_completion_format","repo":"ai4bharat/indicinstruct","repo_kind":"official","path":"open_instruct/finetune.py","file_url":"https://github.com/ai4bharat/indicinstruct/blob/HEAD/open_instruct/finetune.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":"661419d69a095bfe"}},{"code_sha256_prefix":"1d0160fa2079785a","entry":"identity","repo":"ai4bharat/indicinstruct","repo_kind":"official","path":"open_instruct/finetune.py","file_url":"https://github.com/ai4bharat/indicinstruct/blob/HEAD/open_instruct/finetune.py","link_basis":"first_harvest_node","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":"1d0160fa2079785a"}},{"code_sha256_prefix":"b4bab7d7cf5218ef","entry":"forward","repo":"ai4bharat/indicinstruct","repo_kind":"official","path":"open_instruct/bloom_flash_attn_monkey_patch.py","file_url":"https://github.com/ai4bharat/indicinstruct/blob/HEAD/open_instruct/bloom_flash_attn_monkey_patch.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":"b4bab7d7cf5218ef"}},{"code_sha256_prefix":"352416cd121404a7","entry":"generate_completions","repo":"ai4bharat/indicinstruct","repo_kind":"official","path":"eval/utils.py","file_url":"https://github.com/ai4bharat/indicinstruct/blob/HEAD/eval/utils.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":"352416cd121404a7"}},{"code_sha256_prefix":"d134c88af0236263","entry":"get_next_word_predictions","repo":"ai4bharat/indicinstruct","repo_kind":"official","path":"eval/utils.py","file_url":"https://github.com/ai4bharat/indicinstruct/blob/HEAD/eval/utils.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":"d134c88af0236263"}},{"code_sha256_prefix":"533568a0e86ef298","entry":"get_statistics_for_messages_data","repo":"ai4bharat/indicinstruct","repo_kind":"official","path":"open_instruct/get_statistics.py","file_url":"https://github.com/ai4bharat/indicinstruct/blob/HEAD/open_instruct/get_statistics.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":"533568a0e86ef298"}},{"code_sha256_prefix":"84aeb6a7586885f5","entry":"get_statistics_for_prompt_completion_data","repo":"ai4bharat/indicinstruct","repo_kind":"official","path":"open_instruct/get_statistics.py","file_url":"https://github.com/ai4bharat/indicinstruct/blob/HEAD/open_instruct/get_statistics.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":"84aeb6a7586885f5"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}