{"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/h2o-open-ecosystem-for-state-of-the-art-large","title":"H2O Open Ecosystem for State-of-the-art Large Language Models","arxiv_id":"2310.13012","date":"2023-10-17","proceeding":null,"authors":["Arno Candel","Jon McKinney","Philipp Singer","Pascal Pfeiffer","Maximilian Jeblick","Chun Ming Lee","Marcos V. Conde"],"abstract":"Large Language Models (LLMs) represent a revolution in AI. However, they also pose many significant risks, such as the presence of biased, private, copyrighted or harmful text. For this reason we need open, transparent and safe solutions. We introduce a complete open-source ecosystem for developing and testing LLMs. The goal of this project is to boost open alternatives to closed-source approaches. We release h2oGPT, a family of fine-tuned LLMs of diverse sizes. We also introduce H2O LLM Studio, a framework and no-code GUI designed for efficient fine-tuning, evaluation, and deployment of LLMs using the most recent state-of-the-art techniques. Our code and models are fully open-source. We believe this work helps to boost AI development and make it more accessible, efficient and trustworthy. The demo is available at: https://gpt.h2o.ai/","url_abs":"https://arxiv.org/abs/2310.13012v2","url_pdf":"https://arxiv.org/pdf/2310.13012v2.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":"h2o-open-ecosystem-for-state-of-the-art-large","repo_url":"https://github.com/h2oai/h2o-llmstudio","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"h2o-open-ecosystem-for-state-of-the-art-large","repo_url":"https://github.com/h2oai/h2ogpt","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2310.13012","atlas_url":"https://app.syntology.ai/?focus=2310.13012","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.13012"}},"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/h2oai/h2ogpt","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":7,"unverified":5},"by_repo_kind":{"official":{"samples":12,"ran":7,"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":"bd66a06aa7050024","entry":"extra_stop_token_ids","repo":"h2oai/h2ogpt","repo_kind":"official","path":"src/enums.py","file_url":"https://github.com/h2oai/h2ogpt/blob/HEAD/src/enums.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":"bd66a06aa7050024"}},{"code_sha256_prefix":"daf097bc0bd836d2","entry":"get_dbid","repo":"h2oai/h2ogpt","repo_kind":"official","path":"src/db_utils.py","file_url":"https://github.com/h2oai/h2ogpt/blob/HEAD/src/db_utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"daf097bc0bd836d2"}},{"code_sha256_prefix":"efa7095cdb85be6c","entry":"get_mem_space","repo":"h2oai/h2ogpt","repo_kind":"official","path":"models/gpu_mem_track.py","file_url":"https://github.com/h2oai/h2ogpt/blob/HEAD/models/gpu_mem_track.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":"efa7095cdb85be6c"}},{"code_sha256_prefix":"cc1bf5a3113b7711","entry":"is_gradio_vision_model","repo":"h2oai/h2ogpt","repo_kind":"official","path":"src/enums.py","file_url":"https://github.com/h2oai/h2ogpt/blob/HEAD/src/enums.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":"cc1bf5a3113b7711"}},{"code_sha256_prefix":"dae40f9ffdf8c10f","entry":"is_vision_model","repo":"h2oai/h2ogpt","repo_kind":"official","path":"src/enums.py","file_url":"https://github.com/h2oai/h2ogpt/blob/HEAD/src/enums.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":"dae40f9ffdf8c10f"}},{"code_sha256_prefix":"cf2ae51214a5eec8","entry":"prune_long_sequences","repo":"h2oai/h2ogpt","repo_kind":"official","path":"finetune.py","file_url":"https://github.com/h2oai/h2ogpt/blob/HEAD/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":"cf2ae51214a5eec8"}},{"code_sha256_prefix":"38cae2d1ced7906a","entry":"tokenize","repo":"h2oai/h2ogpt","repo_kind":"official","path":"finetune.py","file_url":"https://github.com/h2oai/h2ogpt/blob/HEAD/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":"38cae2d1ced7906a"}},{"code_sha256_prefix":"ad6c3608d441e75a","entry":"covert_prompt_to_input_ids_with_history","repo":"h2oai/h2ogpt","repo_kind":"official","path":"models/predict_aquila.py","file_url":"https://github.com/h2oai/h2ogpt/blob/HEAD/models/predict_aquila.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":"ad6c3608d441e75a"}},{"code_sha256_prefix":"f393883643980cc1","entry":"get_conv_template","repo":"h2oai/h2ogpt","repo_kind":"official","path":"models/predict_aquila.py","file_url":"https://github.com/h2oai/h2ogpt/blob/HEAD/models/predict_aquila.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":"f393883643980cc1"}},{"code_sha256_prefix":"96e06a37fa7389cf","entry":"get_conversation_template","repo":"h2oai/h2ogpt","repo_kind":"official","path":"models/predict_aquila.py","file_url":"https://github.com/h2oai/h2ogpt/blob/HEAD/models/predict_aquila.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":"96e06a37fa7389cf"}},{"code_sha256_prefix":"aca03ba436af1dd6","entry":"get_sentences","repo":"h2oai/h2ogpt","repo_kind":"official","path":"src/create_data.py","file_url":"https://github.com/h2oai/h2ogpt/blob/HEAD/src/create_data.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":"aca03ba436af1dd6"}},{"code_sha256_prefix":"4a3ce15d96849109","entry":"parse_rst_file","repo":"h2oai/h2ogpt","repo_kind":"official","path":"src/create_data.py","file_url":"https://github.com/h2oai/h2ogpt/blob/HEAD/src/create_data.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":"4a3ce15d96849109"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}