Papers › H2O Open Ecosystem for State-of-the-art Large Language Models

H2O Open Ecosystem for State-of-the-art Large Language Models

17 Oct 2023arXiv:2310.13012archive 2025-07-28

Arno Candel, Jon McKinney, Philipp Singer, Pascal Pfeiffer, Maximilian Jeblick, Chun Ming Lee, Marcos V. Conde

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/

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 12 code samples harvested from 1 repository linked to this paper: 7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: official repository: 12 samples from 1 repository, 7 ran (7 with no instrument failure; 0 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

No sample is linked to this paper from 1 of its repositories that Syntology harvested for other papers:

Levels written on 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

h2oai/h2o-llmstudio officialmentioned in paperpytorchApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to LoRA: Low-Rank Adaptation of Large Language Models (arXiv:2106.09685; that paper's own run record: 51 ran (of which 19 constructed an object rather than computing a result; 43 with no instrument failure: 1 honoured, 0 violated, 42 with no contract checked; 8 where Syntology's instrument failed) · 33 unverified); nothing checks that they implement this paper's method. report
h2oai/h2ogpt officialmentioned in paperpytorchApache-2.0Syntology: 12 samples, 7 ran (0 instrument-failed) · 5 unverified report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

12 samples harvested: 7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran · honoured contract
6ran
5unverified

Licence: 1 of the 12 samples is pointer only, meaning Syntology does not serve that copy's text. For that sample, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from h2oai/h2ogpt. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: 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. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity.

h2oai/h2ogpt official repository 12 samples, 7 ran (0 instrument-failed) · 5 unverified
extra_stop_token_ids src/enums.py ran Apache-2.0 (permissive) · bd66a06aa7050024 · report fixture: signature base_model:str/0/str, tokenizer:MockTokenizer/0/?, as_ids:bool/0/bool · returned list · level recorded 2026-09-24
get_dbid src/db_utils.py ran fingerprinted Apache-2.0 (permissive) · daf097bc0bd836d2 · report fixture: signature db1:list/1/int · returned int · level recorded 2026-09-24
get_mem_space in 8 papers models/gpu_mem_track.py ran · honoured contract Apache-2.0 (permissive) here; the stored copy is pointer only · efa7095cdb85be6c · report fixture: signature x:dtype/0/? · returned float · level recorded 2026-09-24
is_gradio_vision_model src/enums.py ran Apache-2.0 (permissive) · cc1bf5a3113b7711 · report fixture: signature base_model:str/0/str · returned bool · level recorded 2026-09-24
is_vision_model src/enums.py ran Apache-2.0 (permissive) · dae40f9ffdf8c10f · report fixture: signature base_model:str/0/str, all_visible_models:list/1/empty, visible_vision_models:list/1/empty · returned bool · level recorded 2026-09-24
prune_long_sequences finetune.py ran Apache-2.0 (permissive) · cf2ae51214a5eec8 · report fixture: signature data_point:dict/0/?, cutoff_len:int/0/int · returned bool · level recorded 2026-09-24
tokenize in 176 papers finetune.py ran Apache-2.0 (permissive) · 38cae2d1ced7906a · report fixture: signature prompt:str/0/str, tokenizer:callable/0/?, cutoff_len:int/0/int, add_eos_token:bool/0/bool · returned dict · level recorded 2026-09-24
covert_prompt_to_input_ids_with_history models/predict_aquila.py unverified Apache-2.0 (permissive) · ad6c3608d441e75a · report
get_conv_template in 72 papers models/predict_aquila.py unverified Apache-2.0 (permissive) · f393883643980cc1 · report
get_conversation_template models/predict_aquila.py unverified Apache-2.0 (permissive) · 96e06a37fa7389cf · report
get_sentences in 6 papers src/create_data.py unverified Apache-2.0 (permissive) · aca03ba436af1dd6 · report
parse_rst_file src/create_data.py unverified Apache-2.0 (permissive) · 4a3ce15d96849109 · report

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections