Important Safety Notice: Always review the code and dependencies of an inference program before running it. If you are unsure about any part of the program or its dependencies, execute it only in an isolated environment, such as a Docker container or sandbox.
Last updated September 29, 2026 · Open in a new tab
By accessing or using the Bolo website, software, inference programs, code snippets, dependency specifications, or other materials provided through Bolo (collectively, the “Services”), you acknowledge that you have read, understood, and agreed to this Disclaimer and Terms of Use.
Bolo is a research project that provides tools and resources for accessing and executing machine learning models. The Services, including any inference programs, generated or curated code, dependency specifications, verification results, and related materials, are provided for research, development, and informational purposes.
Bolo does not provide professional, legal, medical, financial, security, or other specialized advice.
THE SERVICES AND ALL MATERIALS PROVIDED THROUGH BOLO ARE PROVIDED “AS IS” AND “AS AVAILABLE,” WITHOUT WARRANTIES OF ANY KIND, WHETHER EXPRESS, IMPLIED, STATUTORY, OR OTHERWISE.
TO THE MAXIMUM EXTENT PERMITTED BY APPLICABLE LAW, THE BOLO AUTHORS, CONTRIBUTORS, MAINTAINERS, AND AFFILIATED INSTITUTIONS DISCLAIM ALL WARRANTIES, INCLUDING, WITHOUT LIMITATION, WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE, ACCURACY, RELIABILITY, AVAILABILITY, SECURITY, AND NON-INFRINGEMENT.
Bolo does not warrant that any code, inference program, dependency specification, model, output, or other material will be correct, complete, error-free, secure, compatible with a particular environment, or suitable for any particular purpose.
Bolo may describe certain inference programs, model integrations, or other artifacts as “verified,” “checked,” “tested,” or similar terms.
Such descriptions mean only that the relevant artifact has been evaluated according to Bolo's applicable verification procedures at the time of evaluation. Verification is necessarily limited by the tests, inputs, environments, assumptions, and analysis used by Bolo.
Verification does not constitute a certification, warranty, guarantee, or representation that an artifact is correct, safe, complete, secure, faithful under all conditions, or suitable for any particular use.
An artifact that passes Bolo's verification process may still contain bugs, security vulnerabilities, incorrect assumptions, unexpected behavior, dependency conflicts, model-specific issues, or other defects.
Users should independently inspect and evaluate any code or artifact before relying on or executing it.
You are solely responsible for determining whether any code, model, dependency, inference program, or other material obtained through Bolo is appropriate for your intended use.
Executing machine learning code may install or execute third-party software, download external resources, consume computing resources, access hardware such as GPUs, read or write files, communicate with external services, or otherwise modify your computing environment.
You are responsible for reviewing such behavior and for using appropriate safeguards, including sandboxing, access controls, backups, and isolated execution environments where appropriate.
You assume all risks arising from your access to or use of the Services.
Bolo may provide access to or information about third-party machine learning models, repositories, libraries, packages, datasets, model weights, code, or other resources.
Such third-party materials are owned and controlled by their respective authors or rights holders and may be subject to separate licenses, terms of use, acceptable-use policies, or other restrictions.
Bolo does not grant any license or rights to third-party materials beyond those provided by their respective rights holders.
You are solely responsible for reviewing and complying with all applicable third-party licenses, terms, restrictions, and legal requirements.
The inclusion, verification, indexing, or availability of a third-party model or resource through Bolo does not constitute endorsement of that resource or its provider.
Machine learning models may produce inaccurate, incomplete, biased, unexpected, offensive, unsafe, or otherwise undesirable outputs.
Bolo does not control or guarantee the behavior or outputs of third-party models.
You are responsible for evaluating model outputs before relying on, publishing, distributing, or using them in downstream applications.
TO THE MAXIMUM EXTENT PERMITTED BY APPLICABLE LAW, THE BOLO AUTHORS, CONTRIBUTORS, MAINTAINERS, COPYRIGHT HOLDERS, AND AFFILIATED INSTITUTIONS SHALL NOT BE LIABLE FOR ANY CLAIM, LOSS, DAMAGE, COST, OR OTHER LIABILITY ARISING FROM OR RELATED TO THE SERVICES OR YOUR USE OF OR INABILITY TO USE THE SERVICES.
THIS INCLUDES, WITHOUT LIMITATION, ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, CONSEQUENTIAL, OR PUNITIVE DAMAGES; LOSS OF DATA; LOSS OF PROFITS OR REVENUE; BUSINESS INTERRUPTION; SECURITY INCIDENTS; HARDWARE OR SOFTWARE DAMAGE; OR CLAIMS ARISING FROM THIRD-PARTY MODELS, SOFTWARE, OR CONTENT.
THIS LIMITATION APPLIES WHETHER THE CLAIM ARISES IN CONTRACT, TORT, NEGLIGENCE, STRICT LIABILITY, OR ANY OTHER THEORY OF LIABILITY, EVEN IF THE POSSIBILITY OF SUCH DAMAGE HAS BEEN ADVISED.
Certain Bolo software, including the Bolo SDK, may be distributed separately under an open-source license, including the MIT License.
Nothing in these Terms is intended to revoke or restrict rights independently granted to you under an applicable open-source license.
Your use of the Bolo website and hosted Services may, however, remain subject to these Terms independently of your rights under any open-source software license.
You should not rely solely on Bolo's verification results, descriptions, documentation, model metadata, generated programs, or other materials when making decisions that could materially affect persons, property, systems, security, finances, legal rights, health, or other important interests.
Independent review and testing are recommended before deploying any artifact obtained through Bolo.
Bolo may modify, suspend, discontinue, or update any portion of the Services at any time.
These Terms may also be updated from time to time. The applicable version will be identified by the “Last Updated” date above.
Where required by Bolo, continued use of the Services may require acceptance of an updated version of these Terms.
By clicking “I Accept”, you confirm that you have read and understood this Disclaimer and Terms of Use and agree to be bound by them.
If you do not agree to these Terms, do not use the Bolo Services.
Supported by the Hugging Face pipeline API.
Supported by the Hugging Face pipeline API.
tscholak/1zha5ono Fine tuned weights for PICARD Parsing Incrementally for Constrained Auto Regressive Decoding from Language Models based on t5.1.1.lm100k.base. Training Data The model has been fine t…
Supported by the Hugging Face pipeline API.
Supported by the Hugging Face pipeline API.
Supported by the Hugging Face pipeline API.
Supported by the Hugging Face pipeline API.
Supported by the Hugging Face pipeline API.
4M: Massively Multimodal Masked Modeling A framework for training any to any multimodal foundation models. <br Scalable. Open sourced. Across tens of modalities and tasks. | | Official implementation…
4M: Massively Multimodal Masked Modeling A framework for training any to any multimodal foundation models. <br Scalable. Open sourced. Across tens of modalities and tasks. | | Official implementation…
4M: Massively Multimodal Masked Modeling A framework for training any to any multimodal foundation models. <br Scalable. Open sourced. Across tens of modalities and tasks. | | Official implementation…
4M: Massively Multimodal Masked Modeling A framework for training any to any multimodal foundation models. <br Scalable. Open sourced. Across tens of modalities and tasks. | | Official implementation…
Supported by the Hugging Face pipeline API.
Supported by the Hugging Face pipeline API.
Supported by the Hugging Face pipeline API.
Supported by the Hugging Face pipeline API.
Supported by the Hugging Face pipeline API.
Supported by the Hugging Face pipeline API.
<iframe src="https://ghbtns.com/github btn.html?user=speechbrain&repo=speechbrain&type=star&count=true&size=large&v=2" frameborder="0" scrolling="0" width="170" height="30" title="GitHub" </iframe <br…
<iframe src="https://ghbtns.com/github btn.html?user=speechbrain&repo=speechbrain&type=star&count=true&size=large&v=2" frameborder="0" scrolling="0" width="170" height="30" title="GitHub" </iframe <br…
See: https://comfyanonymous.github.io/ComfyUI examples/audio/ or https://docs.comfy.org/tutorials/audio/ace step/ace step v1 for how to use it in ComfyUI.
Introduction We introduce AceInstruct, a family of advanced SFT models for coding, mathematics, and general purpose tasks. The AceInstruct family, which includes AceInstruct 1.5B, 7B, and 72B, is <b I…
Introduction We introduce AceMath, a family of frontier models designed for mathematical reasoning. The models in AceMath family, including AceMath 1.5B/7B/72B Instruct and AceMath 7B/72B RM, are <b I…