sentence-transformers How to use lw2134/policy_gte_large_2plus with sentence-transformers:
from sentence_transformers import SentenceTransformer
model = SentenceTransformer("lw2134/policy_gte_large_2plus", trust_remote_code=True)
sentences = [
"Explain the spectrum of openness in AI systems as described in the document. How do open-source AI systems differ from fully closed AI systems in terms of accessibility and innovation?",
"targets of cyber attacks; or\n (iii) permitting the evasion of human control or oversight through\nmeans of deception or obfuscation.\nModels meet this definition even if they are provided to end users with\ntechnical safeguards that attempt to prevent users from taking advantage of\nthe relevant unsafe capabilities. \n (l) The term “Federal law enforcement agency” has the meaning set forth\nin section 21(a) of Executive Order 14074 of May 25, 2022 (Advancing\nEffective, Accountable Policing and Criminal Justice Practices To Enhance\nPublic Trust and Public Safety).\n (m) The term “floating-point operation” means any mathematical\noperation or assignment involving floating-point numbers, which are a\nsubset of the real numbers typically represented on computers by an integer\nof fixed precision scaled by an integer exponent of a fixed base.\n (n) The term “foreign person” has the meaning set forth in section 5(c) of\nExecutive Order 13984 of January 19, 2021 (Taking Additional Steps To\nAddress the National Emergency With Respect to Significant Malicious\nCyber-Enabled Activities).\n (o) The terms “foreign reseller” and “foreign reseller of United States\nInfrastructure as a Service Products” mean a foreign person who has\nestablished an Infrastructure as a Service Account to provide Infrastructure\nas a Service Products subsequently, in whole or in part, to a third party.\n (p) The term “generative AI” means the class of AI models that emulate\nthe structure and characteristics of input data in order to generate derived\nsynthetic content. This can include images, videos, audio, text, and other\ndigital content.\n (q) The terms “Infrastructure as a Service Product,” “United States\nInfrastructure as a Service Product,” “United States Infrastructure as a\nService Provider,” and “Infrastructure as a Service Account” each have the\nrespective meanings given to those terms in section 5 of Executive Order\n13984.\n (r) The term “integer operation” means any mathematical operation or\nassignment involving only integers, or whole numbers expressed without a\ndecimal point.05/10/2024, 16:36 Executive Order on the Safe, Secure, and Trustworthy Development and Use of Artificial Intelligence | The White House\nhttps://www.whitehouse.gov/briefing-room/presidential-actions/2023/10/30/executive-order-on-the-safe-secure-and-trustworthy-development-and-use-of-artific… 7/59",
"AI safety, enable next-generation medical diagnoses and further other\ncritical AI priorities.\n\u0000\u0000 Released a for designing safe, secure, and trustworthy AI tools\nfor use in education. The Department of Education’s guide discusses\nhow developers of educational technologies can design AI that benefits\nstudents and teachers while advancing equity, civil rights, trust, and\ntransparency. This work builds on the Department’s 2023 \noutlining recommendations for the use of AI in teaching and learning.\n\u0000\u0000 Published guidance on evaluating the eligibility of patent claims\ninvolving inventions related to AI technology, as well as other\nemerging technologies. The guidance by the U.S. Patent and Trademark\nOffice will guide those inventing in the AI space to protect their AI\ninventions and assist patent examiners reviewing applications for\npatents on AI inventions.\n\u0000\u0000 Issued a on federal research and development (R&D) to\nadvance trustworthy AI over the past four years. The report by the\nNational Science and Technology Council examines an annual federal AI\nR&D budget of nearly $3 billion.\n\u0000\u0000 Launched a $23 million initiative to promote the use of privacy-\nenhancing technologies to solve real-world problems, including\nrelated to AI. Working with industry and agency partners, NSF will\ninvest through its new Privacy-preserving Data Sharing in Practice\nprogram in efforts to apply, mature, and scale privacy-enhancing\ntechnologies for specific use cases and establish testbeds to accelerate\ntheir adoption.\n\u0000\u0000 Announced millions of dollars in further investments to advance\nresponsible AI development and use throughout our society. These\ninclude $30 million invested through NSF’s Experiential Learning in\nEmerging and Novel Technologies program—which supports inclusive\nexperiential learning in fields like AI—and $10 million through NSF’s\nExpandAI program, which helps build capacity in AI research at\nminority-serving institutions while fostering the development of a\ndiverse, AI-ready workforce.\nAdvancing U.S. Leadership Abroad\nPresident Biden’s Executive Order emphasized that the United States lead\nglobal efforts to unlock AI’s potential and meet its challenges. To advance\nU.S. leadership on AI, agencies have:guide\nreport\nreport05/10/2024, 16:35 FACT SHEET: Biden-Harris Administration Announces New AI Actions and Receives Additional Major Voluntary Commitment on AI | The…\nhttps://www.whitehouse.gov/briefing-room/statements-releases/2024/07/26/fact-sheet-biden-harris-administration-announces-new-ai-actions-and-receives-addit… 4/10",
"50 Governing AI for Humanity processes such as the recent scientific report \non the risks of advanced AI commissioned by \nthe United Kingdom,25 and relevant regional \norganizations.\ne. A steering committee would develop a research \nagenda ensuring the inclusivity of views and \nincorporation of ethical considerations, oversee \nthe allocation of resources, foster collaboration \nwith a network of academic institutions and \nother stakeholders, and review the panel’s \nactivities and deliverables.100 By drawing on the unique convening power of the \nUnited Nations and inclusive global reach across \nstakeholder groups, an international scientific panel \ncan deliver trusted scientific collaboration processes \nand outputs and correct information asymmetries \nin ways that address the representation and \ncoordination gaps identified in paragraphs 66 and \n73, thereby promoting equitable and effective \ninternational AI governance.\nAmong the topics discussed in our consultations was the ongoing debate over open versus closed AI systems. \nAI systems that are open in varying degrees are often referred to as “open-source AI”, but this is somewhat of a \nmisnomer when compared with open-source software (code). It is important to recognize that openness in AI \nsystems is more of a spectrum than a single attribute.\nOne article explained that a “fully closed AI system is only accessible to a particular group. It could be an AI \ndeveloper company or a specific group within it, mainly for internal research and development purposes. On the \nother hand, more open systems may allow public access or make available certain parts, such as data, code, or \nmodel characteristics, to facilitate external AI development.”a\nOpen-source AI systems in the generative AI field present both risks and opportunities. Companies often cite “AI \nsafety” as a reason for not disclosing system specifications, reflecting the ongoing tension between open and \nclosed approaches in the industry. Debates typically revolve around two extremes: full openness, which entails \nsharing all model components and data sets; and partial openness, which involves disclosing only model weights. \nOpen-source AI systems encourage innovation and are often a requirement for public funding. On the open \nextreme of the spectrum, when the underlying code is made freely available, developers around the world can \nexperiment, improve and create new applications. This fosters a collaborative environment where ideas and \nexpertise are readily shared. Some industry leaders argue that this openness is vital to innovation and economic \ngrowth.\nHowever, in most cases, open-source AI models are available as application programming interfaces. In this case, \nthe original code is not shared, the original weights are never changed and model updates become new models. \nAdditionally, open-source models tend to be smaller and more transparent. This transparency can build trust, \nallow for ethical considerations to be proactively addressed, and support validation and replication because users \ncan examine the inner workings of the AI system, understand its decision-making process and identify potential \nbiases.Box 9: Open versus closed AI systems\na Angela Luna, “The open or closed AI dilemma”, 2 May 2024. Available at https://bipartisanpolicy.org/blog/the-open-or-closed-ai-dilemma .\n25 International Scientific Report on the Safety of Advanced AI: Interim Report. Available at https://gov.uk/government/publications/international-scientific-report-\non-the-safety-of-advanced-ai ."
]
embeddings = model.encode(sentences)
similarities = model.similarity(embeddings, embeddings)
print(similarities.shape)
# [4, 4] 
