Hugging Face's logo

Ayush-1722
/
Llama-2-7b-chat-Summarize-24K-LoRANET-Merged

Text Generation
Transformers
Safetensors
PyTorch
English
llama
facebook
meta
llama-2
conversational
text-generation-inference
Inference Endpoints
Model card Files Community
Llama-2-7b-chat-Summarize-24K-LoRANET-Merged / README.md
Ayush-1722's picture
Ayush-1722
Upload README.md with huggingface_hub
13293f2 verified
preview code
|
raw
history blame
166 kB
    <link rel="stylesheet" href="/front/build/kube-cc446aa/style.css" />

    <link rel="preconnect" href="https://fonts.gstatic.com" />
    <link
        href="https://fonts.googleapis.com/css2?family=Source+Sans+Pro:ital,wght@0,200;0,300;0,400;0,600;0,700;0,900;1,200;1,300;1,400;1,600;1,700;1,900&display=swap"
        rel="stylesheet"
    />
    <link
        href="https://fonts.googleapis.com/css2?family=IBM+Plex+Mono:wght@400;600;700&display=swap"
        rel="stylesheet"
    />

    <link
        rel="preload"
        href="https://cdnjs.cloudflare.com/ajax/libs/KaTeX/0.12.0/katex.min.css"
        as="style"
        onload="this.onload=null;this.rel='stylesheet'"
    />
    <noscript>
        <link rel="stylesheet" href="https://cdnjs.cloudflare.com/ajax/libs/KaTeX/0.12.0/katex.min.css" />
    </noscript>

    <link rel="canonical" href="https://huggingface.co/meta-llama/Llama-2-7b-chat-hf/blob/main/README.md">  

    <title>README.md · meta-llama/Llama-2-7b-chat-hf at main</title>

    <script
        defer
        data-domain="huggingface.co"
        event-loggedIn="false"
        src="/js/script.pageview-props.js"
    ></script>
    <script>
        window.plausible =
            window.plausible ||
            function () {
                (window.plausible.q = window.plausible.q || []).push(arguments);
            };
    </script>
    <script type="text/javascript" src="https://de5282c3ca0c.edge.sdk.awswaf.com/de5282c3ca0c/526cf06acb0d/challenge.js" defer></script>
</head>
<body class="flex flex-col min-h-screen bg-white dark:bg-gray-950 text-black ViewerBlobPage">
    <div class="flex min-h-screen flex-col">
<div class="SVELTE_HYDRATER contents" data-target="MainHeader" data-props="{&quot;classNames&quot;:&quot;&quot;,&quot;isWide&quot;:false,&quot;isZh&quot;:false}"><header class="border-b border-gray-100 "><div class="w-full px-4 container flex h-16 items-center"><div class="flex flex-1 items-center"><a class="mr-5 flex flex-none items-center lg:mr-6" href="/"><img alt="Hugging Face's logo" class="w-7 md:mr-2" src="/front/assets/huggingface_logo-noborder.svg">
            <span class="hidden whitespace-nowrap text-lg font-bold md:block">Hugging Face</span></a>
        <div class="relative flex-1 lg:max-w-sm mr-2 sm:mr-4 md:mr-3 xl:mr-6"><input autocomplete="off" class="w-full dark:bg-gray-950 pl-8 form-input-alt h-9 pr-3 focus:shadow-xl " name="" placeholder="Search models, datasets, users..."  spellcheck="false" type="text" value="">
<svg class="absolute left-2.5 text-gray-400 top-1/2 transform -translate-y-1/2" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M30 28.59L22.45 21A11 11 0 1 0 21 22.45L28.59 30zM5 14a9 9 0 1 1 9 9a9 9 0 0 1-9-9z" fill="currentColor"></path></svg>
</div>
        <div class="flex flex-none items-center justify-center p-0.5 place-self-stretch lg:hidden"><button class="relative z-40 flex h-6 w-8 items-center justify-center" type="button"><svg width="1em" height="1em" viewBox="0 0 10 10" class="text-xl" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" focusable="false" role="img" preserveAspectRatio="xMidYMid meet" fill="currentColor"><path fill-rule="evenodd" clip-rule="evenodd" d="M1.65039 2.9999C1.65039 2.8066 1.80709 2.6499 2.00039 2.6499H8.00039C8.19369 2.6499 8.35039 2.8066 8.35039 2.9999C8.35039 3.1932 8.19369 3.3499 8.00039 3.3499H2.00039C1.80709 3.3499 1.65039 3.1932 1.65039 2.9999ZM1.65039 4.9999C1.65039 4.8066 1.80709 4.6499 2.00039 4.6499H8.00039C8.19369 4.6499 8.35039 4.8066 8.35039 4.9999C8.35039 5.1932 8.19369 5.3499 8.00039 5.3499H2.00039C1.80709 5.3499 1.65039 5.1932 1.65039 4.9999ZM2.00039 6.6499C1.80709 6.6499 1.65039 6.8066 1.65039 6.9999C1.65039 7.1932 1.80709 7.3499 2.00039 7.3499H8.00039C8.19369 7.3499 8.35039 7.1932 8.35039 6.9999C8.35039 6.8066 8.19369 6.6499 8.00039 6.6499H2.00039Z"></path></svg>
    </button>

</div></div>
    <nav aria-label="Main" class="ml-auto hidden lg:block"><ul class="flex items-center space-x-1.5 xl:space-x-2"><li><a class="group flex items-center px-2 py-0.5 dark:hover:text-gray-400 hover:text-indigo-700" href="/models"><svg class="mr-1.5 text-gray-400 group-hover:text-indigo-500" style="" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 24 24"><path class="uim-quaternary" d="M20.23 7.24L12 12L3.77 7.24a1.98 1.98 0 0 1 .7-.71L11 2.76c.62-.35 1.38-.35 2 0l6.53 3.77c.29.173.531.418.7.71z" opacity=".25" fill="currentColor"></path><path class="uim-tertiary" d="M12 12v9.5a2.09 2.09 0 0 1-.91-.21L4.5 17.48a2.003 2.003 0 0 1-1-1.73v-7.5a2.06 2.06 0 0 1 .27-1.01L12 12z" opacity=".5" fill="currentColor"></path><path class="uim-primary" d="M20.5 8.25v7.5a2.003 2.003 0 0 1-1 1.73l-6.62 3.82c-.275.13-.576.198-.88.2V12l8.23-4.76c.175.308.268.656.27 1.01z" fill="currentColor"></path></svg>
                Models</a>
        </li><li><a class="group flex items-center px-2 py-0.5 dark:hover:text-gray-400 hover:text-red-700" href="/datasets"><svg class="mr-1.5 text-gray-400 group-hover:text-red-500" style="" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 25 25"><ellipse cx="12.5" cy="5" fill="currentColor" fill-opacity="0.25" rx="7.5" ry="2"></ellipse><path d="M12.5 15C16.6421 15 20 14.1046 20 13V20C20 21.1046 16.6421 22 12.5 22C8.35786 22 5 21.1046 5 20V13C5 14.1046 8.35786 15 12.5 15Z" fill="currentColor" opacity="0.5"></path><path d="M12.5 7C16.6421 7 20 6.10457 20 5V11.5C20 12.6046 16.6421 13.5 12.5 13.5C8.35786 13.5 5 12.6046 5 11.5V5C5 6.10457 8.35786 7 12.5 7Z" fill="currentColor" opacity="0.5"></path><path d="M5.23628 12C5.08204 12.1598 5 12.8273 5 13C5 14.1046 8.35786 15 12.5 15C16.6421 15 20 14.1046 20 13C20 12.8273 19.918 12.1598 19.7637 12C18.9311 12.8626 15.9947 13.5 12.5 13.5C9.0053 13.5 6.06886 12.8626 5.23628 12Z" fill="currentColor"></path></svg>
                Datasets</a>
        </li><li><a class="group flex items-center px-2 py-0.5 dark:hover:text-gray-400 hover:text-blue-700" href="/spaces"><svg class="mr-1.5 text-gray-400 group-hover:text-blue-500" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" focusable="false" role="img" width="1em" height="1em" viewBox="0 0 25 25"><path opacity=".5" d="M6.016 14.674v4.31h4.31v-4.31h-4.31ZM14.674 14.674v4.31h4.31v-4.31h-4.31ZM6.016 6.016v4.31h4.31v-4.31h-4.31Z" fill="currentColor"></path><path opacity=".75" fill-rule="evenodd" clip-rule="evenodd" d="M3 4.914C3 3.857 3.857 3 4.914 3h6.514c.884 0 1.628.6 1.848 1.414a5.171 5.171 0 0 1 7.31 7.31c.815.22 1.414.964 1.414 1.848v6.514A1.914 1.914 0 0 1 20.086 22H4.914A1.914 1.914 0 0 1 3 20.086V4.914Zm3.016 1.102v4.31h4.31v-4.31h-4.31Zm0 12.968v-4.31h4.31v4.31h-4.31Zm8.658 0v-4.31h4.31v4.31h-4.31Zm0-10.813a2.155 2.155 0 1 1 4.31 0 2.155 2.155 0 0 1-4.31 0Z" fill="currentColor"></path><path opacity=".25" d="M16.829 6.016a2.155 2.155 0 1 0 0 4.31 2.155 2.155 0 0 0 0-4.31Z" fill="currentColor"></path></svg>
                Spaces</a>
        </li><li><a class="group flex items-center px-2 py-0.5 dark:hover:text-gray-400 hover:text-yellow-700" href="/posts"><svg class="mr-1.5 text-gray-400 group-hover:text-yellow-500 !text-yellow-500" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" focusable="false" role="img" width="1em" height="1em" viewBox="0 0 12 12" preserveAspectRatio="xMidYMid meet"><path fill="currentColor" fill-rule="evenodd" d="M3.73 2.4A4.25 4.25 0 1 1 6 10.26H2.17l-.13-.02a.43.43 0 0 1-.3-.43l.01-.06a.43.43 0 0 1 .12-.22l.84-.84A4.26 4.26 0 0 1 3.73 2.4Z" clip-rule="evenodd"></path></svg>
                Posts</a>
        </li><li><a class="group flex items-center px-2 py-0.5 dark:hover:text-gray-400 hover:text-yellow-700" href="/docs"><svg xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" role="img" class="mr-1.5 text-gray-400 group-hover:text-yellow-500" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path opacity="0.5" d="M20.9022 5.10334L10.8012 10.8791L7.76318 9.11193C8.07741 8.56791 8.5256 8.11332 9.06512 7.7914L15.9336 3.73907C17.0868 3.08811 18.5002 3.26422 19.6534 3.91519L19.3859 3.73911C19.9253 4.06087 20.5879 4.56025 20.9022 5.10334Z" fill="currentColor"></path><path d="M10.7999 10.8792V28.5483C10.2136 28.5475 9.63494 28.4139 9.10745 28.1578C8.5429 27.8312 8.074 27.3621 7.74761 26.7975C7.42122 26.2327 7.24878 25.5923 7.24756 24.9402V10.9908C7.25062 10.3319 7.42358 9.68487 7.74973 9.1123L10.7999 10.8792Z" fill="currentColor" fill-opacity="0.75"></path><path fill-rule="evenodd" clip-rule="evenodd" d="M21.3368 10.8499V6.918C21.3331 6.25959 21.16 5.61234 20.8346 5.03949L10.7971 10.8727L10.8046 10.874L21.3368 10.8499Z" fill="currentColor"></path><path opacity="0.5" d="M21.7937 10.8488L10.7825 10.8741V28.5486L21.7937 28.5234C23.3344 28.5234 24.5835 27.2743 24.5835 25.7335V13.6387C24.5835 12.0979 23.4365 11.1233 21.7937 10.8488Z" fill="currentColor"></path></svg>
                Docs</a>
        </li>
    <li class="max-2xl:hidden"><div class="relative ">
<button class="px-2 py-0.5 group hover:text-green-700 dark:hover:text-gray-400 flex items-center " type="button">
    <svg class="mr-1.5 text-gray-400 group-hover:text-green-500" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 24 24"><path class="uim-tertiary" d="M19 6H5a3 3 0 0 0-3 3v2.72L8.837 14h6.326L22 11.72V9a3 3 0 0 0-3-3z" opacity=".5" fill="currentColor"></path><path class="uim-primary" d="M10 6V5h4v1h2V5a2.002 2.002 0 0 0-2-2h-4a2.002 2.002 0 0 0-2 2v1h2zm-1.163 8L2 11.72V18a3.003 3.003 0 0 0 3 3h14a3.003 3.003 0 0 0 3-3v-6.28L15.163 14H8.837z" fill="currentColor"></path></svg>
        Solutions
    </button>


</div></li>
    <li><a class="group flex items-center px-2 py-0.5 hover:text-gray-500 dark:hover:text-gray-400" href="/pricing">Pricing
        </a></li>

    <li><div class="relative group">
<button class="px-2 py-0.5 hover:text-gray-500 dark:hover:text-gray-600 flex items-center " type="button">
    <svg class="mr-1.5 text-gray-500 w-5 group-hover:text-gray-400 dark:text-gray-300 dark:group-hover:text-gray-400" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" focusable="false" role="img" width="1em" height="1em" viewBox="0 0 32 18" preserveAspectRatio="xMidYMid meet"><path fill-rule="evenodd" clip-rule="evenodd" d="M14.4504 3.30221C14.4504 2.836 14.8284 2.45807 15.2946 2.45807H28.4933C28.9595 2.45807 29.3374 2.836 29.3374 3.30221C29.3374 3.76842 28.9595 4.14635 28.4933 4.14635H15.2946C14.8284 4.14635 14.4504 3.76842 14.4504 3.30221Z" fill="currentColor"></path><path fill-rule="evenodd" clip-rule="evenodd" d="M14.4504 9.00002C14.4504 8.53382 14.8284 8.15588 15.2946 8.15588H28.4933C28.9595 8.15588 29.3374 8.53382 29.3374 9.00002C29.3374 9.46623 28.9595 9.84417 28.4933 9.84417H15.2946C14.8284 9.84417 14.4504 9.46623 14.4504 9.00002Z" fill="currentColor"></path><path fill-rule="evenodd" clip-rule="evenodd" d="M14.4504 14.6978C14.4504 14.2316 14.8284 13.8537 15.2946 13.8537H28.4933C28.9595 13.8537 29.3374 14.2316 29.3374 14.6978C29.3374 15.164 28.9595 15.542 28.4933 15.542H15.2946C14.8284 15.542 14.4504 15.164 14.4504 14.6978Z" fill="currentColor"></path><path fill-rule="evenodd" clip-rule="evenodd" d="M1.94549 6.87377C2.27514 6.54411 2.80962 6.54411 3.13928 6.87377L6.23458 9.96907L9.32988 6.87377C9.65954 6.54411 10.194 6.54411 10.5237 6.87377C10.8533 7.20343 10.8533 7.73791 10.5237 8.06756L6.23458 12.3567L1.94549 8.06756C1.61583 7.73791 1.61583 7.20343 1.94549 6.87377Z" fill="currentColor"></path></svg>
        
    </button>


</div></li>
    <li><hr class="h-5 w-0.5 border-none bg-gray-100 dark:bg-gray-800"></li>
    <li><a class="block cursor-pointer px-2 py-0.5 hover:text-gray-500 dark:hover:text-gray-400" href="/login">Log In
            </a></li>
        <li><a class="rounded-full border border-transparent bg-gray-900 px-3 py-1 leading-none text-white hover:border-black hover:bg-white hover:text-black" href="/join">Sign Up
                </a></li></ul></nav></div></header></div>



<div class="SVELTE_HYDRATER contents" data-target="SSOBanner" data-props="{}"></div>


<main class="flex flex-1 flex-col"><div class="SVELTE_HYDRATER contents" data-target="ModelHeader" data-props="{&quot;activeTab&quot;:&quot;files&quot;,&quot;author&quot;:{&quot;avatarUrl&quot;:&quot;https://cdn-avatars.huggingface.co/v1/production/uploads/646cf8084eefb026fb8fd8bc/oCTqufkdTkjyGodsx1vo1.png&quot;,&quot;fullname&quot;:&quot;Meta Llama&quot;,&quot;name&quot;:&quot;meta-llama&quot;,&quot;type&quot;:&quot;org&quot;,&quot;isHf&quot;:false,&quot;isEnterprise&quot;:false},&quot;canReadRepoSettings&quot;:false,&quot;canWriteRepoContent&quot;:false,&quot;canDisable&quot;:false,&quot;model&quot;:{&quot;author&quot;:&quot;meta-llama&quot;,&quot;cardData&quot;:{&quot;extra_gated_heading&quot;:&quot;You need to share contact information with Meta to access this model&quot;,&quot;extra_gated_prompt&quot;:&quot;### LLAMA 2 COMMUNITY LICENSE AGREEMENT\n\&quot;Agreement\&quot; means the terms and conditions for use, reproduction, distribution and  modification of the Llama Materials set forth herein. \n\&quot;Documentation\&quot; means the specifications, manuals and documentation  accompanying Llama 2 distributed by Meta at https://ai.meta.com/resources/models-and-libraries/llama-downloads/.  \n\&quot;Licensee\&quot; or \&quot;you\&quot; means you, or your employer or any other person or entity (if you are entering into this Agreement on such person or entity's behalf), of the age required under applicable laws, rules or regulations to provide legal consent and that has legal authority to bind your employer or such other person or  entity if you are  entering in this Agreement on their behalf. \n\&quot;Llama 2\&quot; means the foundational large language models and software and algorithms, including machine-learning model code, trained model weights, inference-enabling code, training-enabling code, fine-tuning enabling code and other  elements of the foregoing distributed by Meta at ai.meta.com/resources/models-and-libraries/llama-downloads/.\n\&quot;Llama Materials\&quot; means, collectively, Meta's proprietary Llama 2 and documentation (and any portion thereof) made available under this Agreement.\n\&quot;Meta\&quot; or \&quot;we\&quot; means Meta Platforms Ireland Limited (if you are located in or, if you are an entity, your principal place of business is in the EEA or Switzerland) and Meta Platforms, Inc. (if you are located outside of the EEA or Switzerland). \n\nBy clicking \&quot;I Accept\&quot; below or by using or distributing any portion or element of the Llama Materials, you agree to be bound by this Agreement.\n1. License Rights and Redistribution. \na. Grant of Rights. You are granted a non-exclusive, worldwide, non- transferable and royalty-free limited license under Meta's intellectual property or  other rights owned by Meta embodied in the Llama Materials to use, reproduce,  distribute, copy, create derivative works of, and make modifications to the Llama  Materials.  \nb. Redistribution and Use.\ni. If you distribute or make the Llama Materials, or any derivative works  thereof, available to a third party, you shall provide a copy of this Agreement to such  third party. \nii.  If you receive Llama Materials, or any derivative works thereof, from  a Licensee as part of an integrated end user product, then Section 2 of this  Agreement will not apply to you. \niii. You must retain in all copies of the Llama Materials that you  distribute the following attribution notice within a \&quot;Notice\&quot; text file distributed as a  part of such copies: \&quot;Llama 2 is licensed under the LLAMA 2 Community License,  Copyright (c) Meta Platforms, Inc. All Rights Reserved.\&quot;\niv. Your use of the Llama Materials must comply with applicable laws  and regulations (including trade compliance laws and regulations) and adhere to the  Acceptable Use Policy for the Llama Materials (available at  https://ai.meta.com/llama/use-policy), which is hereby incorporated by reference into  this Agreement.\nv. You will not use the Llama Materials or any output or results of the  Llama Materials to improve any other large language model (excluding Llama 2 or  derivative works thereof).  \n\n2. Additional Commercial Terms. If, on the Llama 2 version release date, the  monthly active users of the products or services made available by or for Licensee,  or Licensee's affiliates, is greater than 700 million monthly active users in the  preceding calendar month, you must request a license from Meta, which Meta may  grant to you in its sole discretion, and you are not authorized to exercise any of the  rights under this Agreement unless or until Meta otherwise expressly grants you  such rights.\n3. Disclaimer of Warranty. UNLESS REQUIRED BY APPLICABLE LAW, THE  LLAMA MATERIALS AND ANY OUTPUT AND RESULTS THEREFROM ARE  PROVIDED ON AN \&quot;AS IS\&quot; BASIS, WITHOUT WARRANTIES OF ANY KIND,  EITHER EXPRESS OR IMPLIED, INCLUDING, WITHOUT LIMITATION, ANY  WARRANTIES OF TITLE, NON-INFRINGEMENT, MERCHANTABILITY, OR  FITNESS FOR A PARTICULAR PURPOSE. YOU ARE SOLELY RESPONSIBLE  FOR DETERMINING THE APPROPRIATENESS OF USING OR REDISTRIBUTING  THE LLAMA MATERIALS AND ASSUME ANY RISKS ASSOCIATED WITH YOUR  USE OF THE LLAMA MATERIALS AND ANY OUTPUT AND RESULTS.\n4. Limitation of Liability. IN NO EVENT WILL META OR ITS AFFILIATES BE  LIABLE UNDER ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, TORT,  NEGLIGENCE, PRODUCTS LIABILITY, OR OTHERWISE, ARISING OUT OF THIS  AGREEMENT, FOR ANY LOST PROFITS OR ANY INDIRECT, SPECIAL,  CONSEQUENTIAL, INCIDENTAL, EXEMPLARY OR PUNITIVE DAMAGES, EVEN  IF META OR ITS AFFILIATES HAVE BEEN ADVISED OF THE POSSIBILITY OF  ANY OF THE FOREGOING.\n\n5. Intellectual Property.\na. No trademark licenses are granted under this Agreement, and in  connection with the Llama Materials, neither Meta nor Licensee may use any name  or mark owned by or associated with the other or any of its affiliates, except as  required for reasonable and customary use in describing and redistributing the  Llama Materials.\nb. Subject to Meta's ownership of Llama Materials and derivatives made by or  for Meta, with respect to any derivative works and modifications of the Llama  Materials that are made by you, as between you and Meta, you are and will be the  owner of such derivative works and modifications.\nc. If you institute litigation or other proceedings against Meta or any entity  (including a cross-claim or counterclaim in a lawsuit) alleging that the Llama  Materials or Llama 2 outputs or results, or any portion of any of the foregoing,  constitutes infringement of intellectual property or other rights owned or licensable  by you, then any licenses granted to you under this Agreement shall terminate as of  the date such litigation or claim is filed or instituted. You will indemnify and hold  harmless Meta from and against any claim by any third party arising out of or related  to your use or distribution of the Llama Materials.\n6. Term and Termination. The term of this Agreement will commence upon your  acceptance of this Agreement or access to the Llama Materials and will continue in  full force and effect until terminated in accordance with the terms and conditions  herein. Meta may terminate this Agreement if you are in breach of any term or  condition of this Agreement. Upon termination of this Agreement, you shall delete  and cease use of the Llama Materials. Sections 3, 4 and 7 shall survive the  termination of this Agreement. \n7. Governing Law and Jurisdiction. This Agreement will be governed and  construed under the laws of the State of California without regard to choice of law  principles, and the UN Convention on Contracts for the International Sale of Goods  does not apply to this Agreement. The courts of California shall have exclusive  jurisdiction of any dispute arising out of this Agreement. \n### Llama 2 Acceptable Use Policy\nMeta is committed to promoting safe and fair use of its tools and features, including Llama 2. If you access or use Llama 2, you agree to this Acceptable Use Policy (“Policy”). The most recent copy of this policy can be found at [ai.meta.com/llama/use-policy](http://ai.meta.com/llama/use-policy).\n#### Prohibited Uses\nWe want everyone to use Llama 2 safely and responsibly. You agree you will not use, or allow others to use, Llama 2 to:\n1. Violate the law or others’ rights, including to:\n      1. Engage in, promote, generate, contribute to, encourage, plan, incite, or further illegal or unlawful activity or content, such as: \n          1. Violence or terrorism \n          2. Exploitation or harm to children, including the solicitation, creation, acquisition, or dissemination of child exploitative content or failure to report Child Sexual Abuse Material\n          3. Human trafficking, exploitation, and sexual violence\n          4. The illegal distribution of information or materials to minors, including obscene materials, or failure to employ legally required age-gating in connection with such information or materials.\n          5. Sexual solicitation\n          6. Any other criminal activity\n      2. Engage in, promote, incite, or facilitate the harassment, abuse, threatening, or bullying of individuals or groups of individuals\n      3. Engage in, promote, incite, or facilitate discrimination or other unlawful or harmful conduct in the provision of employment, employment benefits, credit, housing, other economic benefits, or other essential goods and services\n      4. Engage in the unauthorized or unlicensed practice of any profession including, but not limited to, financial, legal, medical/health, or related professional practices \n      5. Collect, process, disclose, generate, or infer health, demographic, or other sensitive personal or private information about individuals without rights and consents required by applicable laws\n      6. Engage in or facilitate any action or generate any content that infringes, misappropriates, or otherwise violates any third-party rights, including the outputs or results of any products or services using the Llama 2 Materials\n      7. Create, generate, or facilitate the creation of malicious code, malware, computer viruses or do anything else that could disable, overburden, interfere with or impair the proper working, integrity, operation or appearance of a website or computer system \n2. Engage in, promote, incite, facilitate, or assist in the planning or development of activities that present a risk of death or bodily harm to individuals, including use of Llama 2 related to the following:\n    1. Military, warfare, nuclear industries or applications, espionage, use for materials or activities that are subject to the International Traffic Arms Regulations (ITAR) maintained by the United States Department of State\n    2. Guns and illegal weapons (including weapon development)\n    3. Illegal drugs and regulated/controlled substances\n    4. Operation of critical infrastructure, transportation technologies, or heavy machinery\n    5. Self-harm or harm to others, including suicide, cutting, and eating disorders\n    6. Any content intended to incite or promote violence, abuse, or any infliction of bodily harm to an individual\n3. Intentionally deceive or mislead others, including use of Llama 2 related to the following:\n    1. Generating, promoting, or furthering fraud or the creation or promotion of disinformation\n    2. Generating, promoting, or furthering defamatory content, including the creation of defamatory statements, images, or other content\n    3. Generating, promoting, or further distributing spam\n    4. Impersonating another individual without consent, authorization, or legal right\n    5. Representing that the use of Llama 2 or outputs are human-generated\n    6. Generating or facilitating false online engagement, including fake reviews and other means of fake online engagement \n    4. Fail to appropriately disclose to end users any known dangers of your AI system \nPlease report any violation of this Policy, software “bug,” or other problems that could lead to a violation of this Policy through one of the following means: \n    * Reporting issues with the model: [github.com/facebookresearch/llama](http://github.com/facebookresearch/llama)\n    * Reporting risky content generated by the model: [developers.facebook.com/llama_output_feedback](http://developers.facebook.com/llama_output_feedback)\n    * Reporting bugs and security concerns: [facebook.com/whitehat/info](http://facebook.com/whitehat/info) \n    * Reporting violations of the Acceptable Use Policy or unlicensed uses of Llama: [LlamaUseReport@meta.com](mailto:LlamaUseReport@meta.com)&quot;,&quot;extra_gated_fields&quot;:{&quot;First Name&quot;:&quot;text&quot;,&quot;Last Name&quot;:&quot;text&quot;,&quot;Date of birth&quot;:&quot;date_picker&quot;,&quot;Country&quot;:&quot;country&quot;,&quot;Affiliation&quot;:&quot;text&quot;,&quot;geo&quot;:&quot;ip_location&quot;,&quot;By clicking Submit below I accept the terms of the license and acknowledge that the information I provide will be collected stored processed and shared in accordance with the Meta Privacy Policy&quot;:&quot;checkbox&quot;},&quot;extra_gated_description&quot;:&quot;The information you provide will be collected, stored, processed and shared in accordance with the [Meta Privacy Policy](https://www.facebook.com/privacy/policy/).&quot;,&quot;extra_gated_button_content&quot;:&quot;Submit&quot;,&quot;language&quot;:[&quot;en&quot;],&quot;pipeline_tag&quot;:&quot;text-generation&quot;,&quot;tags&quot;:[&quot;facebook&quot;,&quot;meta&quot;,&quot;pytorch&quot;,&quot;llama&quot;,&quot;llama-2&quot;],&quot;license&quot;:&quot;llama2&quot;},&quot;cardExists&quot;:true,&quot;config&quot;:{&quot;architectures&quot;:[&quot;LlamaForCausalLM&quot;],&quot;model_type&quot;:&quot;llama&quot;,&quot;tokenizer_config&quot;:{&quot;bos_token&quot;:{&quot;__type&quot;:&quot;AddedToken&quot;,&quot;content&quot;:&quot;<s>&quot;,&quot;lstrip&quot;:false,&quot;normalized&quot;:false,&quot;rstrip&quot;:false,&quot;single_word&quot;:false},&quot;chat_template&quot;:&quot;{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% set system_message = false %}{% endif %}{% for message in loop_messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if loop.index0 == 0 and system_message != false %}{% set content = '<<SYS>>\\n' + system_message + '\\n<</SYS>>\\n\\n' + message['content'] %}{% else %}{% set content = message['content'] %}{% endif %}{% if message['role'] == 'user' %}{{ bos_token + '[INST] ' + content.strip() + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ ' '  + content.strip() + ' ' + eos_token }}{% endif %}{% endfor %}&quot;,&quot;eos_token&quot;:{&quot;__type&quot;:&quot;AddedToken&quot;,&quot;content&quot;:&quot;</s>&quot;,&quot;lstrip&quot;:false,&quot;normalized&quot;:false,&quot;rstrip&quot;:false,&quot;single_word&quot;:false},&quot;pad_token&quot;:null,&quot;unk_token&quot;:{&quot;__type&quot;:&quot;AddedToken&quot;,&quot;content&quot;:&quot;<unk>&quot;,&quot;lstrip&quot;:false,&quot;normalized&quot;:false,&quot;rstrip&quot;:false,&quot;single_word&quot;:false}}},&quot;createdAt&quot;:&quot;2023-07-13T16:45:23.000Z&quot;,&quot;discussionsDisabled&quot;:true,&quot;downloads&quot;:1373626,&quot;downloadsAllTime&quot;:9922091,&quot;id&quot;:&quot;meta-llama/Llama-2-7b-chat-hf&quot;,&quot;isLikedByUser&quot;:false,&quot;isWatchedByUser&quot;:false,&quot;inference&quot;:&quot;Yes&quot;,&quot;lastModified&quot;:&quot;2024-04-17T08:40:48.000Z&quot;,&quot;likes&quot;:3509,&quot;pipeline_tag&quot;:&quot;text-generation&quot;,&quot;library_name&quot;:&quot;transformers&quot;,&quot;librariesOther&quot;:[],&quot;model-index&quot;:null,&quot;private&quot;:false,&quot;repoType&quot;:&quot;model&quot;,&quot;gated&quot;:&quot;manual&quot;,&quot;pwcLink&quot;:{&quot;error&quot;:&quot;Unknown error, can't generate link to Papers With Code.&quot;},&quot;tags&quot;:[&quot;transformers&quot;,&quot;pytorch&quot;,&quot;safetensors&quot;,&quot;llama&quot;,&quot;text-generation&quot;,&quot;facebook&quot;,&quot;meta&quot;,&quot;llama-2&quot;,&quot;conversational&quot;,&quot;en&quot;,&quot;arxiv:2307.09288&quot;,&quot;license:llama2&quot;,&quot;autotrain_compatible&quot;,&quot;endpoints_compatible&quot;,&quot;text-generation-inference&quot;,&quot;region:us&quot;],&quot;tag_objs&quot;:[{&quot;id&quot;:&quot;text-generation&quot;,&quot;label&quot;:&quot;Text Generation&quot;,&quot;type&quot;:&quot;pipeline_tag&quot;,&quot;subType&quot;:&quot;nlp&quot;},{&quot;id&quot;:&quot;transformers&quot;,&quot;label&quot;:&quot;Transformers&quot;,&quot;type&quot;:&quot;library&quot;},{&quot;id&quot;:&quot;pytorch&quot;,&quot;label&quot;:&quot;PyTorch&quot;,&quot;type&quot;:&quot;library&quot;},{&quot;id&quot;:&quot;safetensors&quot;,&quot;label&quot;:&quot;Safetensors&quot;,&quot;type&quot;:&quot;library&quot;},{&quot;id&quot;:&quot;en&quot;,&quot;label&quot;:&quot;English&quot;,&quot;type&quot;:&quot;language&quot;},{&quot;id&quot;:&quot;llama&quot;,&quot;label&quot;:&quot;llama&quot;,&quot;type&quot;:&quot;other&quot;},{&quot;id&quot;:&quot;facebook&quot;,&quot;label&quot;:&quot;facebook&quot;,&quot;type&quot;:&quot;other&quot;},{&quot;id&quot;:&quot;meta&quot;,&quot;label&quot;:&quot;meta&quot;,&quot;type&quot;:&quot;other&quot;},{&quot;id&quot;:&quot;llama-2&quot;,&quot;label&quot;:&quot;llama-2&quot;,&quot;type&quot;:&quot;other&quot;},{&quot;id&quot;:&quot;conversational&quot;,&quot;label&quot;:&quot;conversational&quot;,&quot;type&quot;:&quot;other&quot;},{&quot;id&quot;:&quot;autotrain_compatible&quot;,&quot;label&quot;:&quot;AutoTrain Compatible&quot;,&quot;type&quot;:&quot;other&quot;},{&quot;id&quot;:&quot;endpoints_compatible&quot;,&quot;label&quot;:&quot;Inference Endpoints&quot;,&quot;type&quot;:&quot;other&quot;},{&quot;id&quot;:&quot;text-generation-inference&quot;,&quot;label&quot;:&quot;text-generation-inference&quot;,&quot;type&quot;:&quot;other&quot;},{&quot;id&quot;:&quot;arxiv:2307.09288&quot;,&quot;label&quot;:&quot;arxiv:2307.09288&quot;,&quot;type&quot;:&quot;arxiv&quot;,&quot;extra&quot;:{&quot;paperTitle&quot;:&quot;Llama 2: Open Foundation and Fine-Tuned Chat Models&quot;}},{&quot;id&quot;:&quot;license:llama2&quot;,&quot;label&quot;:&quot;llama2&quot;,&quot;type&quot;:&quot;license&quot;},{&quot;type&quot;:&quot;region&quot;,&quot;label&quot;:&quot;🇺🇸 Region: US&quot;,&quot;id&quot;:&quot;region:us&quot;}],&quot;transformersInfo&quot;:{&quot;auto_model&quot;:&quot;AutoModelForCausalLM&quot;,&quot;pipeline_tag&quot;:&quot;text-generation&quot;,&quot;processor&quot;:&quot;AutoTokenizer&quot;},&quot;widgetData&quot;:[{&quot;text&quot;:&quot;Hey my name is Julien! How are you?&quot;},{&quot;text&quot;:&quot;Hey my name is Thomas! How are you?&quot;},{&quot;text&quot;:&quot;Hey my name is Mariama! How are you?&quot;},{&quot;text&quot;:&quot;Hey my name is Clara! How are you?&quot;},{&quot;text&quot;:&quot;Hey my name is Julien! How are you?&quot;},{&quot;text&quot;:&quot;Hi.&quot;}],&quot;safetensors&quot;:{&quot;parameters&quot;:{&quot;F16&quot;:6738417664},&quot;total&quot;:6738417664,&quot;sharded&quot;:true}},&quot;discussionsStats&quot;:{&quot;closed&quot;:2,&quot;open&quot;:1,&quot;total&quot;:3}}"><header class="from-gray-50-to-white border-b border-gray-100 bg-gradient-to-t via-white dark:via-gray-950 pt-6 sm:pt-9"><div class="container relative "><h1 class="flex flex-wrap items-center leading-tight mb-3 text-lg max-sm:gap-y-1.5 md:text-xl">
        <div class="group flex flex-none items-center"><div class="relative mr-1.5 flex items-center">

        <img alt="" class="w-3.5 h-3.5 rounded  flex-none" src="https://cdn-avatars.huggingface.co/v1/production/uploads/646cf8084eefb026fb8fd8bc/oCTqufkdTkjyGodsx1vo1.png" crossorigin="anonymous"></div>
    <a href="/meta-llama" class="text-gray-400 hover:text-blue-600">meta-llama</a>
    <div class="mx-0.5 text-gray-300">/</div></div>
Llama-2-7b-chat-hf 
</div>
    


    


    


    


    

</div>

</div></div>
    <div class="relative mb-2 flex flex-wrap items-center"><a class="truncate text-gray-800 hover:underline" href="/meta-llama/Llama-2-7b-chat-hf/tree/main">Llama-2-7b-chat-hf</a>
        <span class="mx-1 text-gray-300">/</span>
            <span class="dark:text-gray-300">README.md</span>
            <div class="SVELTE_HYDRATER contents" data-target="CopyButton" data-props="{&quot;value&quot;:&quot;README.md&quot;,&quot;classNames&quot;:&quot;text-xs ml-2&quot;,&quot;title&quot;:&quot;Copy path&quot;}"><button class="relative text-xs ml-2 inline-flex cursor-pointer items-center text-sm focus:outline-none  mx-0.5   text-gray-600 " title="Copy path" type="button"><svg class="" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg>

</button></div></div></div>


</header>
        <div class="SVELTE_HYDRATER contents" data-target="LastCommit" data-props="{&quot;commitLast&quot;:{&quot;date&quot;:&quot;2024-04-17T08:40:48.000Z&quot;,&quot;verified&quot;:&quot;verified&quot;,&quot;subject&quot;:&quot;Update README.md&quot;,&quot;authors&quot;:[{&quot;_id&quot;:&quot;6032802e1f993496bc14d9e3&quot;,&quot;avatar&quot;:&quot;https://cdn-avatars.huggingface.co/v1/production/uploads/6032802e1f993496bc14d9e3/w6hr-DEQot4VVkoyRIBiy.png&quot;,&quot;isHf&quot;:true,&quot;user&quot;:&quot;osanseviero&quot;}],&quot;commit&quot;:{&quot;id&quot;:&quot;f5db02db724555f92da89c216ac04704f23d4590&quot;,&quot;parentIds&quot;:[&quot;c961cb2e60639583e2c425af9775de0da01e2371&quot;]},&quot;title&quot;:&quot;Update README.md&quot;},&quot;repo&quot;:{&quot;name&quot;:&quot;meta-llama/Llama-2-7b-chat-hf&quot;,&quot;type&quot;:&quot;model&quot;}}"><div class="from-gray-100-to-white flex items-baseline rounded-t-lg border border-b-0 bg-gradient-to-t px-3 py-2 dark:border-gray-800"><img class="mr-2.5 mt-0.5 h-4 w-4 self-center rounded-full" alt="osanseviero's picture" src="https://cdn-avatars.huggingface.co/v1/production/uploads/6032802e1f993496bc14d9e3/w6hr-DEQot4VVkoyRIBiy.png">
        <div class="mr-5 flex flex-none items-center truncate"><a class="hover:underline" href="/osanseviero">osanseviero
                </a>
            <span class="max-w-[175px] truncate border text-xs font-semibold leading-snug sm:max-w-xs rounded px-1  border-yellow-100 bg-yellow-50 text-yellow-500 dark:bg-yellow-800 dark:text-yellow-400 mt-0.5 ml-1.5 uppercase" title="member of the Hugging Face team">HF staff</span>
        </div>
    <div class="mr-4 truncate font-mono text-sm text-gray-500 hover:prose-a:underline"><!-- HTML_TAG_START -->Update README.md<!-- HTML_TAG_END --></div>
    <a class="rounded border bg-gray-50 px-1.5 text-sm hover:underline dark:border-gray-800 dark:bg-gray-900" href="/meta-llama/Llama-2-7b-chat-hf/commit/f5db02db724555f92da89c216ac04704f23d4590">f5db02d</a>
    <span class="mx-2 text-green-500 dark:text-green-600 px-1.5 border-green-100 dark:border-green-800 rounded-full border text-xs uppercase" title="This commit is signed and the signature is verified">verified</span>
    <time class="ml-auto hidden flex-none truncate pl-2 text-gray-500 dark:text-gray-400 lg:block" datetime="2024-04-17T08:40:48" title="Wed, 17 Apr 2024 08:40:48 GMT">29 days ago</time></div></div>
        <div class="flex flex-wrap items-center border px-3 py-1.5 text-sm text-gray-800 dark:border-gray-800 dark:bg-gray-900"><div class="flex items-center gap-3 text-sm font-medium"><a class="rounded-md px-1.5 capitalize bg-gray-200 dark:bg-gray-800" href="/meta-llama/Llama-2-7b-chat-hf/blob/main/README.md">preview</a>
                    <a class="rounded-md px-1.5 capitalize " href="/meta-llama/Llama-2-7b-chat-hf/blob/main/README.md?code=true">code</a></div>
                <div class="mx-4 text-gray-200">|</div>
            <a class="my-1 mr-4 flex items-center hover:underline " href="/meta-llama/Llama-2-7b-chat-hf/raw/main/README.md"><svg class="mr-1.5" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32" style="transform: rotate(360deg);"><path d="M31 16l-7 7l-1.41-1.41L28.17 16l-5.58-5.59L24 9l7 7z" fill="currentColor"></path><path d="M1 16l7-7l1.41 1.41L3.83 16l5.58 5.59L8 23l-7-7z" fill="currentColor"></path><path d="M12.419 25.484L17.639 6l1.932.518L14.35 26z" fill="currentColor"></path></svg>
                        raw
                    </a><a class="my-1 mr-4 flex items-center hover:underline " href="/meta-llama/Llama-2-7b-chat-hf/commits/main/README.md"><svg class="mr-1.5" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32" style="transform: rotate(360deg);"><path d="M16 4C9.383 4 4 9.383 4 16s5.383 12 12 12s12-5.383 12-12S22.617 4 16 4zm0 2c5.535 0 10 4.465 10 10s-4.465 10-10 10S6 21.535 6 16S10.465 6 16 6zm-1 2v9h7v-2h-5V8z" fill="currentColor"></path></svg>
                        history
                    </a><a class="my-1 mr-4 flex items-center hover:underline " href="/meta-llama/Llama-2-7b-chat-hf/blame/main/README.md"><svg class="mr-1.5" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32" style="transform: rotate(360deg);"><path d="M16 2a14 14 0 1 0 14 14A14 14 0 0 0 16 2zm0 26a12 12 0 1 1 12-12a12 12 0 0 1-12 12z" fill="currentColor"></path><path d="M11.5 11a2.5 2.5 0 1 0 2.5 2.5a2.48 2.48 0 0 0-2.5-2.5z" fill="currentColor"></path><path d="M20.5 11a2.5 2.5 0 1 0 2.5 2.5a2.48 2.48 0 0 0-2.5-2.5z" fill="currentColor"></path></svg>
                        blame
                    </a>
            <div class="mr-4 flex items-center text-gray-400"><svg class="text-gray-300 text-sm mr-1.5 -translate-y-px" width="1em" height="1em" viewBox="0 0 22 28" fill="none" xmlns="http://www.w3.org/2000/svg"><path fill-rule="evenodd" clip-rule="evenodd" d="M15.3634 10.3639C15.8486 10.8491 15.8486 11.6357 15.3634 12.1209L10.9292 16.5551C10.6058 16.8785 10.0814 16.8785 9.7579 16.5551L7.03051 13.8277C6.54532 13.3425 6.54532 12.5558 7.03051 12.0707C7.51569 11.5855 8.30234 11.5855 8.78752 12.0707L9.7579 13.041C10.0814 13.3645 10.6058 13.3645 10.9292 13.041L13.6064 10.3639C14.0916 9.8787 14.8782 9.8787 15.3634 10.3639Z" fill="currentColor"></path><path fill-rule="evenodd" clip-rule="evenodd" d="M10.6666 27.12C4.93329 25.28 0 19.2267 0 12.7867V6.52001C0 5.40001 0.693334 4.41334 1.73333 4.01334L9.73333 1.01334C10.3333 0.786673 11 0.786673 11.6 1.02667L19.6 4.02667C20.1083 4.21658 20.5465 4.55701 20.8562 5.00252C21.1659 5.44803 21.3324 5.97742 21.3333 6.52001V12.7867C21.3333 19.24 16.4 25.28 10.6666 27.12Z" fill="currentColor" fill-opacity="0.22"></path><path d="M10.0845 1.94967L10.0867 1.94881C10.4587 1.8083 10.8666 1.81036 11.2286 1.95515L11.2387 1.95919L11.2489 1.963L19.2489 4.963L19.25 4.96342C19.5677 5.08211 19.8416 5.29488 20.0351 5.57333C20.2285 5.85151 20.3326 6.18203 20.3333 6.52082C20.3333 6.52113 20.3333 6.52144 20.3333 6.52176L20.3333 12.7867C20.3333 18.6535 15.8922 24.2319 10.6666 26.0652C5.44153 24.2316 1 18.6409 1 12.7867V6.52001C1 5.82357 1.42893 5.20343 2.08883 4.94803L10.0845 1.94967Z" stroke="currentColor" stroke-opacity="0.30" stroke-width="2"></path></svg>

                        No virus
                    </div>
            
            <div class="dark:text-gray-300 sm:ml-auto">22.3 kB</div></div>

        <div class="relative min-h-[100px] rounded-b-lg border border-t-0 leading-tight dark:border-gray-800 dark:bg-gray-925">
            <div class="py-4 px-4 sm:px-6 prose hf-sanitized hf-sanitized-IncAW5ay1r9XFjm75tDSp"><div class="not-prose -mx-6 -mt-4 mb-8 max-h-[300px] min-w-full overflow-auto border-b bg-gradient-to-t from-gray-50 px-6 pb-5 pt-4 font-mono text-xs transition-all dark:from-gray-900 dark:to-gray-950"><div class="mb-2 inline-block rounded-lg border px-2 py-1 font-mono text-xs leading-none">metadata</div>
        <pre><!-- HTML_TAG_START --><span class="hljs-attr">extra_gated_heading:</span> <span class="hljs-string">You</span> <span class="hljs-string">need</span> <span class="hljs-string">to</span> <span class="hljs-string">share</span> <span class="hljs-string">contact</span> <span class="hljs-string">information</span> <span class="hljs-string">with</span> <span class="hljs-string">Meta</span> <span class="hljs-string">to</span> <span class="hljs-string">access</span> <span class="hljs-string">this</span> <span class="hljs-string">model</span>

extra_gated_prompt: >- ### LLAMA 2 COMMUNITY LICENSE AGREEMENT "Agreement" means the terms and conditions for use, reproduction, distribution and modification of the Llama Materials set forth herein.

"Documentation" means the specifications, manuals and documentation accompanying Llama 2 distributed by Meta at https://ai.meta.com/resources/models-and-libraries/llama-downloads/.

"Licensee" or "you" means you, or your employer or any other person or entity (if you are entering into this Agreement on such person or entity's behalf), of the age required under applicable laws, rules or regulations to provide legal consent and that has legal authority to bind your employer or such other person or entity if you are entering in this Agreement on their behalf.

"Llama 2" means the foundational large language models and software and algorithms, including machine-learning model code, trained model weights, inference-enabling code, training-enabling code, fine-tuning enabling code and other elements of the foregoing distributed by Meta at ai.meta.com/resources/models-and-libraries/llama-downloads/.

"Llama Materials" means, collectively, Meta's proprietary Llama 2 and documentation (and any portion thereof) made available under this Agreement.

"Meta" or "we" means Meta Platforms Ireland Limited (if you are located in or, if you are an entity, your principal place of business is in the EEA or Switzerland) and Meta Platforms, Inc. (if you are located outside of the EEA or Switzerland).

By clicking "I Accept" below or by using or distributing any portion or element of the Llama Materials, you agree to be bound by this Agreement.

1. License Rights and Redistribution.

a. Grant of Rights. You are granted a non-exclusive, worldwide, non- transferable and royalty-free limited license under Meta's intellectual property or other rights owned by Meta embodied in the Llama Materials to use, reproduce, distribute, copy, create derivative works of, and make modifications to the Llama Materials.

b. Redistribution and Use.

i. If you distribute or make the Llama Materials, or any derivative works thereof, available to a third party, you shall provide a copy of this Agreement to such third party.

ii. If you receive Llama Materials, or any derivative works thereof, from a Licensee as part of an integrated end user product, then Section 2 of this Agreement will not apply to you.

iii. You must retain in all copies of the Llama Materials that you distribute the following attribution notice within a "Notice" text file distributed as a part of such copies: "Llama 2 is licensed under the LLAMA 2 Community License, Copyright (c) Meta Platforms, Inc. All Rights Reserved."

iv. Your use of the Llama Materials must comply with applicable laws and regulations (including trade compliance laws and regulations) and adhere to the Acceptable Use Policy for the Llama Materials (available at https://ai.meta.com/llama/use-policy), which is hereby incorporated by reference into this Agreement.

v. You will not use the Llama Materials or any output or results of the Llama Materials to improve any other large language model (excluding Llama 2 or derivative works thereof).

2. Additional Commercial Terms. If, on the Llama 2 version release date, the monthly active users of the products or services made available by or for Licensee, or Licensee's affiliates, is greater than 700 million monthly active users in the preceding calendar month, you must request a license from Meta, which Meta may grant to you in its sole discretion, and you are not authorized to exercise any of the rights under this Agreement unless or until Meta otherwise expressly grants you such rights.

3. Disclaimer of Warranty. UNLESS REQUIRED BY APPLICABLE LAW, THE LLAMA MATERIALS AND ANY OUTPUT AND RESULTS THEREFROM ARE PROVIDED ON AN "AS IS" BASIS, WITHOUT WARRANTIES OF ANY KIND, EITHER EXPRESS OR IMPLIED, INCLUDING, WITHOUT LIMITATION, ANY WARRANTIES OF TITLE, NON-INFRINGEMENT, MERCHANTABILITY, OR FITNESS FOR A PARTICULAR PURPOSE. YOU ARE SOLELY RESPONSIBLE FOR DETERMINING THE APPROPRIATENESS OF USING OR REDISTRIBUTING THE LLAMA MATERIALS AND ASSUME ANY RISKS ASSOCIATED WITH YOUR USE OF THE LLAMA MATERIALS AND ANY OUTPUT AND RESULTS.

4. Limitation of Liability. IN NO EVENT WILL META OR ITS AFFILIATES BE LIABLE UNDER ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, TORT, NEGLIGENCE, PRODUCTS LIABILITY, OR OTHERWISE, ARISING OUT OF THIS AGREEMENT, FOR ANY LOST PROFITS OR ANY INDIRECT, SPECIAL, CONSEQUENTIAL, INCIDENTAL, EXEMPLARY OR PUNITIVE DAMAGES, EVEN IF META OR ITS AFFILIATES HAVE BEEN ADVISED OF THE POSSIBILITY OF ANY OF THE FOREGOING.

5. Intellectual Property.

a. No trademark licenses are granted under this Agreement, and in connection with the Llama Materials, neither Meta nor Licensee may use any name or mark owned by or associated with the other or any of its affiliates, except as required for reasonable and customary use in describing and redistributing the Llama Materials.

b. Subject to Meta's ownership of Llama Materials and derivatives made by or for Meta, with respect to any derivative works and modifications of the Llama Materials that are made by you, as between you and Meta, you are and will be the owner of such derivative works and modifications.

c. If you institute litigation or other proceedings against Meta or any entity (including a cross-claim or counterclaim in a lawsuit) alleging that the Llama Materials or Llama 2 outputs or results, or any portion of any of the foregoing, constitutes infringement of intellectual property or other rights owned or licensable by you, then any licenses granted to you under this Agreement shall terminate as of the date such litigation or claim is filed or instituted. You will indemnify and hold harmless Meta from and against any claim by any third party arising out of or related to your use or distribution of the Llama Materials.

6. Term and Termination. The term of this Agreement will commence upon your acceptance of this Agreement or access to the Llama Materials and will continue in full force and effect until terminated in accordance with the terms and conditions herein. Meta may terminate this Agreement if you are in breach of any term or condition of this Agreement. Upon termination of this Agreement, you shall delete and cease use of the Llama Materials. Sections 3, 4 and 7 shall survive the termination of this Agreement.

7. Governing Law and Jurisdiction. This Agreement will be governed and construed under the laws of the State of California without regard to choice of law principles, and the UN Convention on Contracts for the International Sale of Goods does not apply to this Agreement. The courts of California shall have exclusive jurisdiction of any dispute arising out of this Agreement.

### Llama 2 Acceptable Use Policy

Meta is committed to promoting safe and fair use of its tools and features, including Llama 2. If you access or use Llama 2, you agree to this Acceptable Use Policy (“Policy”). The most recent copy of this policy can be found at [ai.meta.com/llama/use-policy](http://ai.meta.com/llama/use-policy).

#### Prohibited Uses

We want everyone to use Llama 2 safely and responsibly. You agree you will not use, or allow others to use, Llama 2 to:

1. Violate the law or others’ rights, including to: 1. Engage in, promote, generate, contribute to, encourage, plan, incite, or further illegal or unlawful activity or content, such as: 1. Violence or terrorism 2. Exploitation or harm to children, including the solicitation, creation, acquisition, or dissemination of child exploitative content or failure to report Child Sexual Abuse Material 3. Human trafficking, exploitation, and sexual violence 4. The illegal distribution of information or materials to minors, including obscene materials, or failure to employ legally required age-gating in connection with such information or materials. 5. Sexual solicitation 6. Any other criminal activity 2. Engage in, promote, incite, or facilitate the harassment, abuse, threatening, or bullying of individuals or groups of individuals 3. Engage in, promote, incite, or facilitate discrimination or other unlawful or harmful conduct in the provision of employment, employment benefits, credit, housing, other economic benefits, or other essential goods and services 4. Engage in the unauthorized or unlicensed practice of any profession including, but not limited to, financial, legal, medical/health, or related professional practices 5. Collect, process, disclose, generate, or infer health, demographic, or other sensitive personal or private information about individuals without rights and consents required by applicable laws 6. Engage in or facilitate any action or generate any content that infringes, misappropriates, or otherwise violates any third-party rights, including the outputs or results of any products or services using the Llama 2 Materials 7. Create, generate, or facilitate the creation of malicious code, malware, computer viruses or do anything else that could disable, overburden, interfere with or impair the proper working, integrity, operation or appearance of a website or computer system 2. Engage in, promote, incite, facilitate, or assist in the planning or development of activities that present a risk of death or bodily harm to individuals, including use of Llama 2 related to the following: 1. Military, warfare, nuclear industries or applications, espionage, use for materials or activities that are subject to the International Traffic Arms Regulations (ITAR) maintained by the United States Department of State 2. Guns and illegal weapons (including weapon development) 3. Illegal drugs and regulated/controlled substances 4. Operation of critical infrastructure, transportation technologies, or heavy machinery 5. Self-harm or harm to others, including suicide, cutting, and eating disorders 6. Any content intended to incite or promote violence, abuse, or any infliction of bodily harm to an individual 3. Intentionally deceive or mislead others, including use of Llama 2 related to the following: 1. Generating, promoting, or furthering fraud or the creation or promotion of disinformation 2. Generating, promoting, or furthering defamatory content, including the creation of defamatory statements, images, or other content 3. Generating, promoting, or further distributing spam 4. Impersonating another individual without consent, authorization, or legal right 5. Representing that the use of Llama 2 or outputs are human-generated 6. Generating or facilitating false online engagement, including fake reviews and other means of fake online engagement 4. Fail to appropriately disclose to end users any known dangers of your AI system Please report any violation of this Policy, software “bug,” or other problems that could lead to a violation of this Policy through one of the following means: Reporting issues with the model: [github.com/facebookresearch/llama](http://github.com/facebookresearch/llama) Reporting risky content generated by the model: [developers.facebook.com/llama_output_feedback](http://developers.facebook.com/llama_output_feedback) Reporting bugs and security concerns: [facebook.com/whitehat/info](http://facebook.com/whitehat/info) Reporting violations of the Acceptable Use Policy or unlicensed uses of Llama: [LlamaUseReport@meta.com](mailto:LlamaUseReport@meta.com) extra_gated_fields: First Name: text Last Name: text Date of birth: date_picker Country: country Affiliation: text geo: ip_location By clicking Submit below I accept the terms of the license and acknowledge that the information I provide will be collected stored processed and shared in accordance with the Meta Privacy Policy: checkbox extra_gated_description: >- The information you provide will be collected, stored, processed and shared in accordance with the Meta Privacy Policy. extra_gated_button_content: Submit language: - en pipeline_tag: text-generation tags: - facebook - meta - pytorch - llama - llama-2 license: llama2

<!-- HTML_TAG_START --><h1 class="relative group flex items-center">
<a rel="nofollow" href="#llama-2" class="block pr-1.5 text-lg md:absolute md:p-1.5 md:opacity-0 md:group-hover:opacity-100 md:right-full" id="llama-2">
    <span class="header-link"><svg viewBox="0 0 256 256" preserveAspectRatio="xMidYMid meet" height="1em" width="1em" role="img" aria-hidden="true" xmlns:xlink="http://www.w3.org/1999/xlink" xmlns="http://www.w3.org/2000/svg" class="text-gray-500 hover:text-black dark:hover:text-gray-200 w-4"><path fill="currentColor" d="M167.594 88.393a8.001 8.001 0 0 1 0 11.314l-67.882 67.882a8 8 0 1 1-11.314-11.315l67.882-67.881a8.003 8.003 0 0 1 11.314 0zm-28.287 84.86l-28.284 28.284a40 40 0 0 1-56.567-56.567l28.284-28.284a8 8 0 0 0-11.315-11.315l-28.284 28.284a56 56 0 0 0 79.196 79.197l28.285-28.285a8 8 0 1 0-11.315-11.314zM212.852 43.14a56.002 56.002 0 0 0-79.196 0l-28.284 28.284a8 8 0 1 0 11.314 11.314l28.284-28.284a40 40 0 0 1 56.568 56.567l-28.285 28.285a8 8 0 0 0 11.315 11.314l28.284-28.284a56.065 56.065 0 0 0 0-79.196z"></path></svg></span>
</a>
<span>
    <strong>Llama 2</strong>
</span>

Llama 2 is a collection of pretrained and fine-tuned generative text models ranging in scale from 7 billion to 70 billion parameters. This is the repository for the 7B fine-tuned model, optimized for dialogue use cases and converted for the Hugging Face Transformers format. Links to other models can be found in the index at the bottom.

Model Details

Note: Use of this model is governed by the Meta license. In order to download the model weights and tokenizer, please visit the website and accept our License before requesting access here.

Meta developed and publicly released the Llama 2 family of large language models (LLMs), a collection of pretrained and fine-tuned generative text models ranging in scale from 7 billion to 70 billion parameters. Our fine-tuned LLMs, called Llama-2-Chat, are optimized for dialogue use cases. Llama-2-Chat models outperform open-source chat models on most benchmarks we tested, and in our human evaluations for helpfulness and safety, are on par with some popular closed-source models like ChatGPT and PaLM.

Model Developers Meta

Variations Llama 2 comes in a range of parameter sizes — 7B, 13B, and 70B — as well as pretrained and fine-tuned variations.

Input Models input text only.

Output Models generate text only.

Model Architecture Llama 2 is an auto-regressive language model that uses an optimized transformer architecture. The tuned versions use supervised fine-tuning (SFT) and reinforcement learning with human feedback (RLHF) to align to human preferences for helpfulness and safety.

    </thead><tbody><tr>
Training Data Params Content Length GQA Tokens LR
Llama 2 A new mix of publicly available online data 7B 4k ✗ 2.0T 3.0 x 10-4
Llama 2 A new mix of publicly available online data 13B 4k ✗ 2.0T 3.0 x 10-4
Llama 2 A new mix of publicly available online data 70B 4k ✔ 2.0T 1.5 x 10-4

Llama 2 family of models. Token counts refer to pretraining data only. All models are trained with a global batch-size of 4M tokens. Bigger models - 70B -- use Grouped-Query Attention (GQA) for improved inference scalability.

Model Dates Llama 2 was trained between January 2023 and July 2023.

Status This is a static model trained on an offline dataset. Future versions of the tuned models will be released as we improve model safety with community feedback.

License A custom commercial license is available at: https://ai.meta.com/resources/models-and-libraries/llama-downloads/

Research Paper "Llama-2: Open Foundation and Fine-tuned Chat Models"

Intended Use

Intended Use Cases Llama 2 is intended for commercial and research use in English. Tuned models are intended for assistant-like chat, whereas pretrained models can be adapted for a variety of natural language generation tasks.

To get the expected features and performance for the chat versions, a specific formatting needs to be followed, including the INST and <<SYS>> tags, BOS and EOS tokens, and the whitespaces and breaklines in between (we recommend calling strip() on inputs to avoid double-spaces). See our reference code in github for details: chat_completion.

Out-of-scope Uses Use in any manner that violates applicable laws or regulations (including trade compliance laws).Use in languages other than English. Use in any other way that is prohibited by the Acceptable Use Policy and Licensing Agreement for Llama 2.

Hardware and Software

Training Factors We used custom training libraries, Meta's Research Super Cluster, and production clusters for pretraining. Fine-tuning, annotation, and evaluation were also performed on third-party cloud compute.

Carbon Footprint Pretraining utilized a cumulative 3.3M GPU hours of computation on hardware of type A100-80GB (TDP of 350-400W). Estimated total emissions were 539 tCO2eq, 100% of which were offset by Meta’s sustainability program.

    </thead><tbody><tr>
Time (GPU hours) Power Consumption (W) Carbon Emitted(tCO2eq)
Llama 2 7B 184320 400 31.22
Llama 2 13B 368640 400 62.44
Llama 2 70B 1720320 400 291.42
Total 3311616 539.00

CO2 emissions during pretraining. Time: total GPU time required for training each model. Power Consumption: peak power capacity per GPU device for the GPUs used adjusted for power usage efficiency. 100% of the emissions are directly offset by Meta's sustainability program, and because we are openly releasing these models, the pretraining costs do not need to be incurred by others.

Training Data

Overview Llama 2 was pretrained on 2 trillion tokens of data from publicly available sources. The fine-tuning data includes publicly available instruction datasets, as well as over one million new human-annotated examples. Neither the pretraining nor the fine-tuning datasets include Meta user data.

Data Freshness The pretraining data has a cutoff of September 2022, but some tuning data is more recent, up to July 2023.

Evaluation Results

In this section, we report the results for the Llama 1 and Llama 2 models on standard academic benchmarks.For all the evaluations, we use our internal evaluations library.

    </thead><tbody><tr>
Model Size Code Commonsense Reasoning World Knowledge Reading Comprehension Math MMLU BBH AGI Eval
Llama 1 7B 14.1 60.8 46.2 58.5 6.95 35.1 30.3 23.9
Llama 1 13B 18.9 66.1 52.6 62.3 10.9 46.9 37.0 33.9
Llama 1 33B 26.0 70.0 58.4 67.6 21.4 57.8 39.8 41.7
Llama 1 65B 30.7 70.7 60.5 68.6 30.8 63.4 43.5 47.6
Llama 2 7B 16.8 63.9 48.9 61.3 14.6 45.3 32.6 29.3
Llama 2 13B 24.5 66.9 55.4 65.8 28.7 54.8 39.4 39.1
Llama 2 70B 37.5 71.9 63.6 69.4 35.2 68.9 51.2 54.2

Overall performance on grouped academic benchmarks. Code: We report the average pass@1 scores of our models on HumanEval and MBPP. Commonsense Reasoning: We report the average of PIQA, SIQA, HellaSwag, WinoGrande, ARC easy and challenge, OpenBookQA, and CommonsenseQA. We report 7-shot results for CommonSenseQA and 0-shot results for all other benchmarks. World Knowledge: We evaluate the 5-shot performance on NaturalQuestions and TriviaQA and report the average. Reading Comprehension: For reading comprehension, we report the 0-shot average on SQuAD, QuAC, and BoolQ. MATH: We report the average of the GSM8K (8 shot) and MATH (4 shot) benchmarks at top 1.

    </thead><tbody><tr>
TruthfulQA Toxigen
Llama 1 7B 27.42 23.00
Llama 1 13B 41.74 23.08
Llama 1 33B 44.19 22.57
Llama 1 65B 48.71 21.77
Llama 2 7B 33.29 21.25
Llama 2 13B 41.86 26.10
Llama 2 70B 50.18 24.60

Evaluation of pretrained LLMs on automatic safety benchmarks. For TruthfulQA, we present the percentage of generations that are both truthful and informative (the higher the better). For ToxiGen, we present the percentage of toxic generations (the smaller the better).

    </thead><tbody><tr>
TruthfulQA Toxigen
Llama-2-Chat 7B 57.04 0.00
Llama-2-Chat 13B 62.18 0.00
Llama-2-Chat 70B 64.14 0.01

Evaluation of fine-tuned LLMs on different safety datasets. Same metric definitions as above.

Ethical Considerations and Limitations

Llama 2 is a new technology that carries risks with use. Testing conducted to date has been in English, and has not covered, nor could it cover all scenarios. For these reasons, as with all LLMs, Llama 2’s potential outputs cannot be predicted in advance, and the model may in some instances produce inaccurate, biased or other objectionable responses to user prompts. Therefore, before deploying any applications of Llama 2, developers should perform safety testing and tuning tailored to their specific applications of the model.

Please see the Responsible Use Guide available at https://ai.meta.com/llama/responsible-use-guide/

Reporting Issues

Please report any software “bug,” or other problems with the models through one of the following means:

Llama Model Index 

    </thead><tbody><tr>
Model Llama2 Llama2-hf Llama2-chat Llama2-chat-hf
7B Link Link Link Link
13B Link Link Link Link
70B Link Link Link Link 
</div>

    <script>
        import("/front/build/kube-cc446aa/index.js");
        window.moonSha = "kube-cc446aa/";
        window.hubConfig = JSON.parse(`{"features":{"signupDisabled":false},"sshGitUrl":"git@hf.co","moonHttpUrl":"https://huggingface.co","captchaApiKey":"bd5f2066-93dc-4bdd-a64b-a24646ca3859","captchaDisabledOnSignup":true,"datasetViewerPublicUrl":"https://datasets-server.huggingface.co","stripePublicKey":"pk_live_x2tdjFXBCvXo2FFmMybezpeM00J6gPCAAc","environment":"production","userAgent":"HuggingFace (production)","spacesIframeDomain":"hf.space","spacesApiUrl":"https://api.hf.space"}`);
    </script>

    <!-- Stripe -->
    <script>
        if (["hf.co", "huggingface.co"].includes(window.location.hostname)) {
            const script = document.createElement("script");
            script.src = "https://js.stripe.com/v3/";
            script.async = true;
            document.head.appendChild(script);
        }
    </script>
</body>