--- language: - de - en tags: - two stage dpo - dpo license: other license_name: llama3 license_link: LICENSE extra_gated_prompt: >- ### META LLAMA 3 COMMUNITY LICENSE AGREEMENT Meta Llama 3 Version Release Date: April 18, 2024 "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 Meta Llama 3 distributed by Meta at https://llama.meta.com/get-started/. "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. "Meta Llama 3" 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 https://llama.meta.com/llama-downloads. "Llama Materials" means, collectively, Meta’s proprietary Meta Llama 3 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). 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 available the Llama Materials (or any derivative works thereof), or a product or service that uses any of them, including another AI model, you shall (A) provide a copy of this Agreement with any such Llama Materials; and (B) prominently display “Built with Meta Llama 3” on a related website, user interface, blogpost, about page, or product documentation. If you use the Llama Materials to create, train, fine tune, or otherwise improve an AI model, which is distributed or made available, you shall also include “Llama 3” at the beginning of any such AI model name. 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: “Meta Llama 3 is licensed under the Meta Llama 3 Community License, Copyright © 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://llama.meta.com/llama3/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 Meta Llama 3 or derivative works thereof). 2. Additional Commercial Terms. If, on the Meta Llama 3 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, AND META DISCLAIMS ALL WARRANTIES OF ANY KIND, BOTH EXPRESS AND 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 or as set forth in this Section 5(a). Meta hereby grants you a license to use “Llama 3” (the “Mark”) solely as required to comply with the last sentence of Section 1.b.i. You will comply with Meta’s brand guidelines (currently accessible at https://about.meta.com/brand/resources/meta/company-brand/ ). All goodwill arising out of your use of the Mark will inure to the benefit of Meta. 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 Meta Llama 3 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. ### Meta Llama 3 Acceptable Use Policy Meta is committed to promoting safe and fair use of its tools and features, including Meta Llama 3. If you access or use Meta Llama 3, you agree to this Acceptable Use Policy (“Policy”). The most recent copy of this policy can be found at [https://llama.meta.com/llama3/use-policy](https://llama.meta.com/llama3/use-policy) #### Prohibited Uses We want everyone to use Meta Llama 3 safely and responsibly. You agree you will not use, or allow others to use, Meta Llama 3 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 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 Meta Llama 3 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 Meta Llama 3 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 Meta Llama 3 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: [https://github.com/meta-llama/llama3](https://github.com/meta-llama/llama3) * Reporting risky content generated by the model: developers.facebook.com/llama_output_feedback * Reporting bugs and security concerns: facebook.com/whitehat/info * Reporting violations of the Acceptable Use Policy or unlicensed uses of Meta Llama 3: 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](https://www.facebook.com/privacy/policy/). extra_gated_button_content: Submit --- ![SauerkrautLM](https://vago-solutions.ai/wp-content/uploads/2024/04/Llama3-Pic.png "Llama-3-SauerkrautLM-8b-Instruct") ## VAGO solutions Llama-3-SauerkrautLM-8b-Instruct Introducing **Llama-3-SauerkrautLM-8b-Instruct** – our Sauerkraut version of the powerful [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co./meta-llama/Meta-Llama-3-8B-Instruct)! The model **Llama-3-SauerkrautLM-8b-Instruct** is a **joint effort** between **VAGO Solutions** and **Hyperspace.ai.** - Aligned with **DPO** # Table of Contents 1. [Overview of all Llama-3-SauerkrautLM-8b-Instruct](#all-Llama-3-SauerkrautLM-8b-Instruct) 2. [Model Details](#model-details) - [Prompt template](#prompt-template) - [Training procedure](#proceed-of-the-training) 3. [Evaluation](#evaluation) 5. [Disclaimer](#disclaimer) 6. [Contact](#contact) 7. [Collaborations](#collaborations) 8. [Acknowledgement](#acknowledgement) ## All SauerkrautLM-llama-3-8B-Instruct | Model | HF | EXL2 | GGUF | AWQ | |-------|-------|-------|-------|-------| | Llama-3-SauerkrautLM-8b-Instruct | [Link](https://huggingface.co./VAGOsolutions/Llama-3-SauerkrautLM-8b-Instruct) | [Link](https://huggingface.co./bartowski/Llama-3-SauerkrautLM-8b-Instruct-exl2) | [Link](https://huggingface.co./bartowski/Llama-3-SauerkrautLM-8b-Instruct-GGUF) | coming soon | ## Model Details **SauerkrautLM-llama-3-8B-Instruct** - **Model Type:** Llama-3-SauerkrautLM-8b-Instruct is a finetuned Model based on [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co./meta-llama/Meta-Llama-3-8B-Instruct) - **Language(s):** German, English - **License:** [meta-llama](https://llama.meta.com/llama3/license) - **Contact:** [VAGO solutions](https://vago-solutions.ai), [Hyperspace.ai](https://hyperspace.computer/) ### Training procedure: - We trained this model in a two staged DPO Fine-Tuning for 1 epoch with 70k data and another epoch with 20k data. - LaserRMT version coming soon **We improved the model's capabilities noticably by feeding it with curated German data.** ### Prompt Template: **English:** ``` <|begin_of_text|><|start_header_id|>system<|end_header_id|> You are a helpful AI assistant.<|eot_id|><|start_header_id|>user<|end_header_id|> Input<|eot_id|><|start_header_id|>assistant<|end_header_id|> ``` **German:** ``` <|begin_of_text|><|start_header_id|>system<|end_header_id|> Du bist ein freundlicher und hilfreicher deutscher KI-Assistent.<|eot_id|><|start_header_id|>user<|end_header_id|> Input<|eot_id|><|start_header_id|>assistant<|end_header_id|> ``` ### Example output of german language: ``` Prompt: Erkläre mir die Vorteile für das Fine-Tuning von Meta's LLama Modellen. Antwort: Sehr gern! Fine-tuning von Meta's LLaMA-Modellen ist eine sehr effektive Möglichkeit, um Ihre Anwendung oder Ihr Projekt mit einer hochentwickelten Sprachverarbeitung auszustatten. Die Vorteile des Fine-Tunings von LLaMA-Modellen sind: Adaptation an spezielle Aufgaben: Durch das Fine-Tuning können Sie die Modelle auf Ihre speziellen Bedürfnisse und Anforderungen anpassen. Dies ermöglicht es Ihnen, die Leistung der Modelle in Ihren Anwendungen zu verbessern. Verbesserte Genauigkeit: Die fine-tuned Modelle lernen, sich an die spezifischen Merkmale Ihres Datenbestands anzupassen, was zu einer besseren Genauigkeit bei der Textklassifizierung, -generierung, -summarisierung usw. führt. Anpassung an Branche oder Domain: Wenn Sie beispielsweise ein Medizinprojekt haben, können Sie die Modelle auf medizinische Fachterminologie und -konzepte trainieren, um eine höhere Präzision bei der Analyse medizinischer Texte zu erzielen. Kosten-Effektivität: Im Vergleich zum Training neuer Modelle von Grund auf kann das Fine-Tuning viel kosteneffektiver sein, da Sie nur einen kleinen Teil des Trainingsdatums benötigen, um die Modelle an Ihre spezifischen Anforderungen anzupassen. Schnellere Entwicklung: Das Fine-Tuning ermöglicht es Entwicklern, schnell neue Funktionen und Features in ihre Anwendungen einzufügen, ohne dass sie lange warten müssen, bis neue Modelle trainiert werden. Bessere Interpretierbarkeit: Da die fine-tuned Modelle auf Ihre spezifischen Daten bestimmt wurden, können Sie leichter verstehen, warum bestimmte Entscheidungen getroffen werden, was wichtig ist, wenn es um Transparenz und Verantwortlichkeit geht. Insgesamt bietet das Fine-Tuning von LLaMA-Modellen eine flexible und effektive Möglichkeit, um Ihre Anwendungen und Projekte durch die Integration von fortschrittlichen Sprachmodellen zu verbessern. ``` ## Evaluation **Open LLM Leaderboard:** evaluated with lm-evaluation-benchmark-harness 0.4.2 | Metric | Value | |-----------------------|---------------------------| | Avg. | **74.57** | | ARC (25-shot) | 74.66 | | HellaSwag (10-shot) | 89.60 | | MMLU (5-shot) | 66.55 | | TruthfulQA (0-shot) | 66.32 | | Winogrande (5-shot) | 80.98 | | GSM8K (5-shot) | 69.29 | **MT-Bench English** ``` ########## First turn ########## score model turn Llama-3-SauerkrautLM-8b-Instruct 1 8.15625 ########## Second turn ########## score model turn Llama-3-SauerkrautLM-8b-Instruct 2 7.65 ########## Average ########## score model Llama-3-SauerkrautLM-8b-Instruct 7.903125 * ``` * due to specific instruction training the english MT-Bench score is slightly lower than the original LLama-3-8B-Instruct **MT-Bench German** ``` ########## First turn ########## score model turn Llama-3-SauerkrautLM-8b-Instruct 1 7.675 ########## Second turn ########## score model turn Llama-3-SauerkrautLM-8b-Instruct 2 7.6375 ########## Average ########## score model Llama-3-SauerkrautLM-8b-Instruct 7.65625 ``` **German RAG LLM Evaluation** corrected result after FIX: https://github.com/huggingface/lighteval/pull/171 ``` | Task |Version|Metric|Value| |Stderr| |------------------------------------------------------|------:|------|----:|---|-----:| |all | |acc |0.910|± |0.0084| |community:german_rag_eval:_average:0 | |acc |0.910|± |0.0084| |community:german_rag_eval:choose_context_by_question:0| 0|acc |0.928|± |0.0082| |community:german_rag_eval:choose_question_by_context:0| 0|acc |0.824|± |0.0120| |community:german_rag_eval:context_question_match:0 | 0|acc |0.982|± |0.0042| |community:german_rag_eval:question_answer_match:0 | 0|acc |0.906|± |0.0092| ``` ## Disclaimer We must inform users that despite our best efforts in data cleansing, the possibility of uncensored content slipping through cannot be entirely ruled out. However, we cannot guarantee consistently appropriate behavior. Therefore, if you encounter any issues or come across inappropriate content, we kindly request that you inform us through the contact information provided. Additionally, it is essential to understand that the licensing of these models does not constitute legal advice. We are not held responsible for the actions of third parties who utilize our models. ## Contact If you are interested in customized LLMs for business applications, please get in contact with us via our websites. We are also grateful for your feedback and suggestions. ## Collaborations We are also keenly seeking support and investment for our startups, VAGO solutions and Hyperspace where we continuously advance the development of robust language models designed to address a diverse range of purposes and requirements. If the prospect of collaboratively navigating future challenges excites you, we warmly invite you to reach out to us at [VAGO solutions](https://vago-solutions.de/#Kontakt), [Hyperspace.computer](https://hyperspace.computer/) ## Acknowledgement Many thanks to [Meta](https://huggingface.co./meta-llama/Meta-Llama-3-8B-Instruct) for providing such valuable model to the Open-Source community. Also many thanks to [bartowski](https://huggingface.co./bartowski) for super fast quantification of our Model in GGUF and EXL format.