初始化项目，由ModelHub XC社区提供模型

Model: TheBloke/SauerkrautLM-7B-v1-AWQ
Source: Original Platform

.gitattributes

@@ -0,0 +1,36 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+model.safetensors filter=lfs diff=lfs merge=lfs -text

LICENSE.txt

@@ -0,0 +1,126 @@
+LLAMA 2 COMMUNITY LICENSE AGREEMENT	
+Llama 2 Version Release Date: July 18, 2023
+
+"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 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. 
+

Notice

@@ -0,0 +1 @@
+Llama 2 is licensed under the LLAMA 2 Community License, Copyright © Meta Platforms, Inc. All Rights Reserved.

README.md

@@ -0,0 +1,400 @@
+---
+base_model: VAGOsolutions/SauerkrautLM-7b-v1
+inference: false
+language:
+- de
+- en
+library_name: transformers
+license: llama2
+model_creator: VAGO solutions
+model_name: SauerkrautLM 7B v1
+model_type: llama
+pipeline_tag: text-generation
+prompt_template: "Ein Chat zwischen einem Benutzer und einem KI-Assistenten. Der KI-Assistent\
+  \ gibt hilfreiche, detaillierte und h\xF6fliche Antworten. \nUser: {prompt} \nAssistant:\n"
+quantized_by: TheBloke
+---
+
+<!-- header start -->
+<!-- 200823 -->
+<div style="width: auto; margin-left: auto; margin-right: auto">
+<img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;">
+</div>
+<div style="display: flex; justify-content: space-between; width: 100%;">
+    <div style="display: flex; flex-direction: column; align-items: flex-start;">
+        <p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://discord.gg/theblokeai">Chat & support: TheBloke's Discord server</a></p>
+    </div>
+    <div style="display: flex; flex-direction: column; align-items: flex-end;">
+        <p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://www.patreon.com/TheBlokeAI">Want to contribute? TheBloke's Patreon page</a></p>
+    </div>
+</div>
+<div style="text-align:center; margin-top: 0em; margin-bottom: 0em"><p style="margin-top: 0.25em; margin-bottom: 0em;">TheBloke's LLM work is generously supported by a grant from <a href="https://a16z.com">andreessen horowitz (a16z)</a></p></div>
+<hr style="margin-top: 1.0em; margin-bottom: 1.0em;">
+<!-- header end -->
+
+# SauerkrautLM 7B v1 - AWQ
+- Model creator: [VAGO solutions](https://huggingface.co/VAGOsolutions)
+- Original model: [SauerkrautLM 7B v1](https://huggingface.co/VAGOsolutions/SauerkrautLM-7b-v1)
+
+<!-- description start -->
+## Description
+
+This repo contains AWQ model files for [VAGO solutions's SauerkrautLM 7B v1](https://huggingface.co/VAGOsolutions/SauerkrautLM-7b-v1).
+
+
+### About AWQ
+
+AWQ is an efficient, accurate and blazing-fast low-bit weight quantization method, currently supporting 4-bit quantization. Compared to GPTQ, it offers faster Transformers-based inference.
+
+It is also now supported by continuous batching server [vLLM](https://github.com/vllm-project/vllm), allowing use of Llama AWQ models for high-throughput concurrent inference in multi-user server scenarios.
+
+As of September 25th 2023, preliminary Llama-only AWQ support has also been added to [Huggingface Text Generation Inference (TGI)](https://github.com/huggingface/text-generation-inference).
+
+Note that, at the time of writing, overall throughput is still lower than running vLLM or TGI with unquantised models, however using AWQ enables using much smaller GPUs which can lead to easier deployment and overall cost savings. For example, a 70B model can be run on 1 x 48GB GPU instead of 2 x 80GB.
+<!-- description end -->
+<!-- repositories-available start -->
+## Repositories available
+
+* [AWQ model(s) for GPU inference.](https://huggingface.co/TheBloke/SauerkrautLM-7B-v1-AWQ)
+* [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/SauerkrautLM-7B-v1-GPTQ)
+* [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/SauerkrautLM-7B-v1-GGUF)
+* [VAGO solutions's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/VAGOsolutions/SauerkrautLM-7b-v1)
+<!-- repositories-available end -->
+
+<!-- prompt-template start -->
+## Prompt template: Sauerkraut
+
+```
+Ein Chat zwischen einem Benutzer und einem KI-Assistenten. Der KI-Assistent gibt hilfreiche, detaillierte und höfliche Antworten. 
+User: {prompt} 
+Assistant:
+
+```
+
+<!-- prompt-template end -->
+
+
+<!-- README_AWQ.md-provided-files start -->
+## Provided files, and AWQ parameters
+
+For my first release of AWQ models, I am releasing 128g models only. I will consider adding 32g as well if there is interest, and once I have done perplexity and evaluation comparisons, but at this time 32g models are still not fully tested with AutoAWQ and vLLM.
+
+Models are released as sharded safetensors files.
+
+| Branch | Bits | GS | AWQ Dataset | Seq Len | Size |
+| ------ | ---- | -- | ----------- | ------- | ---- |
+| [main](https://huggingface.co/TheBloke/SauerkrautLM-7B-v1-AWQ/tree/main) | 4 | 128 | [German Quad](https://huggingface.co/datasets/deepset/germanquad) | 4096 | 3.89 GB
+
+<!-- README_AWQ.md-provided-files end -->
+
+<!-- README_AWQ.md-use-from-vllm start -->
+## Serving this model from vLLM
+
+Documentation on installing and using vLLM [can be found here](https://vllm.readthedocs.io/en/latest/).
+
+Note: at the time of writing, vLLM has not yet done a new release with AWQ support.
+
+If you try the vLLM examples below and get an error about `quantization` being unrecognised, or other AWQ-related issues, please install vLLM from Github source.
+
+- When using vLLM as a server, pass the `--quantization awq` parameter, for example:
+
+```shell
+python3 python -m vllm.entrypoints.api_server --model TheBloke/SauerkrautLM-7B-v1-AWQ --quantization awq --dtype half
+```
+
+When using vLLM from Python code, pass the `quantization=awq` parameter, for example:
+
+```python
+from vllm import LLM, SamplingParams
+
+prompts = [
+    "Hello, my name is",
+    "The president of the United States is",
+    "The capital of France is",
+    "The future of AI is",
+]
+sampling_params = SamplingParams(temperature=0.8, top_p=0.95)
+
+llm = LLM(model="TheBloke/SauerkrautLM-7B-v1-AWQ", quantization="awq", dtype="half")
+
+outputs = llm.generate(prompts, sampling_params)
+
+# Print the outputs.
+for output in outputs:
+    prompt = output.prompt
+    generated_text = output.outputs[0].text
+    print(f"Prompt: {prompt!r}, Generated text: {generated_text!r}")
+```
+<!-- README_AWQ.md-use-from-vllm start -->
+
+<!-- README_AWQ.md-use-from-tgi start -->
+## Serving this model from Text Generation Inference (TGI)
+
+Use TGI version 1.1.0 or later. The official Docker container is: `ghcr.io/huggingface/text-generation-inference:1.1.0`
+
+Example Docker parameters:
+
+```shell
+--model-id TheBloke/SauerkrautLM-7B-v1-AWQ --port 3000 --quantize awq --max-input-length 3696 --max-total-tokens 4096 --max-batch-prefill-tokens 4096
+```
+
+Example Python code for interfacing with TGI (requires huggingface-hub 0.17.0 or later):
+
+```shell
+pip3 install huggingface-hub
+```
+
+```python
+from huggingface_hub import InferenceClient
+
+endpoint_url = "https://your-endpoint-url-here"
+
+prompt = "Tell me about AI"
+prompt_template=f'''Ein Chat zwischen einem Benutzer und einem KI-Assistenten. Der KI-Assistent gibt hilfreiche, detaillierte und höfliche Antworten. 
+User: {prompt} 
+Assistant:
+
+'''
+
+client = InferenceClient(endpoint_url)
+response = client.text_generation(prompt,
+                                  max_new_tokens=128,
+                                  do_sample=True,
+                                  temperature=0.7,
+                                  top_p=0.95,
+                                  top_k=40,
+                                  repetition_penalty=1.1)
+
+print(f"Model output: {response}")
+```
+<!-- README_AWQ.md-use-from-tgi end -->
+
+<!-- README_AWQ.md-use-from-python start -->
+## How to use this AWQ model from Python code
+
+### Install the necessary packages
+
+Requires: [AutoAWQ](https://github.com/casper-hansen/AutoAWQ) 0.1.1 or later
+
+```shell
+pip3 install autoawq
+```
+
+If you have problems installing [AutoAWQ](https://github.com/casper-hansen/AutoAWQ) using the pre-built wheels, install it from source instead:
+
+```shell
+pip3 uninstall -y autoawq
+git clone https://github.com/casper-hansen/AutoAWQ
+cd AutoAWQ
+pip3 install .
+```
+
+### You can then try the following example code
+
+```python
+from awq import AutoAWQForCausalLM
+from transformers import AutoTokenizer
+
+model_name_or_path = "TheBloke/SauerkrautLM-7B-v1-AWQ"
+
+# Load model
+model = AutoAWQForCausalLM.from_quantized(model_name_or_path, fuse_layers=True,
+                                          trust_remote_code=False, safetensors=True)
+tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, trust_remote_code=False)
+
+prompt = "Tell me about AI"
+prompt_template=f'''Ein Chat zwischen einem Benutzer und einem KI-Assistenten. Der KI-Assistent gibt hilfreiche, detaillierte und höfliche Antworten. 
+User: {prompt} 
+Assistant:
+
+'''
+
+print("\n\n*** Generate:")
+
+tokens = tokenizer(
+    prompt_template,
+    return_tensors='pt'
+).input_ids.cuda()
+
+# Generate output
+generation_output = model.generate(
+    tokens,
+    do_sample=True,
+    temperature=0.7,
+    top_p=0.95,
+    top_k=40,
+    max_new_tokens=512
+)
+
+print("Output: ", tokenizer.decode(generation_output[0]))
+
+"""
+# Inference should be possible with transformers pipeline as well in future
+# But currently this is not yet supported by AutoAWQ (correct as of September 25th 2023)
+from transformers import pipeline
+
+print("*** Pipeline:")
+pipe = pipeline(
+    "text-generation",
+    model=model,
+    tokenizer=tokenizer,
+    max_new_tokens=512,
+    do_sample=True,
+    temperature=0.7,
+    top_p=0.95,
+    top_k=40,
+    repetition_penalty=1.1
+)
+
+print(pipe(prompt_template)[0]['generated_text'])
+"""
+```
+<!-- README_AWQ.md-use-from-python end -->
+
+<!-- README_AWQ.md-compatibility start -->
+## Compatibility
+
+The files provided are tested to work with:
+
+- [AutoAWQ](https://github.com/casper-hansen/AutoAWQ)
+- [vLLM](https://github.com/vllm-project/vllm)
+- [Huggingface Text Generation Inference (TGI)](https://github.com/huggingface/text-generation-inference)
+
+TGI merged AWQ support on September 25th, 2023: [TGI PR #1054](https://github.com/huggingface/text-generation-inference/pull/1054).  Use the `:latest` Docker container until the next TGI release is made.
+
+<!-- README_AWQ.md-compatibility end -->
+
+<!-- footer start -->
+<!-- 200823 -->
+## Discord
+
+For further support, and discussions on these models and AI in general, join us at:
+
+[TheBloke AI's Discord server](https://discord.gg/theblokeai)
+
+## Thanks, and how to contribute
+
+Thanks to the [chirper.ai](https://chirper.ai) team!
+
+Thanks to Clay from [gpus.llm-utils.org](llm-utils)!
+
+I've had a lot of people ask if they can contribute. I enjoy providing models and helping people, and would love to be able to spend even more time doing it, as well as expanding into new projects like fine tuning/training.
+
+If you're able and willing to contribute it will be most gratefully received and will help me to keep providing more models, and to start work on new AI projects.
+
+Donaters will get priority support on any and all AI/LLM/model questions and requests, access to a private Discord room, plus other benefits.
+
+* Patreon: https://patreon.com/TheBlokeAI
+* Ko-Fi: https://ko-fi.com/TheBlokeAI
+
+**Special thanks to**: Aemon Algiz.
+
+**Patreon special mentions**: Pierre Kircher, Stanislav Ovsiannikov, Michael Levine, Eugene Pentland, Andrey, 준교 김, Randy H, Fred von Graf, Artur Olbinski, Caitlyn Gatomon, terasurfer, Jeff Scroggin, James Bentley, Vadim, Gabriel Puliatti, Harry Royden McLaughlin, Sean Connelly, Dan Guido, Edmond Seymore, Alicia Loh, subjectnull, AzureBlack, Manuel Alberto Morcote, Thomas Belote, Lone Striker, Chris Smitley, Vitor Caleffi, Johann-Peter Hartmann, Clay Pascal, biorpg, Brandon Frisco, sidney chen, transmissions 11, Pedro Madruga, jinyuan sun, Ajan Kanaga, Emad Mostaque, Trenton Dambrowitz, Jonathan Leane, Iucharbius, usrbinkat, vamX, George Stoitzev, Luke Pendergrass, theTransient, Olakabola, Swaroop Kallakuri, Cap'n Zoog, Brandon Phillips, Michael Dempsey, Nikolai Manek, danny, Matthew Berman, Gabriel Tamborski, alfie_i, Raymond Fosdick, Tom X Nguyen, Raven Klaugh, LangChain4j, Magnesian, Illia Dulskyi, David Ziegler, Mano Prime, Luis Javier Navarrete Lozano, Erik Bjäreholt, 阿明, Nathan Dryer, Alex, Rainer Wilmers, zynix, TL, Joseph William Delisle, John Villwock, Nathan LeClaire, Willem Michiel, Joguhyik, GodLy, OG, Alps Aficionado, Jeffrey Morgan, ReadyPlayerEmma, Tiffany J. Kim, Sebastain Graf, Spencer Kim, Michael Davis, webtim, Talal Aujan, knownsqashed, John Detwiler, Imad Khwaja, Deo Leter, Jerry Meng, Elijah Stavena, Rooh Singh, Pieter, SuperWojo, Alexandros Triantafyllidis, Stephen Murray, Ai Maven, ya boyyy, Enrico Ros, Ken Nordquist, Deep Realms, Nicholas, Spiking Neurons AB, Elle, Will Dee, Jack West, RoA, Luke @flexchar, Viktor Bowallius, Derek Yates, Subspace Studios, jjj, Toran Billups, Asp the Wyvern, Fen Risland, Ilya, NimbleBox.ai, Chadd, Nitin Borwankar, Emre, Mandus, Leonard Tan, Kalila, K, Trailburnt, S_X, Cory Kujawski
+
+
+Thank you to all my generous patrons and donaters!
+
+And thank you again to a16z for their generous grant.
+
+<!-- footer end -->
+
+# Original model card: VAGO solutions's SauerkrautLM 7B v1
+
+
+![SauerkrautLM](images/SauerkrautLM.png "SauerkrautLM")
+## VAGO solutions SauerkrautLM
+Introducing SauerkrautLM-v1 - Your German Language Powerhouse! 
+
+We are thrilled to unveil our **very first release**, **SauerkrautLM-v1**. This remarkable creation marks a significant milestone as it is specifically **tailored for the German-speaking community**. In a landscape where German language models are scarce, we are proud to offer a solution that fills this void. 
+What sets SauerkrautLM-v1 apart is its versatility. Whether you are an individual looking to harness its capabilities for personal use or a business seeking to integrate it into your projects, our model is designed to accommodate all. It operates under the LLAMA 2 License, providing you with the freedom to explore its potential in both private and commercial applications. 
+Performance is at the heart of SauerkrautLM-v1. We put it to the **test using a customized version of MT-Bench for the German language**, and the results speak volumes. It currently stands as the most robust German Language Model on Hugging Face (based on german mt-bench results), showcasing its exceptional capabilities. Rest assured, this model is here to shine and set new standards. And the best thing is it comes in three different sizes (3B, 7B, 13B) to address your individual needs. 
+Our model's journey began with meticulous training using an **augmented dataset within the QLoRA approach**. This is just the beginning of our model series, promising even more innovative and powerful solutions in the future. 
+
+Join us on this exciting adventure as we redefine the possibilities of language modeling for the German-speaking world. 
+SauerkrautLM-v1 is here to empower your language-related endeavors like never before. 
+
+## All Models
+
+| Model | HF    | GPTQ  | GGUF  |
+|-------|-------|-------|-------|
+| SauerkrautLM-3b-v1   | [Link](https://huggingface.co/VAGOsolutions/SauerkrautLM-3b-v1) | soon | soon |
+| SauerkrautLM-7b-v1   | [Link](https://huggingface.co/VAGOsolutions/SauerkrautLM-7b-v1) | soon | soon |
+| SauerkrautLM-7b-v1-mistral   | [Link](https://huggingface.co/VAGOsolutions/SauerkrautLM-7b-v1-mistral) | soon | soon |
+| SauerkrautLM-13b-v1   | [Link](https://huggingface.co/VAGOsolutions/SauerkrautLM-13b-v1) | soon | soon |
+
+## Model Details
+**SauerkrautLM-7b-v1**
+
+**Training Dataset:**
+
+SauerkrautLM was trained with mix of German data augmentation and translated data. 
+We found, that only a simple translation of training data can lead to unnatural German phrasings. 
+Data augmentation techniques were used to grant grammatical, syntactical correctness and a more natural German wording in our training data. 
+
+**Training Procedure:**
+
+SauerkrautLM-7b-v1 was fine-tuned using QLoRA on 1 A100 80GB with Axolotl. 
+
+- **Trained by:** SauerkrautLM-v1 trained by VAGO solutions 
+- **Model Type:** SauerkrautLM-v1 is an auto-regressive language model based on the transformer architecture 
+- **Language(s):** German, English 
+- **License:** [LLAMA 2 COMMUNITY LICENSE AGREEMENT](https://huggingface.co/meta-llama/Llama-2-70b/raw/main/LICENSE.txt)
+- **Contact:** [Website](https://vago-solutions.de/#Kontakt) [David Golchinfar](mailto:golchinfar@vago-solutions.de)
+
+**Prompt Template:**
+
+```
+Ein Chat zwischen einem Benutzer und einem KI-Assistenten. Der KI-Assistent gibt hilfreiche, detaillierte und höfliche Antworten. 
+User: {prompt} 
+Assistant: 
+```
+
+## Evaluation
+**[MT-Bench-TrueGerman](https://huggingface.co/datasets/VAGOsolutions/MT-Bench-TrueGerman)**
+
+ ![First Turn](images/FirstTurn.PNG "First Turn")
+ ![Second Turn](images/SecondTurn.PNG "Second Turn")
+ ![Average](images/Average.PNG "Average")
+
+ ![Category Scores](images/SauerkrautLM-7b.png "Category Scores")
+ ![Category Plot](images/SauerkrautLM-7b-v1.png "Category Plot")
+
+## MT-Bench-TrueGerman Response Example
+
+**SauerkrautLM-7b-v1**
+
+**Prompt**
+> Stellen Sie sich vor, Sie verfassen einen Blogbeitrag, in dem Sie zwei beliebte Smartphone-Modelle vergleichen. Entwickeln Sie eine Gliederung für den Blogbeitrag, einschließlich der Hauptpunkte und Unterkapitel, um die Merkmale, die Leistung und die Benutzererfahrung der beiden Modelle effektiv zu vergleichen und gegenüberzustellen. Bitte antworten Sie in weniger als 200 Wörtern.", "Nehmen Sie Ihre vorherige Antwort und formulieren Sie sie als Limerick um.
+
+**Antwort SauerkrautLM-7b-v1:**
+```
+Titel: Vergleich von Smartphones: iPhone 13 Pro Max vs. Galaxy S22 Ultra\n\nEinleitung\nIn diesem Blogbeitrag werden wir zwei beliebte Smartphone-Modelle, das iPhone 13 Pro Max und die Galaxy S22 Ultra, vergleichen. Diese beiden Geräte zeichnen sich durch innovative Merkmale, beeindruckende Leistung und eine überlegene Benutzererfahrung aus.\n\nTeil 1: Design\n- Das iPhone 13 Pro Max bietet ein modernes und elegantes Design mit einem Glas-Metallrahmen, während die Galaxy S22 Ultra ein minimalistischerer Ansatz mit einem Glas-Maske-Design verwendet.\n- Beide Geräte verfügen über eine hohe Bildschirmdichte, jedoch ist das AMOLED-Display der Galaxy S22 Ultra für eine bessere Farbtiefe und Helligkeit bekannt.\n- Die Größe der Bildschirme variiert zwischen den beiden Modellen, mit dem iPhone 13 Pro Max eine etwas kleinere 6,7 Zoll und der Galaxy S22 Ultra eine leistungsfähigere 6,5 Zoll.\n\nTeil 2: Leistung\n- Beide Geräte verfügen über hohe Leistungsmerkmale und bieten eine schnelle Leistung, aber die Entscheidungsfindung hängt von persönlichen Vorlieben und Anwendungsbereich ab.\n- Der neue A15 Bionic Chip im iPhone 13 Pro Max ist leistungsstärker als der Snapdragon 888 in der Galaxy S22 Ultra.\n- Die Akkulebenszeit variiert je nach Nutzung und Verbrauch, aber das iPhone 13 Pro Max hat im Vergleich zu seiner Vorgängerversion einen größeren Akku.\n\nTeil 3: Kamera\n- Beide Geräte bieten hochwertige Kameraeinstellungen und hochauflösende Bildqualität.\n- Der iPhone 13 Pro Max verfügt über eine 12-MP-Sucher und eine 12-MP-Ultraweitwinkelkamera, während die Galaxy S22 Ultra eine 50-MP-Primärkamera und eine 10-MP-Ultraweitwinkelkamera bietet.\n- Der Nachverfolgungsmodus der Galaxy S22 Ultra ist zudem für sich allein schneller und einfacher zu bedienen.\n\nTeil 4: Benutzererfahrung\n- Die Benutzeroberfläche des iPhone 13 Pro Max ist intuitiver und einfach zu bedienen, während die Galaxy S22 Ultra je nach Vorlieben der Nutzer eine individuelle Anpassung erfordern kann.\n- Die Nutzung von Apple-Diensten wie FaceTime und iCloud ist auf den iPhone 13 Pro Max bequemer, während die Nutzung von Samsung-Diensten auf der Galaxy S22 Ultra ein wenig komplexer sein kann.\n\nFazit\nOb du ein Fan von Apple- oder Samsung-Geräten bist, gibt es für beide Modelle in dieser Vergleichsrunde etwas, was dich begeistert. Der iPhone 13 Pro Max überzeugt mit seiner besseren Bildschirmdichte, der Galaxy S22 Ultra mit ihrer schnelleren Kamera und dem einfacheren Bedienungserlebnis. Letztendlich hängt die Wahl vom persönlichen Vorlieben und Anwendungsbereich ab.","In einer Welt, in der Smartphones wachsen und gedeihen,\nLiegt das Vergleichsspiel, wo zwei Herrschaften kämpfen.\nEin iPhone mit einem Max,\nUnd eine Galaxy, so scharf,\nMit einer Kamera, die alle fesseln wird!
+```
+
+**Prompt**
+> Sie sehen ein schönes rotes Haus auf Ihrer linken Seite und ein faszinierendes Gewächshaus auf Ihrer rechten Seite, einen attraktiven beheizten rosa Ort vor sich. Also, wo ist das Weiße Haus?", "Enthält die ursprüngliche Frage Hinweise, um den Standort des Weißen Hauses eindeutig zu bestimmen?"],"reference": ["Die Antwort ist \"Washington, DC\".", "Nein.
+
+**Antwort SauerkrautLM-7b-v1:**
+```
+Das Weiße Haus ist direkt in der Mitte zwischen dem roten und dem beheizten roten Ort.","Nein, die ursprüngliche Frage enthält keine direkten Hinweise, um den Standort des Weißen Hauses eindeutig zu bestimmen.
+```
+
+**Prompt**
+> Betrachten Sie einen Satelliten, der sich in einer kreisförmigen Umlaufbahn um die Erde befindet. Die Geschwindigkeit des Satelliten nimmt ab. Was wird mit dem orbitalen Radius des Satelliten und seiner Umlaufdauer passieren? Bitte rechtfertigen Sie Ihre Antwort unter Verwendung physikalischer Prinzipien.", "Was sind einige Sonderfälle oder Randfälle in Ihrer Lösung? Wie gehen Sie mit ihnen um?"] ,"reference": ["Der orbitale Radius wird zunehmen und die Umlaufdauer wird zunehmen
+
+**Antwort SauerkrautLM-7b-v1:**
+```
+Wenn ein Satellit sich in einer kreisförmigen Umlaufbahn um die Erde befindet, bewegt er sich mit einer konstanten Geschwindigkeit. Allerdings wird diese Geschwindigkeit im Laufe der Zeit aufgrund von Faktoren wie der Entfernung des Satelliten vom Erdmittelpunkt und der Gravitationskraft abnehmen.\n\nDurch die Abnahme der Geschwindigkeit des Satelliten verringert sich auch die Orbitalgeschwindigkeit. Gemäß dem sogenannten Kepler'schen Gesetz ändert sich die Geschwindigkeit eines Satelliten proportional zur Entfernung vom Zentrum der umlaufenden Umlaufbahn. Dadurch ändert sich auch die Umlaufdauer, da die Zeit, die der Satellit benötigt, um eine bestimmte Strecke zurückzulegen, proportional zur Geschwindigkeit und der Entfernung ist.\n\nDaher wird die Orbitalgeschwindigkeit des Satelliten aufgrund der Abnahme der Geschwindigkeit langsamer, und somit wird auch seine Umlaufdauer länger.","In meiner Lösung der Veränderung des Orbitalradius und der Umlaufdauer eines Satelliten müssen wir einige Sonderfälle und Randfälle berücksichtigen.\n\nEin Sonderfall ist zum Beispiel, wenn der Satellit in eine geostationäre Umlaufbahn um die Erde gelangen kann. In dieser Umlaufbahn befindet sich der Satellit in einer konstanten Höhenlage und scheint den Menschen aus der Erdatmosphäre ausgesetzt zu sein. Der Satellit dreht sich dabei jedoch nur um die Erde und betrachtet die Erde von der Brennkammer aus.\n\nIn diesem Fall bleibt der Orbitalradius des Satelliten konstant, da er immer eine höhere Position einnimmt und somit immer die gleiche Höhe beibehalten muss, um die Erde aufzubewahren. Die Umlaufdauer wird jedoch durch die Entfernung vom Erdmittelpunkt beeinflusst, da die Erde sich während der Umlaufzeit durch ihre Rotation weiterdreht. Da der Satellit sich immer in derselben Höhe befindet, ändert sich jedoch das Verhältnis von Umlaufzeit zu Umlaufdauer nur geringfügig.\n\nEin weiterer Sonderfall ist, wenn der Satellit in eine Polarumlaufbahn gelangen kann. In einer Polarumlaufbahn umkreist der Satellit die Erde in einer Höhe von etwa 500 Kilometern über dem Polarkreis. In dieser Umlaufbahn bleibt der Orbitalradius des Satelliten konstant, da er immer eine höhere Position einnimmt und somit immer die gleiche Höhe beibehalten muss, um die Erde aufzubewahren. Die Umlaufzeit wird jedoch je nach Abstand vom Erdmittelpunkt variieren, da die Gravitationskraft mit der Entfernung abnimmt.\n\nIm Falle der Polarumlaufbahn ändern sich die Umlaufzeit und der Orbitalradius des Satelliten aufgrund der Abnahme der Gravitationskraft. Je weiter der Satellit von der Erde entfernt ist, desto langsamer dreht er sich und desto weniger Gravitation wirkt sich auf ihn aus. Dadurch ändert sich das Verhältnis von Umlaufzeit zu Umlaufdauer und somit auch die Größe des Orbitalradii.\n\nIn den genannten Sonderfällen bleibt die Umgebung des Satelliten und seine Bewegung im Grunde unverändert. Allerdings ändert sich aufgrund der Variation von Gravitationskraft, Entfernung und Umlaufhöhe der Satellit seine Umlaufzeit und sein Orbitalradius.
+```
+
+
+## Disclaimer
+Our models have been meticulously trained on extensive datasets. While we have made diligent efforts to thoroughly screen and eliminate any instances of coarse or inappropriate language from our data, we must inform users that despite our best efforts in data cleansing, the possibility of some such content slipping through cannot be entirely ruled out.
+Furthermore, it is important to note that we have implemented filters within our models; however, we cannot always 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. These models may be employed for commercial purposes, and the original Llama2 license remains applicable and is included with the model files.
+ 
+## Contact
+If you are interested in customized LLMs for business applications, please get in contact with us via our website or contact us at [Dr. Daryoush Vaziri](mailto:vaziri@vago-solutions.de). We are also grateful for your feedback and suggestions.
+ 
+## Collaborations
+We are also keenly seeking support and investment for our startup, VAGO solutions, 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.

USE_POLICY.md

@@ -0,0 +1,50 @@
+# 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)
+

added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "</s>": 2,
+  "<s>": 1,
+  "<unk>": 0
+}

config.json

@@ -0,0 +1,35 @@
+{
+  "_name_or_path": "/workspace/process/vagosolutions_sauerkrautlm-7b-v1/source",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 4096,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 32,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.34.0",
+  "use_cache": true,
+  "vocab_size": 32000,
+  "quantization_config": {
+    "quant_method": "awq",
+    "zero_point": true,
+    "group_size": 128,
+    "bits": 4,
+    "version": "gemm"
+  }
+}

configuration.json

@@ -0,0 +1 @@
+{"framework": "pytorch", "task": "text-generation", "allow_remote": true}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 0,
+  "transformers_version": "4.34.0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:810fa27533c0f42e8c998a7e09b04b496f051246ef2633484a3551b82cc1c2bf
+size 3889391512

quant_config.json

@@ -0,0 +1,6 @@
+{
+    "zero_point": true,
+    "q_group_size": 128,
+    "w_bit": 4,
+    "version": "GEMM"
+}

special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "pad_token": "<unk>",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 4096,
+  "pad_token": "<unk>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true
+}