TheBloke
/

LUNA-SOLARkrautLM-Instruct-GGUF

+---
+base_model: fblgit/LUNA-SOLARkrautLM-Instruct
+datasets:
+- argilla/distilabel-math-preference-dpo
+inference: false
+language:
+- en
+- de
+library_name: transformers
+license: cc-by-nc-4.0
+model_creator: FBL
+model_name: Luna SOLARkrautLM Instruct
+model_type: solar
+pipeline_tag: text-generation
+prompt_template: '<|im_start|>system
+  {system_message}<|im_end|>
+  <|im_start|>user
+  {prompt}<|im_end|>
+  <|im_start|>assistant
+  '
+quantized_by: TheBloke
+tags:
+- finetune
+- dpo
+- Instruct
+- augmentation
+- german
+---
+<!-- markdownlint-disable MD041 -->
+<!-- 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 -->
+# Luna SOLARkrautLM Instruct - GGUF
+- Model creator: [FBL](https://huggingface.co/fblgit)
+- Original model: [Luna SOLARkrautLM Instruct](https://huggingface.co/fblgit/LUNA-SOLARkrautLM-Instruct)
+<!-- description start -->
+## Description
+This repo contains GGUF format model files for [FBL's Luna SOLARkrautLM Instruct](https://huggingface.co/fblgit/LUNA-SOLARkrautLM-Instruct).
+These files were quantised using hardware kindly provided by [Massed Compute](https://massedcompute.com/).
+<!-- description end -->
+<!-- README_GGUF.md-about-gguf start -->
+### About GGUF
+GGUF is a new format introduced by the llama.cpp team on August 21st 2023. It is a replacement for GGML, which is no longer supported by llama.cpp.
+Here is an incomplete list of clients and libraries that are known to support GGUF:
+* [llama.cpp](https://github.com/ggerganov/llama.cpp). The source project for GGUF. Offers a CLI and a server option.
+* [text-generation-webui](https://github.com/oobabooga/text-generation-webui), the most widely used web UI, with many features and powerful extensions. Supports GPU acceleration.
+* [KoboldCpp](https://github.com/LostRuins/koboldcpp), a fully featured web UI, with GPU accel across all platforms and GPU architectures. Especially good for story telling.
+* [GPT4All](https://gpt4all.io/index.html), a free and open source local running GUI, supporting Windows, Linux and macOS with full GPU accel.
+* [LM Studio](https://lmstudio.ai/), an easy-to-use and powerful local GUI for Windows and macOS (Silicon), with GPU acceleration. Linux available, in beta as of 27/11/2023.
+* [LoLLMS Web UI](https://github.com/ParisNeo/lollms-webui), a great web UI with many interesting and unique features, including a full model library for easy model selection.
+* [Faraday.dev](https://faraday.dev/), an attractive and easy to use character-based chat GUI for Windows and macOS (both Silicon and Intel), with GPU acceleration.
+* [llama-cpp-python](https://github.com/abetlen/llama-cpp-python), a Python library with GPU accel, LangChain support, and OpenAI-compatible API server.
+* [candle](https://github.com/huggingface/candle), a Rust ML framework with a focus on performance, including GPU support, and ease of use.
+* [ctransformers](https://github.com/marella/ctransformers), a Python library with GPU accel, LangChain support, and OpenAI-compatible AI server. Note, as of time of writing (November 27th 2023), ctransformers has not been updated in a long time and does not support many recent models.
+<!-- README_GGUF.md-about-gguf end -->
+<!-- repositories-available start -->
+## Repositories available
+* [AWQ model(s) for GPU inference.](https://huggingface.co/TheBloke/LUNA-SOLARkrautLM-Instruct-AWQ)
+* [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/LUNA-SOLARkrautLM-Instruct-GPTQ)
+* [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/LUNA-SOLARkrautLM-Instruct-GGUF)
+* [FBL's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/fblgit/LUNA-SOLARkrautLM-Instruct)
+<!-- repositories-available end -->
+<!-- prompt-template start -->
+## Prompt template: ChatML
+```
+<|im_start|>system
+{system_message}<|im_end|>
+<|im_start|>user
+{prompt}<|im_end|>
+<|im_start|>assistant
+```
+<!-- prompt-template end -->
+<!-- compatibility_gguf start -->
+## Compatibility
+These quantised GGUFv2 files are compatible with llama.cpp from August 27th onwards, as of commit [d0cee0d](https://github.com/ggerganov/llama.cpp/commit/d0cee0d36d5be95a0d9088b674dbb27354107221)
+They are also compatible with many third party UIs and libraries - please see the list at the top of this README.
+## Explanation of quantisation methods
+<details>
+  <summary>Click to see details</summary>
+The new methods available are:
+* GGML_TYPE_Q2_K - "type-1" 2-bit quantization in super-blocks containing 16 blocks, each block having 16 weight. Block scales and mins are quantized with 4 bits. This ends up effectively using 2.5625 bits per weight (bpw)
+* GGML_TYPE_Q3_K - "type-0" 3-bit quantization in super-blocks containing 16 blocks, each block having 16 weights. Scales are quantized with 6 bits. This end up using 3.4375 bpw.
+* GGML_TYPE_Q4_K - "type-1" 4-bit quantization in super-blocks containing 8 blocks, each block having 32 weights. Scales and mins are quantized with 6 bits. This ends up using 4.5 bpw.
+* GGML_TYPE_Q5_K - "type-1" 5-bit quantization. Same super-block structure as GGML_TYPE_Q4_K resulting in 5.5 bpw
+* GGML_TYPE_Q6_K - "type-0" 6-bit quantization. Super-blocks with 16 blocks, each block having 16 weights. Scales are quantized with 8 bits. This ends up using 6.5625 bpw
+Refer to the Provided Files table below to see what files use which methods, and how.
+</details>
+<!-- compatibility_gguf end -->
+<!-- README_GGUF.md-provided-files start -->
+## Provided files
+| Name | Quant method | Bits | Size | Max RAM required | Use case |
+| ---- | ---- | ---- | ---- | ---- | ----- |
+| [luna-solarkrautlm-instruct.Q2_K.gguf](https://huggingface.co/TheBloke/LUNA-SOLARkrautLM-Instruct-GGUF/blob/main/luna-solarkrautlm-instruct.Q2_K.gguf) | Q2_K | 2 | 4.55 GB| 7.05 GB | smallest, significant quality loss - not recommended for most purposes |
+| [luna-solarkrautlm-instruct.Q3_K_S.gguf](https://huggingface.co/TheBloke/LUNA-SOLARkrautLM-Instruct-GGUF/blob/main/luna-solarkrautlm-instruct.Q3_K_S.gguf) | Q3_K_S | 3 | 4.66 GB| 7.16 GB | very small, high quality loss |
+| [luna-solarkrautlm-instruct.Q3_K_M.gguf](https://huggingface.co/TheBloke/LUNA-SOLARkrautLM-Instruct-GGUF/blob/main/luna-solarkrautlm-instruct.Q3_K_M.gguf) | Q3_K_M | 3 | 5.19 GB| 7.69 GB | very small, high quality loss |
+| [luna-solarkrautlm-instruct.Q3_K_L.gguf](https://huggingface.co/TheBloke/LUNA-SOLARkrautLM-Instruct-GGUF/blob/main/luna-solarkrautlm-instruct.Q3_K_L.gguf) | Q3_K_L | 3 | 5.65 GB| 8.15 GB | small, substantial quality loss |
+| [luna-solarkrautlm-instruct.Q4_0.gguf](https://huggingface.co/TheBloke/LUNA-SOLARkrautLM-Instruct-GGUF/blob/main/luna-solarkrautlm-instruct.Q4_0.gguf) | Q4_0 | 4 | 6.07 GB| 8.57 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
+| [luna-solarkrautlm-instruct.Q4_K_S.gguf](https://huggingface.co/TheBloke/LUNA-SOLARkrautLM-Instruct-GGUF/blob/main/luna-solarkrautlm-instruct.Q4_K_S.gguf) | Q4_K_S | 4 | 6.10 GB| 8.60 GB | small, greater quality loss |
+| [luna-solarkrautlm-instruct.Q4_K_M.gguf](https://huggingface.co/TheBloke/LUNA-SOLARkrautLM-Instruct-GGUF/blob/main/luna-solarkrautlm-instruct.Q4_K_M.gguf) | Q4_K_M | 4 | 6.46 GB| 8.96 GB | medium, balanced quality - recommended |
+| [luna-solarkrautlm-instruct.Q5_0.gguf](https://huggingface.co/TheBloke/LUNA-SOLARkrautLM-Instruct-GGUF/blob/main/luna-solarkrautlm-instruct.Q5_0.gguf) | Q5_0 | 5 | 7.40 GB| 9.90 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
+| [luna-solarkrautlm-instruct.Q5_K_S.gguf](https://huggingface.co/TheBloke/LUNA-SOLARkrautLM-Instruct-GGUF/blob/main/luna-solarkrautlm-instruct.Q5_K_S.gguf) | Q5_K_S | 5 | 7.40 GB| 9.90 GB | large, low quality loss - recommended |
+| [luna-solarkrautlm-instruct.Q5_K_M.gguf](https://huggingface.co/TheBloke/LUNA-SOLARkrautLM-Instruct-GGUF/blob/main/luna-solarkrautlm-instruct.Q5_K_M.gguf) | Q5_K_M | 5 | 7.60 GB| 10.10 GB | large, very low quality loss - recommended |
+| [luna-solarkrautlm-instruct.Q6_K.gguf](https://huggingface.co/TheBloke/LUNA-SOLARkrautLM-Instruct-GGUF/blob/main/luna-solarkrautlm-instruct.Q6_K.gguf) | Q6_K | 6 | 8.81 GB| 11.31 GB | very large, extremely low quality loss |
+| [luna-solarkrautlm-instruct.Q8_0.gguf](https://huggingface.co/TheBloke/LUNA-SOLARkrautLM-Instruct-GGUF/blob/main/luna-solarkrautlm-instruct.Q8_0.gguf) | Q8_0 | 8 | 11.40 GB| 13.90 GB | very large, extremely low quality loss - not recommended |
+**Note**: the above RAM figures assume no GPU offloading. If layers are offloaded to the GPU, this will reduce RAM usage and use VRAM instead.
+<!-- README_GGUF.md-provided-files end -->
+<!-- README_GGUF.md-how-to-download start -->
+## How to download GGUF files
+**Note for manual downloaders:** You almost never want to clone the entire repo! Multiple different quantisation formats are provided, and most users only want to pick and download a single file.
+The following clients/libraries will automatically download models for you, providing a list of available models to choose from:
+* LM Studio
+* LoLLMS Web UI
+* Faraday.dev
+### In `text-generation-webui`
+Under Download Model, you can enter the model repo: TheBloke/LUNA-SOLARkrautLM-Instruct-GGUF and below it, a specific filename to download, such as: luna-solarkrautlm-instruct.Q4_K_M.gguf.
+Then click Download.
+### On the command line, including multiple files at once
+I recommend using the `huggingface-hub` Python library:
+```shell
+pip3 install huggingface-hub
+```
+Then you can download any individual model file to the current directory, at high speed, with a command like this:
+```shell
+huggingface-cli download TheBloke/LUNA-SOLARkrautLM-Instruct-GGUF luna-solarkrautlm-instruct.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False
+```
+<details>
+  <summary>More advanced huggingface-cli download usage (click to read)</summary>
+You can also download multiple files at once with a pattern:
+```shell
+huggingface-cli download TheBloke/LUNA-SOLARkrautLM-Instruct-GGUF --local-dir . --local-dir-use-symlinks False --include='*Q4_K*gguf'
+```
+For more documentation on downloading with `huggingface-cli`, please see: [HF -> Hub Python Library -> Download files -> Download from the CLI](https://huggingface.co/docs/huggingface_hub/guides/download#download-from-the-cli).
+To accelerate downloads on fast connections (1Gbit/s or higher), install `hf_transfer`:
+```shell
+pip3 install hf_transfer
+```
+And set environment variable `HF_HUB_ENABLE_HF_TRANSFER` to `1`:
+```shell
+HF_HUB_ENABLE_HF_TRANSFER=1 huggingface-cli download TheBloke/LUNA-SOLARkrautLM-Instruct-GGUF luna-solarkrautlm-instruct.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False
+```
+Windows Command Line users: You can set the environment variable by running `set HF_HUB_ENABLE_HF_TRANSFER=1` before the download command.
+</details>
+<!-- README_GGUF.md-how-to-download end -->
+<!-- README_GGUF.md-how-to-run start -->
+## Example `llama.cpp` command
+Make sure you are using `llama.cpp` from commit [d0cee0d](https://github.com/ggerganov/llama.cpp/commit/d0cee0d36d5be95a0d9088b674dbb27354107221) or later.
+```shell
+./main -ngl 35 -m luna-solarkrautlm-instruct.Q4_K_M.gguf --color -c 4096 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "<|im_start|>system\n{system_message}<|im_end|>\n<|im_start|>user\n{prompt}<|im_end|>\n<|im_start|>assistant"
+```
+Change `-ngl 32` to the number of layers to offload to GPU. Remove it if you don't have GPU acceleration.
+Change `-c 4096` to the desired sequence length. For extended sequence models - eg 8K, 16K, 32K - the necessary RoPE scaling parameters are read from the GGUF file and set by llama.cpp automatically. Note that longer sequence lengths require much more resources, so you may need to reduce this value.
+If you want to have a chat-style conversation, replace the `-p <PROMPT>` argument with `-i -ins`
+For other parameters and how to use them, please refer to [the llama.cpp documentation](https://github.com/ggerganov/llama.cpp/blob/master/examples/main/README.md)
+## How to run in `text-generation-webui`
+Further instructions can be found in the text-generation-webui documentation, here: [text-generation-webui/docs/04 ‐ Model Tab.md](https://github.com/oobabooga/text-generation-webui/blob/main/docs/04%20%E2%80%90%20Model%20Tab.md#llamacpp).
+## How to run from Python code
+You can use GGUF models from Python using the [llama-cpp-python](https://github.com/abetlen/llama-cpp-python) or [ctransformers](https://github.com/marella/ctransformers) libraries. Note that at the time of writing (Nov 27th 2023), ctransformers has not been updated for some time and is not compatible with some recent models. Therefore I recommend you use llama-cpp-python.
+### How to load this model in Python code, using llama-cpp-python
+For full documentation, please see: [llama-cpp-python docs](https://abetlen.github.io/llama-cpp-python/).
+#### First install the package
+Run one of the following commands, according to your system:
+```shell
+# Base ctransformers with no GPU acceleration
+pip install llama-cpp-python
+# With NVidia CUDA acceleration
+CMAKE_ARGS="-DLLAMA_CUBLAS=on" pip install llama-cpp-python
+# Or with OpenBLAS acceleration
+CMAKE_ARGS="-DLLAMA_BLAS=ON -DLLAMA_BLAS_VENDOR=OpenBLAS" pip install llama-cpp-python
+# Or with CLBLast acceleration
+CMAKE_ARGS="-DLLAMA_CLBLAST=on" pip install llama-cpp-python
+# Or with AMD ROCm GPU acceleration (Linux only)
+CMAKE_ARGS="-DLLAMA_HIPBLAS=on" pip install llama-cpp-python
+# Or with Metal GPU acceleration for macOS systems only
+CMAKE_ARGS="-DLLAMA_METAL=on" pip install llama-cpp-python
+# In windows, to set the variables CMAKE_ARGS in PowerShell, follow this format; eg for NVidia CUDA:
+$env:CMAKE_ARGS = "-DLLAMA_OPENBLAS=on"
+pip install llama-cpp-python
+```
+#### Simple llama-cpp-python example code
+```python
+from llama_cpp import Llama
+# Set gpu_layers to the number of layers to offload to GPU. Set to 0 if no GPU acceleration is available on your system.
+llm = Llama(
+  model_path="./luna-solarkrautlm-instruct.Q4_K_M.gguf",  # Download the model file first
+  n_ctx=4096,  # The max sequence length to use - note that longer sequence lengths require much more resources
+  n_threads=8,            # The number of CPU threads to use, tailor to your system and the resulting performance
+  n_gpu_layers=35         # The number of layers to offload to GPU, if you have GPU acceleration available
+)
+# Simple inference example
+output = llm(
+  "<|im_start|>system\n{system_message}<|im_end|>\n<|im_start|>user\n{prompt}<|im_end|>\n<|im_start|>assistant", # Prompt
+  max_tokens=512,  # Generate up to 512 tokens
+  stop=["</s>"],   # Example stop token - not necessarily correct for this specific model! Please check before using.
+  echo=True        # Whether to echo the prompt
+)
+# Chat Completion API
+llm = Llama(model_path="./luna-solarkrautlm-instruct.Q4_K_M.gguf", chat_format="llama-2")  # Set chat_format according to the model you are using
+llm.create_chat_completion(
+    messages = [
+        {"role": "system", "content": "You are a story writing assistant."},
+        {
+            "role": "user",
+            "content": "Write a story about llamas."
+        }
+    ]
+)
+```
+## How to use with LangChain
+Here are guides on using llama-cpp-python and ctransformers with LangChain:
+* [LangChain + llama-cpp-python](https://python.langchain.com/docs/integrations/llms/llamacpp)
+* [LangChain + ctransformers](https://python.langchain.com/docs/integrations/providers/ctransformers)
+<!-- README_GGUF.md-how-to-run 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**: Michael Levine, 阿明, Trailburnt, Nikolai Manek, John Detwiler, Randy H, Will Dee, Sebastain Graf, NimbleBox.ai, Eugene Pentland, Emad Mostaque, Ai Maven, Jim Angel, Jeff Scroggin, Michael Davis, Manuel Alberto Morcote, Stephen Murray, Robert, Justin Joy, Luke @flexchar, Brandon Frisco, Elijah Stavena, S_X, Dan Guido, Undi ., Komninos Chatzipapas, Shadi, theTransient, Lone Striker, Raven Klaugh, jjj, Cap'n Zoog, Michel-Marie MAUDET (LINAGORA), Matthew Berman, David, Fen Risland, Omer Bin Jawed, Luke Pendergrass, Kalila, OG, Erik Bjäreholt, Rooh Singh, Joseph William Delisle, Dan Lewis, TL, John Villwock, AzureBlack, Brad, Pedro Madruga, Caitlyn Gatomon, K, jinyuan sun, Mano Prime, Alex, Jeffrey Morgan, Alicia Loh, Illia Dulskyi, Chadd, transmissions 11, fincy, Rainer Wilmers, ReadyPlayerEmma, knownsqashed, Mandus, biorpg, Deo Leter, Brandon Phillips, SuperWojo, Sean Connelly, Iucharbius, Jack West, Harry Royden McLaughlin, Nicholas, terasurfer, Vitor Caleffi, Duane Dunston, Johann-Peter Hartmann, David Ziegler, Olakabola, Ken Nordquist, Trenton Dambrowitz, Tom X Nguyen, Vadim, Ajan Kanaga, Leonard Tan, Clay Pascal, Alexandros Triantafyllidis, JM33133, Xule, vamX, ya boyyy, subjectnull, Talal Aujan, Alps Aficionado, wassieverse, Ari Malik, James Bentley, Woland, Spencer Kim, Michael Dempsey, Fred von Graf, Elle, zynix, William Richards, Stanislav Ovsiannikov, Edmond Seymore, Jonathan Leane, Martin Kemka, usrbinkat, Enrico Ros
+Thank you to all my generous patrons and donaters!
+And thank you again to a16z for their generous grant.
+<!-- footer end -->
+<!-- original-model-card start -->
+# Original model card: FBL's Luna SOLARkrautLM Instruct
+![Juanako.AI & SauerkrautLM Productions](https://vago-solutions.de/wp-content/uploads/2023/12/sauerkrautlm-solar.png "LUNA-SOLARkrautLM-Instruct")
+## VAGO solutions LUNA-SOLARkrautLM-Instruct
+Introducing **LUNA-SOLARkrautLM-Instruct** – a UNA-Sauerkraut version of the powerful [upstage/SOLAR-10.7B-Instruct-v1.0](https://huggingface.co/upstage/SOLAR-10.7B-Instruct-v1.0) !
+Aligned with **DPO** and tamed with **UNA**.
+# Table of Contents
+1. [Overview of all LUNA-SOLARkrautLM-Instruct models](#all-sauerkrautlm-solar-instruct-models)
+2. [Model Details](#model-details)
+   - [Prompt template](#prompt-template)
+   - [Training Dataset](#training-dataset)
+   - [Data Contamination Test](#data-contamination-test-results)
+3. [Evaluation](#evaluation)
+5. [Disclaimer](#disclaimer)
+6. [Contact](#contact)
+7. [Collaborations](#collaborations)
+8. [Acknowledgement](#acknowledgement)
+## Model Details
+**LUNA-SOLARkrautLM-Instruct**
+- **Model Type:** LUNA-SOLARkrautLM-Instruct is a UNA  Model based on [fblgit/UNA-SOLAR-10.7B-Instruct-v1.0](https://huggingface.co/fblgit/UNA-SOLAR-10.7B-Instruct-v1.0) and the powerful set of [SauerkrautLM-SOLAR-Instruct](https://huggingface.co/VAGOsolutions/SauerkrautLM-SOLAR-Instruct/)
+- **Language(s):** English, German
+- **License:** cc-by-nc-4.0
+- **Contact:** [Website](https://vago-solutions.de/#Kontakt) [David Golchinfar](mailto:golchinfar@vago-solutions.de) [Juanako.AI - UNA](mailto:info@juanako.ai)
+### Training Dataset:
+LUNA-SOLARkrautLM-Instruct was trained with mix of German data augmentation and translated data.
+Aligned through **DPO** with our **new German SauerkrautLM-DPO dataset** based on parts of the SFT SauerkrautLM dataset
+as chosen answers and [Sauerkraut-7b-HerO](https://huggingface.co/VAGOsolutions/SauerkrautLM-7b-HerO) as rejected answers. Added with additional **translated Parts of the [HuggingFaceH4/ultrafeedback_binarized](https://huggingface.co/datasets/HuggingFaceH4/ultrafeedback_binarized)** (Our dataset do not contain any TruthfulQA prompts - check Data Contamination Test Results) and **[argilla/distilabel-math-preference-dpo](https://huggingface.co/datasets/argilla/distilabel-math-preference-dpo).**
+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.
+We improved the German language skills on this model. Nevertheless, certain formulations may occur that are not entirely correct.
+### Data Contamination Test Results
+Some models on the HuggingFace leaderboard had problems with wrong data getting mixed in.
+We checked our SauerkrautLM-DPO dataset with a special test [1] on this model as target model and upstage/SOLAR-10.7B-Instruct-v1.0 as reference model.
+The HuggingFace team used the same methods [2, 3].
+Our results, with `result < 0.1, %:` being well below 0.9, indicate that our dataset is free from contamination.
+*The data contamination test results of HellaSwag and Winograde will be added once [1] supports them.*
+| Dataset                        | ARC   | MMLU | TruthfulQA | GSM8K |
+|------------------------------|-------|-------|-------|-------|
+| **SauerkrautLM-DPO**| result < 0.1, %: 0.0 |result < 0.1, %: 0.09 | result < 0.1, %: 0.13 | result < 0.1, %: 0.16 |
+[1] https://github.com/swj0419/detect-pretrain-code-contamination
+[2] https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard/discussions/474#657f2245365456e362412a06
+[3] https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard/discussions/265#657b6debf81f6b44b8966230
+### Prompt Template:
+```
+<|im_start|>system
+Du bist LUNA-SOLARkrautLM, ein großes Sprachmodell, das höflich und kompetent antwortet.<|im_end|>
+<|im_start|>user
+Wie geht es dir?<|im_end|>
+<|im_start|>assistant
+```
+```
+### User:
+Hello, how are you?
+### Assistant:
+Hi there! I am an AI language model, so I don't have personal feelings or emotions in the traditional sense. However, I can assure you that my systems and processes are functioning well at this moment, allowing me to provide helpful responses for your queries.
+How may I assist you today?
+```
+## Evaluation
+```
+hf (pretrained=fblgit/LUNA-SOLARkrautLM-Instruct), gen_kwargs: (), limit: None, num_fewshot: 5, batch_size: auto
+|Tasks|Version|  Filter  |n-shot|  Metric   |Value |   |Stderr|
+|-----|-------|----------|-----:|-----------|-----:|---|-----:|
+|gsm8k|Yaml   |get-answer|     5|exact_match|0.6467|±  |0.0132|
+hf (pretrained=fblgit/LUNA-SOLARkrautLM-Instruct), gen_kwargs: (), limit: None, num_fewshot: 0, batch_size: auto (64)
+|    Tasks     |Version|Filter|n-shot|Metric|Value |   |Stderr|
+|--------------|-------|------|-----:|------|-----:|---|-----:|
+|truthfulqa_mc2|Yaml   |none  |     0|acc   |0.7368|±  |0.0149|
+hf (pretrained=fblgit/LUNA-SOLARkrautLM-Instruct), gen_kwargs: (), limit: None, num_fewshot: 25, batch_size: auto (32)
+|    Tasks    |Version|Filter|n-shot| Metric |Value|   |Stderr|
+|-------------|-------|------|-----:|--------|----:|---|-----:|
+|arc_challenge|Yaml   |none  |    25|acc     |0.692|±  |0.0135|
+|             |       |none  |    25|acc_norm|0.715|±  |0.0132|
+hf (pretrained=fblgit/LUNA-SOLARkrautLM-Instruct), gen_kwargs: (), limit: None, num_fewshot: 0, batch_size: auto (64)
+|   Tasks   |Version|Filter|n-shot|Metric| Value |   |Stderr|
+|-----------|-------|------|-----:|------|------:|---|-----:|
+|paws_de    |Yaml   |none  |     0|acc   | 0.3965|±  |0.0109|
+|wmt16-en-de|Yaml   |none  |     0|bleu  | 3.5784|±  |0.1325|
+|           |       |none  |     0|ter   |64.5707|±  |0.4514|
+|           |       |none  |     0|chrf  |45.7068|±  |0.3861|
+|xnli_de    |Yaml   |none  |     0|acc   | 0.4129|±  |0.0099|
+hf (pretrained=fblgit/LUNA-SOLARkrautLM-Instruct), gen_kwargs: (), limit: None, num_fewshot: 10, batch_size: auto (32)
+|  Tasks  |Version|Filter|n-shot| Metric |Value |   |Stderr|
+|---------|-------|------|-----:|--------|-----:|---|-----:|
+|hellaswag|Yaml   |none  |    10|acc     |0.7131|±  |0.0045|
+|         |       |none  |    10|acc_norm|0.8815|±  |0.0032|
+hf (pretrained=fblgit/LUNA-SOLARkrautLM-Instruct), gen_kwargs: (), limit: None, num_fewshot: 5, batch_size: auto (64)
+|   Tasks   |Version|Filter|n-shot|Metric| Value |   |Stderr|
+|-----------|-------|------|-----:|------|------:|---|-----:|
+|wmt16-de-en|Yaml   |none  |     5|bleu  |14.9310|±  |0.8014|
+|           |       |none  |     5|ter   |46.3206|±  |0.4087|
+|           |       |none  |     5|chrf  |60.8637|±  |0.4436|
+|wmt16-en-de|Yaml   |none  |     5|bleu  | 6.2016|±  |0.2918|
+|           |       |none  |     5|ter   |63.9997|±  |0.4591|
+|           |       |none  |     5|chrf  |51.1399|±  |0.3978|
+|xnli_de    |Yaml   |none  |     5|acc   | 0.4703|±  |0.0100|
+hf (pretrained=fblgit/LUNA-SOLARkrautLM-Instruct,dtype=float16), gen_kwargs: (), limit: None, num_fewshot: 5, batch_size: auto (16)
+|                 Tasks                 |Version|Filter|n-shot|Metric|Value |   |Stderr|
+|---------------------------------------|-------|------|-----:|------|-----:|---|-----:|
+|mmlu                                   |N/A    |none  |     0|acc   |0.6461|±  |0.1215|
+| - humanities                          |N/A    |none  |     5|acc   |0.5960|±  |0.1200|
+|  - formal_logic                       |Yaml   |none  |     5|acc   |0.4683|±  |0.0446|
+|  - high_school_european_history       |Yaml   |none  |     5|acc   |0.8121|±  |0.0305|
+|  - high_school_us_history             |Yaml   |none  |     5|acc   |0.8480|±  |0.0252|
+|  - high_school_world_history          |Yaml   |none  |     5|acc   |0.8312|±  |0.0244|
+|  - international_law                  |Yaml   |none  |     5|acc   |0.7851|±  |0.0375|
+|  - jurisprudence                      |Yaml   |none  |     5|acc   |0.7685|±  |0.0408|
+|  - logical_fallacies                  |Yaml   |none  |     5|acc   |0.7423|±  |0.0344|
+|  - moral_disputes                     |Yaml   |none  |     5|acc   |0.7283|±  |0.0239|
+|  - moral_scenarios                    |Yaml   |none  |     5|acc   |0.3899|±  |0.0163|
+|  - philosophy                         |Yaml   |none  |     5|acc   |0.7074|±  |0.0258|
+|  - prehistory                         |Yaml   |none  |     5|acc   |0.7716|±  |0.0234|
+|  - professional_law                   |Yaml   |none  |     5|acc   |0.4824|±  |0.0128|
+|  - world_religions                    |Yaml   |none  |     5|acc   |0.7661|±  |0.0325|
+| - other                               |N/A    |none  |     5|acc   |0.7097|±  |0.0900|
+|  - business_ethics                    |Yaml   |none  |     5|acc   |0.7700|±  |0.0423|
+|  - clinical_knowledge                 |Yaml   |none  |     5|acc   |0.6792|±  |0.0287|
+|  - college_medicine                   |Yaml   |none  |     5|acc   |0.6647|±  |0.0360|
+|  - global_facts                       |Yaml   |none  |     5|acc   |0.3600|±  |0.0482|
+|  - human_aging                        |Yaml   |none  |     5|acc   |0.6861|±  |0.0311|
+|  - management                         |Yaml   |none  |     5|acc   |0.8350|±  |0.0368|
+|  - marketing                          |Yaml   |none  |     5|acc   |0.8504|±  |0.0234|
+|  - medical_genetics                   |Yaml   |none  |     5|acc   |0.6700|±  |0.0473|
+|  - miscellaneous                      |Yaml   |none  |     5|acc   |0.7893|±  |0.0146|
+|  - nutrition                          |Yaml   |none  |     5|acc   |0.7549|±  |0.0246|
+|  - professional_accounting            |Yaml   |none  |     5|acc   |0.5213|±  |0.0298|
+|  - professional_medicine              |Yaml   |none  |     5|acc   |0.7353|±  |0.0268|
+|  - virology                           |Yaml   |none  |     5|acc   |0.5783|±  |0.0384|
+| - social_sciences                     |N/A    |none  |     5|acc   |0.7501|±  |0.0684|
+|  - econometrics                       |Yaml   |none  |     5|acc   |0.5175|±  |0.0470|
+|  - high_school_geography              |Yaml   |none  |     5|acc   |0.8485|±  |0.0255|
+|  - high_school_government_and_politics|Yaml   |none  |     5|acc   |0.8912|±  |0.0225|
+|  - high_school_macroeconomics         |Yaml   |none  |     5|acc   |0.6615|±  |0.0240|
+|  - high_school_microeconomics         |Yaml   |none  |     5|acc   |0.7311|±  |0.0288|
+|  - high_school_psychology             |Yaml   |none  |     5|acc   |0.8385|±  |0.0158|
+|  - human_sexuality                    |Yaml   |none  |     5|acc   |0.7023|±  |0.0401|
+|  - professional_psychology            |Yaml   |none  |     5|acc   |0.6683|±  |0.0190|
+|  - public_relations                   |Yaml   |none  |     5|acc   |0.6909|±  |0.0443|
+|  - security_studies                   |Yaml   |none  |     5|acc   |0.7633|±  |0.0272|
+|  - sociology                          |Yaml   |none  |     5|acc   |0.8358|±  |0.0262|
+|  - us_foreign_policy                  |Yaml   |none  |     5|acc   |0.8800|±  |0.0327|
+| - stem                                |N/A    |none  |     5|acc   |0.5569|±  |0.1360|
+|  - abstract_algebra                   |Yaml   |none  |     5|acc   |0.3800|±  |0.0488|
+|  - anatomy                            |Yaml   |none  |     5|acc   |0.6148|±  |0.0420|
+|  - astronomy                          |Yaml   |none  |     5|acc   |0.7237|±  |0.0364|
+|  - college_biology                    |Yaml   |none  |     5|acc   |0.7708|±  |0.0351|
+|  - college_chemistry                  |Yaml   |none  |     5|acc   |0.4600|±  |0.0501|
+|  - college_computer_science           |Yaml   |none  |     5|acc   |0.5400|±  |0.0501|
+|  - college_mathematics                |Yaml   |none  |     5|acc   |0.2700|±  |0.0446|
+|  - college_physics                    |Yaml   |none  |     5|acc   |0.3333|±  |0.0469|
+|  - computer_security                  |Yaml   |none  |     5|acc   |0.7300|±  |0.0446|
+|  - conceptual_physics                 |Yaml   |none  |     5|acc   |0.6213|±  |0.0317|
+|  - electrical_engineering             |Yaml   |none  |     5|acc   |0.6276|±  |0.0403|
+|  - elementary_mathematics             |Yaml   |none  |     5|acc   |0.4788|±  |0.0257|
+|  - high_school_biology                |Yaml   |none  |     5|acc   |0.8065|±  |0.0225|
+|  - high_school_chemistry              |Yaml   |none  |     5|acc   |0.5123|±  |0.0352|
+|  - high_school_computer_science       |Yaml   |none  |     5|acc   |0.7000|±  |0.0461|
+|  - high_school_mathematics            |Yaml   |none  |     5|acc   |0.3889|±  |0.0297|
+|  - high_school_physics                |Yaml   |none  |     5|acc   |0.3576|±  |0.0391|
+|  - high_school_statistics             |Yaml   |none  |     5|acc   |0.5926|±  |0.0335|
+|  - machine_learning                   |Yaml   |none  |     5|acc   |0.4554|±  |0.0473|
+|      Groups      |Version|Filter|n-shot|Metric|Value |   |Stderr|
+|------------------|-------|------|-----:|------|-----:|---|-----:|
+|mmlu              |N/A    |none  |     0|acc   |0.6461|±  |0.1215|
+| - humanities     |N/A    |none  |     5|acc   |0.5960|±  |0.1200|
+| - other          |N/A    |none  |     5|acc   |0.7097|±  |0.0900|
+| - social_sciences|N/A    |none  |     5|acc   |0.7501|±  |0.0684|
+| - stem           |N/A    |none  |     5|acc   |0.5569|±  |0.1360|
+```
+### MT-Bench
+```
+########## Average ##########
+                                  score
+model
+gpt-4                          8.990625
+gpt-3.5-turbo                  7.943750
+claude-instant-v1              7.905660
+claude-v1                      7.900000
+UNA-SOLAR-10.7B-Instruct-v1.0  7.521875
+LUNA-SOLARkrautLM-Instruct     7.462500
+vicuna-33b-v1.3                7.121875
+wizardlm-30b                   7.009375
+Llama-2-70b-chat               6.856250
+Llama-2-13b-chat               6.650000
+guanaco-33b                    6.528125
+tulu-30b                       6.434375
+guanaco-65b                    6.409375
+oasst-sft-7-llama-30b          6.409375
+palm-2-chat-bison-001          6.400000
+mpt-30b-chat                   6.393750
+vicuna-13b-v1.3                6.387500
+wizardlm-13b                   6.353125
+Llama-2-7b-chat                6.268750
+vicuna-7b-v1.3                 5.996875
+baize-v2-13b                   5.750000
+nous-hermes-13b                5.553459
+mpt-7b-chat                    5.459119
+gpt4all-13b-snoozy             5.452830
+koala-13b                      5.350000
+mpt-30b-instruct               5.218750
+falcon-40b-instruct            5.168750
+h2ogpt-oasst-open-llama-13b    4.625000
+alpaca-13b                     4.531250
+chatglm-6b                     4.500000
+oasst-sft-4-pythia-12b         4.318750
+rwkv-4-raven-14b               3.984375
+dolly-v2-12b                   3.275000
+fastchat-t5-3b                 3.040625
+stablelm-tuned-alpha-7b        2.753125
+llama-13b                      2.606250
+```
+## 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 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](https://huggingface.co/VAGOsolutions), 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.
+[Juanako.AI](https://huggingface.co/fblgit) is also seeking support and investment for our startup, we also are open for collaborating with other labs to make awesome models like this one.
+## Acknowledgement
+Big Hug to [VAGO Solutions](https://huggingface.co/VAGOsolutions), we merely used our UNA transformers library on their code and dataset, nothing else. This won't be possible without them, thanks!
+Many thanks to [argilla](https://huggingface.co/datasets/argilla) and [Huggingface](https://huggingface.co) for providing such valuable datasets to the Open-Source community. And of course a big thanks to [upstage](https://huggingface.co/upstage) for providing the open source community with their latest technology!
+<!-- original-model-card end -->