Upload README.md

README.md

@@ -0,0 +1,426 @@
+---
+base_model: jphme/em_german_leo_mistral
+inference: false
+language:
+- de
+library_name: transformers
+license: apache-2.0
+model_creator: Jan Philipp Harries
+model_name: EM German Leo Mistral
+model_type: mistral
+pipeline_tag: text-generation
+prompt_template: 'Du bist ein hilfreicher Assistent. USER: {prompt} ASSISTANT:
+
+  '
+quantized_by: TheBloke
+tags:
+- pytorch
+- german
+- deutsch
+- mistral
+- leolm
+---
+
+<!-- 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 -->
+
+# EM German Leo Mistral - AWQ
+- Model creator: [Jan Philipp Harries](https://huggingface.co/jphme)
+- Original model: [EM German Leo Mistral](https://huggingface.co/jphme/em_german_leo_mistral)
+
+<!-- description start -->
+## Description
+
+This repo contains AWQ model files for [Jan Philipp Harries's EM German Leo Mistral](https://huggingface.co/jphme/em_german_leo_mistral).
+
+
+### 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/em_german_leo_mistral-AWQ)
+* [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/em_german_leo_mistral-GPTQ)
+* [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/em_german_leo_mistral-GGUF)
+* [Jan Philipp Harries's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/jphme/em_german_leo_mistral)
+<!-- repositories-available end -->
+
+<!-- prompt-template start -->
+## Prompt template: EmGerman
+
+```
+Du bist ein hilfreicher Assistent. 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/em_german_leo_mistral-AWQ/tree/main) | 4 | 128 | [German Quad](https://huggingface.co/datasets/deepset/germanquad) | 4096 | 4.15 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/em_german_leo_mistral-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/em_german_leo_mistral-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/em_german_leo_mistral-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'''Du bist ein hilfreicher Assistent. 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/em_german_leo_mistral-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'''Du bist ein hilfreicher Assistent. 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: Jan Philipp Harries's EM German Leo Mistral
+
+![EM Logo](em_model_logo_web.jpeg)
+
+In our opinion, this is the strongest open 7b model for German-language applications.
+
+**Many thanks to the [LeoLM](https://huggingface.co/LeoLM) team for the publication of a base model that has received continued pretraining with German texts, greatly improving generation capabilities.**
+
+*Please note that the Mistral architecture is very recent and still not supported by all libraries (e.g. AutoGPTQ). In case of any problems, please try a different format/base model.*
+
+# Table of Contents
+
+1. [Introduction](#introduction)
+2. [Links & Demos](#links--demos)
+   - [Model Links](#model-links)
+   - [Demos](#demos)
+3. [Prompt Format](#prompt-format)
+4. [Example Output](#example-output)
+5. [Acknowledgements](#acknowledgements)
+6. [Contact](#contact)
+7. [Disclaimer](#disclaimer)
+
+# Introduction
+
+**EM German** is a Llama2/Mistral/LeoLM-based model family, finetuned on a large dataset of various instructions in German language. The models are optimized for German text, providing proficiency in understanding, generating, and interacting with German language content.
+
+We offer versions based on 7b, 13b and 70b Llama-2, Mistral and LeoLM (Llama-2/Mistral with continued pretraining on German texts) models.
+
+Please find all Informations, Example Outputs, the special RAG prompt format, output examples and eval results for the EM German Model family in [our Github Repository](https://github.com/jphme/EM_German).  ([Deutsche Version](https://github.com/jphme/EM_German/blob/main/README_DE.md))
+
+
+# Links & Demos
+
+## Model Links
+
+Should you try only one model version, I strongly recommend the **LeoLM Mistral** model which offers by far the best combination of performance and computing requirements!
+
+| Base Model | HF    | GPTQ  | GGUF  | AWQ   |
+|-------|-------|-------|-------|-------|
+| Llama2 7b   | [Link](https://huggingface.co/jphme/em_german_7b_v01) | [Link](https://huggingface.co/TheBloke/em_german_7b_v01-GPTQ) | [Link](https://huggingface.co/TheBloke/em_german_7b_v01-GGUF) | [Link](https://huggingface.co/TheBloke/em_german_7b_v01-AWQ) |
+| Llama2 13b  | [Link](https://huggingface.co/jphme/em_german_13b_v01) | [Link](https://huggingface.co/TheBloke/em_german_13b_v01-GPTQ) | [Link](https://huggingface.co/TheBloke/em_german_13b_v01-GGUF) | [Link](https://huggingface.co/TheBloke/em_german_13b_v01-AWQ) |
+| Llama2 70b   | [Link](https://huggingface.co/jphme/em_german_70b_v01) | [Link](https://huggingface.co/TheBloke/em_german_70b_v01-GPTQ) | [Link](https://huggingface.co/TheBloke/em_german_70b_v01-GGUF) | [Link](https://huggingface.co/TheBloke/em_german_70b_v01-AWQ) |
+| [Mistral 7b](https://huggingface.co/mistralai/Mistral-7B-v0.1) | [Link](https://huggingface.co/jphme/em_german_mistral_v01) | [Link](https://huggingface.co/TheBloke/em_german_mistral_v01-GPTQ) | [Link](https://huggingface.co/TheBloke/em_german_mistral_v01-GGUF) | [Link](https://huggingface.co/TheBloke/em_german_mistral_v01-AWQ) |
+| [LeoLM 7b](https://huggingface.co/LeoLM/leo-hessianai-7b) | [Link](https://huggingface.co/jphme/em_german_7b_leo) | [Link](https://huggingface.co/jphme/em_german_7b_leo_gptq) | [Link](hhttps://huggingface.co/jphme/em_german_7b_leo_gguf) | tbc |
+| [LeoLM 13b](https://huggingface.co/LeoLM/leo-hessianai-13b) | soon | soon | [Link](https://huggingface.co/jphme/em_german_13b_leo_gguf) | tbc |
+| [LeoLM Mistral 7b](tbc) | [Link](https://huggingface.co/jphme/em_german_leo_mistral) | soon | [Link](https://huggingface.co/jphme/em_german_leo_mistral_gguf) | tbc |
+
+### Notes about the different versions:
+See also the [comparison of example outputs](https://github.com/jphme/EM_German/blob/main/example_output_comparison.md) for a comparison of (7b) model capabilities.
+
+If you get unsatisfying results with one or another EM German version, please try a different (and/or larger) model or version for your usecase.
+
+
+## Demos:
+
+You can use some of the models with **free** google Colab instances (e.g. the 7bn model in 8bit or the 13b model with GPTQ):
+
+* [Example Colab Notebook for 13b with GPTQ](https://colab.research.google.com/drive/1IJfJdVwGkfe5MYOqHptystR3FBeEUdGn?usp=sharing)
+* [Example Colab Notebook for 7b with 8bit-Loading](https://colab.research.google.com/drive/1bsv6vkLM4AlCpSyXA6ol9P32zxZmf7Zu?usp=sharing)
+* [Example Colab Notebook for 7b Mistral GGUF with Grammar-based structured output](https://colab.research.google.com/drive/17O-a3D4BnVc_V9Of3dFfed18v1ULu1Sv?usp=sharing)
+
+
+# Prompt Format
+
+This model follows the Vicuna format without linebreaks (but should work with linebreaks as well). The format is as follows:
+
+```
+Du bist ein hilfreicher Assistent. USER: <instruction> ASSISTANT:
+```
+
+You can swap the standard system prompt for a better suited one (see below for RAG-tasks).
+
+# Example Output
+
+Please find a selection of various example outputs for all 7b versions of EM German [here](https://github.com/jphme/EM_German/blob/main/example_output_comparison.md).
+
+**Prompt:**
+> Erkläre die Bedeutung von drei wesentlichen Elementen der Bilanzierung und des Accountings nach IFRS für Unternehmen, die auf internationaler Ebene tätig sind.
+
+**Antwort EM German Leo Mistral 7b:**
+```
+Die International Financial Reporting Standards (IFRS) sind eine Reihe von internationalen Rechnungslegungsstandards, die von der International Accounting Standards Board (IASB) entwickelt wurden. Sie sollen dazu beitragen, dass Finanzberichte vergleichbar, zuverlässig und relevant sind.
+
+1. Fair Value: Dieses Konzept ist ein zentraler Bestandteil der IFRS. Es besagt, dass Vermögenswerte und Schulden zum fairen Wert bilanziert werden sollten, was dem Preis entspricht, zu dem sie zwischen Marktteilnehmern gehandelt werden könnten. Dadurch wird sichergestellt, dass das Unternehmen eine genaue Darstellung seiner finanziellen Lage liefert.
+
+2. Konsolidierung: Die IFRS verlangen von Unternehmen, ihre Finanzergebnisse auf konsolidierter Basis darzustellen. Das bedeutet, dass alle Tochtergesellschaften und verbundenen Unternehmen in die Bilanz des Mutterunternehmens aufgenommen werden. Dadurch wird ein klareres Bild von der finanziellen Situation des Konzerns geschaffen.
+
+3. Vollständigkeitsprinzip: Die IFRS verlangen von Unternehmen, alle relevanten Informationen offenzulegen. Dies umfasst sowohl positive als auch negative Faktoren, wie zum Beispiel Gewinne und Verluste, Einnahmen und Ausgaben sowie Risiken und Unsicherheiten. Durch dieses Prinzip wird sichergestellt, dass Investoren, Kreditgeber und andere Stakeholder eine umfassende Einschätzung der finanziellen Lage des Unternehmens vornehmen können.
+```
+
+**Prompt:**
+> Ein Mensch atmet durchschnittlich 16 Mal pro Minute. Wie oft atmet er an einem Tag?
+
+**Antwort EM German Leo Mistral 7b:**
+```
+ Zuerst berechnen wir, wie oft eine Person in einer Stunde atmet. Wir wissen, dass eine Stunde 60 Minuten hat, also:
+
+Atemzüge pro Stunde = Atemfrequenz * Minuten pro Stunde
+= 16 Atemzüge pro Minute * 60 Minuten
+= 960 Atemzüge
+
+Um herauszufinden, wie viele Atemzüge eine Person an einem Tag macht, müssen wir diese stündliche Rate mit der Anzahl der Stunden an einem Tag multiplizieren, also 24:
+
+Atemzüge pro Tag = Atemzüge pro Stunde * Stunden pro Tag
+= 960 Atemzüge * 24 Stunden
+= 23.040 Atemzüge
+
+Also macht ein durchschnittlicher Mensch etwa 23.040 Atemzüge an einem Tag.
+```
+(For more examples,  please visit [our Github Repository](https://github.com/jphme/EM_German).)
+
+# Acknowledgements:
+
+Many thanks to [winglian/caseus](https://huggingface.co/winglian) for his great work on Axolotl which I used to train the EM mdoels. I am also grateful to [Jon Durbin](https://huggingface.co/jondurbin) and his [Airoboros](https://huggingface.co/jondurbin/airoboros-l2-70b-2.2.1) models and code from which I borrowed many ideas and code snippets.
+Additionally many thanks to [Björn Plüster](https://huggingface.co/bjoernp) and the LeoLM team for the outstanding pretraining work on LeoLM and last but not least many many thanks to [TheBloke](https://huggingface.co/TheBloke) for the preparation of quantized versions in all formats under the sun.
+The 70b model was trained with support of the [OVH Cloud Startup Program](https://startup.ovhcloud.com/en/).
+
+# Contact
+
+I you are interested in customized LLMs for business applications, please get in contact with me via [my website](https://www.jph.me). I am also always happy about suggestions and feedback.
+
+*PS: We are also always interested in support for our startup [ellamind](https://ellamind.com), which will offer customized models for business applications in the future (we are currently still in stealth mode). If you use our models for business applications and have advanced needs for specialized capabilities, please get in touch.*
+
+# Disclaimer:
+
+I am not responsible for the actions of third parties who use this model or the outputs of the model. This model should only be used for research purposes. The original base model license applies and is distributed with the model files.