Edit model card
TheBlokeAI

TheBloke's LLM work is generously supported by a grant from andreessen horowitz (a16z)


EM German 70B v01 - GGUF

Description

This repo contains GGUF format model files for Jan Philipp Harries's EM German 70B v01.

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 incomplate list of clients and libraries that are known to support GGUF:

  • llama.cpp. The source project for GGUF. Offers a CLI and a server option.
  • text-generation-webui, the most widely used web UI, with many features and powerful extensions. Supports GPU acceleration.
  • KoboldCpp, a fully featured web UI, with GPU accel across all platforms and GPU architectures. Especially good for story telling.
  • LM Studio, an easy-to-use and powerful local GUI for Windows and macOS (Silicon), with GPU acceleration.
  • LoLLMS Web UI, a great web UI with many interesting and unique features, including a full model library for easy model selection.
  • Faraday.dev, an attractive and easy to use character-based chat GUI for Windows and macOS (both Silicon and Intel), with GPU acceleration.
  • ctransformers, a Python library with GPU accel, LangChain support, and OpenAI-compatible AI server.
  • llama-cpp-python, a Python library with GPU accel, LangChain support, and OpenAI-compatible API server.
  • candle, a Rust ML framework with a focus on performance, including GPU support, and ease of use.

Repositories available

Prompt template: EmGerman

Du bist ein hilfreicher Assistent. USER: {prompt} ASSISTANT:

Compatibility

These quantised GGUFv2 files are compatible with llama.cpp from August 27th onwards, as of commit d0cee0d

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

Click to see details

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.

Provided files

Name Quant method Bits Size Max RAM required Use case
em_german_70b_v01.Q2_K.gguf Q2_K 2 29.28 GB 31.78 GB smallest, significant quality loss - not recommended for most purposes
em_german_70b_v01.Q3_K_S.gguf Q3_K_S 3 29.92 GB 32.42 GB very small, high quality loss
em_german_70b_v01.Q3_K_M.gguf Q3_K_M 3 33.19 GB 35.69 GB very small, high quality loss
em_german_70b_v01.Q3_K_L.gguf Q3_K_L 3 36.15 GB 38.65 GB small, substantial quality loss
em_german_70b_v01.Q4_0.gguf Q4_0 4 38.87 GB 41.37 GB legacy; small, very high quality loss - prefer using Q3_K_M
em_german_70b_v01.Q4_K_S.gguf Q4_K_S 4 39.07 GB 41.57 GB small, greater quality loss
em_german_70b_v01.Q4_K_M.gguf Q4_K_M 4 41.42 GB 43.92 GB medium, balanced quality - recommended
em_german_70b_v01.Q5_0.gguf Q5_0 5 47.46 GB 49.96 GB legacy; medium, balanced quality - prefer using Q4_K_M
em_german_70b_v01.Q5_K_S.gguf Q5_K_S 5 47.46 GB 49.96 GB large, low quality loss - recommended
em_german_70b_v01.Q5_K_M.gguf Q5_K_M 5 48.75 GB 51.25 GB large, very low quality loss - recommended
em_german_70b_v01.Q6_K.gguf Q6_K 6 56.59 GB 59.09 GB very large, extremely low quality loss
em_german_70b_v01.Q8_0.gguf Q8_0 8 73.29 GB 75.79 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.

Q6_K and Q8_0 files are split and require joining

Note: HF does not support uploading files larger than 50GB. Therefore I have uploaded the Q6_K and Q8_0 files as split files.

Click for instructions regarding Q6_K and Q8_0 files

q6_K

Please download:

  • em_german_70b_v01.Q6_K.gguf-split-a
  • em_german_70b_v01.Q6_K.gguf-split-b

q8_0

Please download:

  • em_german_70b_v01.Q8_0.gguf-split-a
  • em_german_70b_v01.Q8_0.gguf-split-b

To join the files, do the following:

Linux and macOS:

cat em_german_70b_v01.Q6_K.gguf-split-* > em_german_70b_v01.Q6_K.gguf && rm em_german_70b_v01.Q6_K.gguf-split-*
cat em_german_70b_v01.Q8_0.gguf-split-* > em_german_70b_v01.Q8_0.gguf && rm em_german_70b_v01.Q8_0.gguf-split-*

Windows command line:

COPY /B em_german_70b_v01.Q6_K.gguf-split-a + em_german_70b_v01.Q6_K.gguf-split-b em_german_70b_v01.Q6_K.gguf
del em_german_70b_v01.Q6_K.gguf-split-a em_german_70b_v01.Q6_K.gguf-split-b

COPY /B em_german_70b_v01.Q8_0.gguf-split-a + em_german_70b_v01.Q8_0.gguf-split-b em_german_70b_v01.Q8_0.gguf
del em_german_70b_v01.Q8_0.gguf-split-a em_german_70b_v01.Q8_0.gguf-split-b

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/em_german_70b_v01-GGUF and below it, a specific filename to download, such as: em_german_70b_v01.Q4_K_M.gguf.

Then click Download.

On the command line, including multiple files at once

I recommend using the huggingface-hub Python library:

pip3 install huggingface-hub

Then you can download any individual model file to the current directory, at high speed, with a command like this:

huggingface-cli download TheBloke/em_german_70b_v01-GGUF em_german_70b_v01.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False
More advanced huggingface-cli download usage

You can also download multiple files at once with a pattern:

huggingface-cli download TheBloke/em_german_70b_v01-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.

To accelerate downloads on fast connections (1Gbit/s or higher), install hf_transfer:

pip3 install hf_transfer

And set environment variable HF_HUB_ENABLE_HF_TRANSFER to 1:

HF_HUB_ENABLE_HF_TRANSFER=1 huggingface-cli download TheBloke/em_german_70b_v01-GGUF em_german_70b_v01.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.

Example llama.cpp command

Make sure you are using llama.cpp from commit d0cee0d or later.

./main -ngl 32 -m em_german_70b_v01.Q4_K_M.gguf --color -c 4096 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "Du bist ein hilfreicher Assistent. USER: {prompt} 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.

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

How to run in text-generation-webui

Further instructions here: text-generation-webui/docs/llama.cpp.md.

How to run from Python code

You can use GGUF models from Python using the llama-cpp-python or ctransformers libraries.

How to load this model in Python code, using ctransformers

First install the package

Run one of the following commands, according to your system:

# Base ctransformers with no GPU acceleration
pip install ctransformers
# Or with CUDA GPU acceleration
pip install ctransformers[cuda]
# Or with AMD ROCm GPU acceleration (Linux only)
CT_HIPBLAS=1 pip install ctransformers --no-binary ctransformers
# Or with Metal GPU acceleration for macOS systems only
CT_METAL=1 pip install ctransformers --no-binary ctransformers

Simple ctransformers example code

from ctransformers import AutoModelForCausalLM

# 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 = AutoModelForCausalLM.from_pretrained("TheBloke/em_german_70b_v01-GGUF", model_file="em_german_70b_v01.Q4_K_M.gguf", model_type="llama", gpu_layers=50)

print(llm("AI is going to"))

How to use with LangChain

Here are guides on using llama-cpp-python and ctransformers with LangChain:

Discord

For further support, and discussions on these models and AI in general, join us at:

TheBloke AI's Discord server

Thanks, and how to contribute

Thanks to the chirper.ai team!

Thanks to Clay from gpus.llm-utils.org!

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.

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.

Original model card: Jan Philipp Harries's EM German 70B v01

EM Logo

EM German 70b

(Zur deutschen Version)

EM German (v01) is an experimental llama2-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.

This is the 70b llama2 version.

Links & Demos

We will publish further instructions, updates and code-snippets in the project's Github-Repo.

Model Links

Base Model HF GPTQ GGUF AWQ
Llama2 7b Link Link Link soon
Llama2 13b Link Link soon soon
Llama2 70b Link Link Link soon
Mistral 7b Link soon soon tbc
LeoLm 7b soon soon soon tbc
LeoLM 13b soon soon soon tbc

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):

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).

Results

Attached a few example outputs. I also developed a few small German benchmarks (based on the Eleuther LM Evaluation Harness), which I will publish soon.

Example Output

Prompt:

Du bist ein hilfreicher Assistent USER: Ein Buch hat 500 Seiten. Jede Seite enthält 300 Wörter. Wie viele Wörter sind im gesamten Buch enthalten? ASSISTANT:

Response EM 7b v01

Die Gesamtzahl der Wörter in dem Buch kann berechnet werden, indem man die Anzahl der Wörter pro Seite mit der Gesamtzahl der Seiten multipliziert.

Gesamtzahl der Wörter = Anzahl der Wörter pro Seite * Gesamtzahl der Seiten = 300 Wörter pro Seite * 500 Seiten = 150.000 Wörter

Das Buch enthält also insgesamt 150.000 Wörter.

Prompt:

Du bist ein hilfreicher Assistent USER: Erläutere die Grundprinzipien der evolutionären Biologie und Genetik, indem du den Prozess der natürlichen Selektion, die Rolle von Mutationen und genetischer Drift sowie das Konzept der adaptiven Radiation erklärst. ASSISTANT:

Response EM 7b v01

Die Evolutionäre Biologie und Genetik sind zwei intim verwandte Disziplinen, die sich mit dem Studium des Verhaltens und der Entwicklung von Organismen in der Natur befassen. Sie untersuchen, wie Arten sich im Laufe der Zeit entwickeln und wie diese Veränderungen genetisch bedingt sind.

    1. Natürliche Selektion: Die natürliche Selektion ist ein grundlegendes Prinzip in der Evolutionäre Biologie. Es besagt, dass Individuen innerhalb einer Spezies unterschiedliche Fähigkeiten oder Merkmale aufweisen können. Diese Merkmale beeinflussen ihre Überlebens- und Fortpflanzungsrate. Diejenigen mit Vorteilen haben eine höhere Wahrscheinlichkeit, ihre Gene an zukünftige Generationen weiterzugeben und so die Art im Laufe der Zeit zu verändern.

    2. Rolle von Mutationen: Mutationen sind Veränderungen im Genom eines Organismus, die entweder durch zufällige Fehler während der Replikation oder durch Exposition gegenüber Strahlung verursacht werden. Diese Veränderungen können dazu führen, dass ein Individuum neue Eigenschaften aufweist, die es im Kampf ums Überleben vorteilhaft machen könnten. Diese Mutationen werden dann von der natürlichen Selektion beeinflusst und können so zur Entwicklung neuer Arten beitragen.

    3. Genetische Drift: Genetische Drift ist ein zufälliger Prozess, der durch die Verteilung von Allelen in einer Population stattfindet. Wenn eine Population kleiner wird oder wenn die Überlebens- und Fortpflanzungsraten zwischen den Individuen variieren, kann dies dazu führen, dass bestimmte Gene stärker oder weniger häufig werden. Dies kann dazu führen, dass die Population im Laufe der Zeit unterschiedliche Merkmale aufweist.

    4. Adaptive Radiation: Adaptive Radiation ist ein Prozess, bei dem eine Art mehrere verschiedene Linien auslässt, die sich auf verschiedene Weise an ihre Umgebung anpassen. Dies geschieht normalerweise, wenn die Umwelt sich ändert und die Art neue Fähigkeiten benötigt, um überleben zu können. Die verschiedenen Linien können dann unterschiedliche Eigenschaften entwickeln, die ihnen helfen, in dieser neuen Umgebung zu überleben.

Factual Retrieval / RAG

EM Models offer a special format for Factual Retrieval/RAG that is optimized for minimizing hallucinations. We use the same format as Airoboros for this:

Example

Prompt

Du bist ein hilfreicher Assistent. Für die folgende Aufgabe stehen dir zwischen den tags BEGININPUT und ENDINPUT mehrere Quellen zur Verfügung. Metadaten zu den einzelnen Quellen wie Autor, URL o.ä. sind zwischen BEGINCONTEXT und ENDCONTEXT zu finden, danach folgt der Text der Quelle. Die eigentliche Aufgabe oder Frage ist zwischen BEGININSTRUCTION und ENDINCSTRUCTION zu finden. Beantworte diese wortwörtlich mit einem Zitat aus den Quellen. Sollten diese keine Antwort enthalten, antworte, dass auf Basis der gegebenen Informationen keine Antwort möglich ist! USER: BEGININPUT
BEGINCONTEXT
Url: https://www.jph.me
ENDCONTEXT
Das Wetter in Düsseldorf wird heute schön und sonnig!
ENDINPUT
BEGININSTRUCTION Was ist 1+1? ENDINSTRUCTION ASSISTANT:

Model response:

Mit den gegebenen Informationen ist diese Frage nicht zu beantworten.

Note that the model would normally always answer with the correct response to a trivial question like this but is trained to deny an answer, if there is no source between the BEGININPUT and ENDINPUT that provides a grounding.

If we keep the same Context/Input but ask instead:

BEGININSTRUCTION Wie wird das Wetter heute in Düsseldorf? Gebe die Quelle mit an! ENDINSTRUCTION ASSISTANT:

We get the correct answer with the source:

Das Wetter in Düsseldorf wird heute schön und sonnig! (Quelle: Url: https://www.jph.me)

Evaluation

I will publish some custom German benchmarks and the results for them soon.

Dataset

The dataset is a mixture of multi-turn chats, retrieval instructions and synthetically generated instructions spawning many topics and applications.

Use with tranformers

Unchanged from the base model:

import torch
from transformers import LlamaForCausalLM, LlamaTokenizer

# Hugging Face model_path
model_path = 'jphme/em_german_7b_v01'
tokenizer = LlamaTokenizer.from_pretrained(model_path)
model = LlamaForCausalLM.from_pretrained(
    model_path, torch_dtype=torch.float16, device_map='auto',
)

def ask_model(instruction, system='Du bist ein hilfreicher Assistent.'):
    prompt=f"{system} USER: {instruction} ASSISTANT:"
    input_tokens=tokenizer(prompt, return_tensors="pt").to(model.device)
    output_tokens=model.generate(**input_tokens,  max_new_tokens=200)[0]
    answer=tokenizer.decode(output_tokens, skip_special_tokens=True)
    return answer

print(ask_model("Nenne mir 10 gute Gründe dafür, heute Sport zu machen!"))

Limitations & Biases

This model can produce factually incorrect output, and should not be relied on to produce factually accurate information. This model was trained on various public datasets. While great efforts have been taken to clean the pretraining data, it is possible that this model could generate lewd, biased or otherwise offensive outputs.

Acknowledgements:

Many thanks to winglian/caseus for his great work on Axolotl which I used to train the EM mdoels. I am also grateful to Jon Durbin and his Airoboros models and code from which I borrowed many ideas and code snippets.

The 70b model was trained with support of the OVH Cloud Startup Program.

Contact

I you are interested in customized LLMs for business applications, please get in contact with me via my website. I am also always happy about suggestions and feedback.

PS: I am also still searching for a Co-Founder.

Disclaimer:

The license on this model does not constitute legal advice. I am not responsible for the actions of third parties who use this model. This model should only be used for research purposes. The original Llama2 license applies and is distributed with the model files.




(Deutsch) EM German

EM German (v01) ist eine experimentelle, Llama2-basierte KI-Modellreihe, die in deutscher Sprache fine-getuned wurde.

Die Modelle sind für deutschen Text optimiert und können Inhalte in deutscher Sprache verstehen und generieren.

Links & Demos

Im Github-Repo Repo werde ich weitere Beispiele und Code-Snippets veröffentlichen.

Model Links

Base Model HF GPTQ GGUF AWQ
Llama2 7b Link Link Link soon
Llama2 13b Link Link soon soon
Llama2 70b Link Link Link soon
Mistral 7b Link soon soon tbc
LeoLm 7b soon soon soon tbc
LeoLM 13b soon soon soon tbc

Colab:

Einige der Modelle können mit kostenlosen Google Colab-Instanzen verwendet werden (z.B. das 7b-Modell in 8-Bit oder das 13b-Modell mit GPTQ):

Eingabeformat

Dieses Modell folgt dem Vicuna-Format ohne Zeilenumbrüche (sollte aber auch mit Zeilenumbrüchen funktionieren). Das Format lautet wie folgt:

Du bist ein hilfreicher Assistent. USER: <Anweisung> ASSISTANT:

Sie können das Standard-Systemprompt aber auch ändern (siehe unten für ein Beispiel bei Aufgaben mit externen Datenbanken).

Ergebnisse

Anbei einige Beispiele für Modell-Outputs. Wir werden demnächst einige kleine deutsche Benchmarks veröffentlichen (basierend auf dem Eleuther LM Evaluation Harness), die wir bei diesen Modellen bereits getstet haben.

Beispiel-Ausgaben

Prompt:

Du bist ein hilfreicher Assistent USER: Ein Buch hat 500 Seiten. Jede Seite enthält 300 Wörter. Wie viele Wörter sind im gesamten Buch enthalten? ASSISTANT:

Antwort EM 7b v01

Die Gesamtzahl der Wörter in dem Buch kann berechnet werden, indem man die Anzahl der Wörter pro Seite mit der Gesamtzahl der Seiten multipliziert.

Gesamtzahl der Wörter = Anzahl der Wörter pro Seite * Gesamtzahl der Seiten = 300 Wörter pro Seite * 500 Seiten = 150.000 Wörter

Das Buch enthält also insgesamt 150.000 Wörter.

Prompt:

Du bist ein hilfreicher Assistent USER: Erläutere die Grundprinzipien der evolutionären Biologie und Genetik, indem du den Prozess der natürlichen Selektion, die Rolle von Mutationen und genetischer Drift sowie das Konzept der adaptiven Radiation erklärst. ASSISTANT:

Antwort EM 7b v01:

Die Evolutionäre Biologie und Genetik sind zwei intim verwandte Disziplinen, die sich mit dem Studium des Verhaltens und der Entwicklung von Organismen in der Natur befassen. Sie untersuchen, wie Arten sich im Laufe der Zeit entwickeln und wie diese Veränderungen genetisch bedingt sind.

    1. Natürliche Selektion: Die natürliche Selektion ist ein grundlegendes Prinzip in der Evolutionäre Biologie. Es besagt, dass Individuen innerhalb einer Spezies unterschiedliche Fähigkeiten oder Merkmale aufweisen können. Diese Merkmale beeinflussen ihre Überlebens- und Fortpflanzungsrate. Diejenigen mit Vorteilen haben eine höhere Wahrscheinlichkeit, ihre Gene an zukünftige Generationen weiterzugeben und so die Art im Laufe der Zeit zu verändern.

    2. Rolle von Mutationen: Mutationen sind Veränderungen im Genom eines Organismus, die entweder durch zufällige Fehler während der Replikation oder durch Exposition gegenüber Strahlung verursacht werden. Diese Veränderungen können dazu führen, dass ein Individuum neue Eigenschaften aufweist, die es im Kampf ums Überleben vorteilhaft machen könnten. Diese Mutationen werden dann von der natürlichen Selektion beeinflusst und können so zur Entwicklung neuer Arten beitragen.

    3. Genetische Drift: Genetische Drift ist ein zufälliger Prozess, der durch die Verteilung von Allelen in einer Population stattfindet. Wenn eine Population kleiner wird oder wenn die Überlebens- und Fortpflanzungsraten zwischen den Individuen variieren, kann dies dazu führen, dass bestimmte Gene stärker oder weniger häufig werden. Dies kann dazu führen, dass die Population im Laufe der Zeit unterschiedliche Merkmale aufweist.

    4. Adaptive Radiation: Adaptive Radiation ist ein Prozess, bei dem eine Art mehrere verschiedene Linien auslässt, die sich auf verschiedene Weise an ihre Umgebung anpassen. Dies geschieht normalerweise, wenn die Umwelt sich ändert und die Art neue Fähigkeiten benötigt, um überleben zu können. Die verschiedenen Linien können dann unterschiedliche Eigenschaften entwickeln, die ihnen helfen, in dieser neuen Umgebung zu überleben.

Sachliche Abfrage / RAG

EM-Modelle bieten ein spezielles Format für RAG (also die Verwendung mit Informationen aus zusätzlichen externen Quellen wie Datenbanken oder Websiten), das für die Minimierung von Halluzinationen und Falscinformationen optimiert ist. Wir verwenden dasselbe Format wie Airoboros dafür.

Beispiel

Prompt

Du bist ein hilfreicher Assistent. Für die folgende Aufgabe stehen dir zwischen den tags BEGININPUT und ENDINPUT mehrere Quellen zur Verfügung. Metadaten zu den einzelnen Quellen wie Autor, URL o.ä. sind zwischen BEGINCONTEXT und ENDCONTEXT zu finden, danach folgt der Text der Quelle. Die eigentliche Aufgabe oder Frage ist zwischen BEGININSTRUCTION und ENDINCSTRUCTION zu finden. Beantworte diese wortwörtlich mit einem Zitat aus den Quellen. Sollten diese keine Antwort enthalten, antworte, dass auf Basis der gegebenen Informationen keine Antwort möglich ist! USER: BEGININPUT
BEGINCONTEXT
Url: https://www.jph.me
ENDCONTEXT
Das Wetter in Düsseldorf wird heute schön und sonnig!
ENDINPUT
BEGININSTRUCTION Was ist 1+1? ENDINSTRUCTION ASSISTANT:

Modellantwort:

Mit den gegebenen Informationen ist diese Frage nicht zu beantworten.

Hier würde das Modell normalerweise die (triviale) Antwort (2) geben, ist aber trainiert, keine Antwort zu geben, wenn es keine Quelle zwischen BEGININPUT und ENDINPUT gibt, die eine belegbare Antwort liefert.

Wenn wir anstattdessen fragen:

BEGININSTRUCTION Wie wird das Wetter heute in Düsseldorf? Gebe die Quelle mit an! ENDINSTRUCTION ASSISTANT:

Bekommen wir die korrekte Antwort mit Quellenangabe

Das Wetter in Düsseldorf wird heute schön und sonnig! (Quelle: Url: https://www.jph.me)

Evaluation

coming soon

Datensatz

Der Datensatz ist eine Mischung aus Multi-Turn-Chats, RAG Instructions und synthetisch generierten Finetuning-Daten, die viele Themen und Anwendungen abdecken.

Einschränkungen & Vorurteile

Dieses Modell kann sachlich falsche Ausgaben produzieren und sollte nur zu Forschubngszwecken verwendet werden.

Danksagungen:

Vielen Dank an winglian/caseus für seine großartige Arbeit an Axolotl, die ich zur Schulung der EM-Modelle verwendet habe. Ich bin auch Jon Durbin für seine Arioboros Modelle und Code-Schnipsel dankbar, von denen ich viele Ideen nutzen konnte.

Das 70b-Modell wurde mit Unterstützung des OVH Cloud Startup Program trainiert.

Kontakt

Wenn Sie an customized LLMs für geschäftliche Anwendungen interessiert sind, kontaktieren Sie mich bitte über meine Website. Ich freue mich auch immer über Anregungen und Feedback zu meinen Modellen.

PS: Ich suche auch immer noch einen Co-Founder für unser Startup, das sich noch im Stealth-Modus befindet.

Haftungsausschluss:

Ich bin nicht verantwortlich für die Handlungen Dritter, die dieses Modell verwenden. Dieses Modell sollte nur für Forschungszwecke verwendet werden. Die ursprüngliche Llama2-Lizenz gilt und wird mit den Modell-Dateien verteilt.

Downloads last month
1,154
GGUF
Inference Examples
Inference API (serverless) has been turned off for this model.

Quantized from