%20--%3e%3cdefs%3e%3cstyle%3e%20.st0%20{%20fill:%20%23061b40;%20}%20.st1%20{%20fill:%20%23306af1;%20}%20.st2%20{%20fill:%20%235ce5cf;%20}%20%3c/style%3e%3c/defs%3e%3cg%3e%3cpath%20class='st0'%20d='M55,10.5h9v3h-9v9h12V7.5h-12v3ZM64,19.5h-6v-3h6v3Z'/%3e%3cpolygon%20class='st0'%20points='69%2016.5%2078%2016.5%2078%2019.5%2069%2019.5%2069%2022.5%2081%2022.5%2081%2013.5%2072%2013.5%2072%2010.5%2081%2010.5%2081%207.5%2069%207.5%2069%2016.5'/%3e%3cpolygon%20class='st0'%20points='95%2010.5%2095%207.5%2083%207.5%2083%2022.5%2095%2022.5%2095%2019.5%2086%2019.5%2086%2016.5%2095%2016.5%2095%2013.5%2086%2013.5%2086%2010.5%2095%2010.5'/%3e%3cpath%20class='st0'%20d='M40,1.5v21h11.6l1.4-1.4v-7.6h0c0,0-1.4-1.5-1.4-1.5l1.4-1.4V2.9l-1.4-1.4h-11.6ZM50,19.5h-7v-6h7v6ZM50,10.5h-7v-6h7v6Z'/%3e%3c/g%3e%3cpath%20class='st1'%20d='M23.1,24L14.7,4.8l-4.9,11.2h3.8l-1.8,4H3.3L12.1,0H2C.9,0,0,.9,0,2v20c0,1.1.9,2,2,2h21.1Z'/%3e%3cpath%20class='st2'%20d='M34,0h-16.8l10.6,24h6.2c1.1,0,2-.9,2-2V2C36,.9,35.1,0,34,0ZM32.5,20h-4V4h4v16Z'/%3e%3c/svg%3e)
EN
Kafkalm 70B German V0.1 GGUF
KafkaLM 70B German V0.1 is a large German language model based on the Llama2 architecture, developed by Seedbox. This model is specifically optimized for German and is suitable for various text generation tasks.
Downloads 1,826
Release Time : 1/31/2024
Model Overview
This is a large German language model with 70B parameters, based on the Llama2 architecture, specifically optimized for German text understanding and generation.
Model Features
Large-scale German Optimization
Specifically optimized for German, enabling better understanding and generation of German text
Based on Llama2 Architecture
Utilizes the advanced Llama2 architecture, providing powerful language understanding and generation capabilities
Multiple Quantization Versions
Offers various quantization versions from 2-bit to 8-bit to accommodate different hardware requirements
Model Capabilities
German Text Generation
German Text Understanding
German Dialogue Systems
German Content Creation
Use Cases
Content Creation
German Article Writing
Generate high-quality German articles, reports, and blog content
German Marketing Copy
Create engaging advertisements and marketing copy for the German market
Dialogue Systems
German Chatbot
Build AI assistants capable of natural and fluent German conversations
đ KafkaLM 70B German V0.1 - GGUF
This repository provides GGUF format model files for KafkaLM 70B German V0.1, enabling efficient text generation in German.
đ Quick Start
This repo contains GGUF format model files for Seedbox's KafkaLM 70B German V0.1. These files were quantised using hardware kindly provided by Massed Compute.
⨠Features
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. 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.
- GPT4All, a free and open source local running GUI, supporting Windows, Linux and macOS with full GPU accel.
- LM Studio, 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, 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.
- 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.
- 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.
đĻ Installation
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/KafkaLM-70B-German-V0.1-GGUF and below it, a specific filename to download, such as: kafkalm-70b-german-v0.1.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/KafkaLM-70B-German-V0.1-GGUF kafkalm-70b-german-v0.1.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False
More advanced huggingface-cli download usage (click to read)
You can also download multiple files at once with a pattern:
huggingface-cli download TheBloke/KafkaLM-70B-German-V0.1-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/KafkaLM-70B-German-V0.1-GGUF kafkalm-70b-german-v0.1.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.
đ Documentation
Repositories available
- AWQ model(s) for GPU inference.
- GPTQ models for GPU inference, with multiple quantisation parameter options.
- 2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference
- Seedbox's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions
Prompt template: Zephyr
<|system|>
{system_message}</s>
<|user|>
{prompt}</s>
<|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 |
|---|---|---|---|---|---|
| kafkalm-70b-german-v0.1.Q2_K.gguf | Q2_K | 2 | 25.46 GB | 27.96 GB | significant quality loss - not recommended for most purposes |
| kafkalm-70b-german-v0.1.Q3_K_S.gguf | Q3_K_S | 3 | 29.92 GB | 32.42 GB | very small, high quality loss |
| kafkalm-70b-german-v0.1.Q3_K_M.gguf | Q3_K_M | 3 | 33.27 GB | 35.77 GB | very small, high quality loss |
| kafkalm-70b-german-v0.1.Q3_K_L.gguf | Q3_K_L | 3 | 36.15 GB | 38.65 GB | small, substantial quality loss |
| kafkalm-70b-german-v0.1.Q4_0.gguf | Q4_0 | 4 | 38.87 GB | 41.37 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
| kafkalm-70b-german-v0.1.Q4_K_S.gguf | Q4_K_S | 4 | 39.25 GB | 41.75 GB | small, greater quality loss |
| kafkalm-70b-german-v0.1.Q4_K_M.gguf | Q4_K_M | 4 | 41.42 GB | 43.92 GB | medium, balanced quality - recommended |
| kafkalm-70b-german-v0.1.Q5_0.gguf | Q5_0 | 5 | 47.46 GB | 49.96 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
| kafkalm-70b-german-v0.1.Q5_K_S.gguf | Q5_K_S | 5 | 47.46 GB | 49.96 GB | large, low quality loss - recommended |
| kafkalm-70b-german-v0.1.Q5_K_M.gguf | Q5_K_M | 5 | 48.75 GB | 51.25 GB | large, very low quality loss - recommended |
| kafkalm-70b-german-v0.1.Q6_K.gguf | Q6_K | 6 | 56.59 GB | 59.09 GB | very large, extremely low quality loss |
| kafkalm-70b-german-v0.1.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:
kafkalm-70b-german-v0.1.Q6_K.gguf-split-akafkalm-70b-german-v0.1.Q6_K.gguf-split-b
q8_0
Please download:
kafkalm-70b-german-v0.1.Q8_0.gguf-split-akafkalm-70b-german-v0.1.Q8_0.gguf-split-b
To join the files, do the following:
Linux and macOS:
cat kafkalm-70b-german-v0.1.Q6_K.gguf-split-* > kafkalm-70b-german-v0.1.Q6_K.gguf && rm kafkalm-70b-german-v0.1.Q6_K.gguf-split-*
cat kafkalm-70b-german-v0.1.Q8_0.gguf-split-* > kafkalm-70b-german-v0.1.Q8_0.gguf && rm kafkalm-70b-german-v0.1.Q8_0.gguf-split-*
Windows command line:
COPY /B kafkalm-70b-german-v0.1.Q6_K.gguf-split-a + kafkalm-70b-german-v0.1.Q6_K.gguf-split-b kafkalm-70b-german-v0.1.Q6_K.gguf
del kafkalm-70b-german-v0.1.Q6_K.gguf-split-a kafkalm-70b-german-v0.1.Q6_K.gguf-split-b
COPY /B kafkalm-70b-german-v0.1.Q8_0.gguf-split-a + kafkalm-70b-german-v0.1.Q8_0.gguf-split-b kafkalm-70b-german-v0.1.Q8_0.gguf
del kafkalm-70b-german-v0.1.Q8_0.gguf-split-a kafkalm-70b-german-v0.1.Q8_0.gguf-split-b
Example llama.cpp command
Make sure you are using llama.cpp from commit d0cee0d
đ§ Technical Details
Model Information
| Property | Details |
|---|---|
| Base Model | seedboxai/KafkaLM-70B-German-V0.1 |
| Datasets | seedboxai/multitask_german_examples_32k |
| Inference | false |
| Language | de |
| Library Name | transformers |
| License | llama2 |
| Model Creator | Seedbox |
| Model Name | KafkaLM 70B German V0.1 |
| Model Type | llama |
| Pipeline Tag | text-generation |
| Prompt Template | '< |
| Quantized By | TheBloke |
| Tags | llama2, deutsch, german, seedbox |
đ License
The model is licensed under the llama2 license.
Phi 2 GGUF
Other
Phi-2 is a small yet powerful language model developed by Microsoft, featuring 2.7 billion parameters, focusing on efficient inference and high-quality text generation.
Large Language Model Supports Multiple Languages
P
TheBloke
41.5M
205
Roberta Large
MIT
A large English language model pre-trained with masked language modeling objectives, using improved BERT training methods
Large Language Model English
R
FacebookAI
19.4M
212
Distilbert Base Uncased
Apache-2.0
DistilBERT is a distilled version of the BERT base model, maintaining similar performance while being more lightweight and efficient, suitable for natural language processing tasks such as sequence classification and token classification.
Large Language Model English
D
distilbert
11.1M
669
Llama 3.1 8B Instruct GGUF
Meta Llama 3.1 8B Instruct is a multilingual large language model optimized for multilingual dialogue use cases, excelling in common industry benchmarks.
Large Language Model English
L
modularai
9.7M
4
Xlm Roberta Base
MIT
XLM-RoBERTa is a multilingual model pretrained on 2.5TB of filtered CommonCrawl data across 100 languages, using masked language modeling as the training objective.
Large Language Model Supports Multiple Languages
X
FacebookAI
9.6M
664
Roberta Base
MIT
An English pre-trained model based on Transformer architecture, trained on massive text through masked language modeling objectives, supporting text feature extraction and downstream task fine-tuning
Large Language Model English
R
FacebookAI
9.3M
488
Opt 125m
Other
OPT is an open pre-trained Transformer language model suite released by Meta AI, with parameter sizes ranging from 125 million to 175 billion, designed to match the performance of the GPT-3 series while promoting open research in large-scale language models.
Large Language Model English
O
facebook
6.3M
198
1
A pretrained model based on the transformers library, suitable for various NLP tasks
Large Language Model
Transformers
Transformers1
unslothai
6.2M
1
Llama 3.1 8B Instruct
Llama 3.1 is Meta's multilingual large language model series, featuring 8B, 70B, and 405B parameter scales, supporting 8 languages and code generation, with optimized multilingual dialogue scenarios.
Large Language Model Transformers Supports Multiple Languages
Transformers Supports Multiple LanguagesL
meta-llama
5.7M
3,898
T5 Base
Apache-2.0
The T5 Base Version is a text-to-text Transformer model developed by Google with 220 million parameters, supporting multilingual NLP tasks.
Large Language Model Supports Multiple Languages
T
google-t5
5.4M
702
Featured Recommended AI Models
Š 2025AIbase