Instructions to use KnutJaegersberg/KafkaLM-8x7B-German with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use KnutJaegersberg/KafkaLM-8x7B-German with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="KnutJaegersberg/KafkaLM-8x7B-German")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("KnutJaegersberg/KafkaLM-8x7B-German")
model = AutoModelForCausalLM.from_pretrained("KnutJaegersberg/KafkaLM-8x7B-German")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use KnutJaegersberg/KafkaLM-8x7B-German with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "KnutJaegersberg/KafkaLM-8x7B-German"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "KnutJaegersberg/KafkaLM-8x7B-German",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/KnutJaegersberg/KafkaLM-8x7B-German

SGLang

How to use KnutJaegersberg/KafkaLM-8x7B-German with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "KnutJaegersberg/KafkaLM-8x7B-German" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "KnutJaegersberg/KafkaLM-8x7B-German",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "KnutJaegersberg/KafkaLM-8x7B-German" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "KnutJaegersberg/KafkaLM-8x7B-German",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use KnutJaegersberg/KafkaLM-8x7B-German with Docker Model Runner:
```
docker model run hf.co/KnutJaegersberg/KafkaLM-8x7B-German
```

KafkaLM-8x7b-German-V0.1

KafkaLM 8x7b is a MoE model based on Mistral AI´s Mixtral 8x7b which was finetuned on an ensemble of popular high-quality open-source instruction sets (translated from English to German).

KafkaLM 8x7b is a Seedbox project trained by Dennis Dickmann.

Why Kafka? The models are proficient, yet creative, have some tendencies to linguistically push boundaries 😊

Model Details

The purpose of releasing the KafkaLM series is to contribute to the German AI community with a set of fine-tuned LLMs that are easy to use in everyday applications across a variety of tasks.

The main goal was to provide LLMs proficient in German, especially to be used in German-speaking business contexts where English alone is not sufficient.

Dataset

I used a 8k filtered version of the following seedboxai/multitask_german_examples_32k

Prompt Format

This model follows the subsequent prompt format:

<|system|>
Du bist ein freundlicher und hilfsbereiter KI-Assistent. Du beantwortest Fragen faktenorientiert und präzise, ohne dabei relevante Fakten auszulassen.</s>
<|user|>
Welche Möglichkeiten der energetischen Sanierung habe ich neben Solar und Energiespeicher?</s>
<|assistant|>

Inference

Getting started with the model is straightforward

import transformers

model_id = "seedboxai/KafkaLM-8x7B-German-V0.1"

model = AutoModelForCausalLM.from_pretrained(model_id, load_in_4bit=True, trust_remote_code=True)

tokenizer = AutoTokenizer.from_pretrained(model_id)

def generate_prompt(input):
    prompt = ''
    sys_prompt = "Du bist ein freundlicher und hilfsbereiter KI-Assistent. Du beantwortest Fragen faktenorientiert und präzise, ohne dabei relevante Fakten auszulassen."
    
    prompt += f"<|system|>\n{sys_prompt.strip()}</s>\n"
    prompt += f"<|user|>\n{input.strip()}</s>\n"
    prompt += f"<|assistant|>\n"

    return prompt.strip()


generate_text = transformers.pipeline(
    model=model, tokenizer=tokenizer,
    return_full_text=True,  
    task='text-generation',
    temperature=0.5,  
    max_new_tokens=512,
    top_p=0.95,
    top_k=40,
    do_sample=True,
)

print(generate_text(generate_prompt("Wer ist eigentlich dieser Kafka?"))

Disclaimer

The license on this model does not constitute legal advice. We are 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 and all restrictions of datasets used to train this model apply.

Downloads last month: 1

Safetensors

Model size

47B params

Tensor type

F32

Duplicated from seedboxai/KafkaLM-8x7B-German-V0.1

KnutJaegersberg
/

KafkaLM-8x7B-German