Kafkalm 13B German V0.1

🚀 KafkaLM-13B-German-V0.1

KafkaLM 13b is a Llama2 13b model. It has been further pre - trained on a large German dataset from Björn Plüster and LAION, and leo - hessianai-13b was finetuned on an ensemble of popular high - quality open - source instruction sets (translated from English to German). KafkaLM 13b is a Seedbox project trained by Dennis Dickmann.

This model aims to contribute to the German AI community by offering a set of fine - tuned LLMs that are easy to use in daily applications for various tasks. Its main goal is to provide LLMs proficient in German, especially for German - speaking business contexts where English alone is not enough.

Why Kafka? The models are proficient yet creative and have a tendency to linguistically push boundaries 😊

🚀 Quick Start

Inference

Getting started with the model is straightforward. Here is a Python code example to show how to use it:

import transformers

model_id = "seedboxai/KafkaLM-13B-German-V0.1"

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

tokenizer = AutoTokenizer.from_pretrained(model_id)

tokenizer.padding_side = "right" 
tokenizer.pad_token = tokenizer.unk_token
tokenizer.add_eos_token = False

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_length=8192,  
    max_new_tokens=512,
    top_p=0.95,
    top_k=50,
    do_sample=True,
)


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

✨ Features

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 an 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|>

📄 License

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.