KafkaLM-Mixtral-8x7B-V0.2

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.

DPO

The model has been aligned with a german and modified version of the ultra feedback dataset from huggingface.

Dataset

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

Inference

Getting started with the model is straightforward

import transformers
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "seedboxai/KafkaLM-Mixtral-8x7B-V0.2"

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16)
tokenizer = transformers.AutoTokenizer.from_pretrained(model_id)

pipeline = transformers.pipeline(
    model=model, tokenizer=tokenizer,
    return_full_text=True,  
    task='text-generation',
    device="cuda",
)

messages = [
    {"role": "system", "content": "Du bist ein hilfreicher KI-Assistent."},
    {"role": "user", "content": "Wer ist eigentlich dieser Kafka?"},
]

prompt = pipeline.tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)

terminators = [
    pipeline.tokenizer.eos_token_id,
    pipeline.tokenizer.convert_tokens_to_ids("</s>")
]

outputs = pipeline(
    prompt,
    max_new_tokens=max_new_tokens,
    eos_token_id=terminators,
    do_sample=True,
    temperature=0.7,
    top_p=0.9,
)

print(outputs[0]["generated_text"][len(prompt):])

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.