Instructions to use doubledsbv/KafkaLM-7B-DARE_TIES-LaserRMT-QLoRA-DPO-v0.5-AWQ with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use doubledsbv/KafkaLM-7B-DARE_TIES-LaserRMT-QLoRA-DPO-v0.5-AWQ with Transformers:

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

pipe = pipeline("text-generation", model="doubledsbv/KafkaLM-7B-DARE_TIES-LaserRMT-QLoRA-DPO-v0.5-AWQ")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("doubledsbv/KafkaLM-7B-DARE_TIES-LaserRMT-QLoRA-DPO-v0.5-AWQ")
model = AutoModelForCausalLM.from_pretrained("doubledsbv/KafkaLM-7B-DARE_TIES-LaserRMT-QLoRA-DPO-v0.5-AWQ", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use doubledsbv/KafkaLM-7B-DARE_TIES-LaserRMT-QLoRA-DPO-v0.5-AWQ with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "doubledsbv/KafkaLM-7B-DARE_TIES-LaserRMT-QLoRA-DPO-v0.5-AWQ"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "doubledsbv/KafkaLM-7B-DARE_TIES-LaserRMT-QLoRA-DPO-v0.5-AWQ",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/doubledsbv/KafkaLM-7B-DARE_TIES-LaserRMT-QLoRA-DPO-v0.5-AWQ

SGLang

How to use doubledsbv/KafkaLM-7B-DARE_TIES-LaserRMT-QLoRA-DPO-v0.5-AWQ 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 "doubledsbv/KafkaLM-7B-DARE_TIES-LaserRMT-QLoRA-DPO-v0.5-AWQ" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "doubledsbv/KafkaLM-7B-DARE_TIES-LaserRMT-QLoRA-DPO-v0.5-AWQ",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "doubledsbv/KafkaLM-7B-DARE_TIES-LaserRMT-QLoRA-DPO-v0.5-AWQ" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "doubledsbv/KafkaLM-7B-DARE_TIES-LaserRMT-QLoRA-DPO-v0.5-AWQ",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use doubledsbv/KafkaLM-7B-DARE_TIES-LaserRMT-QLoRA-DPO-v0.5-AWQ with Docker Model Runner:
```
docker model run hf.co/doubledsbv/KafkaLM-7B-DARE_TIES-LaserRMT-QLoRA-DPO-v0.5-AWQ
```

Configuration Parsing Warning:In config.json: "quantization_config.modules_to_not_convert" must be an array

KafkaLM-7B-DARE_TIES-LaserRMT-QLoRA-DPO-v0.5

KafkaLM 7b is a Mistral 7b model - further pre-trained on a large German dataset from Björn Plüster and LAION. leo-mistral-hessianai-7b - which was finetuned on an ensemble of popular high-quality open-source instruction sets (translated from English to German).

KafkaLM 7b is a Seedbox project trained by Dennis Dickmann.

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

THE MODEL CAN BE TESTET HERE Kafka-7B HF Space

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 Training with laserRMT w/ Q-Lora

Based on the brilliant work from laserRMT team, I used the SNR implementation for identifying candiate layers to be used for the DPO training.

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|>

🧩 Configuration

models:
  - model: mistralai/Mistral-7B-v0.1
    # no parameters necessary for base model
  - model: seedboxai/KafkaLM-7B-German-V0.1
    parameters:
      density: 0.65
      weight: 0.50
  - model: mlabonne/Monarch-7B
    parameters:
      density: 0.60
      weight: 0.30
  - model: mayflowergmbh/Wiedervereinigung-7b-dpo-laser
    parameters:
      density: 0.60
      weight: 0.20
merge_method: dare_ties
base_model: mistralai/Mistral-7B-v0.1
parameters:
  int8_mask: true
dtype: bfloat16
random_seed: 0

💻 Usage (fast vLLM inference example)

!pip install -qU vllm

import torch
from vllm import LLM, SamplingParams

sampling_params = SamplingParams(
    temperature=0.7, 
    top_p=0.95, 
    top_k=50,
    max_tokens=512,
)

llm = LLM(model="doubledsbv/KafkaLM-7B-DARE_TIES-DPO-v0.5-AWQ", quantization = "awq", dtype=torch.float16)


def generate_prompt(input, sys_prompt = None):
    prompt = ''
    if not sys_prompt:
      sys_prompt = "Du bist ein freundlicher und hilfsbereiter KI-Assistent. Du beantwortest Fragen faktenorientiert, präzise und ausführlich."
    
    prompt += f"<|system|>\n{sys_prompt.strip()}</s>\n"
    prompt += f"<|user|>\n{input.strip()}</s>\n"
    prompt += f"<|assistant|>\n"

    return prompt

outputs = llm.generate(generate_prompt("Was ist der Unterschied zwischen Ironie und Sarkasmus?"), sampling_params)
primt(outputs[0].outputs[0].text.strip())

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: 12

Safetensors

Model size

7B params

Tensor type

I32

F16

doubledsbv
/

KafkaLM-7B-DARE_TIES-LaserRMT-QLoRA-DPO-v0.5-AWQ