Instructions to use VAGOsolutions/SauerkrautLM-Qwen-32b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use VAGOsolutions/SauerkrautLM-Qwen-32b with Transformers:

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

pipe = pipeline("text-generation", model="VAGOsolutions/SauerkrautLM-Qwen-32b")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("VAGOsolutions/SauerkrautLM-Qwen-32b")
model = AutoModelForCausalLM.from_pretrained("VAGOsolutions/SauerkrautLM-Qwen-32b")
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

vLLM

How to use VAGOsolutions/SauerkrautLM-Qwen-32b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "VAGOsolutions/SauerkrautLM-Qwen-32b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "VAGOsolutions/SauerkrautLM-Qwen-32b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/VAGOsolutions/SauerkrautLM-Qwen-32b

SGLang

How to use VAGOsolutions/SauerkrautLM-Qwen-32b 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 "VAGOsolutions/SauerkrautLM-Qwen-32b" \
    --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": "VAGOsolutions/SauerkrautLM-Qwen-32b",
		"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 "VAGOsolutions/SauerkrautLM-Qwen-32b" \
        --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": "VAGOsolutions/SauerkrautLM-Qwen-32b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use VAGOsolutions/SauerkrautLM-Qwen-32b with Docker Model Runner:
```
docker model run hf.co/VAGOsolutions/SauerkrautLM-Qwen-32b
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

VAGO solutions SauerkrautLM-Qwen-32b

Introducing SauerkrautLM-Qwen-32b – our Sauerkraut version of the powerful Qwen/Qwen1.5-32B!

The model SauerkrautLM-Qwen-32b is a joint effort between VAGO solutions and Hyperspace.ai.

Finetuned with SFT
Aligned with DPO

Overview of all SauerkrautLM-Qwen-32b
Model Details
- Prompt template
- Training procedure
Evaluation
Disclaimer
Contact
Collaborations
Acknowledgement

All SauerkrautLM-Qwen-32b

Model	HF	EXL2	GGUF	AWQ
SauerkrautLM-Qwen-32b	Link	coming soon	coming soon	coming soon

Model Details

SauerkrautLM-Qwen-32b

Model Type: SauerkrautLM-Qwen-32b is a finetuned Model based on Qwen/Qwen1.5-32B
Language(s): German, English
License: tongyi-qianwen-research
Contact: VAGO solutions, Hyperspace.ai

Training procedure:

We trained this model for 2 epochs on 160k data samples with SFT.
Afterwards we applied DPO for 1 epoch with 110k data.
LaserRMT version coming soon

We teached German language skills on this model. As far as we know, it is the first Qwen 32B model with bilingual skills in German and English. Nevertheless, formulations may occur that are not entirely correct (still work in progress).

Prompt Template:

English:

<|im_start|>system
You are SauerkrautLM, a helpful AI assistant.<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant

German:

<|im_start|>system
Du bist SauerkrautLM, ein hilfreicher und freundlicher KI-Assistent.<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant

Example output of german language:

Die Karte zeigte eine verborgene Höhle, die in den umliegenden Bergen zu finden war. Mia war von der Idee fasziniert, diese Höhle zu entdecken und ihre Geheimnisse zu lüften. Sie nahm die Karte mit sich und machte sich auf den Weg, um die Höhle zu finden.
Die Wanderung zu den Bergen war eine Herausforderung, aber Mia war fest entschlossen, ihr Abenteuer zu vollenden. Sie überwand steinige Wege und überquerte klirrende Bäche, die ihre Füße kühlten und ihr die Energie für den Rest des Weges gab.
Endlich erreichte Mia die Höhle, die von einem dichten Wald umgeben war. Die Höhle war ein Ort der Geheimnisse und des Staunens, der ihr Herz höher schlagen ließ. Sie betrat die Höhle, und die Dunkelheit umhüllte sie wie ein Schleier aus Stille.
In der Höhle fand Mia eine alte Schatzkiste, die mit einem alten, verwitterten Holz verziert war. Mit zitternden Händen öffnete sie die Schatzkiste und fand darin eine alte, zerfledderte Schriftrolle. Die Schriftrolle war ein geheimnisvolles Artefakt, das ihr die Geschichte der Höhle offenbarte.

Evaluation

Open LLM Leaderboard:

Metric	Value
Avg.	73.11
ARC (25-shot)	59.22
HellaSwag (10-shot)	82.32
MMLU (5-shot)	74.40
TruthfulQA (0-shot)	61.03
Winogrande (5-shot)	82.16
GSM8K (5-shot)	79.53

Disclaimer

We must inform users that despite our best efforts in data cleansing, the possibility of uncensored content slipping through cannot be entirely ruled out. However, we cannot guarantee consistently appropriate behavior. Therefore, if you encounter any issues or come across inappropriate content, we kindly request that you inform us through the contact information provided. Additionally, it is essential to understand that the licensing of these models does not constitute legal advice. We are not held responsible for the actions of third parties who utilize our models.

Contact

If you are interested in customized LLMs for business applications, please get in contact with us via our websites. We are also grateful for your feedback and suggestions.

Collaborations

We are also keenly seeking support and investment for our startups, VAGO solutions and Hyperspace where we continuously advance the development of robust language models designed to address a diverse range of purposes and requirements. If the prospect of collaboratively navigating future challenges excites you, we warmly invite you to reach out to us at VAGO solutions, Hyperspace.computer

Acknowledgement

Many thanks to Qwen for providing such valuable model to the Open-Source community

Downloads last month: 18

Safetensors

Model size

33B params

Tensor type

BF16

Model tree for VAGOsolutions/SauerkrautLM-Qwen-32b

Quantizations

4 models

Spaces using VAGOsolutions/SauerkrautLM-Qwen-32b 2

Collection including VAGOsolutions/SauerkrautLM-Qwen-32b

SauerkrautLM-qwen

Collection

Find our empowered SauerrkautLM Versions of various Qwen models here • 4 items • Updated Nov 9, 2024 • 2

VAGOsolutions
/

SauerkrautLM-Qwen-32b