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

Libraries

How to use VAGOsolutions/SauerkrautLM-SOLAR-Instruct with Transformers:

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("VAGOsolutions/SauerkrautLM-SOLAR-Instruct")
model = AutoModelForCausalLM.from_pretrained("VAGOsolutions/SauerkrautLM-SOLAR-Instruct")
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]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use VAGOsolutions/SauerkrautLM-SOLAR-Instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "VAGOsolutions/SauerkrautLM-SOLAR-Instruct"
# 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-SOLAR-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/VAGOsolutions/SauerkrautLM-SOLAR-Instruct

SGLang

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

Docker Model Runner
How to use VAGOsolutions/SauerkrautLM-SOLAR-Instruct with Docker Model Runner:
```
docker model run hf.co/VAGOsolutions/SauerkrautLM-SOLAR-Instruct
```

License - commercial use

by pepperscene - opened Jan 16, 2024

Discussion

pepperscene

Jan 16, 2024

Hey there,
thanks for your great work offering models that work well in German.

I noticed that this model has a non-commercial license while your other models have the apache-2.0 licenses. Is that a general shift in your approach that will be reflected in future models? Is it just this one? Or are there any plans to change this models license in the future?

Cheers

DaryoushV

VAGO solutions org Jan 16, 2024

•

edited Jan 16, 2024

Hey,

thanks for your feedback. Appreciate it. In general, we try to publish all our models for commercial use. However, in this case, the SOLAR model, provided by Upstage, uses a non-commercial license, which we need to respect.

pepperscene

Jan 16, 2024

Oh. I see that they changed their license after original release under apache-2.0. Thanks for the quick feedback.

DavidGF changed discussion status to closed Jan 16, 2024

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment