Instructions to use julien31/Soar-qwen-7b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use julien31/Soar-qwen-7b with Transformers:

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

pipe = pipeline("text-generation", model="julien31/Soar-qwen-7b")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("julien31/Soar-qwen-7b")
model = AutoModelForCausalLM.from_pretrained("julien31/Soar-qwen-7b", 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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use julien31/Soar-qwen-7b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "julien31/Soar-qwen-7b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "julien31/Soar-qwen-7b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/julien31/Soar-qwen-7b

SGLang

How to use julien31/Soar-qwen-7b 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 "julien31/Soar-qwen-7b" \
    --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": "julien31/Soar-qwen-7b",
		"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 "julien31/Soar-qwen-7b" \
        --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": "julien31/Soar-qwen-7b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use julien31/Soar-qwen-7b with Docker Model Runner:
```
docker model run hf.co/julien31/Soar-qwen-7b
```

Improve model card: Add library_name, update paper link, and expand usage info

by nielsr HF Staff - opened Jul 22, 2025

base: refs/heads/main

←

from: refs/pr/1

Discussion Files changed

+94

-6

nielsr

Jul 22, 2025

This PR enhances the model card for Soar-qwen-7b by:

Adding library_name: transformers to the metadata, enabling the "Use in Transformers" widget and improving discoverability.
Updating the paper link in both the header and the citation block to the official Hugging Face Papers page (https://huggingface.co/papers/2507.14172), providing a consistent and preferred link within the Hugging Face ecosystem.
Including a direct Python code example for model inference using the transformers library in the "How to Use the Model" section, offering a quick start for users.
Integrating detailed conda installation instructions and guidance on running SOAR directly from the project's GitHub README, making the model card a more comprehensive resource for setup and operation.

These updates improve the model's documentation, making it easier for researchers and developers to utilize and understand the SOAR framework and its models.

Improve model card: Add library_name, update paper link, and expand usage infof066b4db

julien31 changed pull request status to merged Jul 25, 2025

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