Instructions to use julien31/Soar-qwen-32b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use julien31/Soar-qwen-32b with Transformers:

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

pipe = pipeline("text-generation", model="julien31/Soar-qwen-32b")
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-32b")
model = AutoModelForCausalLM.from_pretrained("julien31/Soar-qwen-32b", 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-32b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "julien31/Soar-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": "julien31/Soar-qwen-32b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/julien31/Soar-qwen-32b

SGLang

How to use julien31/Soar-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 "julien31/Soar-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": "julien31/Soar-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 "julien31/Soar-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": "julien31/Soar-qwen-32b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use julien31/Soar-qwen-32b with Docker Model Runner:
```
docker model run hf.co/julien31/Soar-qwen-32b
```

julien31

nielsr HF Staff commited on Jul 25, 2025

Commit

4f42e43

verified ·

1 Parent(s): 67a840f

Improve model card: Add `library_name` and update paper link (#1)

Browse files

- Improve model card: Add `library_name` and update paper link (2e3699d6b4a71978dae3ea2de9f051cad5c4f105)

Co-authored-by: Niels Rogge <nielsr@users.noreply.huggingface.co>

Files changed (1) hide show

README.md +8 -9

README.md CHANGED Viewed

@@ -1,9 +1,9 @@
 ---
-license: apache-2.0
-datasets:
-- julien31/soar_arc_train_5M
 base_model:
 - Qwen/Qwen2.5-Coder-32B-Instruct
 pipeline_tag: text-generation
 tags:
 - text-generation
@@ -13,16 +13,18 @@ tags:
 - arc
 - arc-agi
 - soar
 ---
 # SOAR-ARC Models: Self-Improving Language Models for Program Synthesis
 <p align="center">
-          🤗 <a href="https://huggingface.co/collections/julien31/soar-arc-6856d27681fce01d9af4c4a3">Hugging Face (data and model)</a>&nbsp&nbsp | &nbsp&nbsp 📑 <a href="https://icml.cc/virtual/2025/poster/43499">Paper</a> &nbsp&nbsp | &nbsp&nbsp 📑 <a href="https://julienp.netlify.app/posts/soar/">Blog</a>
 </p>
 This repository contains one of the models fine-tuned using the **SOAR** (**S**elf-improving **O**perators for **A**utomated program **R**efinements) framework, as presented in the paper:
-> [**Self-Improving Language Models for Evolutionary Program Synthesis: A Case Study on ARC-AGI**](https://icml.cc/virtual/2025/poster/43499)
 >
 > Julien Pourcel, Cédric Colas, Pierre-Yves Oudeyer.
 > *Proceedings of the 42nd International Conference on Machine Learning (ICML), 2025.*
@@ -67,7 +69,4 @@ The primary use of this model is to generate a Python function that solves an AR
 For a complete, end-to-end example of how to format the prompt, run inference, execute the generated code, and visualize the results, please refer to the official repository and notebook:
 *   **Official SOAR GitHub Repository**: [https://github.com/flowersteam/SOAR](https://github.com/flowersteam/SOAR)
-*   **Inference & Visualization Notebook**: [https://github.com/flowersteam/SOAR/blob/main/notebook/inference_visualisation.ipynb](https://github.com/flowersteam/SOAR/blob/main/notebook/inference_visualisation.ipynb)
-# SOAR-ARC Models: Self-Improving Language Models for Program Synthesis
-<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/made with unsloth.png" width="20%" />

 ---
 base_model:
 - Qwen/Qwen2.5-Coder-32B-Instruct
+datasets:
+- julien31/soar_arc_train_5M
+license: apache-2.0
 pipeline_tag: text-generation
 tags:
 - text-generation
 - arc
 - arc-agi
 - soar
+library_name: transformers
 ---
 # SOAR-ARC Models: Self-Improving Language Models for Program Synthesis
 <p align="center">
+          🤗 <a href="https://huggingface.co/collections/julien31/soar-arc-6856d27681fce01d9af4c4a3">Hugging Face (data and model)</a>&nbsp&nbsp | &nbsp&nbsp 📑 <a href="https://huggingface.co/papers/2507.14172">Paper</a> &nbsp&nbsp | &nbsp&nbsp 📑 <a href="https://julienp.netlify.app/posts/soar/">Blog</a>
 </p>
 This repository contains one of the models fine-tuned using the **SOAR** (**S**elf-improving **O**perators for **A**utomated program **R**efinements) framework, as presented in the paper:
+> [**Self-Improving Language Models for Evolutionary Program Synthesis: A Case Study on ARC-AGI**](https://huggingface.co/papers/2507.14172)
 >
 > Julien Pourcel, Cédric Colas, Pierre-Yves Oudeyer.
 > *Proceedings of the 42nd International Conference on Machine Learning (ICML), 2025.*
 For a complete, end-to-end example of how to format the prompt, run inference, execute the generated code, and visualize the results, please refer to the official repository and notebook:
 *   **Official SOAR GitHub Repository**: [https://github.com/flowersteam/SOAR](https://github.com/flowersteam/SOAR)
+*   **Inference & Visualization Notebook**: [https://github.com/flowersteam/SOAR/blob/main/notebook/inference_visualisation.ipynb](https://github.com/flowersteam/SOAR/blob/main/notebook/inference_visualisation.ipynb)