Instructions to use morganstanley/qqWen-32B-RL-Reasoning with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use morganstanley/qqWen-32B-RL-Reasoning with Transformers:

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

pipe = pipeline("text-generation", model="morganstanley/qqWen-32B-RL-Reasoning")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("morganstanley/qqWen-32B-RL-Reasoning")
model = AutoModelForCausalLM.from_pretrained("morganstanley/qqWen-32B-RL-Reasoning")
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 morganstanley/qqWen-32B-RL-Reasoning with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/morganstanley/qqWen-32B-RL-Reasoning

SGLang

How to use morganstanley/qqWen-32B-RL-Reasoning 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 "morganstanley/qqWen-32B-RL-Reasoning" \
    --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": "morganstanley/qqWen-32B-RL-Reasoning",
		"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 "morganstanley/qqWen-32B-RL-Reasoning" \
        --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": "morganstanley/qqWen-32B-RL-Reasoning",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use morganstanley/qqWen-32B-RL-Reasoning with Docker Model Runner:
```
docker model run hf.co/morganstanley/qqWen-32B-RL-Reasoning
```

bhogan commited on Aug 27, 2025

Commit

4e9e487

verified ·

1 Parent(s): d5e22a5

Update README.md

Browse files

Files changed (1) hide show

README.md +12 -2

README.md CHANGED Viewed

@@ -12,7 +12,7 @@ base_model:
 **qqWen-32B-RL** is a 32-billion parameter language model specifically designed for advanced reasoning and code generation in the Q programming language. Built upon the robust Qwen 2.5 architecture, this model has undergone a comprehensive three-stage training process: pretraining, supervised fine-tuning (SFT), and reinforcement learning (RL) for the Q programming language.
 **qqWen-32B-RL** is a reasoning model.
-**Associated Technical Report**: [Link to paper will be added here]
 ## 🔤 About Q Programming Language
@@ -35,4 +35,14 @@ Q is a high-performance, vector-oriented programming language developed by Kx Sy
 If you use this model in your research or applications, please cite our technical report.
-```

 **qqWen-32B-RL** is a 32-billion parameter language model specifically designed for advanced reasoning and code generation in the Q programming language. Built upon the robust Qwen 2.5 architecture, this model has undergone a comprehensive three-stage training process: pretraining, supervised fine-tuning (SFT), and reinforcement learning (RL) for the Q programming language.
 **qqWen-32B-RL** is a reasoning model.
+**Associated Technical Report**: [Report](https://arxiv.org/abs/2508.06813)
 ## 🔤 About Q Programming Language
 If you use this model in your research or applications, please cite our technical report.
+```
+@misc{hogan2025technicalreportfullstackfinetuning,
+      title={Technical Report: Full-Stack Fine-Tuning for the Q Programming Language},
+      author={Brendan R. Hogan and Will Brown and Adel Boyarsky and Anderson Schneider and Yuriy Nevmyvaka},
+      year={2025},
+      eprint={2508.06813},
+      archivePrefix={arXiv},
+      primaryClass={cs.LG},
+      url={https://arxiv.org/abs/2508.06813},
+}
+```