Instructions to use ngqtrung/M3OPD-MixRL-Baseline-9B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ngqtrung/M3OPD-MixRL-Baseline-9B with Transformers:

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

pipe = pipeline("image-text-to-text", model="ngqtrung/M3OPD-MixRL-Baseline-9B")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("ngqtrung/M3OPD-MixRL-Baseline-9B")
model = AutoModelForMultimodalLM.from_pretrained("ngqtrung/M3OPD-MixRL-Baseline-9B", device_map="auto")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.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(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use ngqtrung/M3OPD-MixRL-Baseline-9B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ngqtrung/M3OPD-MixRL-Baseline-9B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ngqtrung/M3OPD-MixRL-Baseline-9B",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/ngqtrung/M3OPD-MixRL-Baseline-9B

SGLang

How to use ngqtrung/M3OPD-MixRL-Baseline-9B 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 "ngqtrung/M3OPD-MixRL-Baseline-9B" \
    --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": "ngqtrung/M3OPD-MixRL-Baseline-9B",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

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 "ngqtrung/M3OPD-MixRL-Baseline-9B" \
        --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": "ngqtrung/M3OPD-MixRL-Baseline-9B",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Docker Model Runner
How to use ngqtrung/M3OPD-MixRL-Baseline-9B with Docker Model Runner:
```
docker model run hf.co/ngqtrung/M3OPD-MixRL-Baseline-9B
```

M3OPD-MixRL-Baseline-9B

MixRL baseline of the M3OPD-Reasoner paper. Qwen3.5-9B gets SFT on the mixed SFT data of all three domains (MixSFT) and then GSPO on all prompts of M3OPD-RL-193K, with the settings of the domain teachers. This is step 240, the best evaluated checkpoint. It is a baseline, not the main model.

All checkpoints of the recipe are in the M3OPD-Reasoner collection. The data are M3OPD-SFT-1.35M and M3OPD-RL-193K.

Usage

The model has the architecture, tokenizer, processor and chat template of Qwen3.5-9B, so it runs wherever Qwen3.5-9B runs (Transformers, vLLM, SGLang). We train and evaluate with the native Qwen3.5 chat template, thinking enabled, no system prompt, and one answer-format line after the question, for example Put your final answer within \boxed{}.

vllm serve ngqtrung/M3OPD-MixRL-Baseline-9B --max-model-len 40960

License

Apache 2.0, the license of Qwen3.5-9B.

Downloads last month: 17

Safetensors

Model size

9B params

Tensor type

BF16

Model tree for ngqtrung/M3OPD-MixRL-Baseline-9B

Base model

Qwen/Qwen3.5-9B-Base

Finetuned

Qwen/Qwen3.5-9B

Finetuned

(1,300)

this model

Datasets used to train ngqtrung/M3OPD-MixRL-Baseline-9B

Collection including ngqtrung/M3OPD-MixRL-Baseline-9B

M3OPD-Reasoner

Collection

Data and checkpoints of M3OPD-Reasoner, an open recipe for reasoning vision-language models with multi-teacher on-policy distillation. • 8 items • Updated 1 day ago