Instructions to use OpenMed/Ministral-3B-PII-Preview with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use OpenMed/Ministral-3B-PII-Preview with Transformers:

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

pipe = pipeline("text-generation", model="OpenMed/Ministral-3B-PII-Preview")
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)

# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("OpenMed/Ministral-3B-PII-Preview")
model = AutoModelForMultimodalLM.from_pretrained("OpenMed/Ministral-3B-PII-Preview")
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=40)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use OpenMed/Ministral-3B-PII-Preview with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "OpenMed/Ministral-3B-PII-Preview"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "OpenMed/Ministral-3B-PII-Preview",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/OpenMed/Ministral-3B-PII-Preview

SGLang

How to use OpenMed/Ministral-3B-PII-Preview 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 "OpenMed/Ministral-3B-PII-Preview" \
    --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": "OpenMed/Ministral-3B-PII-Preview",
		"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 "OpenMed/Ministral-3B-PII-Preview" \
        --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": "OpenMed/Ministral-3B-PII-Preview",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use OpenMed/Ministral-3B-PII-Preview with Docker Model Runner:
```
docker model run hf.co/OpenMed/Ministral-3B-PII-Preview
```

Ministral-3B-PII-Preview / config.json

MaziyarPanahi

Add Ministral-3B-PII: GRPO-trained structured PII extraction (text-to-text)

5515f8a verified about 1 month ago

Raw

History Blame Contribute Delete

1.7 kB

	{
	"architectures": [
	"Mistral3ForConditionalGeneration"
	],
	"dtype": "bfloat16",
	"image_token_index": 10,
	"model_type": "mistral3",
	"multimodal_projector_bias": false,
	"projector_hidden_act": "gelu",
	"spatial_merge_size": 2,
	"text_config": {
	"attention_dropout": 0.0,
	"bos_token_id": 1,
	"dtype": "bfloat16",
	"eos_token_id": 2,
	"head_dim": 128,
	"hidden_act": "silu",
	"hidden_size": 3072,
	"initializer_range": 0.02,
	"intermediate_size": 9216,
	"max_position_embeddings": 262144,
	"model_type": "ministral3",
	"num_attention_heads": 32,
	"num_hidden_layers": 26,
	"num_key_value_heads": 8,
	"pad_token_id": 11,
	"rms_norm_eps": 1e-05,
	"rope_parameters": {
	"beta_fast": 32.0,
	"beta_slow": 1.0,
	"factor": 16.0,
	"llama_4_scaling_beta": 0.1,
	"mscale": 1.0,
	"mscale_all_dim": 1.0,
	"original_max_position_embeddings": 16384,
	"rope_theta": 1000000.0,
	"rope_type": "yarn",
	"type": "yarn"
	},
	"sliding_window": null,
	"tie_word_embeddings": true,
	"use_cache": true,
	"vocab_size": 131072
	},
	"tie_word_embeddings": true,
	"transformers_version": "5.3.0",
	"vision_config": {
	"attention_dropout": 0.0,
	"dtype": "bfloat16",
	"head_dim": 64,
	"hidden_act": "silu",
	"hidden_size": 1024,
	"image_size": 1540,
	"initializer_range": 0.02,
	"intermediate_size": 4096,
	"model_type": "pixtral",
	"num_attention_heads": 16,
	"num_channels": 3,
	"num_hidden_layers": 24,
	"patch_size": 14,
	"rope_parameters": {
	"rope_theta": 10000.0,
	"rope_type": "default"
	}
	},
	"vision_feature_layer": -1
	}