Instructions to use Danielbrdz/MedBarcenas-MedlinePlus-4b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Danielbrdz/MedBarcenas-MedlinePlus-4b with Transformers:

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

pipe = pipeline("image-text-to-text", model="Danielbrdz/MedBarcenas-MedlinePlus-4b")
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, AutoModelForImageTextToText

processor = AutoProcessor.from_pretrained("Danielbrdz/MedBarcenas-MedlinePlus-4b")
model = AutoModelForImageTextToText.from_pretrained("Danielbrdz/MedBarcenas-MedlinePlus-4b")
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

vLLM

How to use Danielbrdz/MedBarcenas-MedlinePlus-4b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Danielbrdz/MedBarcenas-MedlinePlus-4b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Danielbrdz/MedBarcenas-MedlinePlus-4b",
		"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/Danielbrdz/MedBarcenas-MedlinePlus-4b

SGLang

How to use Danielbrdz/MedBarcenas-MedlinePlus-4b 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 "Danielbrdz/MedBarcenas-MedlinePlus-4b" \
    --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": "Danielbrdz/MedBarcenas-MedlinePlus-4b",
		"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 "Danielbrdz/MedBarcenas-MedlinePlus-4b" \
        --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": "Danielbrdz/MedBarcenas-MedlinePlus-4b",
		"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 Danielbrdz/MedBarcenas-MedlinePlus-4b with Docker Model Runner:
```
docker model run hf.co/Danielbrdz/MedBarcenas-MedlinePlus-4b
```

MedBarcenas MedlinePlus 4b

Basado en medgemma-1.5-4b-it y entrenado con el dataset MedBarcenas-MedlinePlus

El objetivo de este LLM es tener un modelo pequeño que tenga toda la información de MedlinePlus en español para que todo tipo de usuarios pueden obtener información confiable de medicina en español, de cierta manera claro

Todo gracias al dataset MedBarcenas-MedlinePlus con 18,988 ejemplos con un formato de preguntas y respuestas relacionado con el mundo médico

Extraído de la página perteneciente al gobierno de los Estados Unidos: MedlinePlus en Español

La información de MedlinePlus es de las más confiables y extensas en el mundo del medicina en español

MedBarcenas MedlinePlus 4b

Based on medgemma-1.5-4b-it and trained with the MedBarcenas-MedlinePlus dataset

The goal of this LLM is to have a small model that contains all the information from MedlinePlus in Spanish so that all kinds of users can obtain reliable medical information in Spanish, in a fairly clear way

All thanks to the MedBarcenas-MedlinePlus dataset with 18,988 examples in a question-and-answer format related to the medical world

Extracted from the page belonging to the government of the United States: MedlinePlus in Spanish

MedlinePlus information is among the most reliable and extensive in the world of medicine in Spanish

Made with ❤️ in Guadalupe, Nuevo Leon, Mexico 🇲🇽

Downloads last month: 3

Safetensors

Model size

4B params

Tensor type

F16

Model tree for Danielbrdz/MedBarcenas-MedlinePlus-4b

Base model

google/medgemma-1.5-4b-it

Finetuned

(64)

this model

Danielbrdz
/

MedBarcenas-MedlinePlus-4b

Model tree for Danielbrdz/MedBarcenas-MedlinePlus-4b

Dataset used to train Danielbrdz/MedBarcenas-MedlinePlus-4b