Instructions to use PabloCano1/ordered-HC-gemma3-4b-fine-tuned with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use PabloCano1/ordered-HC-gemma3-4b-fine-tuned with Transformers:

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

pipe = pipeline("text-generation", model="PabloCano1/ordered-HC-gemma3-4b-fine-tuned")
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("PabloCano1/ordered-HC-gemma3-4b-fine-tuned")
model = AutoModelForMultimodalLM.from_pretrained("PabloCano1/ordered-HC-gemma3-4b-fine-tuned", 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 PabloCano1/ordered-HC-gemma3-4b-fine-tuned with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "PabloCano1/ordered-HC-gemma3-4b-fine-tuned"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "PabloCano1/ordered-HC-gemma3-4b-fine-tuned",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/PabloCano1/ordered-HC-gemma3-4b-fine-tuned

SGLang

How to use PabloCano1/ordered-HC-gemma3-4b-fine-tuned 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 "PabloCano1/ordered-HC-gemma3-4b-fine-tuned" \
    --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": "PabloCano1/ordered-HC-gemma3-4b-fine-tuned",
		"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 "PabloCano1/ordered-HC-gemma3-4b-fine-tuned" \
        --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": "PabloCano1/ordered-HC-gemma3-4b-fine-tuned",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use PabloCano1/ordered-HC-gemma3-4b-fine-tuned with Docker Model Runner:
```
docker model run hf.co/PabloCano1/ordered-HC-gemma3-4b-fine-tuned
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Model description

This model is one of two population-specific models created to study linguistic differences between healthy controls and patients with psychosis. The general idea of the project is to compare both models using perplexity and other language-based signals. This is the Healthy model for simulating responses from healthy control participants in clinical interviews.

Training data

The model was trained on question-answer pairs extracted from the Discourse-UWO clinical interview dataset.

Intended use

This model is intended for research in clinical NLP, language modeling, and psychosis-related speech analysis. It can also be used for experiments with population-specific text generation.

Limitations

This model is for research purposes only and is not intended for diagnosis or clinical decision-making. The dataset is limited and imbalanced, so outputs may reflect dataset-specific biases.

Citation

If you use this model, cite the associated thesis documentation:

@misc{cano2026population_modeling_psychosis,
  title={Towards Explainable AI for Psychosis Detection Through Clinical Language Modeling},
  author={Pablo Ramon Cano Ortiz},
  year={2026},
  note={Undergraduate thesis, Universidad Politecnica de Madrid}
}

Downloads last month: 6

Safetensors

Model size

4B params

Tensor type

BF16

Model tree for PabloCano1/ordered-HC-gemma3-4b-fine-tuned

Base model

google/gemma-3-4b-pt

Finetuned

google/gemma-3-4b-it

Adapter

(536)

this model

Quantizations

1 model