Instructions to use vicgalle/configurable-preference-phi4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use vicgalle/configurable-preference-phi4 with Transformers:

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

pipe = pipeline("text-generation", model="vicgalle/configurable-preference-phi4")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("vicgalle/configurable-preference-phi4", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use vicgalle/configurable-preference-phi4 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "vicgalle/configurable-preference-phi4"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "vicgalle/configurable-preference-phi4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/vicgalle/configurable-preference-phi4

SGLang

How to use vicgalle/configurable-preference-phi4 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 "vicgalle/configurable-preference-phi4" \
    --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": "vicgalle/configurable-preference-phi4",
		"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 "vicgalle/configurable-preference-phi4" \
        --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": "vicgalle/configurable-preference-phi4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use vicgalle/configurable-preference-phi4 with Docker Model Runner:
```
docker model run hf.co/vicgalle/configurable-preference-phi4
```

nielsr HF Staff commited on Jun 16, 2025

Commit

5d6fa18

verified ·

1 Parent(s): 01c9ef2

Add model card

Browse files

This PR adds a model card, ensuring people can find your model at https://huggingface.co/models?pipeline_tag=text-generation. It also links the model to the paper [Configurable Preference Tuning with Rubric-Guided Synthetic Data](https://huggingface.co/papers/2506.11702).

Files changed (1) hide show

README.md +4 -0

README.md CHANGED Viewed

@@ -2,4 +2,8 @@
 base_model: unsloth/phi-4-unsloth-bnb-4bit
 datasets:
 - vicgalle/creative-rubrics-preferences
 ---

 base_model: unsloth/phi-4-unsloth-bnb-4bit
 datasets:
 - vicgalle/creative-rubrics-preferences
+library_name: transformers
+pipeline_tag: text-generation
 ---
+This repository contains the model described in the paper [Configurable Preference Tuning with Rubric-Guided Synthetic Data](https://huggingface.co/papers/2506.11702).