How to use from
vLLM
Install from pip and serve model
# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "kyr0/phi4-r1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "kyr0/phi4-r1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'
Use Docker
docker model run hf.co/kyr0/phi4-r1
Quick Links

Uploaded model

  • Developed by: kyr0
  • License: MIT
  • Finetuned from model : unsloth/phi-4-bnb-4bit
Downloads last month
22
Safetensors
Model size
15B params
Tensor type
BF16
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for kyr0/phi4-r1

Base model

microsoft/phi-4
Quantized
(23)
this model