Instructions to use AXCXEPT/phi-4-deepseek-R1K-RL-EZO with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use AXCXEPT/phi-4-deepseek-R1K-RL-EZO with Transformers:

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

pipe = pipeline("text-generation", model="AXCXEPT/phi-4-deepseek-R1K-RL-EZO", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("AXCXEPT/phi-4-deepseek-R1K-RL-EZO", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("AXCXEPT/phi-4-deepseek-R1K-RL-EZO", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.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(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use AXCXEPT/phi-4-deepseek-R1K-RL-EZO with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "AXCXEPT/phi-4-deepseek-R1K-RL-EZO"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "AXCXEPT/phi-4-deepseek-R1K-RL-EZO",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/AXCXEPT/phi-4-deepseek-R1K-RL-EZO

SGLang

How to use AXCXEPT/phi-4-deepseek-R1K-RL-EZO 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 "AXCXEPT/phi-4-deepseek-R1K-RL-EZO" \
    --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": "AXCXEPT/phi-4-deepseek-R1K-RL-EZO",
		"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 "AXCXEPT/phi-4-deepseek-R1K-RL-EZO" \
        --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": "AXCXEPT/phi-4-deepseek-R1K-RL-EZO",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use AXCXEPT/phi-4-deepseek-R1K-RL-EZO with Docker Model Runner:
```
docker model run hf.co/AXCXEPT/phi-4-deepseek-R1K-RL-EZO
```

AXCXEPT commited on Jan 30, 2025

Commit

0da30e8

verified ·

1 Parent(s): 94003ae

Update README.md

Browse files

Files changed (1) hide show

README.md +2 -3

README.md CHANGED Viewed

@@ -30,11 +30,10 @@ This model is the result of combining Phi-4 with a reinforcement learning (RL) a
 ##### Key Features & Improvements
 Enhanced Multilingual Performance: Unlike previous iterations, this model strengthens English capabilities without compromising Japanese proficiency.
-Optimized Training Efficiency: Inspired by Deepseek R1 research, we fine-tuned Phi-4 with a 14K dataset in just two days, achieving substantial gains.
 Benchmark-Proven Quality:
 Outperforms the base Phi-4 model on OpenAI’s Simple-eval and translation benchmarks (Japanese MT Bench, MT Bench).
 Surpasses gpt-4o-mini in multiple evaluation categories, proving its capability as a high-performance 14B model.
-Secure and Scalable for Enterprises: Designed to function efficiently in local and on-premise environments, making it suitable for high-security industries where cloud-based solutions are not viable.
 ##### Why Local LLMs Still Matter
 Despite rapid advancements in cloud-based models, local LLMs remain crucial for enterprises that require high security and strict data privacy compliance. Many organizations—especially in public institutions, manufacturing, and design industries—cannot risk exposing sensitive data externally. This model is developed with the goal of delivering state-of-the-art performance in a secure, closed environment.
@@ -130,4 +129,4 @@ print(response)
 ```
 ### Special Thanks:
-To the Phi-4 development team, the Deepseek research team, and everyone who contributed to this project.

 ##### Key Features & Improvements
 Enhanced Multilingual Performance: Unlike previous iterations, this model strengthens English capabilities without compromising Japanese proficiency.
+Optimized Training Efficiency: Inspired by Deepseek R1 research, we fine-tuned Phi-4 with a 14K dataset in just two days, achieving both gains.
 Benchmark-Proven Quality:
 Outperforms the base Phi-4 model on OpenAI’s Simple-eval and translation benchmarks (Japanese MT Bench, MT Bench).
 Surpasses gpt-4o-mini in multiple evaluation categories, proving its capability as a high-performance 14B model.
 ##### Why Local LLMs Still Matter
 Despite rapid advancements in cloud-based models, local LLMs remain crucial for enterprises that require high security and strict data privacy compliance. Many organizations—especially in public institutions, manufacturing, and design industries—cannot risk exposing sensitive data externally. This model is developed with the goal of delivering state-of-the-art performance in a secure, closed environment.
 ```
 ### Special Thanks:
+To the Phi-4 development team who developed high-quality base model, the Deepseek research team, and everyone who contributed to this project.