Instructions to use yongchao98/R1-Code-Interpreter-14B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use yongchao98/R1-Code-Interpreter-14B with Transformers:

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

pipe = pipeline("text-generation", model="yongchao98/R1-Code-Interpreter-14B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("yongchao98/R1-Code-Interpreter-14B")
model = AutoModelForCausalLM.from_pretrained("yongchao98/R1-Code-Interpreter-14B")
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]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use yongchao98/R1-Code-Interpreter-14B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "yongchao98/R1-Code-Interpreter-14B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "yongchao98/R1-Code-Interpreter-14B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/yongchao98/R1-Code-Interpreter-14B

SGLang

How to use yongchao98/R1-Code-Interpreter-14B 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 "yongchao98/R1-Code-Interpreter-14B" \
    --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": "yongchao98/R1-Code-Interpreter-14B",
		"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 "yongchao98/R1-Code-Interpreter-14B" \
        --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": "yongchao98/R1-Code-Interpreter-14B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use yongchao98/R1-Code-Interpreter-14B with Docker Model Runner:
```
docker model run hf.co/yongchao98/R1-Code-Interpreter-14B
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

R1-Code-Interpreter: Training LLMs to Reason with Code via Supervised and Reinforcement Learning

The model was presented in the paper R1-Code-Interpreter: Training LLMs to Reason with Code via Supervised and Reinforcement Learning.

Our code is based on Llama-factory/VeRL/Search-R1 for the SFT and RL training and SymBench/BIG-Bench-Hard/reasoning-gym for datasets/benchmarks of reasoning/planning tasks.

📝 Introduction

R1-Code-Interpreter is the first framework to train LLMs for step-by-step code reasoning using multi-turn supervised fine-tuning and reinforcement learning. By curating 144 diverse reasoning and planning tasks, we enable Qwen-2.5 models (3B/7B/14B) to autonomously decide when and how to invoke code. Our best model, R1-CI-14B, outperforms GPT-4o (text-only) and approaches GPT-4o with Code Interpreter, showing emergent self-checking behavior via code generation.

Github repository

Project page: https://huggingface.co/yongchao98

Downloads last month: 11

Safetensors

Model size

15B params

Tensor type

F32

Model tree for yongchao98/R1-Code-Interpreter-14B

Quantizations

2 models

Paper for yongchao98/R1-Code-Interpreter-14B

R1-Code-Interpreter: Training LLMs to Reason with Code via Supervised and Reinforcement Learning

Paper • 2505.21668 • Published May 27, 2025 • 2