Instructions to use stepfun-ai/PaCoRe-8B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use stepfun-ai/PaCoRe-8B with Transformers:

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

pipe = pipeline("text-generation", model="stepfun-ai/PaCoRe-8B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("stepfun-ai/PaCoRe-8B")
model = AutoModelForCausalLM.from_pretrained("stepfun-ai/PaCoRe-8B")
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

vLLM

How to use stepfun-ai/PaCoRe-8B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "stepfun-ai/PaCoRe-8B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "stepfun-ai/PaCoRe-8B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/stepfun-ai/PaCoRe-8B

SGLang

How to use stepfun-ai/PaCoRe-8B 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 "stepfun-ai/PaCoRe-8B" \
    --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": "stepfun-ai/PaCoRe-8B",
		"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 "stepfun-ai/PaCoRe-8B" \
        --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": "stepfun-ai/PaCoRe-8B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use stepfun-ai/PaCoRe-8B with Docker Model Runner:
```
docker model run hf.co/stepfun-ai/PaCoRe-8B
```

Here is a unofficial Live Chat implementation.

by ikaganacar - opened Dec 15, 2025

Discussion

ikaganacar

Dec 15, 2025

Hey everyone! 👋

I’ve been experimenting with PaCoRe and wanted to share a fork I created that adapts the framework for interactive, daily usage on consumer hardware.

I implemented a terminal-based "Live Chat" tui (using rich) that visualizes the parallel reasoning branches in real-time before synthesizing the final answer. It’s tuned for efficiency with a lightweight configuration (2-4 branches).

I've tested this configuration on an NVIDIA RTX 5070 (12GB) using 8-bit quantization and it runs smoothly with a 9k context window.

Check it out here if you want to try running PaCoRe real-time: https://github.com/ikaganacar1/PaCoRe-LiveChat

Hope this is useful for anyone wanting to run this locally!

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment