Instructions to use openbmb/AgentCPM-Explore with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use openbmb/AgentCPM-Explore with Transformers:

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

pipe = pipeline("text-generation", model="openbmb/AgentCPM-Explore")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("openbmb/AgentCPM-Explore")
model = AutoModelForCausalLM.from_pretrained("openbmb/AgentCPM-Explore")
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 openbmb/AgentCPM-Explore with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/openbmb/AgentCPM-Explore

SGLang

How to use openbmb/AgentCPM-Explore 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 "openbmb/AgentCPM-Explore" \
    --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": "openbmb/AgentCPM-Explore",
		"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 "openbmb/AgentCPM-Explore" \
        --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": "openbmb/AgentCPM-Explore",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use openbmb/AgentCPM-Explore with Docker Model Runner:
```
docker model run hf.co/openbmb/AgentCPM-Explore
```

DennisHuang648 commited on Jan 14

Commit

b7bd7bd

verified ·

1 Parent(s): d958e80

Update Readme.md (#3)

Browse files

- Update Readme.md (d451f83dbc0685c90880ff47a810a24c4e3c6535)

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -10,7 +10,7 @@ library_name: transformers
 ## Latest News
-* [2025-01-12]🚀🚀🚀 We have open-sourced **AgentCPM-Explore**, an agent foundation model with only **4B parameters**, together with its **entire training and inference infrastructure**. AgentCPM-Explore has successfully entered **8 classic long-horizon agent benchmarks**, including **GAIA,HLE, and BrowserComp**. AgentCPM-Explore achieves **SOTA performance at the same parameter scale** and demonstrates its **accurate deep research capabilities**, effectively breaking the performance bottleneck for **on-device agents**.
 ## Overview

 ## Latest News
+* [2026-01-12]🚀🚀🚀 We have open-sourced **AgentCPM-Explore**, an agent foundation model with only **4B parameters**, together with its **entire training and inference infrastructure**. AgentCPM-Explore has successfully entered **8 classic long-horizon agent benchmarks**, including **GAIA,HLE, and BrowserComp**. AgentCPM-Explore achieves **SOTA performance at the same parameter scale** and demonstrates its **accurate deep research capabilities**, effectively breaking the performance bottleneck for **on-device agents**.
 ## Overview