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

Libraries

How to use openbmb/AgentCPM-Report with Transformers:

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

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

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("openbmb/AgentCPM-Report", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use openbmb/AgentCPM-Report with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "openbmb/AgentCPM-Report"
# 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-Report",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

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

SGLang

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

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

Kaguya-19 commited on Jan 26

Commit

8d4168d

verified ·

1 Parent(s): 8b34b5d

Update README.md

Browse files

Files changed (1) hide show

README.md +4 -1

README.md CHANGED Viewed

@@ -1,5 +1,8 @@
 ---
 license: apache-2.0
 ---
 # AgentCPM-Report: Gemini-2.5-pro-DeepResearch Level Local DeepResearch
@@ -346,4 +349,4 @@ If **AgentCPM-Report** is helpful for your research, please cite it as follows:
   year   = {2026},
   url    = {https://github.com/OpenBMB/AgentCPM}
 }
-```

 ---
 license: apache-2.0
+tags:
+- text-generation-inference
+- agent
 ---
 # AgentCPM-Report: Gemini-2.5-pro-DeepResearch Level Local DeepResearch
   year   = {2026},
   url    = {https://github.com/OpenBMB/AgentCPM}
 }
+```