Instructions to use openbmb/BitCPM-CANN-1B-unquantized with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use openbmb/BitCPM-CANN-1B-unquantized with Transformers:

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

pipe = pipeline("text-generation", model="openbmb/BitCPM-CANN-1B-unquantized", 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("openbmb/BitCPM-CANN-1B-unquantized", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("openbmb/BitCPM-CANN-1B-unquantized", 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

vLLM

How to use openbmb/BitCPM-CANN-1B-unquantized with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "openbmb/BitCPM-CANN-1B-unquantized"
# 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/BitCPM-CANN-1B-unquantized",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/openbmb/BitCPM-CANN-1B-unquantized

SGLang

How to use openbmb/BitCPM-CANN-1B-unquantized 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/BitCPM-CANN-1B-unquantized" \
    --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/BitCPM-CANN-1B-unquantized",
		"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/BitCPM-CANN-1B-unquantized" \
        --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/BitCPM-CANN-1B-unquantized",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use openbmb/BitCPM-CANN-1B-unquantized with Docker Model Runner:
```
docker model run hf.co/openbmb/BitCPM-CANN-1B-unquantized
```

guanwenyu1995 commited on 2 days ago

Commit

68beec3

verified ·

1 Parent(s): a415ed2

Upload README.md with huggingface_hub

Browse files

Files changed (1) hide show

README.md +2 -2

README.md CHANGED Viewed

@@ -12,7 +12,7 @@ library_name: transformers
 <p align="center">
 <a href="https://github.com/OpenBMB/MiniCPM/" target="_blank">GitHub Repo</a> |
-<a href="TODO_TECHNICAL_REPORT_LINK" target="_blank">Technical Report</a>
 </p>
 <p align="center">
 👋 Join us on <a href="https://discord.gg/3cGQn9b3YM" target="_blank">Discord</a> and <a href="https://github.com/OpenBMB/MiniCPM/blob/main/assets/wechat.jpg" target="_blank">WeChat</a>
@@ -108,7 +108,7 @@ The converted model can then be loaded for inference in the same way as [openbmb
 BitCPM4-CANN uses a ternary quantizer that maps each weight group to {-1, 0, 1} scaled by a group-wise factor, trained with Straight-Through Estimator (STE) for gradient flow. The unquantized checkpoint preserves the full-precision latent weights alongside the quantizer parameters, allowing the model to continue learning under quantization constraints during fine-tuning.
-For full technical details, please refer to our [Technical Report](TODO_TECHNICAL_REPORT_LINK).
 ## Statement
 - As a language model, BitCPM4-CANN generates content by learning from a vast amount of text.

 <p align="center">
 <a href="https://github.com/OpenBMB/MiniCPM/" target="_blank">GitHub Repo</a> |
+<a href="https://github.com/OpenBMB/MiniCPM/blob/main/docs/BitCPM_CANN.pdf" target="_blank">Technical Report</a>
 </p>
 <p align="center">
 👋 Join us on <a href="https://discord.gg/3cGQn9b3YM" target="_blank">Discord</a> and <a href="https://github.com/OpenBMB/MiniCPM/blob/main/assets/wechat.jpg" target="_blank">WeChat</a>
 BitCPM4-CANN uses a ternary quantizer that maps each weight group to {-1, 0, 1} scaled by a group-wise factor, trained with Straight-Through Estimator (STE) for gradient flow. The unquantized checkpoint preserves the full-precision latent weights alongside the quantizer parameters, allowing the model to continue learning under quantization constraints during fine-tuning.
+For full technical details, please refer to our [Technical Report](https://github.com/OpenBMB/MiniCPM/blob/main/docs/BitCPM_CANN.pdf).
 ## Statement
 - As a language model, BitCPM4-CANN generates content by learning from a vast amount of text.