Instructions to use openbmb/BitCPM-CANN-0.5B-unquantized with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use openbmb/BitCPM-CANN-0.5B-unquantized with Transformers:

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

pipe = pipeline("text-generation", model="openbmb/BitCPM-CANN-0.5B-unquantized", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("openbmb/BitCPM-CANN-0.5B-unquantized", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use openbmb/BitCPM-CANN-0.5B-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-0.5B-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-0.5B-unquantized",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/openbmb/BitCPM-CANN-0.5B-unquantized

SGLang

How to use openbmb/BitCPM-CANN-0.5B-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-0.5B-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-0.5B-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-0.5B-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-0.5B-unquantized",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use openbmb/BitCPM-CANN-0.5B-unquantized with Docker Model Runner:
```
docker model run hf.co/openbmb/BitCPM-CANN-0.5B-unquantized
```

BitCPM-CANN-0.5B-unquantized / README.md

guanwenyu1995

Update README naming from BitCPM4 to BitCPM

8fd38e0 verified 1 day ago

preview code

raw

history blame contribute delete

6.36 kB

	---
	license: apache-2.0
	language:
	- zh
	- en
	pipeline_tag: text-generation
	library_name: transformers
	---
	<div align="center">
	<img src="https://github.com/OpenBMB/MiniCPM/blob/main/assets/minicpm_logo.png?raw=true" width="500em" ></img>
	</div>

	<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>
	</p>

	## Overview

	BitCPM-CANN-0.5B-unquantized is the unquantized QAT (Quantization-Aware Training) checkpoint of BitCPM-CANN-0.5B, designed for continued pre-training and fine-tuning. It preserves full-precision latent weights with ternary fake quantizers (weights → {-1, 0, 1} with group-wise scaling, trained via STE) defined in `modeling.py`, enabling the model to keep learning under quantization constraints. For technical details, see our [Technical Report](https://github.com/OpenBMB/MiniCPM/blob/main/docs/BitCPM_CANN.pdf).

	> ⚠️ This model is NOT for direct inference. For inference, use the pseudo-quantized version: [openbmb/BitCPM-CANN-0.5B](https://huggingface.co/openbmb/BitCPM-CANN-0.5B).

	## Continued Pre-training & Fine-tuning

	The only requirement is that the forward pass must go through the bundled `modeling.py` (which contains the ternary fake quantizer). Load with `trust_remote_code=True` and do NOT replace or bypass the model's forward logic.

	### Option 1: DeepSpeed (Recommended)

	We provide ready-to-use training scripts in the [example](https://huggingface.co/openbmb/BitCPM-CANN-0.5B-unquantized/tree/main/example) directory (using the 1B model as an example):

	- Continued pre-training: `example/run.sh` + `example/train.py`
	- SFT (Supervised Fine-tuning): `example/run_sft.sh` + `example/train_sft.py`

	Quick start:

	```bash
	# Continued pre-training
	cd example && bash run.sh

	# Supervised fine-tuning
	cd example && bash run_sft.sh
	```

	### Option 2: HuggingFace-compatible Frameworks

	Any framework that supports HuggingFace model loading with custom code can be used, such as LLaMA Factory, HuggingFace Trainer, etc. The key is to ensure `trust_remote_code=True`:

	```python
	from transformers import AutoModelForCausalLM, AutoTokenizer

	path = 'openbmb/BitCPM-CANN-0.5B-unquantized'
	tokenizer = AutoTokenizer.from_pretrained(path, trust_remote_code=True)
	model = AutoModelForCausalLM.from_pretrained(
	path,
	torch_dtype=torch.bfloat16,
	trust_remote_code=True
	)

	# Use with your preferred framework (LLaMA Factory, HF Trainer, etc.)
	# The ternary fake quantizer in modeling.py is applied automatically during forward pass.
	```

	## Post-Training Conversion

	After training, use `qat-convert.py` to fuse the fake quantizer and produce inference-ready pseudo-quantized weights:

	```bash
	python qat-convert.py \
	--input_bin <path-to-finetuned-pytorch.bin> \
	--output <path-to-output-pseudo-quantized-pytorch.bin> \
	--quant_type ternary \
	--group_size -1
	```

	The converted model can be loaded for inference in the same way as [openbmb/BitCPM-CANN-0.5B](https://huggingface.co/openbmb/BitCPM-CANN-0.5B)—no special quantization libraries required.

	## Workflow

	```
	┌─────────────────────────────────┐
	│ BitCPM-CANN-0.5B-unquantized │ ← This model (QAT checkpoint + fake quantizer in modeling.py)
	└───────────────┬─────────────────┘
	│
	▼ Train (DeepSpeed / LLaMA Factory / HF Trainer / ...)
	┌─────────────────────────────────┐
	│ Fine-tuned checkpoint │ ← Still contains un-fused QAT parameters
	└───────────────┬─────────────────┘
	│
	▼ python qat-convert.py --quant_type ternary --group_size -1
	┌─────────────────────────────────┐
	│ Pseudo-quantized model │ ← Ready for inference (same format as BitCPM-CANN-0.5B)
	└─────────────────────────────────┘
	```

	## BitCPM-CANN Model Family

	\| Model \| HuggingFace (Inference) \| HuggingFace (Fine-tuning) \|
	\|-------\|-------------------------\|---------------------------\|
	\| BitCPM-CANN-0.5B \| [openbmb/BitCPM-CANN-0.5B](https://huggingface.co/openbmb/BitCPM-CANN-0.5B) \| [openbmb/BitCPM-CANN-0.5B-unquantized](https://huggingface.co/openbmb/BitCPM-CANN-0.5B-unquantized) \|
	\| BitCPM-CANN-1B \| [openbmb/BitCPM-CANN-1B](https://huggingface.co/openbmb/BitCPM-CANN-1B) \| [openbmb/BitCPM-CANN-1B-unquantized](https://huggingface.co/openbmb/BitCPM-CANN-1B-unquantized) \|
	\| BitCPM-CANN-3B \| [openbmb/BitCPM-CANN-3B](https://huggingface.co/openbmb/BitCPM-CANN-3B) \| [openbmb/BitCPM-CANN-3B-unquantized](https://huggingface.co/openbmb/BitCPM-CANN-3B-unquantized) \|
	\| BitCPM-CANN-8B \| [openbmb/BitCPM-CANN-8B](https://huggingface.co/openbmb/BitCPM-CANN-8B) \| [openbmb/BitCPM-CANN-8B-unquantized](https://huggingface.co/openbmb/BitCPM-CANN-8B-unquantized) \|

	## Statement
	- As a language model, BitCPM-CANN generates content by learning from a vast amount of text.
	- However, it does not possess the ability to comprehend or express personal opinions or value judgments.
	- Any content generated by BitCPM-CANN does not represent the viewpoints or positions of the model developers.
	- Therefore, when using content generated by BitCPM-CANN, users should take full responsibility for evaluating and verifying it on their own.

	## LICENSE
	- This repository and BitCPM-CANN models are released under the [Apache-2.0](https://github.com/OpenBMB/MiniCPM/blob/main/LICENSE) License.

	## Citation
	- Please cite our technical report if you find our work valuable.

	```bibtex
	@article{bitcpmcann,
	title={{BitCPM-CANN}: Native 1.58-Bit Large Language Model Training on Ascend NPU},
	author={BitCPM Team},
	year={2026}
	}
	```