Instructions to use openbmb/BitCPM-CANN-8B-unquantized with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use openbmb/BitCPM-CANN-8B-unquantized with Transformers:

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

pipe = pipeline("text-generation", model="openbmb/BitCPM-CANN-8B-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-8B-unquantized", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use openbmb/BitCPM-CANN-8B-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-8B-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-8B-unquantized",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/openbmb/BitCPM-CANN-8B-unquantized

SGLang

How to use openbmb/BitCPM-CANN-8B-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-8B-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-8B-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-8B-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-8B-unquantized",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use openbmb/BitCPM-CANN-8B-unquantized with Docker Model Runner:
```
docker model run hf.co/openbmb/BitCPM-CANN-8B-unquantized
```

guanwenyu1995 commited on 3 days ago

Commit

6c7c9ae

verified ·

1 Parent(s): 41544f6

Upload README.md with huggingface_hub

Browse files

Files changed (1) hide show

README.md +5 -5

README.md CHANGED Viewed

@@ -20,9 +20,9 @@ library_name: transformers
 ## Introduction
-BitCPM4-CANN-0.5B-unquantized is the **unquantized QAT training checkpoint** of the BitCPM4-CANN-0.5B model. This model stores the raw quantization-aware training (QAT) parameters **before** fake-quantizer fusion—the ternary fake quantizers are defined in `modeling.py` and applied during forward propagation.
-> ⚠️ **This model is NOT intended for direct inference.** It is designed as the starting point for fine-tuning BitCPM4-CANN. If you need a model for inference, please use the pseudo-quantized version: [openbmb/BitCPM4-CANN-0.5B](https://huggingface.co/openbmb/BitCPM4-CANN-0.5B).
 ### Key Characteristics
@@ -47,7 +47,7 @@ This model is designed for fine-tuning with frameworks that support custom model
 #### Supported Fine-tuning Frameworks
-- **DeepSpeed** (recommended): See [example](https://huggingface.co/openbmb/BitCPM4-CANN-0.5B-unquantized/tree/main/example)
 - **LLaMA Factory**: Supports custom model loading with `trust_remote_code=True`
 - **Other Frameworks**: Any framework that supports HuggingFace-compatible model loading with custom modeling code
@@ -60,7 +60,7 @@ When fine-tuning, you **must** ensure:
 ```python
 from transformers import AutoModelForCausalLM, AutoTokenizer
-path = 'openbmb/BitCPM4-CANN-0.5B-unquantized'
 tokenizer = AutoTokenizer.from_pretrained(path, trust_remote_code=True)
 model = AutoModelForCausalLM.from_pretrained(
     path,
@@ -90,7 +90,7 @@ The converted model can then be loaded for inference in the same way as [openbmb
 ```
 ┌─────────────────────────────────┐
-│  BitCPM4-CANN-0.5B-unquantized  │   ← This model (QAT parameters + fake quantizer in modeling.py)
 └───────────────┬─────────────────┘
                 │
                 ▼  Fine-tune (DeepSpeed / LLaMA Factory / ...)

 ## Introduction
+BitCPM4-CANN-8B-unquantized is the **unquantized QAT training checkpoint** of the BitCPM4-CANN-8B model. This model stores the raw quantization-aware training (QAT) parameters **before** fake-quantizer fusion—the ternary fake quantizers are defined in `modeling.py` and applied during forward propagation.
+> ⚠️ **This model is NOT intended for direct inference.** It is designed as the starting point for fine-tuning BitCPM4-CANN. If you need a model for inference, please use the pseudo-quantized version: [openbmb/BitCPM4-CANN-8B](https://huggingface.co/openbmb/BitCPM4-CANN-8B).
 ### Key Characteristics
 #### Supported Fine-tuning Frameworks
+- **DeepSpeed** (recommended): See [example](https://huggingface.co/openbmb/BitCPM4-CANN-8B-unquantized/tree/main/example)
 - **LLaMA Factory**: Supports custom model loading with `trust_remote_code=True`
 - **Other Frameworks**: Any framework that supports HuggingFace-compatible model loading with custom modeling code
 ```python
 from transformers import AutoModelForCausalLM, AutoTokenizer
+path = 'openbmb/BitCPM4-CANN-8B-unquantized'
 tokenizer = AutoTokenizer.from_pretrained(path, trust_remote_code=True)
 model = AutoModelForCausalLM.from_pretrained(
     path,
 ```
 ┌─────────────────────────────────┐
+│  BitCPM4-CANN-8B-unquantized  │   ← This model (QAT parameters + fake quantizer in modeling.py)
 └───────────────┬─────────────────┘
                 │
                 ▼  Fine-tune (DeepSpeed / LLaMA Factory / ...)