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 2 days ago

Commit

27f0f34

verified ·

1 Parent(s): cadc794

Update modeling_minicpm.py: hardcode bias=False in MLP LinearQuantizer

Browse files

Files changed (1) hide show

modeling_minicpm.py +3 -3

modeling_minicpm.py CHANGED Viewed

@@ -863,9 +863,9 @@ class MiniCPMMLP(nn.Module):
         self.config = config
         self.hidden_size = config.hidden_size
         self.intermediate_size = config.intermediate_size
-        self.gate_proj = LinearQuantizer(self.hidden_size, self.intermediate_size, bias=config.mlp_bias, quant_type="ternary", bit=4, group_size=-1)
-        self.up_proj = LinearQuantizer(self.hidden_size, self.intermediate_size, bias=config.mlp_bias, quant_type="ternary", bit=4, group_size=-1)
-        self.down_proj = LinearQuantizer(self.intermediate_size, self.hidden_size, bias=config.mlp_bias, quant_type="ternary", bit=4, group_size=-1)
         # self.gate_proj = nn.Linear(self.hidden_size, self.intermediate_size, bias=False)
         # self.up_proj = nn.Linear(self.hidden_size, self.intermediate_size, bias=False)
         # self.down_proj = nn.Linear(self.intermediate_size, self.hidden_size, bias=False)

         self.config = config
         self.hidden_size = config.hidden_size
         self.intermediate_size = config.intermediate_size
+        self.gate_proj = LinearQuantizer(self.hidden_size, self.intermediate_size, bias=False, quant_type="ternary", bit=4, group_size=-1)
+        self.up_proj = LinearQuantizer(self.hidden_size, self.intermediate_size, bias=False, quant_type="ternary", bit=4, group_size=-1)
+        self.down_proj = LinearQuantizer(self.intermediate_size, self.hidden_size, bias=False, quant_type="ternary", bit=4, group_size=-1)
         # self.gate_proj = nn.Linear(self.hidden_size, self.intermediate_size, bias=False)
         # self.up_proj = nn.Linear(self.hidden_size, self.intermediate_size, bias=False)
         # self.down_proj = nn.Linear(self.intermediate_size, self.hidden_size, bias=False)