Instructions to use openbmb/MiniCPM4.1-8B-AutoAWQ with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use openbmb/MiniCPM4.1-8B-AutoAWQ with Transformers:

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

pipe = pipeline("text-generation", model="openbmb/MiniCPM4.1-8B-AutoAWQ", 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/MiniCPM4.1-8B-AutoAWQ", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use openbmb/MiniCPM4.1-8B-AutoAWQ with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "openbmb/MiniCPM4.1-8B-AutoAWQ"
# 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/MiniCPM4.1-8B-AutoAWQ",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/openbmb/MiniCPM4.1-8B-AutoAWQ

SGLang

How to use openbmb/MiniCPM4.1-8B-AutoAWQ 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/MiniCPM4.1-8B-AutoAWQ" \
    --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/MiniCPM4.1-8B-AutoAWQ",
		"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/MiniCPM4.1-8B-AutoAWQ" \
        --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/MiniCPM4.1-8B-AutoAWQ",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use openbmb/MiniCPM4.1-8B-AutoAWQ with Docker Model Runner:
```
docker model run hf.co/openbmb/MiniCPM4.1-8B-AutoAWQ
```

guanwenyu1995 commited on Sep 5, 2025

Commit

7cb5938

verified ·

1 Parent(s): 84b2452

Update README.md

Browse files

Files changed (1) hide show

README.md +8 -8

README.md CHANGED Viewed

@@ -37,10 +37,10 @@ tokenizer = AutoTokenizer.from_pretrained(
 )
 device = next(model.model.parameters()).device
-# if enable_think
-# formatted_prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt = True, enable_thinking = True)
-# if disable_think
-formatted_prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt = True, enable_thinking = False)
 input_ids = tokenizer.encode(formatted_prompt, return_tensors='pt').to(device)
 outputs = model.generate(
@@ -48,10 +48,10 @@ outputs = model.generate(
     max_new_tokens=1000,
     do_sample=True
 )
-# if enable think
-# ans = [i.split("<|im_start|> assistant\n", 1)[1].strip() for i in tokenizer.batch_decode(outputs)]
-# if disable think
-ans = [i.split("<|im_start|> assistant\n<think>\n\n</think>", 1)[1].strip() for i in tokenizer.batch_decode(outputs)]
 ```
 <p align="center">

 )
 device = next(model.model.parameters()).device
+# if open think mode, use the following code
+formatted_prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt = True, enable_thinking = True)
+# if close think mode, use the following code
+# formatted_prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt = True, enable_thinking = False)
 input_ids = tokenizer.encode(formatted_prompt, return_tensors='pt').to(device)
 outputs = model.generate(
     max_new_tokens=1000,
     do_sample=True
 )
+# if open think mode, use the following code
+ans = [i.split("<|im_start|> assistant\n", 1)[1].strip() for i in tokenizer.batch_decode(outputs)]
+# if close think mode, use the following code
+# ans = [i.split("<|im_start|> assistant\n<think>\n\n</think>", 1)[1].strip() for i in tokenizer.batch_decode(outputs)]
 ```
 <p align="center">