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

Libraries

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

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

pipe = pipeline("text-generation", model="openbmb/MiniCPM4-8B", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("openbmb/MiniCPM4-8B", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

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

Install from pip and serve model

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

Use Docker

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

SGLang

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

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

BigDong commited on Jun 6, 2025

Commit

addde69

1 Parent(s): aea7d23

update README.md

Browse files

Files changed (1) hide show

README.md +5 -5

README.md CHANGED Viewed

@@ -148,13 +148,13 @@ To enable InfLLM v2, you need to add the `sparse_config` field in `config.json`:
 ```
 These parameters control the behavior of InfLLM v2:
-* `kernel_size` (default: 32): size of semantic kernels.
-* `kernel_stride` (default: 16): stride between adjacent kernels.
 * `init_blocks` (default: 1): The number of initial blocks that every query token attends to. This ensures attention to the beginning of the sequence.
-* `block_size` (default: 64): block size for key-value blocks.
 * `window_size` (default: 2048): The size of the local sliding window.
-* `topk` (default: 64): Specifies that each token computes attention with only the top-k most relevant key-value blocks.
-* `use_nope` (default: false): whether to use the NOPE technique in block selection for improved performance.
 * `dense_len` (default: 8192): Since Sparse Attention offers limited benefits for short sequences, the model can use standard (dense) attention for shorter texts. The model will use dense attention for sequences with a token length below `dense_len` and switch to sparse attention for sequences exceeding this length. Set this to `-1` to always use sparse attention regardless of sequence length.
 MiniCPM4 natively supports context lengths of up to 32,768 tokens. For conversations where the total length (including both input and output) significantly exceeds this limit, we recommend using RoPE scaling techniques for effective handling of long texts. We have validated the model's performance on context lengths of up to 131,072 tokens by modifying the LongRoPE factor.

 ```
 These parameters control the behavior of InfLLM v2:
+* `kernel_size` (default: 32): The size of semantic kernels.
+* `kernel_stride` (default: 16): The stride between adjacent kernels.
 * `init_blocks` (default: 1): The number of initial blocks that every query token attends to. This ensures attention to the beginning of the sequence.
+* `block_size` (default: 64): The block size for key-value blocks.
 * `window_size` (default: 2048): The size of the local sliding window.
+* `topk` (default: 64): The specifies that each token computes attention with only the top-k most relevant key-value blocks.
+* `use_nope` (default: false): Whether to use the NOPE technique in block selection for improved performance.
 * `dense_len` (default: 8192): Since Sparse Attention offers limited benefits for short sequences, the model can use standard (dense) attention for shorter texts. The model will use dense attention for sequences with a token length below `dense_len` and switch to sparse attention for sequences exceeding this length. Set this to `-1` to always use sparse attention regardless of sequence length.
 MiniCPM4 natively supports context lengths of up to 32,768 tokens. For conversations where the total length (including both input and output) significantly exceeds this limit, we recommend using RoPE scaling techniques for effective handling of long texts. We have validated the model's performance on context lengths of up to 131,072 tokens by modifying the LongRoPE factor.