Instructions to use openbmb/MiniCPM3-4B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use openbmb/MiniCPM3-4B with Transformers:

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

pipe = pipeline("text-generation", model="openbmb/MiniCPM3-4B", 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/MiniCPM3-4B", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use openbmb/MiniCPM3-4B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "openbmb/MiniCPM3-4B"
# 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/MiniCPM3-4B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/openbmb/MiniCPM3-4B

SGLang

How to use openbmb/MiniCPM3-4B 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/MiniCPM3-4B" \
    --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/MiniCPM3-4B",
		"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/MiniCPM3-4B" \
        --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/MiniCPM3-4B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use openbmb/MiniCPM3-4B with Docker Model Runner:
```
docker model run hf.co/openbmb/MiniCPM3-4B
```

FrankC0st1e commited on Sep 5, 2024

Commit

43b498b

1 Parent(s): a4f2dcb

fix: empty system prompt

Browse files

Files changed (1) hide show

tokenization_minicpm.py +3 -2

tokenization_minicpm.py CHANGED Viewed

@@ -4,6 +4,7 @@ import keyword
 import traceback
 import uuid
 from collections import deque
 from logging import getLogger
 from typing import Any, Dict, List, Optional, Union
@@ -324,6 +325,8 @@ def input_format(messages: List[Dict], tools: List[Dict], add_to_system=True):
             the tools list you can use
             For example:
     """
     if tools is not None and len(tools) > 0:
         header = (
             "from enum import Enum\nfrom typing import List, Dict, Optional\nfrom pydantic import BaseModel, Field\n\n"
@@ -363,8 +366,6 @@ func2(params)
         tools_string = ""
     if add_to_system:
-        if len(messages) > 0 and messages[0]["role"] != "system":
-            messages.insert(0, {"role": "system", "content": ""})
         return [message_format(msg, system_suffix=tools_string, user_prefix="") for msg in messages]
     else:
         return [message_format(msg, system_suffix="", user_prefix=tools_string) for msg in messages]

 import traceback
 import uuid
 from collections import deque
+from copy import deepcopy
 from logging import getLogger
 from typing import Any, Dict, List, Optional, Union
             the tools list you can use
             For example:
     """
+    messages = deepcopy(messages)
+    tools = deepcopy(tools)
     if tools is not None and len(tools) > 0:
         header = (
             "from enum import Enum\nfrom typing import List, Dict, Optional\nfrom pydantic import BaseModel, Field\n\n"
         tools_string = ""
     if add_to_system:
         return [message_format(msg, system_suffix=tools_string, user_prefix="") for msg in messages]
     else:
         return [message_format(msg, system_suffix="", user_prefix=tools_string) for msg in messages]