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

Libraries

How to use openbmb/MiniCPM-SALA with Transformers:

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

pipe = pipeline("text-generation", model="openbmb/MiniCPM-SALA", 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/MiniCPM-SALA", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use openbmb/MiniCPM-SALA with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/openbmb/MiniCPM-SALA

SGLang

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

Docker Model Runner
How to use openbmb/MiniCPM-SALA with Docker Model Runner:
```
docker model run hf.co/openbmb/MiniCPM-SALA
```

Fix _init_rope compatibility with transformers >= 5.x rope_scaling standardization

#10

by DennisHuang648 - opened 1 day ago

base: refs/heads/main

←

from: refs/pr/10

Discussion Files changed

+29

-13

DennisHuang648

OpenBMB org 1 day ago

Problem

Starting from transformers 4.43+, AutoConfig automatically standardizes a missing or None rope_scaling to {"rope_type": "default", "factor": 1.0} during config initialization. MiniCPM-SALA's _init_rope() only handles None, "linear", "dynamic", and "longrope" — encountering "default" causes:

ValueError: Unknown RoPE scaling type default

This is triggered when loading MiniCPM-SALA via any library that depends on transformers >= 5.x (e.g. GPTQModel 7.0.0 pulls in transformers 5.8.0), even though the model does not use RoPE scaling (config.json has no rope_scaling field).

Changes

Modified both _init_rope() methods in modeling_minicpm_sala.py (MiniCPMInfLLMv2Attention at line 879 and MiniCPMSALAMLA at line 2144):

Treat rope_scaling of None or scaling_type in (None, "default") as no-scaling, falling through to the standard MiniCPMRotaryEmbedding.
Support both legacy "type" key and new "rope_type" key for cross-version compatibility.
Extract rope_scaling into a local variable to avoid repeated self.config.rope_scaling access.

Impact

No behavioral change: The model's config.json has no rope_scaling field; this fix only ensures the auto-filled "default" is correctly treated as no scaling.
Backward compatible: Works with both transformers 4.x (rope_scaling=None) and 5.x (rope_scaling={"rope_type": "default", ...}).
Verified: Tested with GPTQModel 7.0.0 + transformers 5.8.0 in the SOAR evaluation Docker image. Without this fix, GPTQModel.load() raises ValueError; with this fix, model loads successfully.

Fix _init_rope compatibility with transformers >= 5.x rope_scaling standardizationf28de5e4

suhmily changed pull request status to merged 1 day ago

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment