Instructions to use DareModels/MiniCpm5-Agent with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use DareModels/MiniCpm5-Agent with Transformers:

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

pipe = pipeline("text-generation", model="DareModels/MiniCpm5-Agent")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("DareModels/MiniCpm5-Agent")
model = AutoModelForCausalLM.from_pretrained("DareModels/MiniCpm5-Agent", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use DareModels/MiniCpm5-Agent with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "DareModels/MiniCpm5-Agent"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "DareModels/MiniCpm5-Agent",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/DareModels/MiniCpm5-Agent

SGLang

How to use DareModels/MiniCpm5-Agent 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 "DareModels/MiniCpm5-Agent" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "DareModels/MiniCpm5-Agent",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "DareModels/MiniCpm5-Agent" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "DareModels/MiniCpm5-Agent",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use DareModels/MiniCpm5-Agent with Docker Model Runner:
```
docker model run hf.co/DareModels/MiniCpm5-Agent
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

MiniCPMv2

This is a merge of pre-trained language models created using mergekit.

Merge Details

Merge Method

This model was merged using the Model Breadcrumbs with TIES merge method using saidutta69/MiniCPM5-1B-Claude-Opus-Fable5-V2-Thinking-heretic as a base.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

merge_method: breadcrumbs_ties
base_model: saidutta69/MiniCPM5-1B-Claude-Opus-Fable5-V2-Thinking-heretic
models:
- model: saidutta69/MiniCPM5-1B-Claude-Opus-Fable5-V2-Thinking-heretic
- model: ktruestory/minicpm5-1b-hermes-toolhv1
  parameters:
    weight: 1
    density: 0.01
- model: MC7ever/MiniCPM5-1B-Agent-safetensors
  parameters:
    weight: 0.45
    density: 0.01
- model: hudsongouge/minicpm5-1B-GLM-5.2-Agentic-v9
  parameters:
    weight: 0.35
    density: 0.01
- model: Healshsj/MiniCPM5-1B-Reasoning-Agent-Ultra
  parameters:
    weight: 0.2
    density: 0.01
dtype: bfloat16