Instructions to use AXERA-TECH/MiniCPM5-1B-AX637 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use AXERA-TECH/MiniCPM5-1B-AX637 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="AXERA-TECH/MiniCPM5-1B-AX637")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("AXERA-TECH/MiniCPM5-1B-AX637", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use AXERA-TECH/MiniCPM5-1B-AX637 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "AXERA-TECH/MiniCPM5-1B-AX637" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "AXERA-TECH/MiniCPM5-1B-AX637", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/AXERA-TECH/MiniCPM5-1B-AX637
- SGLang
How to use AXERA-TECH/MiniCPM5-1B-AX637 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 "AXERA-TECH/MiniCPM5-1B-AX637" \ --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": "AXERA-TECH/MiniCPM5-1B-AX637", "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 "AXERA-TECH/MiniCPM5-1B-AX637" \ --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": "AXERA-TECH/MiniCPM5-1B-AX637", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use AXERA-TECH/MiniCPM5-1B-AX637 with Docker Model Runner:
docker model run hf.co/AXERA-TECH/MiniCPM5-1B-AX637
| { | |
| "binary": "bin/axllm", | |
| "target": "AX637 aarch64", | |
| "ax_llm_branch": "ax-minicpm-v-4-6", | |
| "ax_llm_commit": "68bc8e3", | |
| "sha256": "a2192f8ea1dac22b08ffe40e7de724b63396d6958f7dd01c433453c572e4753c", | |
| "model": "AXERA-TECH/MiniCPM5-1B-AX637-C128-P896-CTX1024", | |
| "profile": { | |
| "chip": "AX637", | |
| "prefill_len": 128, | |
| "prefill_max_token_num": 896, | |
| "kv_cache_len": 1024, | |
| "last_kv_cache_len": [128, 256, 384, 512, 640, 768] | |
| }, | |
| "verified": { | |
| "date": "2026-07-23", | |
| "board": "AX637", | |
| "status": "passed", | |
| "result": "All 24 decoder layers and post model loaded; a 846-token request exercised all six prefill ladder groups and returned the expected answer." | |
| } | |
| } | |