level-ai/LevelField

What this model is for:

This project is an intelligent manufacturing process generation system based on multi-modal large language models. It aims to automatically generate process sequences and machining steps by analyzing manufacturing drawings.

How to use me:

Make sure you have vllm>=0.19.1 installed. Check if your server has computation force at least with 1 H100. The model runs good on Nvidia 12.9 in our lab.

Then run the script:

CUDA_VISIBLE_DEVICES=0 \
OMP_NUM_THREADS=1 \
vllm serve \
    /the/local/path/to/the/model/ \
    --port 18124 \
    --served-model-name LevelField \
    --reasoning-parser qwen3 \
    --chat-template-content-format openai \
    --trust-remote-code \
    --max-model-len 32768 \
    --gpu-memory-utilization 0.9 \
    --mm-processor-cache-type shm