GitHub - cyysky/WebcamGenAI: Interactive multimodal Vision + LLM with Paligemma, Phi-3-Vision, and Llama3-V

Branches Tags

Name		Name	Last commit message	Last commit date
Latest commit History 5 Commits
static		static
cert.pem		cert.pem
demo.sh		demo.sh
demo_llama_3_v.py		demo_llama_3_v.py
demo_llama_3_v_chinese.py		demo_llama_3_v_chinese.py
demo_phi_3.py		demo_phi_3.py
demo_qwen2.5_vl_7B.py		demo_qwen2.5_vl_7B.py
example_fastapi.py		example_fastapi.py
example_fastapi_ssl.py		example_fastapi_ssl.py
key.pem		key.pem
readme.txt		readme.txt
rustdesk_o3LpFaUjAB.png		rustdesk_o3LpFaUjAB.png
test_qwen2.5_vl.py		test_qwen2.5_vl.py

Repository files navigation

pip install pytorch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu121

uvicorn demo_phi_3:app --host 0.0.0.0 --port 16986 --ssl-keyfile=key.pem --ssl-certfile=cert.pem

hostname -I
netsh interface portproxy add v4tov4 listenport=16986 listenaddress=0.0.0.0 connectport=16986 connectaddress=172.22.214.45
sudo ufw allow 16986

window firewall enable the port 16986