Update README.md for clearer documentation

#1
by umm-dev - opened

Expanded the README to better reflect the current implementation.

Clarified that AgGPT-13 nano uses INT8 quantization with dequantization on load.

Added a quick features list for easy scanning.

Included installation and usage examples for faster onboarding.

Added a short “How It Works” section summarizing the model loading process.

Cleaned up the license section for consistency.

AGofficial changed pull request status to merged

Sign up or log in to comment