glyph-adapters / README.md
robertkeus's picture
Upload folder using huggingface_hub
ed07a91 verified
|
Raw
History Blame Contribute Delete
578 Bytes
metadata
license: cc0-1.0
base_model: Qwen/Qwen2.5-Coder-3B-Instruct
library_name: peft
tags:
  - lora
  - emergent-language
  - agent-communication
  - code

Glyph — trained LoRA adapters

Three LoRA adapters on Qwen2.5-Coder-3B for a seeded logographic agent-language:

  • speaker: English task → glyph symbols
  • builder: glyph symbols → Python code
  • translator: glyph symbols → English

Results (seed=0): compositional decode 12/22, cold-model self-explanation 13/22, byte reduction 98.8% vs English agent-to-agent. Code + demo: https://github.com/robertkeus/glyph-ai