# LLM backbone config (T2.3 / T2.4)
# Design ref: docs/superpowers/specs/2026-06-29-ts-as-modality-design.md §2.2
# Qwen2.5-0.5B-Instruct: hidden=896, 24 layers, vocab=151936, BF16 ~1GB

# Local offline path (downloaded via proxy; HF hub unreachable on this host)
model_path: /home/zhangzp/models/Qwen2.5-0.5B-Instruct
hf_model_id: Qwen/Qwen2.5-0.5B-Instruct   # for reference; offline use model_path

hidden_size: 896
torch_dtype: bfloat16