张宗平
545802d62c
- src/tsmm/model/ts_encoder.py: Patchify (channel-independent unfold) + TSEncoder (shared per-channel patch linear, mean-pool over channels, learnable positional embedding, 2-layer pre-norm Transformer, LayerNorm). - configs/ts_encoder.yaml: encoder/projector hyperparameters. - tests/test_ts_encoder.py: 10 tests (shape, n_patches formula, window values, determinism, gradient flow, param sanity). - 61 tests passing; GPU fwd/bwd verified on RTX 3060 (39 MB peak). Spec clarifications (small tier, comet-build Step 4): - n_patches = (T-P)//S+1 ⇒ 127 for T=512 (design said 128; arithmetic slip). - 'Channel-independent' = shared per-channel patch embed + mean-pool → C-free output [B,n_patches,d]; channel identity carried by [属性] tokens. - Actual params ≈2.1M (design's '≈4M' was a rough estimate).
21 lines
635 B
YAML
21 lines
635 B
YAML
# TS Encoder + Projector hyperparameters (T2.1 / T2.2)
|
|
# Design ref: docs/superpowers/specs/2026-06-29-ts-as-modality-design.md §2.2
|
|
|
|
# Patchify (channel-independent)
|
|
patch_len: 8 # P
|
|
stride: 4 # S (overlap); n_patches = (T - P) // S + 1
|
|
|
|
# TS Encoder (2-layer Transformer)
|
|
d: 256 # hidden dim
|
|
layers: 2
|
|
heads: 4
|
|
ffn_mult: 4 # dim_feedforward = d * ffn_mult
|
|
dropout: 0.1
|
|
|
|
# Projector (T2.2) — maps TS token d → LLM hidden
|
|
llm_hidden: 896 # Qwen2.5-0.5B hidden size
|
|
|
|
# Context
|
|
T: 512 # default window length → 127 TS tokens
|
|
max_patches: 2048 # positional-embedding budget
|