张宗平
357e2e60bd
- src/tsmm/train/stage2.py: loads stage1 ckpt (optional), freeze_llm + enable_lora(r=16) on q/v_proj, masked LM loss on sft.jsonl, bs=4/grad_accum=8/ ctx=1024/BF16/gradient checkpointing, ckpt every 2000 steps (encoder+projector state + peft LoRA adapter via save_pretrained). - scripts/train_stage2.sh: wrapper with design defaults. - Smoke verified: --max_steps 4, LoRA injected, finite loss, peak 3.29 GB (≤11GB budget), ckpt+adapter saved.
tsmm
Time-series as a Modality — an experimental, single-GPU multimodal model that treats multivariate time series as an independent modality, jointly injected into a small LLM (Qwen2.5-0.5B) for time-series question answering and reasoning (ChatTS route).
Status
M1 (data pipeline) under construction. See
docs/superpowers/specs/2026-06-29-ts-as-modality-design.md for the design and
docs/superpowers/plans/2026-06-29-ts-as-modality-plan.md for the task plan.
Layout
src/tsmm/ package (data, model, train, eval)
configs/ training / data configs
scripts/ offline generation & training entrypoints
tests/ pytest suite
data/ generated datasets (gitignored)
checkpoints/ model checkpoints (gitignored)
Install (dev)
python3 -m venv .venv
. .venv/bin/activate
pip install -e . # full deps (incl. torch/transformers/peft/...)
# M1-only lightweight install:
pip install numpy tqdm pyyaml pytest && pip install -e . --no-deps