research: add reduced AttnRes runner

2026-07-30 06:38:26 +08:00
parent e3617532de
commit f99872039f
3 changed files with 950 additions and 0 deletions
@@ -0,0 +1,43 @@
+# Reduced Attention Residuals reproduction
+
+This directory implements protocol
+`llm-atlas-k3-attnres-reduced-v1`, frozen in
+`research/K3_ATTNRES_REDUCED_PROTOCOL.md`.
+
+The experiment is a reduced independent mechanism probe. It is not a Kimi K3
+checkpoint forward pass and not a reproduction of the paper-scale training run.
+
+## Environment
+
+The pinned execution environment used by this project is:
+
+```text
+Python /home/wuyang/.pyenv/versions/3.10.14/envs/navi-router-cu128/bin/python
+PyTorch 2.11.0+cu128
+GPU NVIDIA GeForce RTX 5090
+CUBLAS_WORKSPACE_CONFIG=:4096:8
+```
+
+## Build the frozen dataset
+
+```bash
+python experiments/k3/attnres/build_dataset.py \
+  --cache-dir /home/wuyang/.cache/llm-atlas/k3-attnres-reduced-v1 \
+  --manifest experiments/k3/attnres/manifest.json
+```
+
+## Run one cell
+
+```bash
+CUBLAS_WORKSPACE_CONFIG=:4096:8 \
+python experiments/k3/attnres/train.py \
+  --architecture baseline \
+  --seed 2026073001 \
+  --cache-dir /home/wuyang/.cache/llm-atlas/k3-attnres-reduced-v1 \
+  --manifest experiments/k3/attnres/manifest.json \
+  --output /home/wuyang/.cache/llm-atlas/k3-attnres-reduced-v1/runs/baseline-2026073001.json
+```
+
+Raw parquet and checkpoints stay in the local cache. Frozen manifests, metric
+JSON, analyses, code, checksums, and a compact website payload enter the public
+repository.