mirror alephllm 0.9.0 (same-session law): presets.py (AlephLMConfig.fusion field, default None; the v3 preset builder + registrations guarded for copies without the data stack), governor.py (raw_block), alephlm.py (the optional fusion stage imported lazily — unfused crafts load without model/fusion.py; the trunk loop factored into _trunk). Gated: strict load of model.safetensors through the vendored path, logits parity 0.0 vs geolip.
Browse files- presets.py +6 -0
presets.py
CHANGED
|
@@ -60,6 +60,12 @@ class AlephLMConfig:
|
|
| 60 |
# x 32 layers) the retained scan tensors alone exceed a 95GB card —
|
| 61 |
# measured OOM, Blackwell preflight 2026-08-26. ~2x hub recompute cost.
|
| 62 |
hub_ckpt: int = 0
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 63 |
|
| 64 |
def to_dict(self):
|
| 65 |
d = asdict(self)
|
|
|
|
| 60 |
# x 32 layers) the retained scan tensors alone exceed a 95GB card —
|
| 61 |
# measured OOM, Blackwell preflight 2026-08-26. ~2x hub recompute cost.
|
| 62 |
hub_ckpt: int = 0
|
| 63 |
+
# v3 (2026-09-19): weak-token fusion at the input plane. None = the
|
| 64 |
+
# byte-resolution trunk verbatim. A dict selects the hourglass form:
|
| 65 |
+
# {"rule": "entropy" | "spacelike", "theta": bits, "witness_floor": n,
|
| 66 |
+
# "table": "<npz path>", "k_lo": front blocks, "k_hi": back blocks} —
|
| 67 |
+
# see model/fusion.py. Old manifests load via the default.
|
| 68 |
+
fusion: Optional[dict] = None
|
| 69 |
|
| 70 |
def to_dict(self):
|
| 71 |
d = asdict(self)
|