mlboydaisuke commited on
Commit
64c64a5
·
verified ·
1 Parent(s): 825e5d7

README: tidy two lines

Browse files
Files changed (1) hide show
  1. README.md +2 -2
README.md CHANGED
@@ -154,7 +154,7 @@ The easy tier and the first 48 standard rows ran on the charger.
154
  matched tokens 50/50, answer slots 50/50 and option argmax 50/50 on both bundles, including the
155
  40- and 255-option rows. int8lin max |Δp| was **0.0226** (`r05-dry`), mean **0.0009**, and max
156
  |Δabstain| **0.0222**; fp16 was **0.0051** (`r05-task`), **0.0003**, and **0.0165** respectively.
157
- These are kit measurements supplied by the supervisor, separate from the Python-runtime
158
  table above. Median int8lin wall time per fixture question was **354 ms** over the 50 rows, two to
159
  three questions per state (a question on a new state pays for the whole state); the 255-option row (1,449 tokens, S=1 prefill) took **7.2 s**. A
160
  three-question Thai ticket took **351 / 316 / 429 ms** for its 57-, 63- and 83-token rows; the
@@ -175,7 +175,7 @@ argmax **50/50**, the 40- and 255-option rows included (the 1,449-token row fits
175
  raw and **0.7249** mean family balanced accuracy — the Mac's figures exactly — at **2,074 ms** median per decision.
176
  Cooled to thermal state "nominal" (2026-09-24, `decide-cli bench --repeat 3`, a 111-token state and eight questions):
177
  **1,527 ms per decision** with the state shared, 1,713 from scratch, 13.5 s for the state and its eight (0 tokens
178
- reused). Load 6.6 s. Records: the SemIf rows in the standup record, and
179
  [`gate-openthai-systemone-iphone-parity.json`](https://github.com/john-rocky/coreai-model-zoo/blob/main/models/openthai-systemone/gate-openthai-systemone-iphone-parity.json).
180
 
181
  ## Bundle
 
154
  matched tokens 50/50, answer slots 50/50 and option argmax 50/50 on both bundles, including the
155
  40- and 255-option rows. int8lin max |Δp| was **0.0226** (`r05-dry`), mean **0.0009**, and max
156
  |Δabstain| **0.0222**; fp16 was **0.0051** (`r05-task`), **0.0003**, and **0.0165** respectively.
157
+ These are kit measurements, separate from the Python-runtime
158
  table above. Median int8lin wall time per fixture question was **354 ms** over the 50 rows, two to
159
  three questions per state (a question on a new state pays for the whole state); the 255-option row (1,449 tokens, S=1 prefill) took **7.2 s**. A
160
  three-question Thai ticket took **351 / 316 / 429 ms** for its 57-, 63- and 83-token rows; the
 
175
  raw and **0.7249** mean family balanced accuracy — the Mac's figures exactly — at **2,074 ms** median per decision.
176
  Cooled to thermal state "nominal" (2026-09-24, `decide-cli bench --repeat 3`, a 111-token state and eight questions):
177
  **1,527 ms per decision** with the state shared, 1,713 from scratch, 13.5 s for the state and its eight (0 tokens
178
+ reused). Load 6.6 s. Record:
179
  [`gate-openthai-systemone-iphone-parity.json`](https://github.com/john-rocky/coreai-model-zoo/blob/main/models/openthai-systemone/gate-openthai-systemone-iphone-parity.json).
180
 
181
  ## Bundle