Skip to content

Commit a58d9bd

Browse files
committed
Organize headings
1 parent 1ca1c1f commit a58d9bd

File tree

1 file changed

+4
-4
lines changed

1 file changed

+4
-4
lines changed

docs/source/01-decode.ipynb

Lines changed: 4 additions & 4 deletions
Original file line numberDiff line numberDiff line change
@@ -6,7 +6,7 @@
66
"source": [
77
"<!-- # Copyright (c) 2024 Graphcore Ltd. All rights reserved. -->\n",
88
"\n",
9-
"## GFloat Basics\n",
9+
"# GFloat Basics\n",
1010
"\n",
1111
"This notebook shows the use of `decode_float` to explore properties of some float formats.\n"
1212
]
@@ -29,7 +29,7 @@
2929
"cell_type": "markdown",
3030
"metadata": {},
3131
"source": [
32-
"### List all the values in a format\n",
32+
"## List all the values in a format\n",
3333
"\n",
3434
"The first example shows how to list all values in a given format.\n",
3535
"We will choose the [OCP](https://www.opencompute.org/documents/ocp-8-bit-floating-point-specification-ofp8-revision-1-0-2023-12-01-pdf-1) E5M2 format.\n",
@@ -273,7 +273,7 @@
273273
"cell_type": "markdown",
274274
"metadata": {},
275275
"source": [
276-
"### Additional format info: special values, min, max, dynamic range\n",
276+
"## Additional format info: special values, min, max, dynamic range\n",
277277
"\n",
278278
"In addition, `FormatInfo` can tell us about other characteristics of each format.\n",
279279
"To reproduce some of the OCP spec's tables 1 and 2:"
@@ -325,7 +325,7 @@
325325
"cell_type": "markdown",
326326
"metadata": {},
327327
"source": [
328-
"### How do subnormals affect dynamic range?\n",
328+
"## How do subnormals affect dynamic range?\n",
329329
"\n",
330330
"Most, if not all, low-precision formats include subnormal numbers, as they increase the number of values near zero, and increase dynamic range.\n",
331331
"A natural question is \"by how much?\". To answer this, we can create a mythical new format, a copy of `e4m3`, but with `has_subnormals` set to true."

0 commit comments

Comments
 (0)