Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

gguf_dump.py: fix markddown kv array print #8588

Merged
merged 6 commits into from
Jul 20, 2024
Merged

gguf_dump.py: fix markddown kv array print #8588

Changes from 4 commits
Commits
Show all changes
6 commits
Select commit Hold shift + click to select a range
d99a34b
gguf_dump.py: fix markddown kv array print
mofosyne Jul 19, 2024
130d396
Update gguf-py/scripts/gguf_dump.py
mofosyne Jul 20, 2024
923886f
gguf_dump.py: refactor kv array string handling
mofosyne Jul 20, 2024
1d37843
gguf_dump.py: escape backticks inside of strings
mofosyne Jul 20, 2024
50d55d6
gguf_dump.py: inline code markdown escape handler added
mofosyne Jul 20, 2024
1949847
gguf_dump.py: handle edge case about backticks on start or end of a s…
mofosyne Jul 20, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
30 changes: 25 additions & 5 deletions gguf-py/scripts/gguf_dump.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -249,21 +249,41 @@ def dump_markdown_metadata(reader: GGUFReader, args: argparse.Namespace) -> None
if len(field.types) == 1:
curr_type = field.types[0]
if curr_type == GGUFValueType.STRING:
value = repr(str(bytes(field.parts[-1]), encoding='utf-8')[:60])
truncate_length = 60
value_string = str(bytes(field.parts[-1]), encoding='utf-8')
if len(value_string) > truncate_length:
head = value_string[:truncate_length // 2].replace("`", "\\`").rstrip()
tail = value_string[-truncate_length // 2:].replace("`", "\\`").rstrip()
value = "`{head}`...`{tail}`".format(head=head, tail=tail)
else:
value = "`{strval}`".format(strval=value_string.replace("`", "\\`"))
elif curr_type in reader.gguf_scalar_to_np:
value = str(field.parts[-1][0])
else:
if field.types[0] == GGUFValueType.ARRAY:
curr_type = field.types[1]
array_elements = []

if curr_type == GGUFValueType.STRING:
render_element = min(5, total_elements)
for element_pos in range(render_element):
value += repr(str(bytes(field.parts[-1 - element_pos]), encoding='utf-8')[:5]) + (", " if total_elements > 1 else "")
truncate_length = 30
value_string = str(bytes(field.parts[-1 - (total_elements - element_pos - 1) * 2]), encoding='utf-8')
if len(value_string) > truncate_length:
head = value_string[:truncate_length // 2].replace("`", "\\`").rstrip()
tail = value_string[-truncate_length // 2:].replace("`", "\\`").rstrip()
value = "`{head}`...`{tail}`".format(head=head, tail=tail)
else:
value = "`{strval}`".format(strval=value_string.replace("`", "\\`"))
mofosyne marked this conversation as resolved.
Show resolved Hide resolved
array_elements.append(value)

elif curr_type in reader.gguf_scalar_to_np:
render_element = min(7, total_elements)
for element_pos in range(render_element):
value += str(field.parts[-1 - element_pos][0]) + (", " if total_elements > 1 else "")
value = f'[ {value}{" ..." if total_elements > 1 else ""} ]'
array_elements.append(str(field.parts[-1 - (total_elements - element_pos - 1)][0]))

value = f'[ {", ".join(array_elements).strip()}{", ..." if total_elements > len(array_elements) else ""} ]'

kv_dump_table.append({"n":n, "pretty_type":pretty_type, "total_elements":total_elements, "field_name":field.name, "value":value})

kv_dump_table_header_map = [
Expand Down Expand Up @@ -382,7 +402,7 @@ def dump_markdown_metadata(reader: GGUFReader, args: argparse.Namespace) -> None
markdown_content += f"- Percentage of total elements: {group_percentage:.2f}%\n"
markdown_content += "\n\n"

print(markdown_content) # noqa: NP100
print(markdown_content) # noqa: NP100


def main() -> None:
Expand Down
Loading