]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
gguf-dump.py: add --markdown dump output (#7853)
authorBrian <redacted>
Mon, 17 Jun 2024 05:25:20 +0000 (15:25 +1000)
committerGitHub <redacted>
Mon, 17 Jun 2024 05:25:20 +0000 (15:25 +1000)
commit006167aaf6b6aaa4daa52961035f7460af19f469
treec4edb5ef09f99e8f13db2040faa333350b4f8b68
parentdf68d4fa5dc929217d3e64d673e099d7a417b206
gguf-dump.py: add --markdown dump output (#7853)

* gguf-dump.py: add --markdown dump output

* gguf-dump.py: Add toc

* gguf-dump.py: use standard tensor name lookup. Also add tensor ID field

* gguf-dump.py: Add tensor overview count

* gguf-dump.py: fix array preview

* gguf-dump.py: markdownTableWithAlignmentSupport() added

* Add type hints and spacing

Co-authored-by: compilade <redacted>
* gguf-dump.py: prettyfy dimention

* gguf-dump: right align element count

* gguf-dump.py: element count autosizing

* Apply suggestions from code review

Co-authored-by: compilade <redacted>
---------

Co-authored-by: compilade <redacted>
gguf-py/scripts/gguf-dump.py