| .. |
|
__init__.py
|
672a6f1018
convert-*.py: GGUF Naming Convention Refactor and Metadata Override Refactor (#7499)
|
hai 1 ano |
|
constants.py
|
3d6bf6919f
llama : add IBM Granite MoE architecture (#9438)
|
hai 1 ano |
|
gguf.py
|
34b0a08207
gguf-py: Refactor and allow reading/modifying existing GGUF files (#3981)
|
%!s(int64=2) %!d(string=hai) anos |
|
gguf_reader.py
|
3fd62a6b1c
py : type-check all Python scripts with Pyright (#8341)
|
hai 1 ano |
|
gguf_writer.py
|
0d2ec43833
llama : support IBM Granite architecture (#9412)
|
hai 1 ano |
|
lazy.py
|
3a14e00366
gguf-py : simplify support for quant types (#8838)
|
hai 1 ano |
|
metadata.py
|
1e6f6554aa
server : add lora hotswap endpoint (WIP) (#8857)
|
hai 1 ano |
|
py.typed
|
dc07dc492e
convert : various script cleanups/fixes + merges and special token handling (#2842)
|
%!s(int64=2) %!d(string=hai) anos |
|
quants.py
|
9bc6db28d0
ggml-quants : ternary packing for TriLMs and BitNet b1.58 (#8151)
|
hai 1 ano |
|
tensor_mapping.py
|
3d6bf6919f
llama : add IBM Granite MoE architecture (#9438)
|
hai 1 ano |
|
utility.py
|
328884f421
gguf-py : fix some metadata name extraction edge cases (#8591)
|
hai 1 ano |
|
vocab.py
|
9c4c9cc83f
Move convert.py to examples/convert-legacy-llama.py (#7430)
|
hai 1 ano |
Gabe Goodhart
3d6bf6919f
llama : add IBM Granite MoE architecture (#9438)