| .. |
|
scripts
|
68ff663a04
repo : update links to new url (#11886)
|
11 months ago |
|
__init__.py
|
672a6f1018
convert-*.py: GGUF Naming Convention Refactor and Metadata Override Refactor (#7499)
|
1 year ago |
|
constants.py
|
0cec062a63
llama : add support for GLM-Edge and GLM-Edge-V series models (#10573)
|
11 months ago |
|
gguf.py
|
34b0a08207
gguf-py: Refactor and allow reading/modifying existing GGUF files (#3981)
|
2 years ago |
|
gguf_reader.py
|
4601a8bb67
gguf-py : numpy 2 newbyteorder fix (#9772)
|
1 year ago |
|
gguf_writer.py
|
08f10f69c3
llama : remove notion of CLS token (#11064)
|
1 year ago |
|
lazy.py
|
3a14e00366
gguf-py : simplify support for quant types (#8838)
|
1 year ago |
|
metadata.py
|
96fa2c5e2d
fix gguf-py: Conversion error when multiple licenses are configured (#9807)
|
1 year ago |
|
py.typed
|
dc07dc492e
convert : various script cleanups/fixes + merges and special token handling (#2842)
|
2 years ago |
|
quants.py
|
9bc6db28d0
ggml-quants : ternary packing for TriLMs and BitNet b1.58 (#8151)
|
1 year ago |
|
tensor_mapping.py
|
ee7136c6d1
llama: add support for QRWKV6 model architecture (#11001)
|
1 year ago |
|
utility.py
|
68ff663a04
repo : update links to new url (#11886)
|
11 months ago |
|
vocab.py
|
68ff663a04
repo : update links to new url (#11886)
|
11 months ago |