 Sigbjørn Skjæret
|
03c0946d73
convert : support models with multiple chat templates (#6588)
|
1 год назад |
 slaren
|
08a0c02060
ggml : mul_mat_id use the same tensor for all the experts (#6387)
|
1 год назад |
 Ondřej Čertík
|
727107707a
gguf-py : bump version to 0.8.0 (#6060)
|
1 год назад |
|
slaren
|
799a1cb13b
llama : add Mixtral support (#4406)
|
2 лет назад |
|
slaren
|
e937066420
gguf-py : export chat templates (#4125)
|
2 лет назад |
 Kerfuffle
|
91f6499393
Respect tokenizer.ggml.add_bos_token value when tokenizing (#4040)
|
2 лет назад |
|
Kerfuffle
|
21fd874c8d
gguf-py: gguf_writer: Use bytearray to build metadata (#4051)
|
2 лет назад |
 M. Yusuf Sarıgöz
|
e86fc56f75
Fix gguf-convert-endian script (#4037)
|
2 лет назад |
|
Kerfuffle
|
34b0a08207
gguf-py: Refactor and allow reading/modifying existing GGUF files (#3981)
|
2 лет назад |
 Jared Van Bortel
|
0a7c980b6f
gguf : track writer state, free unneeded tensors, cleanup (#3871)
|
2 лет назад |
 Qin Yue Chen
|
8cf19d60dc
gguf : support big endian platform (#3552)
|
2 лет назад |
|
M. Yusuf Sarıgöz
|
4d03833211
gguf.py : fix CI for publishing GGUF package (#3532)
|
2 лет назад |
|
cebtenzzre
|
0fe321031a
gguf : general usability improvements (#3409)
|
2 лет назад |
|
Kerfuffle
|
e394084166
gguf-py : support identity operation in TensorNameMap (#3095)
|
2 лет назад |
|
Kerfuffle
|
6519e9c99c
gguf(python): Fix special vocab handling when id < 0 (#2984)
|
2 лет назад |
|
Cebtenzzre
|
92d0b751a7
convert : fix python 3.8 support, modernize type annotations (#2916)
|
2 лет назад |
|
Kerfuffle
|
dc07dc492e
convert : various script cleanups/fixes + merges and special token handling (#2842)
|
2 лет назад |
|
M. Yusuf Sarıgöz
|
8194cd8772
gguf : export objects to user code (#2780)
|
2 лет назад |
|
M. Yusuf Sarıgöz
|
87e3733f24
gguf : make gguf pip-installable
|
2 лет назад |
