 Gabriel Larson
|
83bc2f288c
model : add text-only support for Kimi-VL (and find special tokens in text_config) (#15051)
|
há 5 meses atrás |
 Xuan-Son Nguyen
|
00fa15fedc
mtmd : add support for Voxtral (#14862)
|
há 6 meses atrás |
 Sigbjørn Skjæret
|
e75ba4c043
gguf-py : add support for chat template jinja files (#14508)
|
há 6 meses atrás |
|
Sigbjørn Skjæret
|
238005c2dc
gguf-py : fix SpecialVocab parsing when post_processor is null (#14330)
|
há 7 meses atrás |
|
Sigbjørn Skjæret
|
aa0ef5c578
gguf-py : fix Qwen3-Embedding eos token (#14314)
|
há 7 meses atrás |
|
Sigbjørn Skjæret
|
58cba76a9a
gguf-py : fix TemplateProcessing pair when bos/eos is missing (#14312)
|
há 7 meses atrás |
|
Sigbjørn Skjæret
|
88fc854b4b
llama : improve sep token handling (#14272)
|
há 7 meses atrás |
 Alex Trotta
|
381174bbda
gguf-py : make sentencepiece optional (#14200)
|
há 7 meses atrás |
|
Sigbjørn Skjæret
|
a686171ea7
convert : Support chat_template.json (#12460)
|
há 10 meses atrás |
 Georgi Gerganov
|
68ff663a04
repo : update links to new url (#11886)
|
há 11 meses atrás |
 compilade
|
e3c355ba65
convert : handle tokenizer merges format from transformers 4.45 (#9696)
|
há 1 ano atrás |
 Galunid
|
9c4c9cc83f
Move convert.py to examples/convert-legacy-llama.py (#7430)
|
há 1 ano atrás |
|
compilade
|
f98eb31c51
convert-hf : save memory with lazy evaluation (#7075)
|
há 1 ano atrás |
 Brian
|
a2ac89d6ef
convert.py : add python logging instead of print() (#6511)
|
há 1 ano atrás |
|
Sigbjørn Skjæret
|
03c0946d73
convert : support models with multiple chat templates (#6588)
|
há 1 ano atrás |
 Michaël de Vries
|
73122473ff
fix(gguf-py): special tokens are no longer skipped when add_<token>_token is set to false (#5487)
|
há 1 ano atrás |
 howlger
|
880e352277
py : open merges file as 'utf-8' (#4566)
|
há 2 anos atrás |
 Jared Van Bortel
|
f7f468a97d
gguf-py : fail fast on nonsensical special token IDs (#4489)
|
há 2 anos atrás |
 slaren
|
e937066420
gguf-py : export chat templates (#4125)
|
há 2 anos atrás |
 Kerfuffle
|
91f6499393
Respect tokenizer.ggml.add_bos_token value when tokenizing (#4040)
|
há 2 anos atrás |
|
Kerfuffle
|
34b0a08207
gguf-py: Refactor and allow reading/modifying existing GGUF files (#3981)
|
há 2 anos atrás |
