 Aarni Koskela
|
3e08ae99ce
convert.py: add mapping for safetensors bf16 (#1598)
|
há 2 anos atrás |
 Judd
|
36680f6e40
convert : update for baichuan (#2081)
|
há 2 anos atrás |
|
Judd
|
471aab6e4c
convert : add support of baichuan-7b (#2055)
|
há 2 anos atrás |
 AN Long
|
c943d823c1
convert : fix invalid params in write_vocab_only (#1975)
|
há 2 anos atrás |
 Erik Scholz
|
7487137227
rework convert.py to read hyper-parameters from config.json (#1958)
|
há 2 anos atrás |
 Jiří Podivín
|
5ddf7ea1fb
hooks : setting up flake8 and pre-commit hooks (#1681)
|
há 2 anos atrás |
 Tom Jobbins
|
2b2646931b
convert.py: Support models which are stored in a single pytorch_model.bin (#1469)
|
há 2 anos atrás |
 ubik2
|
95078cc554
convert: add ability to convert safetensors files (#1276)
|
há 2 anos atrás |
 Benjamin Lecaillon
|
a90e96b266
Convert.py @staticmethod (#1327)
|
há 2 anos atrás |
 Ivan Stepanov
|
d3e8093e9b
convert: support DT_BF16 tensors (#1309)
|
há 2 anos atrás |
 Cameron
|
4ad73137a1
add 4_0 to default outfile namestr dict (#1031)
|
há 2 anos atrás |
 Georgi Gerganov
|
3173a62eb9
stdout : vertical align outputs for better readibility
|
há 2 anos atrás |
 comex
|
74f5899df4
convert.py: Fix loading safetensors and ggml format on Windows (#991)
|
há 2 anos atrás |
 Pavol Rusnak
|
43ffdefb74
py : fix flake8 and isort nitpicks (#960)
|
há 2 anos atrás |
|
comex
|
723dac55fa
py : new conversion script (#545)
|
há 2 anos atrás |
