| .. |
|
__init__.py
|
ee52225067
convert-hf : support direct Q8_0 conversion (#7234)
|
hai 1 ano |
|
constants.py
|
fabf30b4c4
llama : remove Persimmon (#7408)
|
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
|
f98eb31c51
convert-hf : save memory with lazy evaluation (#7075)
|
hai 1 ano |
|
gguf_writer.py
|
ee52225067
convert-hf : support direct Q8_0 conversion (#7234)
|
hai 1 ano |
|
lazy.py
|
ee52225067
convert-hf : support direct Q8_0 conversion (#7234)
|
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
|
ee52225067
convert-hf : support direct Q8_0 conversion (#7234)
|
hai 1 ano |
|
tensor_mapping.py
|
b83cc3f5b3
llama : add Jina Embeddings architecture (#6826)
|
hai 1 ano |
|
vocab.py
|
f98eb31c51
convert-hf : save memory with lazy evaluation (#7075)
|
hai 1 ano |
Georgi Gerganov
fabf30b4c4
llama : remove Persimmon (#7408)