| .. |
|
__init__.py
|
34b0a08207
gguf-py: Refactor and allow reading/modifying existing GGUF files (#3981)
|
há 2 anos atrás |
|
constants.py
|
f4ab2a4147
llama : fix BPE pre-tokenization (#6920)
|
há 1 ano atrás |
|
gguf.py
|
34b0a08207
gguf-py: Refactor and allow reading/modifying existing GGUF files (#3981)
|
há 2 anos atrás |
|
gguf_reader.py
|
f4ab2a4147
llama : fix BPE pre-tokenization (#6920)
|
há 1 ano atrás |
|
gguf_writer.py
|
f4ab2a4147
llama : fix BPE pre-tokenization (#6920)
|
há 1 ano atrás |
|
py.typed
|
dc07dc492e
convert : various script cleanups/fixes + merges and special token handling (#2842)
|
há 2 anos atrás |
|
tensor_mapping.py
|
c8297c6af5
llama : add phi3 support (#6852)
|
há 1 ano atrás |
|
vocab.py
|
03c0946d73
convert : support models with multiple chat templates (#6588)
|
há 1 ano atrás |
Georgi Gerganov
f4ab2a4147
llama : fix BPE pre-tokenization (#6920)