Sākums Izpētīt Palīdzība
Pierakstīties
cturan
/
llama.cpp
spogulis no https://github.com/cturan/llama.cpp
1
0
Atdalīts 0
Faili Problēmas 0 Vikivietne
Koks: b83cc3f5b3
Atzari Tagi
llama.cpp
/
gguf-py
/
gguf
Joan Fontanals b83cc3f5b3 llama : add Jina Embeddings architecture (#6826) 1 gadu atpakaļ
..
__init__.py 34b0a08207 gguf-py: Refactor and allow reading/modifying existing GGUF files (#3981) 2 gadi atpakaļ
constants.py b83cc3f5b3 llama : add Jina Embeddings architecture (#6826) 1 gadu atpakaļ
gguf.py 34b0a08207 gguf-py: Refactor and allow reading/modifying existing GGUF files (#3981) 2 gadi atpakaļ
gguf_reader.py f98eb31c51 convert-hf : save memory with lazy evaluation (#7075) 1 gadu atpakaļ
gguf_writer.py f98eb31c51 convert-hf : save memory with lazy evaluation (#7075) 1 gadu atpakaļ
py.typed dc07dc492e convert : various script cleanups/fixes + merges and special token handling (#2842) 2 gadi atpakaļ
tensor_mapping.py b83cc3f5b3 llama : add Jina Embeddings architecture (#6826) 1 gadu atpakaļ
vocab.py f98eb31c51 convert-hf : save memory with lazy evaluation (#7075) 1 gadu atpakaļ