 Brian
|
a2ac89d6ef
convert.py : add python logging instead of print() (#6511)
|
преди 1 година |
 Georgi Gerganov
|
f4ab2a4147
llama : fix BPE pre-tokenization (#6920)
|
преди 1 година |
 Xuan Son Nguyen
|
7bb36ccf91
gguf : enforce that tensor names are unique (#6905)
|
преди 1 година |
 Sigbjørn Skjæret
|
03c0946d73
convert : support models with multiple chat templates (#6588)
|
преди 1 година |
 Daniel Bevenius
|
4fbd8098e6
gguf : add special tokens metadata for FIM/Infill (#6689)
|
преди 1 година |
|
Brian
|
a8bd14d557
gguf.py : add licence and version to gguf writer (#6504)
|
преди 1 година |
 Andrew Canis
|
12247f4c69
llama : add Command-R support (#6033)
|
преди 1 година |
 Ondřej Čertík
|
7ce2c77f88
gguf : add support for I64 and F64 arrays (#6062)
|
преди 1 година |
 Michael Podvitskiy
|
69ff61397d
llama : support models without vocabulary (#5798)
|
преди 1 година |
|
Georgi Gerganov
|
77178eedc8
gguf-py : fix dtype check (#6045)
|
преди 1 година |
|
Ondřej Čertík
|
3ca23481dd
gguf-py : add support for I8, I16 and I32 (#6045)
|
преди 1 година |
 compilade
|
c2101a2e90
llama : support Mamba Selective State Space Models (#5328)
|
преди 1 година |
 Jared Van Bortel
|
c7a0ad8ec9
convert-hf : make model class definitions self-contained (#5825)
|
преди 1 година |
 Douglas Hanley
|
4524290e87
Use correct type of pooling for embedding models (#5500)
|
преди 1 година |
 Michaël de Vries
|
73122473ff
fix(gguf-py): special tokens are no longer skipped when add_<token>_token is set to false (#5487)
|
преди 1 година |
|
Douglas Hanley
|
03bf161eb6
llama : support batched embeddings (#5466)
|
преди 1 година |
|
Douglas Hanley
|
2891c8aa9a
Add support for BERT embedding models (#5423)
|
преди 1 година |
 Guoteng
|
ce32060198
llama : support InternLM2 (#5184)
|
преди 1 година |
 postmasters
|
83e633c27e
llama : differentiate the KV dims in the attention (#4657)
|
преди 2 години |
 slaren
|
799a1cb13b
llama : add Mixtral support (#4406)
|
преди 2 години |
 Galunid
|
f23c0359a3
ci : add flake8 to github actions (python linting) (#4129)
|
преди 2 години |
|
slaren
|
e937066420
gguf-py : export chat templates (#4125)
|
преди 2 години |
 Kerfuffle
|
21fd874c8d
gguf-py: gguf_writer: Use bytearray to build metadata (#4051)
|
преди 2 години |
|
Kerfuffle
|
34b0a08207
gguf-py: Refactor and allow reading/modifying existing GGUF files (#3981)
|
преди 2 години |
