Georgi Gerganov
|
254098a279
common : refactor common_sampler + grammar logic changes (#17937)
|
1 kuukausi sitten |
compilade
|
19f68fa5a4
imatrix : warn when GGUF imatrix is saved without .gguf suffix (#15076)
|
5 kuukautta sitten |
compilade
|
d31192b4ee
imatrix : use GGUF by default (#14842)
|
5 kuukautta sitten |
compilade
|
0a2f5496be
imatrix : fix 3d activation handling for hybrid and recurrent models (#14994)
|
5 kuukautta sitten |
Ed Addario
|
d1aa0cc5d1
imatrix: add option to display importance score statistics for a given imatrix file (#12718)
|
5 kuukautta sitten |
compilade
|
90083283ec
imatrix : use GGUF to store importance matrices (#9400)
|
6 kuukautta sitten |
Georgi Gerganov
|
745aa5319b
llama : deprecate llama_kv_self_ API (#14030)
|
7 kuukautta sitten |
Bartowski
|
efb8b47eda
imatrix : Add --parse-special for enabling parsing of special tokens in imatrix calculation (#13389)
|
8 kuukautta sitten |
Georgi Gerganov
|
51fb96b1ff
context : remove logits_all flag (#13284)
|
8 kuukautta sitten |
Johannes Gäßler
|
3e959f0976
imatrix: fix oob writes if src1 is not contiguous (#13286)
|
8 kuukautta sitten |
Diego Devesa
|
1d36b3670b
llama : move end-user examples to tools directory (#13249)
|
8 kuukautta sitten |