 MistApproach
|
a27152b602
fix: add missing short command line argument -mli for multiline-input (#8261)
|
vor 1 Jahr |
 Xuan Son Nguyen
|
9ef0780062
Fix new line issue with chat template, disable template when in-prefix/suffix is set (#8203)
|
vor 1 Jahr |
 Sigbjørn Skjæret
|
38373cfbab
Add SPM infill support (#8016)
|
vor 1 Jahr |
|
Xuan Son Nguyen
|
16791b8f0b
Add chatml fallback for cpp `llama_chat_apply_template` (#8160)
|
vor 1 Jahr |
 jukofyork
|
97877eb10b
Control vector loading fixes (#8137)
|
vor 1 Jahr |
|
Xuan Son Nguyen
|
49c03c79cd
cvector: better prompt handling, add "mean vector" method (#8069)
|
vor 1 Jahr |
|
Xuan Son Nguyen
|
48e6b92cc3
Add chat template support for llama-cli (#8068)
|
vor 1 Jahr |
 HatsuneMikuUwU33
|
f702a90e24
Update control vector help (#8104)
|
vor 1 Jahr |
 Yann Follet
|
646ef4a9cf
embedding : more cli arguments (#7458)
|
vor 1 Jahr |
|
Xuan Son Nguyen
|
3e58b0ee35
cvector: fix CI + correct help message (#8064)
|
vor 1 Jahr |
 Douglas Hanley
|
80ea089d77
llama : allow pooled embeddings on any model (#7477)
|
vor 1 Jahr |
 Johannes Gäßler
|
abd894ad96
common: fix warning (#8036)
|
vor 1 Jahr |
|
Xuan Son Nguyen
|
0c7b3595b9
Add `cvector-generator` example (#7514)
|
vor 1 Jahr |
 Olivier Chafik
|
d4d915d351
url: save -mu downloads to new cache location (#7826)
|
vor 1 Jahr |
 sasha0552
|
7a16ce7db2
server : smart slot selection using Longest Common Prefix (#7728)
|
vor 1 Jahr |
 Georgi Gerganov
|
ee459f40f6
server : fix --threads-http arg (#7801)
|
vor 1 Jahr |
|
Georgi Gerganov
|
f83351f9a6
imatrix : migrate to gpt_params (#7771)
|
vor 1 Jahr |
|
Georgi Gerganov
|
1442677f92
common : refactor cli arg parsing (#7675)
|
vor 1 Jahr |
|
Georgi Gerganov
|
554c247caf
ggml : remove OpenCL (#7735)
|
vor 1 Jahr |
 0cc4m
|
3d7ebf6312
Vulkan Mixture of Experts (MoE) support (#7628)
|
vor 1 Jahr |
 Brian
|
d298382ad9
main: replace --no-special with --special (#7534)
|
vor 1 Jahr |
 Justine Tunney
|
00c6390793
main : don't print special tokens with --grammar (#6923)
|
vor 1 Jahr |
 Masaya, Kato
|
faa0e6979a
ggml: aarch64: SVE kernels for q8_0_q8_0, q4_0_q8_0 vector dot (#7433)
|
vor 1 Jahr |
|
Xuan Son Nguyen
|
902184dd3a
fix missing slash in `fs_get_cache_directory()` (#7503)
|
vor 1 Jahr |
|
Georgi Gerganov
|
6ff13987ad
common : normalize naming style (#7462)
|
vor 1 Jahr |
 Amir
|
11474e756d
examples: cache hf model when --model not provided (#7353)
|
vor 1 Jahr |
 Herman Semenov
|
359cbe3f46
ggml-quants, llama : removed excess checks (#7274)
|
vor 1 Jahr |
 Radoslav Gerganov
|
5e31828d3e
ggml : add RPC backend (#6829)
|
vor 1 Jahr |
|
Justine Tunney
|
4e3880978f
Fix memory bug in grammar parser (#7194)
|
vor 1 Jahr |
 HanishKVC
|
f89fe2732c
Main+: optionally allow special tokens from user in interactive mode (#7097)
|
vor 1 Jahr |
