 Galunid
|
32a28217f4
Fix aya-23 conversion scripts (#7539)
|
пре 1 година |
 Bartowski
|
c429b33beb
llama : add Smaug 70B support (#7402)
|
пре 1 година |
 Aarni Koskela
|
9146d36fe7
Readme: add akx/ggify to tools (#1484)
|
пре 1 година |
 HanishKVC
|
b9adcbbf92
SimpleChat Completion Mode flexibility and cleanup, Settings gMe, Optional sliding window (#7480)
|
пре 1 година |
 Georgi Gerganov
|
9588f196b1
train : change default FA argument (#7528)
|
пре 1 година |
 Brian
|
3cbd23ed88
labeler: added Apple Metal detector (+Kompute) (#7529)
|
пре 1 година |
 Justine Tunney
|
00c6390793
main : don't print special tokens with --grammar (#6923)
|
пре 1 година |
 Masaya, Kato
|
faa0e6979a
ggml: aarch64: SVE kernels for q8_0_q8_0, q4_0_q8_0 vector dot (#7433)
|
пре 1 година |
 Elton Kola
|
9791f40258
android : module (#7502)
|
пре 1 година |
 Xuan Son Nguyen
|
902184dd3a
fix missing slash in `fs_get_cache_directory()` (#7503)
|
пре 1 година |
 Mikko Juola
|
57684331fc
Make tokenize CLI tool have nicer command line arguments. (#6188)
|
пре 1 година |
 compilade
|
b83bab15a5
gguf-py : fix and simplify quantized shape round-trip (#7483)
|
пре 1 година |
|
Georgi Gerganov
|
d041d2ceaa
flake.lock: Update (#7232)
|
пре 1 година |
|
Brian
|
27891f6db0
docker.yml: disable light-intel and server-intel test (#7515)
|
пре 1 година |
 fairydreaming
|
fbca2f27fc
Add support for ArcticForCausalLM (#7020)
|
пре 1 година |
 Neo Zhang
|
0df0aa8e43
add build shared lib in win release package (#7438)
|
пре 1 година |
|
Georgi Gerganov
|
74f33adf5f
readme : remove trailing space (#7469)
|
пре 1 година |
|
Georgi Gerganov
|
1debe72737
ggml : silence UB sanitizer error during iq2_xxs quantization (#0)
|
пре 1 година |
 Tristan Druyen
|
007489e895
Fix phi3 chat template confusion with zephyr (#7449)
|
пре 1 година |
 Raj Hammeer Singh Hada
|
8b94e799df
readme : add Bunny in supported models [no ci] (#7469)
|
пре 1 година |
 Daniel Bevenius
|
3015851c5a
llama : add getters for n_threads/n_threads_batch (#7464)
|
пре 1 година |
|
Georgi Gerganov
|
55ac3b7aea
ci : use Pythia models instead of OpenLlama (#7470)
|
пре 1 година |
 Victor Nogueira
|
dacfcebd60
readme : add GPT-NeoX + Pythia to the list of supported models (#7491)
|
пре 1 година |
|
fairydreaming
|
9b82476ee9
Add missing inference support for GPTNeoXForCausalLM (Pythia and GPT-NeoX base models) (#7461)
|
пре 1 година |
|
Georgi Gerganov
|
a61a94e543
llama : rename n_ctx -> cache.size, less confusing (#0)
|
пре 1 година |
|
Brian
|
152da28ae5
labeler.yml: add embedding label detector [no ci] (#7482)
|
пре 1 година |
|
Georgi Gerganov
|
d48c88cbd5
ggml : remove ggml_flash_attn and ggml_flash_ff (#7463)
|
пре 1 година |
|
Georgi Gerganov
|
e84b71c2c6
ggml : drop support for QK_K=64 (#7473)
|
пре 1 година |
 0cc4m
|
1b1e27cb49
Update vulkan rope implementation to support frequency factors (#7475)
|
пре 1 година |
|
Georgi Gerganov
|
fbf777d2b9
main : minor (#7462)
|
пре 1 година |
