 shibe2
|
40e5ce054f
CLBlast: Fix temporary buffer size for f16 conversion (wsize)
|
2 years ago |
 slaren
|
a5e8c1d8c7
train-text-from-scratch : fix assert failure in ggml-alloc (#3618)
|
2 years ago |
 Georgi Gerganov
|
e74c705e15
editorconfig : remove trailing spaces
|
2 years ago |
 coezbek
|
3ad1e3f1a1
server : documentation of JSON return value of /completion endpoint (#3632)
|
2 years ago |
|
Georgi Gerganov
|
1142013da4
save-load-state : fix example + add ci test (#3655)
|
2 years ago |
 ldwang
|
5fe268a4d9
readme : add Aquila2 links (#3610)
|
2 years ago |
 staviq
|
1a159553f9
tokenizer : special token handling (#3538)
|
2 years ago |
|
Georgi Gerganov
|
281ef73c25
k-quants : fix quantization ranges (#3646)
|
2 years ago |
|
Georgi Gerganov
|
940efa95fe
llava : fix tokenization to not add bos between image embeddings and user prompt (#3645)
|
2 years ago |
 cebtenzzre
|
11bff29045
MPT : support GQA for replit-code-v1.5 (#3627)
|
2 years ago |
 M. Yusuf Sarıgöz
|
11dc1091f6
Honor -ngl option for Cuda offloading in llava (#3621)
|
2 years ago |
 Daniel Bevenius
|
2a4bcbacea
llama : remove n_threads from llama_decode_internal (#3614)
|
2 years ago |
|
slaren
|
424b6381c4
ggml : add context enumeration functions (#3605)
|
2 years ago |
|
shibe2
|
1e0e873c37
CLBlast: Fix matrix-vector multiplication (#3544)
|
2 years ago |
|
M. Yusuf Sarıgöz
|
370359e5ba
examples: support LLaVA v1.5 (multimodal model) (#3436)
|
2 years ago |
 uint256_t
|
9e24cc6e2e
docs : fix typo GOMP_CPU_AFFINITY (#3597)
|
2 years ago |
|
Georgi Gerganov
|
d28e572c02
cmake : fix add_compile_options on macOS
|
2 years ago |
 Ian Scrivener
|
f3040beaab
typo : it is `--n-gpu-layers` not `--gpu-layers` (#3592)
|
2 years ago |
|
Georgi Gerganov
|
1a8c8795d6
ci : check if there is enough VRAM (#3596)
|
2 years ago |
 Aarni Koskela
|
b016596d90
server : add completion mode (no chat) (#3582)
|
2 years ago |
|
Georgi Gerganov
|
6b3ae4da92
prompts : add mnemonics.txt
|
2 years ago |
|
Georgi Gerganov
|
57dd55e2c7
server : fix kv cache management (#3588)
|
2 years ago |
|
Georgi Gerganov
|
b8fe4b5cc9
main : fix session loading bug (#3400)
|
2 years ago |
 Michael Coppola
|
a8bdd65525
server : add parameter -tb N, --threads-batch N (#3584)
|
2 years ago |
 Kerfuffle
|
70c29da118
common : fix mirostat state when using multiple sequences (#3543)
|
2 years ago |
|
Georgi Gerganov
|
8c70a5ff25
batched : add bench tool (#3545)
|
2 years ago |
 Zane Shannon
|
24ba3d829e
examples : add batched.swift + improve CI for swift (#3562)
|
2 years ago |
 Galunid
|
9f6ede19f3
Add MPT model to supported models in README.md (#3574)
|
2 years ago |
 goerch
|
233fc1c69f
Minor improvements in GPT2 tokenizer (#3567)
|
2 years ago |
 Xingchen Song(宋星辰)
|
c5b49360d0
readme : add bloom (#3570)
|
2 years ago |
