Georgi Gerganov
|
1a8c8795d6
ci : check if there is enough VRAM (#3596)
|
2 лет назад |
Aarni Koskela
|
b016596d90
server : add completion mode (no chat) (#3582)
|
2 лет назад |
Georgi Gerganov
|
6b3ae4da92
prompts : add mnemonics.txt
|
2 лет назад |
Georgi Gerganov
|
57dd55e2c7
server : fix kv cache management (#3588)
|
2 лет назад |
Georgi Gerganov
|
b8fe4b5cc9
main : fix session loading bug (#3400)
|
2 лет назад |
Michael Coppola
|
a8bdd65525
server : add parameter -tb N, --threads-batch N (#3584)
|
2 лет назад |
Kerfuffle
|
70c29da118
common : fix mirostat state when using multiple sequences (#3543)
|
2 лет назад |
Georgi Gerganov
|
8c70a5ff25
batched : add bench tool (#3545)
|
2 лет назад |
Zane Shannon
|
24ba3d829e
examples : add batched.swift + improve CI for swift (#3562)
|
2 лет назад |
Galunid
|
9f6ede19f3
Add MPT model to supported models in README.md (#3574)
|
2 лет назад |
goerch
|
233fc1c69f
Minor improvements in GPT2 tokenizer (#3567)
|
2 лет назад |
Xingchen Song(宋星辰)
|
c5b49360d0
readme : add bloom (#3570)
|
2 лет назад |
Xingchen Song(宋星辰)
|
02d2875def
llm : add bloom models (#3553)
|
2 лет назад |
Jhen-Jie Hong
|
0aa6595ae0
swift : improvements and fixes (#3564)
|
2 лет назад |
Jan Ploski
|
f5f9121de1
llm : add MPT support (#3417)
|
2 лет назад |
vvhg1
|
11ea5c7d96
infill. : fix tokenization (#3508)
|
2 лет назад |
slaren
|
95bd60a0a6
ggml-alloc : fix assert in debug builds (#3555)
|
2 лет назад |
Georgi Gerganov
|
fcca0a7004
refact : fix convert script + zero out KV cache to avoid nans (#3523)
|
2 лет назад |
Georgi Gerganov
|
dcc09d2596
metal : do not use mul_mm kernels when ne00 < 64 (#3542)
|
2 лет назад |
Georgi Gerganov
|
db3abcc114
sync : ggml (ggml-backend) (#3548)
|
2 лет назад |
Matheus C. França
|
eee42c670e
ci : add Zig CI/CD and fix build (#2996)
|
2 лет назад |
Ryder Wishart
|
8e6716a102
api_like_OAI.py : compat with Microsoft Guidance (#2746)
|
2 лет назад |
arcrank
|
9c38d181d4
api_like_OAI.py : simplify function (#2796)
|
2 лет назад |
Johannes Rudolph
|
a1202a31ed
k-quants : fix comments about block sizing (#3499)
|
2 лет назад |
Georgi Gerganov
|
94e502dfb7
ci : enable on obj-c changes + fix metal build (#3540)
|
2 лет назад |
Luo Tian
|
7d8b24932f
zig : fix build by introducing train.cpp (#3539)
|
2 лет назад |
Georgi Gerganov
|
b0ec5218c3
metal : support MTLGPUFamily < Apple7, formatting, style (#3524)
|
2 лет назад |
Kerfuffle
|
63d3b06a43
llama : fix missing break in Persimmon arch case statements (#3535)
|
2 лет назад |
Kerfuffle
|
a16e89cec8
Fix trying to strip newline from empty prompt and cfg prompt file content (#3534)
|
2 лет назад |
M. Yusuf Sarıgöz
|
4d03833211
gguf.py : fix CI for publishing GGUF package (#3532)
|
2 лет назад |