xaedes
|
f954edda93
ggml : implement backward pass for llama + small training-llama-from-scratch example (#1360)
|
2 years ago |
Georgi Gerganov
|
f048af0230
ggml : sync alibi fix from ggml repo
|
2 years ago |
3ooabkhxtn
|
ac0cd259d5
Adding SSE instructions to ggml_vec_dot_q4_0_q8_0 (#1413)
|
2 years ago |
Georgi Gerganov
|
0cd22e190a
llama : fix various warnings
|
2 years ago |
Rinne
|
6456a4eb9f
embedding : remove unused code (#1426)
|
2 years ago |
Georgi Gerganov
|
cdd5350892
readme : update Q4_0 perplexities
|
2 years ago |
Georgi Gerganov
|
738ace394a
llama : free ggml context in set / copy state data (close #1425)
|
2 years ago |
Henri Vasserman
|
699b1ad7fe
opencl : fix kernels for the new formats (#1422)
|
2 years ago |
Georgi Gerganov
|
fb62f92433
llama : fix --mtest option (close #1414)
|
2 years ago |
Johannes Gäßler
|
773ee249fb
CLI args use - instead of _, backwards compatible (#1416)
|
2 years ago |
slaren
|
553fd4d4b5
Add clang-tidy reviews to CI (#1407)
|
2 years ago |
Rinne
|
089b1c93ba
readme : add C#/.NET bindings repo (#1409)
|
2 years ago |
Georgi Gerganov
|
b9fd7eee57
ggml : remove bit shuffling (#1405)
|
2 years ago |
CRD716
|
b608b55a3e
prompts : model agnostic DAN (#1304)
|
2 years ago |
Evan Jones
|
cf348a60e0
main : add option to save full output to session (#1338)
|
2 years ago |
DannyDaemonic
|
e6a46b0ed1
Locale fix for Windows (#1379)
|
2 years ago |
Sami Farin
|
9f8dbc4787
use pause asm insn in busyloop to run the CPU (13600K) 10 °C cooler (#1314)
|
2 years ago |
DannyDaemonic
|
41654efea8
Interface improvements and `--multiline-input` (previously `--author-mode`) (#1040)
|
2 years ago |
Georgi Gerganov
|
56551bc11f
readme : add notice about upcoming breaking change
|
2 years ago |
AlpinDale
|
fe60904eef
readme : add TOC and Pygmalion instructions (#1359)
|
2 years ago |
Pavol Rusnak
|
003ba2fb43
llama : fix hparams shadow (#1367)
|
2 years ago |
Georgi Gerganov
|
f9a6364912
llama : require first token to be BOS (#1303)
|
2 years ago |
ubik2
|
95078cc554
convert: add ability to convert safetensors files (#1276)
|
2 years ago |
Johannes Gäßler
|
1f48b0abcf
Documented CUDA reproducibility, added warning (#1346)
|
2 years ago |
Henri Vasserman
|
e1295513a4
CI: add Windows CLBlast and OpenBLAS builds (#1277)
|
2 years ago |
swittk
|
1b0fd45465
ggml : Allow usage of CLBlast alongside Accelerate.framework (#1336)
|
2 years ago |
Jed Fox
|
3924088512
Remove default arguments from sampling functions (#1343)
|
2 years ago |
DaniAndTheWeb
|
173d0e6419
makefile: automatic Arch Linux detection (#1332)
|
2 years ago |
Erik Scholz
|
a3b85b28da
ci : add cublas to windows release (#1271)
|
2 years ago |
Pavol Rusnak
|
921dcee00a
readme: add missing info (#1324)
|
2 years ago |