 Georgi Gerganov
|
ecb217db4f
llama : Metal inference (#1642)
|
2 years ago |
|
Georgi Gerganov
|
0cd22e190a
llama : fix various warnings
|
2 years ago |
|
Georgi Gerganov
|
b9fd7eee57
ggml : remove bit shuffling (#1405)
|
2 years ago |
|
Georgi Gerganov
|
f9a6364912
llama : require first token to be BOS (#1303)
|
2 years ago |
 Jed Fox
|
3924088512
Remove default arguments from sampling functions (#1343)
|
2 years ago |
 DannyDaemonic
|
f4cef87edf
Add git-based build information for better issue tracking (#1232)
|
2 years ago |
 Stephan Walter
|
f0d70f147d
Various fixes to mat_mul benchmark (#1253)
|
2 years ago |
 CRD716
|
5fba3c016b
examples : add Jeopardy example (#1168)
|
2 years ago |
|
Georgi Gerganov
|
574406dc7e
ggml : add Q5_0 and Q5_1 quantization (#1187)
|
2 years ago |
|
Georgi Gerganov
|
884e7d7a2b
ggml : use 8-bit precision for Q4_1 intermediate results (#1047)
|
2 years ago |
|
Georgi Gerganov
|
4caebf6d40
gitignore : vdot
|
2 years ago |
|
Georgi Gerganov
|
c85980acd0
gitignore : benchmark
|
2 years ago |
 unbounded
|
62cfc54f77
Add quantize-stats command for testing quantization (#728)
|
2 years ago |
 iacore
|
ed1c214e66
zig : add build.zig (#773)
|
2 years ago |
 Justine Tunney
|
78ca9838ee
Make loading weights 10-100x faster
|
2 years ago |
|
Jed Fox
|
20e1e84884
deploy : add a Package.swift for SwiftPM support (#393)
|
2 years ago |
|
Georgi Gerganov
|
e0670260fb
gitignore : add "embedding"
|
2 years ago |
|
Georgi Gerganov
|
a316a425d0
Overhaul the examples structure
|
2 years ago |
 Niklas Korz
|
a292747893
Nix flake (#40)
|
2 years ago |
|
Georgi Gerganov
|
f60fa9e50a
.gitignore models/
|
2 years ago |
|
Georgi Gerganov
|
26c0846629
Initial release
|
2 years ago |
