 Stephan Walter
|
3e6e70d8e8
Add enum llama_ftype, sync ggml_type to model files (#709)
|
il y a 2 ans |
 comex
|
f963b63afa
Rewrite loading code to try to satisfy everyone:
|
il y a 2 ans |
 unbounded
|
62cfc54f77
Add quantize-stats command for testing quantization (#728)
|
il y a 2 ans |
 Christian Falch
|
e986f94829
Added api for getting/setting the kv_cache (#685)
|
il y a 2 ans |
 Justine Tunney
|
78ca9838ee
Make loading weights 10-100x faster
|
il y a 2 ans |
 anzz1
|
a5c42c4b13
Fix typo in llama.h (#593)
|
il y a 2 ans |
|
anzz1
|
7f4c5c6651
llama : fix linkage with mingw (#551)
|
il y a 2 ans |
|
Stephan Walter
|
436e561931
all : be more strict about converting float to double (#458)
|
il y a 2 ans |
|
Stephan Walter
|
c1f885067c
ggml : introduce structs for the q4 data blocks (#356)
|
il y a 2 ans |
 Georgi Gerganov
|
03f7e33560
Cleanup STL headers + fix embedding examples + minor stuff
|
il y a 2 ans |
 Jed Fox
|
58e6c9f36f
Add support for file load progress reporting callbacks (#434)
|
il y a 2 ans |
 Doomsdayrs
|
36d07532ef
Add missing struct annotation (#483)
|
il y a 2 ans |
|
comex
|
563cdc391d
Support calling mlock() on loaded model data on Linux and macOS (#453)
|
il y a 2 ans |
 Luciano
|
8d4a855c24
Add embedding mode with arg flag. Currently working (#282)
|
il y a 2 ans |
|
Georgi Gerganov
|
f5a77a629b
Introduce C-style API (#370)
|
il y a 2 ans |
