 Bach Le
|
c9c74b4e3f
llama : add classifier-free guidance (#2135)
|
il y a 2 ans |
 WangHaoranRobin
|
d7d2e6a0f0
server: add option to output probabilities for completion (#1962)
|
il y a 2 ans |
 Howard Su
|
b8c8dda75f
Use unsigned for random seed (#2006)
|
il y a 2 ans |
 zrm
|
b853d45601
ggml : add NUMA support (#1556)
|
il y a 2 ans |
 Didzis Gosko
|
527b6fba1d
llama : make model stateless and context stateful (llama_state) (#1797)
|
il y a 2 ans |
 Johannes Gäßler
|
254a7a7a5f
CUDA full GPU acceleration, KV cache in VRAM (#1827)
|
il y a 2 ans |
 Kerfuffle
|
fa84c4b3e8
Fix issue where interactive mode crashes when input exceeds ctx size (#1789)
|
il y a 2 ans |
 Willy Tarreau
|
35a84916fb
main: add the possibility to open the prompt cache read-only (#1640)
|
il y a 2 ans |
|
Johannes Gäßler
|
17366df842
Multi GPU support, CUDA refactor, CUDA scratch buffer (#1703)
|
il y a 2 ans |
 Georgi Gerganov
|
ecb217db4f
llama : Metal inference (#1642)
|
il y a 2 ans |
 Vladimir Zorin
|
337aea1139
examples : add --alias option to gpt_params to set use friendly model name (#1614)
|
il y a 2 ans |
|
Georgi Gerganov
|
4b7e245adf
minor : fix compile warnings
|
il y a 2 ans |
 Stephan Walter
|
dc271c52ed
Remove unused n_parts parameter (#1509)
|
il y a 2 ans |
 András Salamon
|
9560655409
define default model path once, sync path with readme (#1366)
|
il y a 2 ans |
|
Johannes Gäßler
|
905d87b70a
ggml : GPU-accelerated token generation (#1412)
|
il y a 2 ans |
 Evan Jones
|
cf348a60e0
main : add option to save full output to session (#1338)
|
il y a 2 ans |
 DannyDaemonic
|
41654efea8
Interface improvements and `--multiline-input` (previously `--author-mode`) (#1040)
|
il y a 2 ans |
 44670
|
2edbdb0f99
main : add --in-suffix option (#1318)
|
il y a 2 ans |
 Ron Evans
|
67c77799e0
examples : add llama_init_from_gpt_params() common function (#1290)
|
il y a 2 ans |
 jon-chuang
|
a5d30b1f53
common : better default number of threads (#934)
|
il y a 2 ans |
|
Georgi Gerganov
|
334637e43e
common : change default parameters to pre-#1126 (#1223)
|
il y a 2 ans |
 Ivan Stepanov
|
dd7eff57d8
llama : new sampling algorithms (#1126)
|
il y a 2 ans |
|
Evan Jones
|
1481a9cf25
llama : add session file format and saved sessions in main (#1169)
|
il y a 2 ans |
 mgroeber9110
|
9b0a4d4214
examples/main README improvements and some light refactoring (#1131)
|
il y a 2 ans |
 eiery
|
10f19c1121
llama : have n_batch default to 512 (#1091)
|
il y a 2 ans |
 slaren
|
315a95a4d3
Add LoRA support (#820)
|
il y a 2 ans |
 Pavol Rusnak
|
c85e03d12e
Revert "main : alternative instruct mode (Vicuna support, etc.) (#863)" (#982)
|
il y a 2 ans |
 Tomáš Pazdiora
|
f4d277ae17
main : alternative instruct mode (Vicuna support, etc.) (#863)
|
il y a 2 ans |
 comex
|
f963b63afa
Rewrite loading code to try to satisfy everyone:
|
il y a 2 ans |
|
Tomáš Pazdiora
|
aaf3b23deb
fix for windows utf-8 input (#840)
|
il y a 2 ans |
