 DannyDaemonic
|
2485d7a4d3
Process escape sequences given in prompts (#1173)
|
2 лет назад |
 slaren
|
bf4b22ffe4
fix missing parameters in `llama_init_from_gpt_params` (#1293)
|
2 лет назад |
 Ron Evans
|
67c77799e0
examples : add llama_init_from_gpt_params() common function (#1290)
|
2 лет назад |
 Robert Brisita
|
2bb992f034
llama : allow 0 as a seed number. (#1275)
|
2 лет назад |
 jon-chuang
|
a5d30b1f53
common : better default number of threads (#934)
|
2 лет назад |
 Ivan Stepanov
|
dd7eff57d8
llama : new sampling algorithms (#1126)
|
2 лет назад |
 Evan Jones
|
1481a9cf25
llama : add session file format and saved sessions in main (#1169)
|
2 лет назад |
 mgroeber9110
|
9b0a4d4214
examples/main README improvements and some light refactoring (#1131)
|
2 лет назад |
 slaren
|
315a95a4d3
Add LoRA support (#820)
|
2 лет назад |
 Pavol Rusnak
|
c85e03d12e
Revert "main : alternative instruct mode (Vicuna support, etc.) (#863)" (#982)
|
2 лет назад |
 Tomáš Pazdiora
|
f4d277ae17
main : alternative instruct mode (Vicuna support, etc.) (#863)
|
2 лет назад |
 CRD716
|
0e07e6a839
common : remove unnecessary includes (#947)
|
2 лет назад |
|
Pavol Rusnak
|
8b679987cd
Fix whitespace, add .editorconfig, add GitHub workflow (#883)
|
2 лет назад |
 comex
|
f963b63afa
Rewrite loading code to try to satisfy everyone:
|
2 лет назад |
|
Tomáš Pazdiora
|
aaf3b23deb
fix for windows utf-8 input (#840)
|
2 лет назад |
 Murilo Santana
|
5b70e7de4c
fix default params for examples/main (#697)
|
2 лет назад |
|
Slaren
|
0d054e292e
Show error message when -f fails
|
2 лет назад |
 Stephan Walter
|
436e561931
all : be more strict about converting float to double (#458)
|
2 лет назад |
 anzz1
|
7b8dbcb78b
main.cpp fixes, refactoring (#571)
|
2 лет назад |
 Georgi Gerganov
|
79b2b266db
If n_predict == -1, generate forever
|
2 лет назад |
|
Georgi Gerganov
|
e2d490dafd
Inifinite generation via context swapping (#71)
|
2 лет назад |
|
Georgi Gerganov
|
a316a425d0
Overhaul the examples structure
|
2 лет назад |
