 Michael Yang
|
ad3a7d0e2c
add NumGQA
|
il y a 1 an |
 Jeffrey Morgan
|
688661ab9b
increase default batch size to 1024
|
il y a 1 an |
|
Michael Yang
|
cca61181cb
sample metrics
|
il y a 1 an |
|
Michael Yang
|
c490416189
lock on llm.lock(); decrease batch size
|
il y a 1 an |
|
Michael Yang
|
f62a882760
add session expiration
|
il y a 1 an |
|
Michael Yang
|
3003fc03fc
update predict code
|
il y a 1 an |
|
Michael Yang
|
32aec66e6a
add load duration
|
il y a 1 an |
|
Michael Yang
|
35af37a2cb
session id
|
il y a 1 an |
 Bruce MacDonald
|
4c1caa3733
download models when creating from modelfile
|
il y a 1 an |
 Patrick Devine
|
4cb42ca55e
add copy command (#191)
|
il y a 1 an |
|
Patrick Devine
|
9f6e97865c
allow pushing/pulling to insecure registries (#157)
|
il y a 1 an |
|
Bruce MacDonald
|
7ba1308595
Merge pull request #147 from jmorganca/brucemacd/cli-err-display
|
il y a 1 an |
|
Patrick Devine
|
e7a393de54
add rm command for models (#151)
|
il y a 1 an |
|
Bruce MacDonald
|
ebaa33ac28
display gin api errors in cli
|
il y a 1 an |
|
Michael Yang
|
68df36ae50
fix pull 0 bytes on completed layer
|
il y a 1 an |
|
Patrick Devine
|
5bea29f610
add new list command (#97)
|
il y a 1 an |
|
Patrick Devine
|
2fb52261ad
basic distribution w/ push/pull (#78)
|
il y a 1 an |
|
Michael Yang
|
965f9ad033
Merge pull request #77 from jmorganca/mem
|
il y a 1 an |
|
Michael Yang
|
5fefaa5d4d
fix typo
|
il y a 1 an |
|
Michael Yang
|
1775647f76
continue conversation
|
il y a 1 an |
|
Michael Yang
|
05e08d2310
return more info in generate response
|
il y a 1 an |
|
Michael Yang
|
fd4792ec56
call llama.cpp directly from go
|
il y a 1 an |
|
Jeffrey Morgan
|
a3ec1ec2a0
consistent error handling for pull and generate
|
il y a 1 an |
|
Michael Yang
|
edba935d67
return error in generate response
|
il y a 1 an |
|
Bruce MacDonald
|
2d49197b3b
increase default model size to 512
|
il y a 1 an |
|
Bruce MacDonald
|
f5e2e150b8
allow overriding default generate options
|
il y a 1 an |
|
Bruce MacDonald
|
61dd87bd90
if directory cannot be resolved, do not fail
|
il y a 1 an |
|
Michael Yang
|
303982b56e
fix run generate
|
il y a 1 an |
 Patrick Devine
|
3f1b7177f2
pass model and predict options
|
il y a 1 an |
|
Michael Yang
|
c4b9e84945
progress
|
il y a 1 an |
