Bruce MacDonald
|
fe6f3b48f7
do not reload the running llm when runtime params change (#840)
|
1 year ago |
Bruce MacDonald
|
6fe178134d
improve api error handling (#781)
|
1 year ago |
Bruce MacDonald
|
7804b8fab9
validate api options fields from map (#711)
|
1 year ago |
Bruce MacDonald
|
274d5a5fdf
optional parameter to not stream response (#639)
|
1 year ago |
Bruce MacDonald
|
2130c0708b
output type parsed from modelfile (#678)
|
1 year ago |
Bruce MacDonald
|
1fbf3585d6
Relay default values to llama runner (#672)
|
1 year ago |
Bruce MacDonald
|
a1b2d95f96
remove unused push/pull params (#650)
|
1 year ago |
Michael Yang
|
f40b3de758
use int64 consistently
|
1 year ago |
Bruce MacDonald
|
f221637053
first pass at linux gpu support (#454)
|
1 year ago |
Patrick Devine
|
790d24eb7b
add show command (#474)
|
1 year ago |
Michael Yang
|
0f541a0367
s/ListResponseModel/ModelResponse/
|
1 year ago |
Bruce MacDonald
|
42998d797d
subprocess llama.cpp server (#401)
|
1 year ago |
Patrick Devine
|
8bbff2df98
add model IDs (#439)
|
1 year ago |
Michael Yang
|
f723bf0879
ignore nil map values
|
1 year ago |
Michael Yang
|
f27bc261cf
s/parmeter/parameter/
|
1 year ago |
Michael Yang
|
81d8d7b73f
fix could not convert int
|
1 year ago |
Patrick Devine
|
be989d89d1
Token auth (#314)
|
1 year ago |
Bruce MacDonald
|
4b3507f036
embeddings endpoint
|
1 year ago |
Bruce MacDonald
|
7a5f3616fd
embed text document in modelfile
|
1 year ago |
Bruce MacDonald
|
21ddcaa1f1
pr comments
|
1 year ago |
Michael Yang
|
f2074ed4c0
Merge pull request #306 from jmorganca/default-keep-system
|
1 year ago |
Jeffrey Morgan
|
8713ac23a8
allow overriding `template` and `system` in `/api/generate`
|
1 year ago |
Michael Yang
|
4dc5b117dd
automatically set num_keep if num_keep < 0
|
1 year ago |
Michael Yang
|
b9f4d67554
configurable rope frequency parameters
|
1 year ago |
Bruce MacDonald
|
1c5a8770ee
read runner parameter options from map
|
1 year ago |
Jeffrey Morgan
|
528bafa585
cache loaded model
|
1 year ago |
Bruce MacDonald
|
184ad8f057
allow specifying stop conditions in modelfile
|
1 year ago |
Jeffrey Morgan
|
822a0e36eb
lower batch size to 512
|
1 year ago |
Michael Yang
|
fadf75f99d
add stop conditions
|
1 year ago |
Michael Yang
|
ad3a7d0e2c
add NumGQA
|
1 year ago |