Michael Yang
846f593dbf
Merge pull request #828 from jmorganca/mxyng/template-parameters
...
image: show parameters
2023-10-19 09:31:31 -07:00
Michael Yang
e1c5be24e7
check json eof
2023-10-19 09:21:51 -07:00
Michael Yang
2ad8a074ac
generate: set created_at
...
move the empty response so it's more visible
2023-10-19 09:21:51 -07:00
Michael Yang
7e547c6833
s/message/error/
2023-10-19 09:21:04 -07:00
Michael Yang
689842b9ff
request: bad request when model missing fields
2023-10-19 09:21:04 -07:00
Michael Yang
a19d47642e
models: rm workDir from CreateModel
...
unused after removing EMBED
2023-10-19 09:21:04 -07:00
Bruce MacDonald
fe6f3b48f7
do not reload the running llm when runtime params change ( #840 )
...
- only reload the running llm if the model has changed, or the options for loading the running model have changed
- rename loaded llm to runner to differentiate from loaded model image
- remove logic which keeps the first system prompt in the generation context
2023-10-19 10:39:58 -04:00
Michael Yang
4dcceeffb7
let the template do the work
2023-10-18 13:12:00 -07:00
Michael Yang
019e4a4558
image: show parameters
2023-10-18 13:12:00 -07:00
Michael Yang
627d04d927
Merge pull request #827 from jmorganca/mxyng/template-adapters
...
model: native gotemplate adapter template
2023-10-18 13:11:25 -07:00
Michael Yang
940e8ebec3
Merge pull request #826 from jmorganca/mxyng/template-system
...
show: no template system if empty
2023-10-18 13:11:09 -07:00
Yiorgis Gozadinos
8c6c2cbc8c
When the .ollama folder is broken or there are no models return an empty list on /api/tags
2023-10-18 08:23:20 +02:00
Michael Yang
8299bf76ed
model: native gotemplate adapter template
2023-10-17 15:28:38 -07:00
Michael Yang
ee4979e510
show: no template system if empty
2023-10-17 15:25:43 -07:00
Michael Yang
1af493c5a0
server: print version on start
2023-10-16 09:59:14 -07:00
Bruce MacDonald
a0c3e989de
deprecate modelfile embed command ( #759 )
2023-10-16 11:07:37 -04:00
Michael Yang
7a537cdca9
Merge pull request #770 from jmorganca/mxyng/fix-download
...
fix download
2023-10-12 12:56:43 -07:00
Michael Yang
257ffeb997
fix download
2023-10-12 12:52:43 -07:00
Bruce MacDonald
7804b8fab9
validate api options fields from map ( #711 )
2023-10-12 11:18:11 -04:00
Michael Yang
c413a55093
download: handle inner errors
2023-10-11 14:15:30 -07:00
Michael Yang
630bb75d2a
dynamically size download parts based on file size
2023-10-11 14:10:25 -07:00
Michael Yang
a2055a1e93
update download
2023-10-11 14:10:25 -07:00
Bruce MacDonald
274d5a5fdf
optional parameter to not stream response ( #639 )
...
* update streaming request accept header
* add optional stream param to request bodies
2023-10-11 12:54:27 -04:00
Jeffrey Morgan
65dcd0ce35
always cleanup blob download ( #747 )
2023-10-10 13:12:29 -04:00
Michael Yang
f6e98334e4
handle upstream proxies
2023-10-09 11:42:36 -07:00
Bruce MacDonald
af4cf55884
not found error before pulling model ( #718 )
2023-10-06 16:06:20 -04:00
Bruce MacDonald
d6786f2945
add feedback for reading model metadata ( #722 )
2023-10-06 16:05:32 -04:00
Michael Yang
0560b28a8d
names
2023-10-06 12:56:56 -07:00
Michael Yang
10199c5987
replace done channel with file check
2023-10-06 12:56:56 -07:00
Michael Yang
288814d3e4
fix ref counts
2023-10-06 12:56:43 -07:00
Michael Yang
04733438da
check head request response
2023-10-06 12:56:43 -07:00
Michael Yang
711e891f0f
fix resumable downloads
...
glob returns files in lexical order which is not appropriate when
rebuilding the parts list
2023-10-06 12:56:43 -07:00
Michael Yang
090d08422b
handle unexpected eofs
2023-10-06 12:56:43 -07:00
Michael Yang
5b84404c64
handle concurrent requests for the same blobs
2023-10-06 12:56:43 -07:00
Michael Yang
8544edca21
parallel chunked downloads
2023-10-06 12:56:43 -07:00
Bruce MacDonald
2130c0708b
output type parsed from modelfile ( #678 )
2023-10-05 14:58:04 -04:00
Jay Nakrani
1d0ebe67e8
Document response stream chunk delimiter. ( #632 )
...
Document response stream chunk delimiter.
2023-09-29 21:45:52 -07:00
Bruce MacDonald
a1b2d95f96
remove unused push/pull params ( #650 )
2023-09-29 17:27:19 -04:00
Michael Yang
9333b0cc82
Merge pull request #612 from jmorganca/mxyng/prune-empty-directories
...
prune empty directories
2023-09-29 11:23:39 -07:00
Michael Yang
f40b3de758
use int64 consistently
2023-09-28 11:07:24 -07:00
Michael Yang
8608eb4760
prune empty directories
2023-09-27 10:58:09 -07:00
Jeffrey Morgan
9b12a511ca
check other request fields before load short circuit in /api/generate
2023-09-22 23:50:55 -04:00
Bruce MacDonald
5d71bda478
close llm on interrupt ( #577 )
2023-09-22 19:41:52 +01:00
Michael Yang
82f5b66c01
register HEAD /api/tags
2023-09-21 16:38:03 -07:00
Michael Yang
c986694367
fix HEAD / request
...
HEAD request should respond like their GET counterparts except without a
response body.
2023-09-21 16:35:58 -07:00
Bruce MacDonald
4cba75efc5
remove tmp directories created by previous servers ( #559 )
...
* remove tmp directories created by previous servers
* clean up on server stop
* Update routes.go
* Update server/routes.go
Co-authored-by: Jeffrey Morgan <jmorganca@gmail.com>
* create top-level temp ollama dir
* check file exists before creating
---------
Co-authored-by: Jeffrey Morgan <jmorganca@gmail.com>
Co-authored-by: Michael Yang <mxyng@pm.me>
2023-09-21 20:38:49 +01:00
Michael Yang
1fabba474b
refactor default allow origins
...
this should be less error prone
2023-09-21 09:42:25 -07:00
Michael Yang
ee4fd16f2c
Merge pull request #556 from jmorganca/pack-cuda
...
pack in cuda libs
2023-09-20 15:02:36 -07:00
Bruce MacDonald
1255bc9b45
only package 11.8 runner
2023-09-20 20:00:41 +01:00
Michael Yang
499e9007a5
pick chunksize based on location
2023-09-20 11:10:24 -07:00