 jmorganca
|
cd776e49ad
llama: wip vision support for `runner`
|
9 months ago |
 Daniel Hiltgen
|
3cc7ec4429
fix dolphin-mistral
|
9 months ago |
|
Daniel Hiltgen
|
46c5f5fd9e
Runtime selection of new or old runners
|
9 months ago |
|
Daniel Hiltgen
|
c1384c8bcc
Implement timings response in Go server
|
9 months ago |
 Daniel Hiltgen
|
d0e239b85f
Merge pull request #6110 from dhiltgen/go_server_embeds
|
9 months ago |
|
Daniel Hiltgen
|
b2f8a6120c
Get embeddings working
|
9 months ago |
|
Daniel Hiltgen
|
71b287264d
Fix parallel requests
|
9 months ago |
|
jmorganca
|
2abf81885d
lint
|
11 months ago |
|
jmorganca
|
ac090b6b71
fix issues with runner
|
11 months ago |
|
jmorganca
|
028fda3582
cleanup stop code
|
11 months ago |
|
jmorganca
|
a796b7aeaf
num predict
|
11 months ago |
|
jmorganca
|
89cb4b8d6b
basic progress
|
11 months ago |
|
jmorganca
|
0d365e8d34
add more runner params
|
11 months ago |
|
jmorganca
|
72ff94efe0
truncate stop properly
|
11 months ago |
|
jmorganca
|
240d4cf0aa
wip stop tokens
|
11 months ago |
|
jmorganca
|
424627c347
embeddings
|
11 months ago |
|
jmorganca
|
1a801fba2a
remove dependency on `llm`
|
11 months ago |
|
jmorganca
|
727494ea54
grammar
|
11 months ago |
|
jmorganca
|
b39fca7088
sampling
|
11 months ago |
|
jmorganca
|
db55b1b89d
better `example` module, add port
|
11 months ago |
|
jmorganca
|
1124e24aff
wip
|
1 year ago |
|
jmorganca
|
df44d119a3
add `llava` to `runner`
|
1 year ago |
|
jmorganca
|
878eb9a19f
add llava
|
1 year ago |
|
jmorganca
|
4dd63c1fef
move `runner` package down
|
1 year ago |
|
jmorganca
|
82214396b5
replace static build in `llm`
|
1 year ago |
