Josh Yan
|
1ef59057d0
patch llama.cpp
|
10 months ago |
Josh Yan
|
b0e4e8d76c
change
|
10 months ago |
Josh Yan
|
369113970a
wooh
|
10 months ago |
Josh Yan
|
24e8292e94
new changes
|
10 months ago |
Josh Yan
|
c63b4ecbf7
quantize
|
10 months ago |
Josh Yan
|
bec9100f32
tensor count
|
10 months ago |
Josh Yan
|
1344843515
image
|
10 months ago |
Josh Yan
|
e87eafe5cd
quantize percentage
|
10 months ago |
Josh Yan
|
10ea0987e9
isLocal firstdraft
|
10 months ago |
Michael Yang
|
269ed6e6a2
update message processing
|
10 months ago |
Michael Yang
|
da8e2a0447
use kvs to detect embedding models
|
11 months ago |
Michael Yang
|
a30915bde1
add capabilities
|
11 months ago |
Michael Yang
|
58e3fff311
rename templates to template
|
11 months ago |
Michael Yang
|
3f0b309ad4
remove ManifestV2
|
11 months ago |
Blake Mizerany
|
cb42e607c5
llm: speed up gguf decoding by a lot (#5246)
|
10 months ago |
Michael Yang
|
e835ef1836
fix: quantization with template
|
10 months ago |
Jeffrey Morgan
|
1fd236d177
server: remove jwt decoding error (#5027)
|
11 months ago |
Michael Yang
|
c16f8af911
fix: multiple templates when creating from model
|
11 months ago |
Michael Yang
|
030e765e76
fix create model when template detection errors
|
11 months ago |
Michael Yang
|
9b6c2e6eb6
detect chat template from KV
|
11 months ago |
Blake Mizerany
|
de5beb06b3
server: skip blob verification for already verified blobs
|
11 months ago |
Michael Yang
|
d61ef8b954
update create handler to use model.Name
|
1 year ago |
Michael Yang
|
6297f85606
gofmt, goimports
|
11 months ago |
Michael Yang
|
e40145a39d
lint
|
11 months ago |
Michael Yang
|
8ffb51749f
nolintlint
|
11 months ago |
Michael Yang
|
04f3c12bb7
replace x/exp/slices with slices
|
11 months ago |
Michael Yang
|
bca7b12284
Merge pull request #3718 from ollama/mxyng/modelname-3
|
11 months ago |
Patrick Devine
|
4cc3be3035
Move envconfig and consolidate env vars (#4608)
|
11 months ago |
Michael Yang
|
807d092761
fix quantize file types
|
11 months ago |
Michael Yang
|
f36f1d6be9
tidy intermediate blobs
|
11 months ago |