| .. |
|
ext_server
|
34f142797a
llm: always add bos token to prompt (#4941)
|
10 months ago |
|
generate
|
ab8c929e20
Add ability to skip oneapi generate
|
10 months ago |
|
llama.cpp @ 5921b8f089
|
22f5c12ced
Update llama.cpp submodule to `5921b8f0` (#4731)
|
11 months ago |
|
patches
|
ce0dc33cb8
llm: patch to fix qwen 2 temporarily on nvidia (#4897)
|
10 months ago |
|
filetype.go
|
d6f692ad1a
Add support for IQ1_S, IQ3_S, IQ2_S, IQ4_XS. IQ4_NL (#4322)
|
11 months ago |
|
ggla.go
|
171eb040fc
simplify safetensors reading
|
11 months ago |
|
ggml.go
|
9b6c2e6eb6
detect chat template from KV
|
10 months ago |
|
gguf.go
|
030e765e76
fix create model when template detection errors
|
10 months ago |
|
llm.go
|
829ff87bd1
revert tokenize ffi (#4761)
|
11 months ago |
|
llm_darwin_amd64.go
|
58d95cc9bd
Switch back to subprocessing for llama.cpp
|
1 year ago |
|
llm_darwin_arm64.go
|
58d95cc9bd
Switch back to subprocessing for llama.cpp
|
1 year ago |
|
llm_linux.go
|
58d95cc9bd
Switch back to subprocessing for llama.cpp
|
1 year ago |
|
llm_windows.go
|
058f6cd2cc
Move nested payloads to installer and zip file on windows
|
1 year ago |
|
memory.go
|
6297f85606
gofmt, goimports
|
11 months ago |
|
payload.go
|
04f3c12bb7
replace x/exp/slices with slices
|
11 months ago |
|
server.go
|
e40145a39d
lint
|
11 months ago |
|
status.go
|
58d95cc9bd
Switch back to subprocessing for llama.cpp
|
1 year ago |
Jeffrey Morgan
34f142797a
llm: always add bos token to prompt (#4941)