jeans/ollama
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

move llama.h

Browse Source
This commit is contained in:
Josh Yan 2024-07-10 14:20:04 -07:00
parent d82d25d70c
commit d352c68ffc
4 changed files with 1235 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
.gitattributes vendored
View File

@ -1 +1,2 @@
llm/ext_server/* linguist-vendored
llm/*.h linguist-vendored

1227
llm/llama.h vendored Normal file
View File

File diff suppressed because it is too large Load Diff

6
llm/llm.go
View File

@ -1,6 +1,6 @@
package llm
// #cgo CFLAGS: -Illama.cpp -Illama.cpp/include -Illama.cpp/ggml/include
// #cgo CPPFLAGS: -Illama.cpp/ggml/include
// #cgo LDFLAGS: -lllama -lggml -lstdc++ -lpthread
// #cgo darwin,arm64 LDFLAGS: -L${SRCDIR}/build/darwin/arm64_static -L${SRCDIR}/build/darwin/arm64_static/src -L${SRCDIR}/build/darwin/arm64_static/ggml/src -framework Accelerate -framework Metal
// #cgo darwin,amd64 LDFLAGS: -L${SRCDIR}/build/darwin/x86_64_static -L${SRCDIR}/build/darwin/x86_64_static/src -L${SRCDIR}/build/darwin/x86_64_static/ggml/src
@ -61,13 +61,13 @@ func Quantize(infile, outfile string, ftype fileType, fn func(resp api.ProgressR
select {
case <-ticker.C:
fn(api.ProgressResponse{
Status: fmt.Sprintf("quantizing model %d/%d", int(*((*C.float)(store))), tensorCount),
Status: fmt.Sprintf("quantizing model tensors %d/%d", int(*((*C.float)(store))), tensorCount),
Quantize: "quant",
})
fmt.Println("Progress: ", *((*C.float)(store)))
case <-done:
fn(api.ProgressResponse{
Status: fmt.Sprintf("quantizing model %d/%d", tensorCount, tensorCount),
Status: fmt.Sprintf("quantizing model tensors %d/%d", tensorCount, tensorCount),
Quantize: "quant",
})
return

5
server/images.go
View File

@ -428,7 +428,10 @@ func CreateModel(ctx context.Context, name model.Name, modelFileDir, quantizatio
if !slices.Contains([]string{"F16", "F32"}, ft.String()) {
return errors.New("quantization is only supported for F16 and F32 models")
} else if want != ft {
fn(api.ProgressResponse{Status: fmt.Sprintf("quantizing %s model to %s", ft, quantization)})
fn(api.ProgressResponse{
Status: "quantizing model tensors",
Quantize: "quant",
})
blob, err := GetBlobsPath(baseLayer.Digest)
if err != nil {