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

wooh

Browse Source
This commit is contained in:
Josh Yan 2024-07-09 17:04:33 -07:00
parent 26ed829415
commit 369113970a
2 changed files with 2 additions and 11 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
llm/llm.go
View File

@ -63,6 +63,7 @@ func Quantize(infile, outfile string, ftype fileType, fn func(resp api.ProgressR
Status: fmt.Sprintf("quantizing model %d%%", int(progress*100)), Status: fmt.Sprintf("quantizing model %d%%", int(progress*100)),
Quantize: "quant", Quantize: "quant",
}) })
fmt.Println("Progress: ", progress)
case <-done: case <-done:
fn(api.ProgressResponse{ fn(api.ProgressResponse{
Status: "quantizing model", Status: "quantizing model",

10
server/images.go
View File

@ -423,11 +423,6 @@ func CreateModel(ctx context.Context, name model.Name, modelFileDir, quantizatio
return err return err
} }
fn(api.ProgressResponse{
Status: "quantizing model",
Quantize: "quant",
})
ft := baseLayer.GGML.KV().FileType() ft := baseLayer.GGML.KV().FileType()
if !slices.Contains([]string{"F16", "F32"}, ft.String()) { if !slices.Contains([]string{"F16", "F32"}, ft.String()) {
return errors.New("quantization is only supported for F16 and F32 models") return errors.New("quantization is only supported for F16 and F32 models")
@ -467,11 +462,6 @@ func CreateModel(ctx context.Context, name model.Name, modelFileDir, quantizatio
baseLayer.Layer = layer baseLayer.Layer = layer
baseLayer.GGML = ggml baseLayer.GGML = ggml
} }
fn(api.ProgressResponse{
Status: "quantizing model done",
Quantize: quantization,
})
} }
if baseLayer.GGML != nil { if baseLayer.GGML != nil {