diff --git a/server/images.go b/server/images.go index 13a3192ae..c163b247c 100644 --- a/server/images.go +++ b/server/images.go @@ -440,6 +440,8 @@ func CreateModel(ctx context.Context, name model.Name, modelFileDir, quantizatio defer temp.Close() defer os.Remove(temp.Name()) + // Quantizes per layer + // Save total quantized tensors if err := llm.Quantize(blob, temp.Name(), want); err != nil { return err } @@ -480,7 +482,7 @@ func CreateModel(ctx context.Context, name model.Name, modelFileDir, quantizatio } fn(api.ProgressResponse{ - Status: fmt.Sprintf("quantizing model %d%%", 100), + Status: "quantizing model done", Quantize: quantization, }) case "license", "template", "system":