baalajimaestro/ollama
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

Merge pull request #4244 from ollama/mxyng/skip-if-same

Browse source 
skip if same quantization
This commit is contained in:
Michael Yang 2024-05-07 19:03:37 -07:00 committed by GitHub
commit 88cf154483
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
2 changed files with 26 additions and 26 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

6
llm/ggml.go
View file

@ -45,12 +45,12 @@ func (kv KV) ParameterCount() uint64 {
return kv.u64("general.parameter_count")
}
func (kv KV) FileType() string {
func (kv KV) FileType() fileType {
if u64 := kv.u64("general.file_type"); u64 > 0 {
return fileType(uint32(u64)).String()
return fileType(uint32(u64))
}
return "unknown"
return fileTypeUnknown
}
func (kv KV) BlockCount() uint64 {

16
server/images.go
View file

@ -370,17 +370,16 @@ func CreateModel(ctx context.Context, name, modelFileDir, quantization string, m
baseLayer.MediaType == "application/vnd.ollama.image.model" &&
baseLayer.GGML != nil &&
baseLayer.GGML.Name() == "gguf" {
ftype, err := llm.ParseFileType(quantization)
want, err := llm.ParseFileType(quantization)
if err != nil {
return err
}
filetype := baseLayer.GGML.KV().FileType()
if !slices.Contains([]string{"F16", "F32"}, filetype) {
ft := baseLayer.GGML.KV().FileType()
if !slices.Contains([]string{"F16", "F32"}, ft.String()) {
return errors.New("quantization is only supported for F16 and F32 models")
}
fn(api.ProgressResponse{Status: fmt.Sprintf("quantizing %s model to %s", filetype, quantization)})
} else if want != ft {
fn(api.ProgressResponse{Status: fmt.Sprintf("quantizing %s model to %s", ft, quantization)})
blob, err := GetBlobsPath(baseLayer.Digest)
if err != nil {
@ -394,7 +393,7 @@ func CreateModel(ctx context.Context, name, modelFileDir, quantization string, m
defer temp.Close()
defer os.Remove(temp.Name())
if err := llm.Quantize(blob, temp.Name(), ftype); err != nil {
if err := llm.Quantize(blob, temp.Name(), want); err != nil {
return err
}
@ -403,12 +402,13 @@ func CreateModel(ctx context.Context, name, modelFileDir, quantization string, m
return err
}
}
}
if baseLayer.GGML != nil {
config.ModelFormat = cmp.Or(config.ModelFormat, baseLayer.GGML.Name())
config.ModelFamily = cmp.Or(config.ModelFamily, baseLayer.GGML.KV().Architecture())
config.ModelType = cmp.Or(config.ModelType, format.HumanNumber(baseLayer.GGML.KV().ParameterCount()))
config.FileType = cmp.Or(config.FileType, baseLayer.GGML.KV().FileType())
config.FileType = cmp.Or(config.FileType, baseLayer.GGML.KV().FileType().String())
config.ModelFamilies = append(config.ModelFamilies, baseLayer.GGML.KV().Architecture())
}