123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194195196197198199200201202203204205206207208209210211212213214215216217218219220221222223224225226227228229230231232233234235236237238239240241242243244245246247248249 |
- package model
- import (
- "errors"
- "fmt"
- "image"
- _ "image/jpeg"
- _ "image/png"
- "log/slog"
- "os"
- "reflect"
- "strconv"
- "strings"
- _ "golang.org/x/image/bmp"
- _ "golang.org/x/image/tiff"
- _ "golang.org/x/image/webp"
- "github.com/ollama/ollama/kvcache"
- "github.com/ollama/ollama/ml"
- _ "github.com/ollama/ollama/ml/backend"
- )
- type Options struct {
- Inputs []int32
- Positions []int32
- Sequences []int
- Outputs []int32
- Images []image.Image
- }
- type config struct {
- Cache kvcache.Cache
- }
- type Base struct {
- b ml.Backend
- config
- }
- func (m *Base) Backend() ml.Backend {
- return m.b
- }
- func (m *Base) Config() config {
- return m.config
- }
- type Model interface {
- Forward(ml.Context, Options) (ml.Tensor, error)
- Backend() ml.Backend
- Config() config
- }
- var models = make(map[string]func(ml.Config) (Model, error))
- func Register(name string, f func(ml.Config) (Model, error)) {
- if _, ok := models[name]; ok {
- panic("model: model already registered")
- }
- models[name] = f
- }
- func New(s string) (Model, error) {
- r, err := os.Open(s)
- if err != nil {
- return nil, err
- }
- defer r.Close()
- b, err := ml.NewBackend(r)
- if err != nil {
- return nil, err
- }
- arch := b.Config().Architecture()
- f, ok := models[arch]
- if !ok {
- return nil, fmt.Errorf("unsupported model architecture %q", arch)
- }
- m, err := f(b.Config())
- if err != nil {
- return nil, err
- }
- base := Base{b: b, config: m.Config()}
- v := reflect.ValueOf(m)
- v.Elem().Set(populateFields(base, v.Elem()))
- return m, nil
- }
- func populateFields(base Base, v reflect.Value, tags ...Tag) reflect.Value {
- t := v.Type()
- if t.Kind() == reflect.Struct {
- allNil := true
- for i := range t.NumField() {
- tt := t.Field(i).Type
- vv := v.Field(i)
- if !vv.CanSet() {
- continue
- }
- // make a copy
- tagsCopy := tags
- if tag := t.Field(i).Tag.Get("gguf"); tag != "" {
- tagsCopy = append(tagsCopy, ParseTags(tag))
- }
- if tt == reflect.TypeOf((*Base)(nil)).Elem() {
- vv.Set(reflect.ValueOf(base))
- } else if tt == reflect.TypeOf((*ml.Tensor)(nil)).Elem() {
- var fn func([]Tag) [][]string
- fn = func(tags []Tag) (values [][]string) {
- if len(tags) < 1 {
- return nil
- }
- values = [][]string{{tags[0].Name}}
- for _, alt := range tags[0].Alternate {
- values = append(values, []string{alt})
- }
- for i, value := range values {
- for _, rest := range fn(tags[1:]) {
- value = append(value, rest...)
- }
- values[i] = value
- }
- return values
- }
- names := fn(tagsCopy)
- for _, name := range names {
- if tensor := base.Backend().Get(strings.Join(name, ".")); tensor != nil {
- slog.Debug("found tensor", "", tensor)
- vv.Set(reflect.ValueOf(tensor))
- break
- }
- }
- } else if tt.Kind() == reflect.Pointer || tt.Kind() == reflect.Interface {
- setPointer(base, vv, tagsCopy)
- } else if tt.Kind() == reflect.Slice || tt.Kind() == reflect.Array {
- for i := range vv.Len() {
- vvv := vv.Index(i)
- if vvv.Kind() == reflect.Pointer || vvv.Kind() == reflect.Interface {
- setPointer(base, vvv, append(tagsCopy, Tag{Name: strconv.Itoa(i)}))
- } else {
- vvv.Set(populateFields(base, vvv, append(tagsCopy, Tag{Name: strconv.Itoa(i)})...))
- }
- }
- }
- if !canNil(tt) || !vv.IsNil() {
- allNil = false
- }
- }
- if allNil {
- return reflect.Zero(t)
- }
- }
- return v
- }
- func setPointer(base Base, v reflect.Value, tags []Tag) {
- vv := v
- if v.Kind() == reflect.Interface {
- if v.IsNil() {
- return
- }
- vv = vv.Elem()
- }
- vv = vv.Elem()
- if v.IsNil() {
- vv = reflect.New(v.Type().Elem()).Elem()
- }
- if f := populateFields(base, vv, tags...); f.CanAddr() {
- v.Set(f.Addr())
- }
- }
- type Tag struct {
- Name string
- Alternate []string
- }
- func ParseTags(s string) (tag Tag) {
- parts := strings.Split(s, ",")
- if len(parts) > 0 {
- tag.Name = parts[0]
- for _, part := range parts[1:] {
- if value, ok := strings.CutPrefix(part, "alt:"); ok {
- tag.Alternate = append(tag.Alternate, value)
- }
- }
- }
- return
- }
- func canNil(t reflect.Type) bool {
- return t.Kind() == reflect.Chan ||
- t.Kind() == reflect.Func ||
- t.Kind() == reflect.Interface ||
- t.Kind() == reflect.Map ||
- t.Kind() == reflect.Pointer ||
- t.Kind() == reflect.Slice
- }
- func Forward(ctx ml.Context, m Model, opts Options) (ml.Tensor, error) {
- if len(opts.Positions) != len(opts.Sequences) {
- return nil, fmt.Errorf("length of positions (%v) must match length of seqs (%v)", len(opts.Positions), len(opts.Sequences))
- }
- if len(opts.Positions) < 1 {
- return nil, errors.New("batch size cannot be less than 1")
- }
- cache := m.Config().Cache
- if cache != nil {
- err := cache.StartForward(ctx, opts.Positions, opts.Sequences)
- if err != nil {
- return nil, err
- }
- }
- t, err := m.Forward(ctx, opts)
- if err != nil {
- return nil, err
- }
- ctx.Forward(t)
- ctx.Compute(t)
- return t, nil
- }
|