highperfocused/ollama
1
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2025-08-27 19:38:41 +02:00
Code Issues Packages Projects Releases Wiki Activity

model: treat 'user defined' tokens as special tokens (#11077)

Browse Source
This commit is contained in:
Jeffrey Morgan
2025-06-16 16:03:16 -07:00
committed by GitHub
parent a6fbfc880c
commit 9e125d884c
2 changed files with 17 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
model/vocabulary.go
View File

@@ -87,7 +87,7 @@ func (v *Vocabulary) Decode(id int32) string {
func (v *Vocabulary) SpecialVocabulary() []string { func (v *Vocabulary) SpecialVocabulary() []string {
v.specialOnce.Do(func() { v.specialOnce.Do(func() {
for i := range v.Values { for i := range v.Values {
if v.Types[i] == TOKEN_TYPE_CONTROL { if v.Types[i] == TOKEN_TYPE_CONTROL || v.Types[i] == TOKEN_TYPE_USER_DEFINED {
v.special = append(v.special, v.Values[i]) v.special = append(v.special, v.Values[i])
} }
} }

16
model/vocabulary_test.go Normal file
View File

@@ -0,0 +1,16 @@
package model
import "testing"
func TestVocabulary_SpecialVocabulary(t *testing.T) {
vocab := &Vocabulary{
Values: []string{"<|startoftext|>", "<|endoftext|>", "<|tool_call_start|>", "<|tool_call_end|>", "hi"},
Types: []int32{TOKEN_TYPE_CONTROL, TOKEN_TYPE_CONTROL, TOKEN_TYPE_USER_DEFINED, TOKEN_TYPE_USER_DEFINED, TOKEN_TYPE_NORMAL},
}
specialVocab := vocab.SpecialVocabulary()
if len(specialVocab) != 4 {
t.Errorf("expected 4 special tokens, got %d", len(specialVocab))
}
}