Skip to content

Commit 4c4910b

Browse files
committed
config(tokenizer): increase max token length to 16384 bytes
1 parent ceb583b commit 4c4910b

File tree

1 file changed

+2
-1
lines changed

1 file changed

+2
-1
lines changed

src/main/kotlin/cc/unitmesh/devti/llms/tokenizer/TokenizerImpl.kt

Lines changed: 2 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -9,7 +9,8 @@ import com.knuddels.jtokkit.api.EncodingType
99
import com.knuddels.jtokkit.api.IntArrayList
1010

1111
@Service(Service.Level.APP)
12-
class TokenizerImpl(private val maxTokenLength: Int = 8192) : Tokenizer {
12+
class TokenizerImpl : Tokenizer {
13+
private val maxTokenLength: Int = 16384
1314
private var registry: EncodingRegistry? = Encodings.newDefaultEncodingRegistry()
1415
private var encoding: Encoding = registry?.getEncoding(EncodingType.CL100K_BASE)!!
1516

0 commit comments

Comments
 (0)