Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 2 additions & 0 deletions src/Microsoft.ML.Tokenizers/Model/TiktokenTokenizer.cs
Original file line number Diff line number Diff line change
Expand Up @@ -1044,6 +1044,7 @@ private static readonly (string Prefix, ModelEncoding Encoding)[] _modelPrefixTo
( "o4-mini-", ModelEncoding.O200kBase ), // e.g. o4-mini

// chat
( "gpt-5.3-", ModelEncoding.O200kBase ),
( "gpt-5.2-", ModelEncoding.O200kBase ),
( "gpt-5.1-", ModelEncoding.O200kBase ),
( "gpt-5-", ModelEncoding.O200kBase ),
Expand Down Expand Up @@ -1073,6 +1074,7 @@ private static readonly (string Prefix, ModelEncoding Encoding)[] _modelPrefixTo
{ "o4-mini", ModelEncoding.O200kBase },

// chat
{ "gpt-5.3", ModelEncoding.O200kBase },
{ "gpt-5.2", ModelEncoding.O200kBase },
{ "gpt-5.1", ModelEncoding.O200kBase },
{ "gpt-5", ModelEncoding.O200kBase },
Expand Down
4 changes: 4 additions & 0 deletions test/Microsoft.ML.Tokenizers.Tests/TiktokenTests.cs
Original file line number Diff line number Diff line change
Expand Up @@ -38,6 +38,7 @@ public class TiktokenTests
public static Tokenizer GPT5 { get; } = TiktokenTokenizer.CreateForModel("gpt-5");
public static Tokenizer GPT5_1 { get; } = TiktokenTokenizer.CreateForModel("gpt-5.1");
public static Tokenizer GPT5_2 { get; } = TiktokenTokenizer.CreateForModel("gpt-5.2");
public static Tokenizer GPT5_3 { get; } = TiktokenTokenizer.CreateForModel("gpt-5.3");
public static Tokenizer Phi4 { get; } = TiktokenTokenizer.CreateForModel("phi-4");
public static TiktokenTokenizer GptOss { get; } = TiktokenTokenizer.CreateForModel("gpt-oss-20b");

Expand Down Expand Up @@ -421,6 +422,8 @@ public void TestEncodeR50kBase()
[InlineData("gpt-5.1-mini")]
[InlineData("gpt-5.2")]
[InlineData("gpt-5.2-mini")]
[InlineData("gpt-5.3")]
[InlineData("gpt-5.3-mini")]
[InlineData("chatgpt-4o-")]
[InlineData("gpt-4")]
[InlineData("gpt-4-")]
Expand Down Expand Up @@ -541,6 +544,7 @@ public void TestEncodingNamesNegativeCases()
[InlineData("gpt-5")]
[InlineData("gpt-5.1")]
[InlineData("gpt-5.2")]
[InlineData("gpt-5.3")]
[InlineData("o1")]
[InlineData("o3")]
[InlineData("o4-mini")]
Expand Down
Loading