in Runtime/Tokenizers/Tokenizers/Tokenizers.cs [116:139]
public List<int> ConvertTokensToIds(List<string> tokens)
{
// Create an array of token IDs by mapping each token to its corresponding ID
List<int> ids = new List<int>();
//Debug.Log("Dictionary Contents:");
foreach (var kvp in TokensToIds)
{
Debug.Log($"Key: {kvp.Key}, Value: {kvp.Value}");
}
// token.Select: applies an operation to each token in tokens
ids = tokens.Select(t => TokensToIds.TryGetValue(t, out int id) ? id : UnknownTokenId).ToList();
if (FuseUnk == false)
{
//ids = Fuse(ids, UnkTokenId);
ids = TokenizersUtils.Utils.Fuse(ids, UnkTokenId ?? -1);
}
return ids;
}