Class TokenizerConfig
- Namespace
- AiDotNet.Tokenization.HuggingFace
- Assembly
- AiDotNet.dll
Configuration for HuggingFace tokenizers.
public class TokenizerConfig
- Inheritance
-
TokenizerConfig
- Inherited Members
Properties
AdditionalSpecialTokens
Gets or sets additional special tokens.
[JsonProperty("additional_special_tokens")]
public List<string>? AdditionalSpecialTokens { get; set; }
Property Value
BosToken
[JsonProperty("bos_token")]
public string? BosToken { get; set; }
Property Value
ClsToken
[JsonProperty("cls_token")]
public string? ClsToken { get; set; }
Property Value
DoLowerCase
Gets or sets whether to lowercase input.
[JsonProperty("do_lower_case")]
public bool DoLowerCase { get; set; }
Property Value
EosToken
[JsonProperty("eos_token")]
public string? EosToken { get; set; }
Property Value
MaskToken
[JsonProperty("mask_token")]
public string? MaskToken { get; set; }
Property Value
MergesFile
Gets or sets the merges file (for BPE).
[JsonProperty("merges_file")]
public string? MergesFile { get; set; }
Property Value
ModelMaxLength
Gets or sets the model max length.
[JsonProperty("model_max_length")]
public int? ModelMaxLength { get; set; }
Property Value
- int?
ModelType
Gets or sets the model type.
[JsonProperty("model_type")]
public string? ModelType { get; set; }
Property Value
PadToken
[JsonProperty("pad_token")]
public string? PadToken { get; set; }
Property Value
SepToken
[JsonProperty("sep_token")]
public string? SepToken { get; set; }
Property Value
TokenizerClass
Gets or sets the tokenizer type.
[JsonProperty("tokenizer_class")]
public string? TokenizerClass { get; set; }
Property Value
UnkToken
Gets or sets special tokens.
[JsonProperty("unk_token")]
public string? UnkToken { get; set; }
Property Value
VocabFile
Gets or sets the vocabulary file.
[JsonProperty("vocab_file")]
public string? VocabFile { get; set; }