Class: DiscourseAi::Tokenizer::MistralTokenizer

Inherits:
BasicTokenizer show all
Defined in:
lib/discourse_ai/tokenizer/mistral_tokenizer.rb

Overview

Tokenizer from Mistral Small 2503 LLM

Class Method Summary collapse

Methods inherited from BasicTokenizer

available_llm_tokenizers, below_limit?, decode, encode, size, tokenize, truncate

Class Method Details

.tokenizerObject



7
8
9
10
11
12
13
14
# File 'lib/discourse_ai/tokenizer/mistral_tokenizer.rb', line 7

def self.tokenizer
  @tokenizer ||=
    ::Tokenizers.from_file(
      DiscourseAi::Tokenizers.vendor_path(
        "mistral-small-3.1-24b-2503.json"
      )
    )
end