Stages Documentation

Differences

This shows you the differences between two versions of the page.

Link to this comparison view

Both sides previous revisionPrevious revision
712:configure_stages [2026/09/23 08:22] – [AI Feature Tokenizer Configuration] Prinz, Patrick712:configure_stages [2026/09/23 08:23] (current) – [AI Feature Tokenizer Configuration] Prinz, Patrick
Line 693: Line 693:
 ===== AI Feature Tokenizer Configuration ===== ===== AI Feature Tokenizer Configuration =====
  
->Attention - Introduced with 7.12.8.1: \\ If no Tokenizer is provided via the conf folder, Stages falls back to a generic o200k based Tokenizer that is suitable for most of the late openAi compatible models.+>Attention - Introduced with 7.12.8.1: \\ If openAiCompatible Adapter is used and no Tokenizer is provided via the conf folder, Stages falls back to a generic o200k based Tokenizer that is suitable for most of the late openAi compatible models.
  
 LLM that are NOT using the standard byte-pair-encoding algorithm or are provided via the openAICompatible adapter CANNOT be used with the Azure tokenizer. Stages implements the HuggingFaceTokenizer from deep java library to support customized tokenizer. LLM that are NOT using the standard byte-pair-encoding algorithm or are provided via the openAICompatible adapter CANNOT be used with the Azure tokenizer. Stages implements the HuggingFaceTokenizer from deep java library to support customized tokenizer.