Just Llama 3b 3.2 tokenizer modified to use two new special tokens replacing the reserved special tokens slots:

[
    {
      "id": 128002,
      "content": "<|reference_text|>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 128003,
      "content": "<|end_reference_text|>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    }
]

Downloads last month: -; Downloads are not tracked for this model. How to track

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support