speech-lora/tokenizer_config.json

{
  "add_prefix_space": false,
  "added_tokens_decoder": {
    "200010": {
      "content": "<|endoftext10|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "200011": {
      "content": "<|endoftext11|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "199999": {
      "content": "<|endoftext|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "200018": {
      "content": "<|endofprompt|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "200019": {
      "content": "<|assistant|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": true,
      "single_word": false,
      "special": true
    },
    "200020": {
      "content": "<|end|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": true,
      "single_word": false,
      "special": true
    },
    "200021": {
      "content": "<|user|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": true,
      "single_word": false,
      "special": true
    },
    "200022": {
      "content": "<|system|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": true,
      "single_word": false,
      "special": true
    },
    "200023": {
      "content": "<|tool|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": true,
      "single_word": false,
      "special": false
    },
    "200024": {
      "content": "<|/tool|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": true,
      "single_word": false,
      "special": false
    },
    "200025": {
      "content": "<|tool_call|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": true,
      "single_word": false,
      "special": false
    },
    "200026": {
      "content": "<|/tool_call|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": true,
      "single_word": false,
      "special": false
    },
    "200027": {
      "content": "<|tool_response|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": true,
      "single_word": false,
      "special": false
    },
    "200028": {
      "content": "<|tag|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": true,
      "single_word": false,
      "special": true
    }
  },
  "bos_token": "<|endoftext|>",
  "chat_template": "{% for message in messages %}{% if message['role'] == 'system' and 'tools' in message and message['tools'] is not none %}{{ '<|' + message['role'] + '|>' + message['content'] + '<|tool|>' + message['tools'] + '<|/tool|>' + '<|end|>' }}{% else %}{{ '<|' + message['role'] + '|>' + message['content'] + '<|end|>' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>' }}{% else %}{{ eos_token }}{% endif %}",
  "clean_up_tokenization_spaces": false,
  "eos_token": "<|endoftext|>",
  "model_max_length": 128000,
  "pad_token": "<|endoftext|>",
  "tokenizer_class": "GPT2TokenizerFast",
  "unk_token": "<|endoftext|>"
}