SpeechLMM-v2.0-L-7B / tokenizer_config.json
nicber's picture
Release SpeechLMM-v2.0-L-7B production weights (stage 00a: final checkpoint, stage 00b:checkpoint-1800, stage 01:checkpoint-5200)
28d7112 verified
Raw History Blame Contribute Delete
2.25 kB
{
"add_prefix_space": false,
"audio_bos_token": "<|audio_bos|>",
"audio_eos_token": "<|audio_eos|>",
"audio_token": "<|AUDIO|>",
"backend": "tokenizers",
"bos_token": null,
"clean_up_tokenization_spaces": false,
"eos_token": "<|im_end|>",
"errors": "replace",
"image_token": "<|IMAGE|>",
"is_local": true,
"model_max_length": 32768,
"model_specific_special_tokens": {
"audio_bos_token": "<|audio_bos|>",
"audio_eos_token": "<|audio_eos|>",
"audio_token": "<|AUDIO|>",
"image_token": "<|IMAGE|>",
"video_token": "<|VIDEO|>",
"vision_bos_token": "<|vision_bos|>",
"vision_eos_token": "<|vision_eos|>"
},
"pad_token": "<|endoftext|>",
"processor_class": "Qwen2_5OmniProcessor",
"split_special_tokens": false,
"tokenizer_class": "Qwen2Tokenizer",
"unk_token": null,
"video_token": "<|VIDEO|>",
"vision_bos_token": "<|vision_bos|>",
"vision_eos_token": "<|vision_eos|>",
"chat_template": "{% set audio_count = namespace(value=0) %}{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_bos|><|IMAGE|><|vision_eos|>{% elif content['type'] == 'audio' or 'audio' in content or 'audio_url' in content %}{% set audio_count.value = audio_count.value + 1 %}{% if add_audio_id %}Audio {{ audio_count.value }}: {% endif %}<|audio_bos|><|AUDIO|><|audio_eos|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_bos|><|VIDEO|><|vision_eos|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}"
}