Instructions to use mispeech/r1-aqa with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use mispeech/r1-aqa with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("mispeech/r1-aqa") model = AutoModelForMultimodalLM.from_pretrained("mispeech/r1-aqa", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download chat_template.json from mispeech/r1-aqa: direct link, hf CLI and curl.
- Browser
- Download file 719 Bytes
-
https://huggingface.co/mispeech/r1-aqa/resolve/refs%2Fpr%2F13/chat_template.json
- Command line
-
hf download hf://mispeech/r1-aqa@refs/pr/13/chat_template.json
-
curl -L -o chat_template.json https://huggingface.co/mispeech/r1-aqa/resolve/refs%2Fpr%2F13/chat_template.json
719 Bytes
| { | |
| "chat_template": "{% set audio_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 'audio' in content or 'audio_url' in content %}{% set audio_count.value = audio_count.value + 1 %}Audio {{ audio_count.value }}: <|audio_bos|><|AUDIO|><|audio_eos|>\n{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}" | |
| } | |