Any-to-Any
Transformers
Safetensors
speechlmm
feature-extraction
multimodal
audio
speech
video
speech-recognition
speech-translation
lip-reading
meetween
custom_code
Instructions to use meetween/SpeechLMM-v2.0-L-7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use meetween/SpeechLMM-v2.0-L-7B with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("meetween/SpeechLMM-v2.0-L-7B", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download tokenizer_config.json from meetween/SpeechLMM-v2.0-L-7B: direct link, hf CLI and curl.
- Browser
- Download file 2.25 kB
-
https://huggingface.co/meetween/SpeechLMM-v2.0-L-7B/resolve/main/tokenizer_config.json
- Command line
-
hf download hf://meetween/SpeechLMM-v2.0-L-7B/tokenizer_config.json
-
curl -L -o tokenizer_config.json https://huggingface.co/meetween/SpeechLMM-v2.0-L-7B/resolve/main/tokenizer_config.json
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 %}" | |
| } | |