d1-omni:2b

11.6K 2 hours ago

d1-omni is a multimodal 600M decision model from Liquid AI

vision decision audio 600m 2b
... /
json
3cff70d801d7 ยท 625B
{
"backend": "tokenizers",
"bos_token": "<|startoftext|>",
"eos_token": "<|im_end|>",
"extra_special_tokens": [],
"image_token": "<|image|>",
"model_max_length": 1000000000000000019884624838656,
"model_specific_special_tokens": {
"image_token": "<|image|>",
"video_token": "<|video|>",
"vision_end_token": "<|vision_end|>",
"vision_start_token": "<|vision_start|>"
},
"pad_token": "<|pad|>",
"processor_class": "Lfm3OmniProcessor",
"tokenizer_class": "TokenizersBackend",
"video_token": "<|video|>",
"vision_end_token": "<|vision_end|>",
"vision_start_token": "<|vision_start|>"
}