Safetensors
English
llava
video-retrieval
text-to-video-search
multimodal-embedding
TARA / processor_config.json
bpiyush's picture
Update TARA to latest Tarsier2 checkpoint and runnable demo.
7daf628
raw
history blame contribute delete
169 Bytes
{
"image_token": "<|image_pad|>",
"max_seq_len": 16384,
"merge_size": 2,
"patch_size": 14,
"processor_class": "TarsierProcessor",
"temporal_patch_size": 2
}