Ola: Pushing the Frontiers of Omni-Modal Language Model
large-v3.pt NotImplementedError: Cannot copy out of meta tensor; no data! Please use torch.nn.Module.to_empty() instead of torch.nn.Module.to() when moving module from meta to a different device.
使用lmms-eval在videomme上评价结果与论文结果差距较大
[bug]infer.py
Cases where image information is missing from the input modality
NameError: name 'Image' is not defined. Did you mean: 'image'?
FileNotFoundError: [Errno 2] No such file or directory: '/mnt/lzy/ola-model/speech_encoders/BEATs_iter3_plus_AS2M_finetuned_on_AS2M_cpt2.pt'
RuntimeError: Model ./large-v3.pt not found; available models = ['tiny.en', 'tiny', 'base.en', 'base', 'small.en', 'small', 'medium.en', 'medium', 'large-v1', 'large-v2', 'large-v3', 'large', 'large-v3-turbo', 'turbo']
Model loading error in VLMEvalKit
error when i run inference code
Query about experiment replication (A800 training time)