Ronglai Zuo

好像是sentence_transformers/pooling_utils.py

I also met with segmentation fault issue..

I met the same problem. It also seems that the token must be one-character.

> I've encountered your first problem when trying to follow the SMPLify-x example as well. The current [model_loader.py](https://github.com/nghorbani/human_body_prior/blob/0278cb45180992e4d39ba1a11601f5ecc53ee148/src/human_body_prior/tools/model_loader.py) file does indeed not contain a function load_vposer. What I did was...

I also met the same problem.

> @ChenFengYe I have another question, how long about the training time of stage1, stage2 and stage3? Same question

Thanks for your reply? Could you please also tell me the training time cost for different model variants, e.g., llama2/mistral

But the code comment out `condition = random.choice(['text', 'motion', 'supervised', 'supervised', 'supervised'])` and use `condition = random.choice([''supervised', 'supervised', 'supervised'])` instead. I am not sure whether this is a mistake. If...