egSat

For API I had to manually insert in completions.py the fields: 'skip_special_tokens': False, 'custom_stopping_strings': '""' as the other side doesnt insert those fields. I think the API should complete the...

Hi all, It's not working for me either, but just using the train.py without the -m torch.distributed.launch does. I don't know if the -m torch.distributed.launch makes the paralelism better though

Hi, have anyone tried this? It should improve tracking results As I understands from the question, it should be: new_covariance = covariance - np.linalg.multi_dot(( kalman_gain, projected_cov, covariance ))