cocoon fde8f60a0d fix: use torch.topk instead of calling top_k parameter as function in sample_from_logits ...

In sample_from_logits(), the branch for sample_logits=False incorrectly
called 'top_k' as if it were a function (top_k(probs, k=1, dim=-1)),
but 'top_k' is an integer parameter in this scope. This raises:
  TypeError: 'int' object is not callable

Fix: replace with torch.topk(probs, k=1, dim=-1) which is the correct
PyTorch API for greedy (argmax) token selection.

Also fix a docstring typo in decode_s2(): 'torch.torch.Tensor' -> 'torch.Tensor'

Closes #231

2026-04-09 16:03:01 +00:00

..

__init__.py

initial

2025-07-01 10:57:41 +08:00

kronos.py

fix: use torch.topk instead of calling top_k parameter as function in sample_from_logits

2026-04-09 16:03:01 +00:00

module.py

Do not collect tokenizer metrics during inference

2025-10-29 12:04:43 -03:00