Run2 pytorch tensor ops
Robust PyTorch tensor operations for implementing loss functions, including handling device placement and numerical stability.From its SKILL.md
npx -y skills add cxcscmu/SkillLearnBench --skill run2_pytorch-tensor-opsAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
SKILL.md
0.5 KB, 83 tokens by cl100k_base, as published. Nobody here has run it
Tensor Operations
torch.gather: Useful for selecting specific log probabilities from logits:torch.gather(log_probs, dim=-1, index=labels.unsqueeze(-1)).squeeze(-1).F.logsigmoid: Stable computation oflog(sigmoid(x))..to(device): Ensure all input tensors and the trainer components are on the same device.
What ships with it
Read from the repository
Just SKILL.md. No reference files, no scripts.