[BUG] [DPO - Direct Policy Optimization][RuntimeError: mat1 and mat2 must have the same dtype, but got Long and Float]
vyomakesh09 opened this issue · comments
v.dundigalla commented
---------------------------------------------------------------------------
RuntimeError Traceback (most recent call last)
[<ipython-input-26-508a53a4cb02>](https://localhost:8080/#) in <cell line: 26>()
24
25 # Compute loss
---> 26 loss = dpo_model(preferred_seq, unpreferred_seq)
27 print(loss)
9 frames
[/usr/local/lib/python3.10/dist-packages/torch/nn/modules/linear.py](https://localhost:8080/#) in forward(self, input)
112
113 def forward(self, input: Tensor) -> Tensor:
--> 114 return F.linear(input, self.weight, self.bias)
115
116 def extra_repr(self) -> str:
RuntimeError: mat1 and mat2 must have the same dtype, but got Long and Float
Upvote & Fund
- We're using Polar.sh so you can upvote and help fund this issue.
- We receive the funding once the issue is completed & confirmed by you.
- Thank you in advance for helping prioritize & fund our backlog.
github-actions commented
Stale issue message