Check if cross entropy is applied correctly in all monkey patch functions #920
Description
🐛 Describe the bug
Some of them aren't patched to the correct object.
For example: InternVL doesn't have nn.CrossEntropy in its modeling file. The monkey patch should be applied to the loss_util file (See comment)
Liger-Kernel/src/liger_kernel/transformers/monkey_patch.py
Lines 2070 to 2072 in da6e705
Note that some monkey patch functions are outdated, so you may need to check them manually
p.s. we only need to support transformers>=4.49.0. bwd-test ci is targeting to 4.49.0.
Reproduce
No response
Versions
liger_kernel==da6e705