Closed a8nova closed 1 month ago
Thanks for reporting the issue! Yes as you mentioned, Phi-3 has an updated attention mechanism which is different from what the library provides as of today. Adding @hheydary to look into the issue (who is original author for the phi-2 example).
Greetings,
We just added a new field to the loader class attn_fused_qkv_proj. Please use that to load model parameters.
Thank you for the quick fix @haozha111 @hheydary
Description of the bug:
I wanted to convert phi3 to tflite, I started modifying phi2.py to apply the differences. In the Attention class of phi3, there is a combined projection layer self.qkv_proj = nn.Linear(self.hidden_size, op_size, bias=False).
I have defined the TENSOR_NAMES for phi3 just like in phi2.py, I am having an issue with ModelLoader class in loader.py where it has:
I can't seem to pass the combined self.qkv_proj to the loader class..
Thanks!
Actual vs expected behavior:
No response
Any other information you'd like to share?
No response