Error in model, scaling only q matrix not qK.T dot product (qk.T/sqrt(dim_per_head)) #357
Conversation
…(dim_per_head) As per Vaswani et al, 2017 p.4 Is torch.matmul(q, k.transpose(2, 3)) / math.sqrt(dim_per_head) not q / math.sqrt(dim_per_head) https://arxiv.org/pdf/1912.05372.pdf
|
Hi @BenoitDalFerro! Thank you for your pull request and welcome to our community. Action RequiredIn order to merge any pull request (code, docs, etc.), we require contributors to sign our Contributor License Agreement, and we don't seem to have one on file for you. ProcessIn order for us to review and merge your suggested changes, please sign at https://code.facebook.com/cla. If you are contributing on behalf of someone else (eg your employer), the individual CLA may not be sufficient and your employer may need to sign the corporate CLA. Once the CLA is signed, our tooling will perform checks and validations. Afterwards, the pull request will be tagged with If you have received this in error or have any questions, please contact us at cla@meta.com. Thanks! |
…t qk.T dot product (qk.T/sqrt(dim_per_head)) As per Vaswani et al, 2017 p.4 - https://arxiv.org/pdf/1912.05372.pdf Is torch.matmul(q, k.transpose(2, 3)) / math.sqrt(dim_per_head) not q / math.sqrt(dim_per_head) This effectively scales queries only and not the queries-keys dot product as should be Mentioned in - original facebookresearch/XLM#357 - dependent original FlauBERT getalp/Flaubert@6d17688 - dependent Huggingface FlauBERT huggingface#21627
facebook-github-bot
added
the
CLA Signed
|
Thank you for signing our Contributor License Agreement. We can now accept your code for this (and any) Meta Open Source project. Thanks! |
As per Vaswani et al, 2017 p.4
Is torch.matmul(q, k.transpose(2, 3)) / math.sqrt(dim_per_head) not q / math.sqrt(dim_per_head) https://arxiv.org/pdf/1912.05372.pdf