Adding a child class of hf's rotary embedding to make hf generate work on multiple gpus. #1334
..
8ed199ed
adding comment
c468e13f
improving test
73213ca7
lint
2a3320c1
Merge branch 'main' into hf_rope_child_class
8116a8cc
dakinggg
approved these changes
on 2024-07-03
Update llmfoundry/models/mpt/modeling_mpt.py
c79b84bb
addressing comments
4afbb09b
Merge branch 'main' into hf_rope_child_class
82728576
Assignees
No one assigned
Login to write a write a comment.
Login via GitHub