423A35C7/LLaMA-Factory
1
0
Fork 0
mirror of https://github.com/hiyouga/LLaMA-Factory.git synced 2025-08-24 23:02:49 +08:00
Code Issues Packages Projects Releases Wiki Activity

Add patch_mixtral_replace_moe_impl for full training Mitral using DeepSpeed Zero3.

Browse Source 
Signed-off-by: ldwang <ftgreat@gmail.com>

Former-commit-id: c284665425e8eefcea2d0dd1c835883e7ce18c97
This commit is contained in:
ldwang 2024-01-24 15:25:31 +08:00
parent db500a2bb6
commit 323ec3f89f
1 changed files with 1 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
src/llmtuner/model/patcher.py
View File

@ -269,6 +269,7 @@ def patch_config(
def patch_mixtral_replace_moe_impl() -> None:
import torch.nn.functional as F
def mlp_forward(self, hidden_states):
current_hidden_states = self.act_fn(self.w1(hidden_states)) * self.w3(hidden_states)
current_hidden_states = self.w2(current_hidden_states)