zhangyiss/mlx-examples
1
0
Fork 0
mirror of https://github.com/ml-explore/mlx-examples.git synced 2025-08-29 04:25:06 +08:00
Code Issues Actions Packages Projects Releases Wiki Activity

more clean ups

Browse Source
This commit is contained in:
Goekdeniz-Guelmez 2025-03-04 22:44:24 +01:00
parent d828bc0c2d
commit 230abad426
1 changed files with 5 additions and 9 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

12
llms/mlx_lm/models/olmoe.py
View File

@ -48,15 +48,11 @@ class Attention(nn.Module):
self.head_dim = head_dim = args.head_dim or args.hidden_size // n_heads
self.scale = head_dim**-0.5
if hasattr(args, "attention_bias"):
attention_bias = args.attention_bias
else:
attention_bias = False
self.q_proj = nn.Linear(dim, n_heads * head_dim, bias=attention_bias)
self.k_proj = nn.Linear(dim, n_kv_heads * head_dim, bias=attention_bias)
self.v_proj = nn.Linear(dim, n_kv_heads * head_dim, bias=attention_bias)
self.o_proj = nn.Linear(n_heads * head_dim, dim, bias=attention_bias)
self.q_proj = nn.Linear(dim, n_heads * head_dim, bias=args.attention_bias)
self.k_proj = nn.Linear(dim, n_kv_heads * head_dim, bias=args.attention_bias)
self.v_proj = nn.Linear(dim, n_kv_heads * head_dim, bias=args.attention_bias)
self.o_proj = nn.Linear(n_heads * head_dim, dim, bias=args.attention_bias)
self.rope = initialize_rope(
self.head_dim,