jeans/ollama
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

use silu

Browse Source
This commit is contained in:
Michael Yang 2025-05-01 12:49:02 -07:00 committed by Bruce MacDonald
parent f1257a7de4
commit 150c499cae
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
model/models/qwen25vl/model_vision.go
View File

@ -108,7 +108,7 @@ func (mlp *VisionMLP) Forward(ctx ml.Context, hiddenStates ml.Tensor, opts *Visi
// Using activation as specified in config (likely GELU or SiLU/Swish) // Using activation as specified in config (likely GELU or SiLU/Swish)
gateOutput := mlp.Gate.Forward(ctx, hiddenStates) gateOutput := mlp.Gate.Forward(ctx, hiddenStates)
upOutput := mlp.Up.Forward(ctx, hiddenStates) upOutput := mlp.Up.Forward(ctx, hiddenStates)
hiddenStates = gateOutput.GELU(ctx).Mul(ctx, upOutput) hiddenStates = gateOutput.SILU(ctx).Mul(ctx, upOutput)
return mlp.Down.Forward(ctx, hiddenStates) return mlp.Down.Forward(ctx, hiddenStates)
} }