zhangyiss/mlx-examples
1
0
Fork 0
mirror of https://github.com/ml-explore/mlx-examples.git synced 2025-06-26 10:41:18 +08:00
Code Issues Actions Packages Projects Releases Wiki Activity

nits

Browse Source
This commit is contained in:
Goekdeniz-Guelmez 2024-12-10 18:15:12 +01:00
parent 9f8a6a3509
commit b10afe3662
1 changed files with 4 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

7
llms/mlx_lm/models/mamba2.py
View File

@ -57,11 +57,12 @@ class MambaRMSNormGated(nn.Module):
variance = mx.mean(hidden_states ** 2, axis=-1, keepdims=True)
hidden_states = hidden_states * mx.rsqrt(variance + self.variance_epsilon)
return self.weight * hidden_states
def silu(x):
return x * mx.sigmoid(x)
def ssd(x, A, B, C, chunk_size):
batch, seqlen, nheads, dim = x.shape
B = mx.expand_dims(B, axis=2)
@ -87,7 +88,7 @@ def ssd(x, A, B, C, chunk_size):
outputs.append(y)
return mx.concatenate(outputs, axis=1), state
class DepthWiseConv1d(nn.Module):
def __init__(self, channels, kernel_size, bias=True, padding=0):
@ -175,7 +176,7 @@ class Mamba2Block(nn.Module):
# Calculate split indices and slice tensors
z = proj[..., :self.d_inner]
x_conv = proj[..., self.d_inner:self.d_inner + (self.d_inner + 2 * self.d_state)]
x_conv = proj[..., self.d_inner:self.d_inner + (self.d_inner + 2 * self.n_groups * self.d_state)]
dt = proj[..., -self.n_heads:]
# Process time steps