[Bugfix] Fix LFM2 ShortConv prefix breaking quant ignore list (#51495)
Signed-off-by: ylsun <1654366371@qq.com> Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
This commit is contained in:
@@ -258,7 +258,7 @@ class Lfm2ShortConvDecoderLayer(nn.Module):
|
||||
model_config=model_config,
|
||||
cache_config=cache_config,
|
||||
quant_config=quant_config,
|
||||
prefix=f"{prefix}.conv",
|
||||
prefix=f"{prefix}.short_conv",
|
||||
)
|
||||
|
||||
self.feed_forward = Lfm2MLP(
|
||||
|
||||
@@ -354,7 +354,7 @@ class Lfm2MoeShortConvDecoderLayer(nn.Module):
|
||||
model_config=model_config,
|
||||
cache_config=cache_config,
|
||||
quant_config=quant_config,
|
||||
prefix=f"{prefix}.conv",
|
||||
prefix=f"{prefix}.short_conv",
|
||||
)
|
||||
|
||||
if layer_idx < config.num_dense_layers:
|
||||
|
||||
Reference in New Issue
Block a user