Fix weight tying (#51665)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
This commit is contained in:
@@ -1082,8 +1082,5 @@ class KimiLinearForCausalLM(
|
||||
return self.logits_processor(self.lm_head, hidden_states)
|
||||
|
||||
def load_weights(self, weights: Iterable[tuple[str, torch.Tensor]]) -> set[str]:
|
||||
loader = AutoWeightsLoader(
|
||||
self,
|
||||
skip_prefixes=(["lm_head."] if self.config.tie_word_embeddings else None),
|
||||
)
|
||||
loader = AutoWeightsLoader(self)
|
||||
return loader.load_weights(weights)
|
||||
|
||||
@@ -1676,10 +1676,7 @@ class KimiLinearForCausalLM(
|
||||
return self.logits_processor(self.lm_head, hidden_states)
|
||||
|
||||
def load_weights(self, weights: Iterable[tuple[str, torch.Tensor]]) -> set[str]:
|
||||
loader = AutoWeightsLoader(
|
||||
self,
|
||||
skip_prefixes=(["lm_head."] if self.config.tie_word_embeddings else None),
|
||||
)
|
||||
loader = AutoWeightsLoader(self)
|
||||
loaded = loader.load_weights(weights)
|
||||
self.model.finalize_mega_moe_weights()
|
||||
# The fused MultiHeadLatentAttention's process_weights_after_loading
|
||||
|
||||
Reference in New Issue
Block a user