[Doc]: fix typos in various files (#24798)
Signed-off-by: Didier Durand <durand.didier@gmail.com>
This commit is contained in:
@@ -740,7 +740,7 @@ class MergedColumnParallelLinear(ColumnParallelLinear):
|
||||
"""
|
||||
Handle special case for models where MLP layers are already
|
||||
fused on disk. In this case, we have no shard id. This function
|
||||
determmines the shard id by splitting these layers and then calls
|
||||
determines the shard id by splitting these layers and then calls
|
||||
the weight loader using the shard id.
|
||||
|
||||
An example of a model with these fused layers:
|
||||
@@ -914,7 +914,7 @@ class QKVParallelLinear(ColumnParallelLinear):
|
||||
"""
|
||||
Handle special case for models where QKV layers are already
|
||||
fused on disk. In this case, we have no shard id. This function
|
||||
determmines the shard id by splitting these layers and then calls
|
||||
determines the shard id by splitting these layers and then calls
|
||||
the weight loader using the shard id.
|
||||
|
||||
An example of a model with these fused layers:
|
||||
|
||||
@@ -258,7 +258,7 @@ class VocabParallelEmbedding(CustomOp):
|
||||
|
||||
if params_dtype is None:
|
||||
params_dtype = torch.get_default_dtype()
|
||||
# Divide the weight matrix along the vocaburaly dimension.
|
||||
# Divide the weight matrix along the vocabulary dimension.
|
||||
self.num_added_embeddings = self.num_embeddings - self.org_vocab_size
|
||||
self.num_embeddings_per_partition = divide(self.num_embeddings_padded,
|
||||
self.tp_size)
|
||||
|
||||
Reference in New Issue
Block a user