SUMIN/HuggingFace_transformer
1
0
Fork 0
Code Issues Pull Requests Actions 7 Packages Projects Releases Wiki Activity

Attempt to fix head index

Browse Source
This commit is contained in:
LysandreJik
2019-08-27 15:56:59 -04:00
parent c85b5db61a
commit 0cd283522a
1 changed files with 3 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
pytorch_transformers/modeling_gpt2.py
View File

@@ -233,12 +233,14 @@ class Attention(nn.Module):
self.c_proj = Conv1D(n_state, nx) self.c_proj = Conv1D(n_state, nx)
self.attn_dropout = nn.Dropout(config.attn_pdrop) self.attn_dropout = nn.Dropout(config.attn_pdrop)
self.resid_dropout = nn.Dropout(config.resid_pdrop) self.resid_dropout = nn.Dropout(config.resid_pdrop)
self.pruned_heads = []
def prune_heads(self, heads): def prune_heads(self, heads):
if len(heads) == 0: if len(heads) == 0:
return return
mask = torch.ones(self.n_head, self.split_size // self.n_head) mask = torch.ones(self.n_head, self.split_size // self.n_head)
for head in heads: for head in heads:
head -= len(list(filter(lambda h: h < head, self.pruned_heads)))
mask[head] = 0 mask[head] = 0
mask = mask.view(-1).contiguous().eq(1) mask = mask.view(-1).contiguous().eq(1)
index = torch.arange(len(mask))[mask].long() index = torch.arange(len(mask))[mask].long()
@@ -249,6 +251,7 @@ class Attention(nn.Module):
# Update hyper params # Update hyper params
self.split_size = (self.split_size // self.n_head) * (self.n_head - len(heads)) self.split_size = (self.split_size // self.n_head) * (self.n_head - len(heads))
self.n_head = self.n_head - len(heads) self.n_head = self.n_head - len(heads)
self.pruned_heads.extend(heads)
def _attn(self, q, k, v, head_mask=None): def _attn(self, q, k, v, head_mask=None):
w = torch.matmul(q, k) w = torch.matmul(q, k)