riaz.somc/transformers
1
0
Fork 0
mirror of https://github.com/huggingface/transformers.git synced 2025-08-02 11:11:05 +06:00
Code Issues Actions 3 Packages Projects Releases Wiki Activity

Make GPT2 traceable in meta state (#28054)

Browse Source 
* Put device in tensor constructor instead of to()

* Fix copy
This commit is contained in:
Ke Wen 2023-12-15 09:45:31 -05:00 committed by GitHub
parent e2b6df7971
commit 74cae670ce
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
2 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
src/transformers/models/decision_transformer/modeling_decision_transformer.py
View File

@ -185,7 +185,7 @@ class DecisionTransformerGPT2Attention(nn.Module):
mask_value = torch.finfo(attn_weights.dtype).min
# Need to be a tensor, otherwise we get error: `RuntimeError: expected scalar type float but found double`.
# Need to be on the same device, otherwise `RuntimeError: ..., x and y to be on the same device`
mask_value = torch.full([], mask_value, dtype=attn_weights.dtype).to(attn_weights.device)
mask_value = torch.full([], mask_value, dtype=attn_weights.dtype, device=attn_weights.device)
attn_weights = torch.where(causal_mask, attn_weights.to(attn_weights.dtype), mask_value)
if attention_mask is not None:

2
src/transformers/models/gpt2/modeling_gpt2.py
View File

@ -198,7 +198,7 @@ class GPT2Attention(nn.Module):
mask_value = torch.finfo(attn_weights.dtype).min
# Need to be a tensor, otherwise we get error: `RuntimeError: expected scalar type float but found double`.
# Need to be on the same device, otherwise `RuntimeError: ..., x and y to be on the same device`
mask_value = torch.full([], mask_value, dtype=attn_weights.dtype).to(attn_weights.device)
mask_value = torch.full([], mask_value, dtype=attn_weights.dtype, device=attn_weights.device)
attn_weights = torch.where(causal_mask, attn_weights.to(attn_weights.dtype), mask_value)
if attention_mask is not None: