deepseekmirror/DeepSeek-Math
1
0
Fork 0
mirror of https://github.com/deepseek-ai/DeepSeek-Math.git synced 2025-06-20 16:33:47 -04:00
Code Issues Actions Packages Projects Releases Wiki Activity

Add commented options for output attentions and hidden states in DeepSeekMathConfig

Browse Source
This commit is contained in:
jayeshthk 2025-06-19 17:46:50 +05:30
parent 735546a4f9
commit 2b3c49c9cb
1 changed files with 2 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
train/model.py
View File

@ -21,6 +21,8 @@ class DeepSeekMathConfig:
use_cache: bool = True
rope_scaling: Optional[dict] = None
tie_word_embeddings: bool = False
# output_attentions:bool=True
# output_hidden_states:int=12
class RMSNorm(nn.Module):
def __init__(self, hidden_size, eps=1e-6):