deepseekmirror/DeepSeek-V3
1
0
Fork 0
mirror of https://github.com/deepseek-ai/DeepSeek-V3.git synced 2025-04-19 10:08:59 -04:00
Code Issues Actions 1 Packages Projects Releases Wiki Activity

improve docs gate bias

Browse Source
This commit is contained in:
Cerebrovinny 2025-02-05 13:38:29 +00:00
parent 1d7d440461
commit 426feee9f7
1 changed files with 1 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
inference/model.py
View File

@ -50,6 +50,7 @@ class ModelArgs:
beta_fast (int): Fast beta correction factor.
beta_slow (int): Slow beta correction factor.
mscale (float): Scaling factor for extended attention.
gate_bias_dim: Optional[int] = 7168 # Dimension threshold that determines if gate bias is used
"""
max_batch_size: int = 8
max_seq_len: int = 4096 * 4