Skip to content
Open
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 2 additions & 2 deletions deepseek_vl2/models/configuration_deepseek.py
Original file line number Diff line number Diff line change
Expand Up @@ -34,7 +34,7 @@ class DeepseekV2Config(PretrainedConfig):
Number of routed experts, None means dense model.
routed_scaling_factor (`float`, *optional*, defaults to 1.0):
Scaling factor or routed experts.
topk_method (`str`, *optional*, defaults to `gready`):
topk_method (`str`, *optional*, defaults to `greedy`):
Topk method used in routed gate.
n_group (`int`, *optional*, defaults to None):
Number of groups for routed experts.
Expand Down Expand Up @@ -132,7 +132,7 @@ def __init__(
qk_rope_head_dim = 64,
v_head_dim = 128,
qk_nope_head_dim = 128,
topk_method = 'gready',
topk_method = 'greedy',
n_group = None,
topk_group = None,
num_experts_per_tok = None,
Expand Down