Unverified Commit e584b85a authored by wang.yuqi's avatar wang.yuqi Committed by GitHub
Browse files

[Misc] duplicate code in deepseek_v2 (#14106)

parent 09e56f92
...@@ -105,7 +105,6 @@ class DeepseekV2MoE(nn.Module): ...@@ -105,7 +105,6 @@ class DeepseekV2MoE(nn.Module):
self.tp_size = get_tensor_model_parallel_world_size() self.tp_size = get_tensor_model_parallel_world_size()
self.routed_scaling_factor = config.routed_scaling_factor self.routed_scaling_factor = config.routed_scaling_factor
self.n_shared_experts = config.n_shared_experts self.n_shared_experts = config.n_shared_experts
self.routed_scaling_factor = config.routed_scaling_factor
if config.hidden_act != "silu": if config.hidden_act != "silu":
raise ValueError(f"Unsupported activation: {config.hidden_act}. " raise ValueError(f"Unsupported activation: {config.hidden_act}. "
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment