[Fix.] apply attention_value_scale.

modeling_mimo_v2_flash.py

@@ -330,6 +330,8 @@ class MiMoV2Attention(nn.Module):
         self.v_proj = nn.Linear(config.hidden_size, v_hidden_size, bias=self.attention_bias)
         self.o_proj = nn.Linear(o_hidden_size, config.hidden_size, bias=False)
 
+        self.v_scale = getattr(config, "attention_value_scale", None)
+
         self.attention_sink_bias = (
             torch.nn.Parameter(torch.empty(config.num_attention_heads), requires_grad=False)
             if (config.add_full_attention_sink_bias and not is_swa) or (config.add_swa_attention_sink_bias and is_swa)
@@ -353,6 +355,9 @@ class MiMoV2Attention(nn.Module):
         query_states = self.q_proj(hidden_states).view(qk_hidden_shape).transpose(1, 2)
         key_states = self.k_proj(hidden_states).view(qk_hidden_shape).transpose(1, 2)
         value_states = self.v_proj(hidden_states).view(v_hidden_shape).transpose(1, 2)
+        
+        if self.v_scale is not None:
+            value_states = value_states * self.v_scale
 
         cos, sin = position_embeddings