feat : NEFTune 噪声注入 + label_smoothing 默认值修正

- Embedding.forward 训练时注入 randn 噪声，缩放系数 neftune_noise_alpha / sqrt(seq_len)
- TrainConfig.neftune_alpha 通过 config 传递（默认 0=关闭）
- TrainContextBuilder 将 config.neftune_alpha 写入 embed_tokens
- --neftune_alpha CLI 参数（典型值 5.0）
- label_smoothing 默认值 0.05 -> 0.0

astrai/model/components/embedding.py

@@ -1,3 +1,5 @@
+import math
+
 import torch
 import torch.nn as nn
 import torch.nn.functional as F
@@ -8,9 +10,14 @@ class Embedding(nn.Module):
     def __init__(self, vocab_size: int, embedding_dim: int):
         super().__init__()
         self.weight = nn.Parameter(torch.empty((vocab_size, embedding_dim)))
+        self.neftune_noise_alpha = 0.0
 
     def reset_parameters(self):
         nn.init.normal_(self.weight, mean=0.0, std=0.02)
 
     def forward(self, x: Tensor) -> Tensor:
-        return F.embedding(x, self.weight)
+        out = F.embedding(x, self.weight)
+        if self.training and self.neftune_noise_alpha > 0.0:
+            eps = self.neftune_noise_alpha / math.sqrt(out.size(1))
+            out = out + eps * torch.randn_like(out)
+        return out