refactor : 将 config 对象直接传给 DecoderBlock,替代 16 个独立参数

- DecoderBlock.__init__ 改为 (config, layer_id),内部用 asdict
  展开字段给 AttnFactory/FFNFactory,factory 按 __init__ 签名自动过滤
- EncoderConfig 补充 attn_type 和 ffn_type 字段
- 314 个测试全部通过
This commit is contained in:
2026-06-19 14:15:33 +08:00
parent 7348bac6ab
commit b1adc40cfb
4 changed files with 11 additions and 63 deletions
+1 -13
View File
@@ -26,19 +26,7 @@ class EmbeddingEncoder(AutoModel):
self.embed_tokens = Embedding(config.vocab_size, config.dim)
self.layers = nn.ModuleList(
[
DecoderBlock(
config.dim,
config.n_heads,
config.dim_ffn,
config.n_kv_heads,
config.norm_eps,
config.use_qk_norm,
config.use_gated_attention,
layer_id,
)
for layer_id in range(config.n_layers)
]
[DecoderBlock(config, layer_id) for layer_id in range(config.n_layers)]
)
self.norm = RMSNorm(config.dim, config.norm_eps)