fz-mirrors/Build-A-Large-Language-Model-CN
1
0
Fork 0
mirror of https://github.com/skindhu/Build-A-Large-Language-Model-CN.git synced 2026-07-29 15:20:24 +08:00
Code Issues Packages Projects Releases Wiki Activity

add fourth chapter

Browse Source
This commit is contained in:
skindhu
2024-11-05 17:39:46 +08:00
parent 714913637b
commit be238a37c5
2 changed files with 36 additions and 36 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
cn-Book/4.从零开始实现一个用于文本生成的 GPT 模型.md
View File

@@ -89,10 +89,10 @@ class DummyGPTModel(nn.Module):
self.pos_emb = nn.Embedding(cfg["context_length"], cfg["emb_dim"])
self.drop_emb = nn.Dropout(cfg["drop_rate"])
self.trf_blocks = nn.Sequential(
*[DummyTransformerBlock(cfg) for _ in range(cfg["n_layers"])]) #A
*[DummyTransformerBlock(cfg) for _ in range(cfg["n_layers"])]) #A
self.final_norm = DummyLayerNorm(cfg["emb_dim"]) #B
self.out_head = nn.Linear(
cfg["emb_dim"], cfg["vocab_size"], bias=False
cfg["emb_dim"], cfg["vocab_size"], bias=False
)
def forward(self, in_idx):