books/LLMs-from-scratch
1
0
Fork 0
mirror of https://github.com/rasbt/LLMs-from-scratch.git synced 2026-04-10 12:33:42 +00:00
Code Issues Packages Projects Releases Wiki Activity

cleanup

Browse Source
This commit is contained in:
rasbt
2024-04-04 07:58:41 -05:00
parent 2de60d1bfb
commit 6de0417321
3 changed files with 12 additions and 12 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
appendix-D/01_main-chapter-code/previous_chapters.py
View File

@@ -164,7 +164,7 @@ class TransformerBlock(nn.Module):
self.att = MultiHeadAttention(
d_in=cfg["emb_dim"],
d_out=cfg["emb_dim"],
context_length=cfg["ctx_len"],
context_length=cfg["context_length"],
num_heads=cfg["n_heads"],
dropout=cfg["drop_rate"],
qkv_bias=cfg["qkv_bias"])
@@ -195,7 +195,7 @@ class GPTModel(nn.Module):
def __init__(self, cfg):
super().__init__()
self.tok_emb = nn.Embedding(cfg["vocab_size"], cfg["emb_dim"])
self.pos_emb = nn.Embedding(cfg["ctx_len"], cfg["emb_dim"])
self.pos_emb = nn.Embedding(cfg["context_length"], cfg["emb_dim"])
self.drop_emb = nn.Dropout(cfg["drop_rate"])
self.trf_blocks = nn.Sequential(