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

Rename drop_resid to drop_shortcut (#136)

Browse Source
This commit is contained in:
Sebastian Raschka
2024-04-28 14:31:27 -05:00
committed by GitHub
parent 70cd174091
commit 97ed38116a
10 changed files with 37 additions and 37 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
ch05/01_main-chapter-code/exercise-solutions.ipynb
View File

@@ -519,7 +519,7 @@
"train_losses, val_losses, tokens_seen = train_model_simple(\n",
" model, train_loader, val_loader, optimizer, device,\n",
" num_epochs=num_epochs, eval_freq=5, eval_iter=5,\n",
" start_context=\"Every effort moves you\",\n",
" start_context=\"Every effort moves you\", tokenizer=tokenizer\n",
")"
]
},
@@ -605,7 +605,7 @@
"text": [
"File already exists and is up-to-date: gpt2/124M/checkpoint\n",
"File already exists and is up-to-date: gpt2/124M/encoder.json\n",
"File already exists and is up-to-date: gpt2/124M/settings.json\n",
"File already exists and is up-to-date: gpt2/124M/hparams.json\n",
"File already exists and is up-to-date: gpt2/124M/model.ckpt.data-00000-of-00001\n",
"File already exists and is up-to-date: gpt2/124M/model.ckpt.index\n",
"File already exists and is up-to-date: gpt2/124M/model.ckpt.meta\n",
@@ -760,7 +760,7 @@
"text": [
"File already exists and is up-to-date: gpt2/1558M/checkpoint\n",
"File already exists and is up-to-date: gpt2/1558M/encoder.json\n",
"File already exists and is up-to-date: gpt2/1558M/settings.json\n",
"File already exists and is up-to-date: gpt2/1558M/hparams.json\n",
"File already exists and is up-to-date: gpt2/1558M/model.ckpt.data-00000-of-00001\n",
"File already exists and is up-to-date: gpt2/1558M/model.ckpt.index\n",
"File already exists and is up-to-date: gpt2/1558M/model.ckpt.meta\n",
@@ -859,7 +859,7 @@
"text": [
"File already exists and is up-to-date: gpt2/1558M/checkpoint\n",
"File already exists and is up-to-date: gpt2/1558M/encoder.json\n",
"File already exists and is up-to-date: gpt2/1558M/settings.json\n",
"File already exists and is up-to-date: gpt2/1558M/hparams.json\n",
"File already exists and is up-to-date: gpt2/1558M/model.ckpt.data-00000-of-00001\n",
"File already exists and is up-to-date: gpt2/1558M/model.ckpt.index\n",
"File already exists and is up-to-date: gpt2/1558M/model.ckpt.meta\n",

6
ch05/01_main-chapter-code/previous_chapters.py
View File

@@ -167,21 +167,21 @@ class TransformerBlock(nn.Module):
self.ff = FeedForward(cfg)
self.norm1 = LayerNorm(cfg["emb_dim"])
self.norm2 = LayerNorm(cfg["emb_dim"])
self.drop_resid = nn.Dropout(cfg["drop_rate"])
self.drop_shortcut = nn.Dropout(cfg["drop_rate"])
def forward(self, x):
# Shortcut connection for attention block
shortcut = x
x = self.norm1(x)
x = self.att(x) # Shape [batch_size, num_tokens, emb_size]
x = self.drop_resid(x)
x = self.drop_shortcut(x)
x = x + shortcut # Add the original input back
# Shortcut connection for feed-forward block
shortcut = x
x = self.norm2(x)
x = self.ff(x)
x = self.drop_resid(x)
x = self.drop_shortcut(x)
x = x + shortcut # Add the original input back
return x

6
ch05/02_alternative_weight_loading/previous_chapters.py
View File

@@ -167,21 +167,21 @@ class TransformerBlock(nn.Module):
self.ff = FeedForward(cfg)
self.norm1 = LayerNorm(cfg["emb_dim"])
self.norm2 = LayerNorm(cfg["emb_dim"])
self.drop_resid = nn.Dropout(cfg["drop_rate"])
self.drop_shortcut = nn.Dropout(cfg["drop_rate"])
def forward(self, x):
# Shortcut connection for attention block
shortcut = x
x = self.norm1(x)
x = self.att(x) # Shape [batch_size, num_tokens, emb_size]
x = self.drop_resid(x)
x = self.drop_shortcut(x)
x = x + shortcut # Add the original input back
# Shortcut connection for feed-forward block
shortcut = x
x = self.norm2(x)
x = self.ff(x)
x = self.drop_resid(x)
x = self.drop_shortcut(x)
x = x + shortcut # Add the original input back
return x

6
ch05/03_bonus_pretraining_on_gutenberg/previous_chapters.py
View File

@@ -164,21 +164,21 @@ class TransformerBlock(nn.Module):
self.ff = FeedForward(cfg)
self.norm1 = LayerNorm(cfg["emb_dim"])
self.norm2 = LayerNorm(cfg["emb_dim"])
self.drop_resid = nn.Dropout(cfg["drop_rate"])
self.drop_shortcut = nn.Dropout(cfg["drop_rate"])
def forward(self, x):
# Shortcut connection for attention block
shortcut = x
x = self.norm1(x)
x = self.att(x) # Shape [batch_size, num_tokens, emb_size]
x = self.drop_resid(x)
x = self.drop_shortcut(x)
x = x + shortcut # Add the original input back
# Shortcut connection for feed-forward block
shortcut = x
x = self.norm2(x)
x = self.ff(x)
x = self.drop_resid(x)
x = self.drop_shortcut(x)
x = x + shortcut # Add the original input back
return x

6
ch05/05_bonus_hparam_tuning/previous_chapters.py
View File

@@ -167,21 +167,21 @@ class TransformerBlock(nn.Module):
self.ff = FeedForward(cfg)
self.norm1 = LayerNorm(cfg["emb_dim"])
self.norm2 = LayerNorm(cfg["emb_dim"])
self.drop_resid = nn.Dropout(cfg["drop_rate"])
self.drop_shortcut = nn.Dropout(cfg["drop_rate"])
def forward(self, x):
# Shortcut connection for attention block
shortcut = x
x = self.norm1(x)
x = self.att(x) # Shape [batch_size, num_tokens, emb_size]
x = self.drop_resid(x)
x = self.drop_shortcut(x)
x = x + shortcut # Add the original input back
# Shortcut connection for feed-forward block
shortcut = x
x = self.norm2(x)
x = self.ff(x)
x = self.drop_resid(x)
x = self.drop_shortcut(x)
x = x + shortcut # Add the original input back
return x