Make quote style consistent (#891)

ch06/03_bonus_imdb-classification/previous_chapters.py

@@ -73,7 +73,7 @@ class MultiHeadAttention(nn.Module):
         self.W_value = nn.Linear(d_in, d_out, bias=qkv_bias)
         self.out_proj = nn.Linear(d_out, d_out)  # Linear layer to combine head outputs
         self.dropout = nn.Dropout(dropout)
-        self.register_buffer('mask', torch.triu(torch.ones(context_length, context_length), diagonal=1))
+        self.register_buffer("mask", torch.triu(torch.ones(context_length, context_length), diagonal=1))
 
     def forward(self, x):
         b, num_tokens, d_in = x.shape
@@ -250,8 +250,8 @@ def assign(left, right):
 
 
 def load_weights_into_gpt(gpt, params):
-    gpt.pos_emb.weight = assign(gpt.pos_emb.weight, params['wpe'])
-    gpt.tok_emb.weight = assign(gpt.tok_emb.weight, params['wte'])
+    gpt.pos_emb.weight = assign(gpt.pos_emb.weight, params["wpe"])
+    gpt.tok_emb.weight = assign(gpt.tok_emb.weight, params["wte"])
 
     for b in range(len(params["blocks"])):
         q_w, k_w, v_w = np.split(
@@ -311,7 +311,7 @@ def load_weights_into_gpt(gpt, params):
 
 
 def text_to_token_ids(text, tokenizer):
-    encoded = tokenizer.encode(text, allowed_special={'<|endoftext|>'})
+    encoded = tokenizer.encode(text, allowed_special={"<|endoftext|>"})
     encoded_tensor = torch.tensor(encoded).unsqueeze(0)  # add batch dimension
     return encoded_tensor
 

ch06/03_bonus_imdb-classification/train_gpt.py

@@ -261,7 +261,7 @@ if __name__ == "__main__":
     )
     parser.add_argument(
         "--average_embeddings",
-        action='store_true',
+        action="store_true",
         default=False,
         help=(
             "Average the output embeddings from all tokens instead of using"