diff --git a/appendix-A/02_installing-python-libraries/python_environment_check.py b/appendix-A/02_installing-python-libraries/python_environment_check.py
index 52f214f..e113fb8 100644
--- a/appendix-A/02_installing-python-libraries/python_environment_check.py
+++ b/appendix-A/02_installing-python-libraries/python_environment_check.py
@@ -25,9 +25,10 @@ def get_packages(pkgs):
                 except AttributeError:
                     try:
                         versions.append(imported.version_info)
-                    except:
+                    except AttributeError:
                         try:
-                            import importlib, importlib_metadata
+                            import importlib
+                            import importlib_metadata
                             imported = importlib.import_module(p)
                             version = importlib_metadata.version(p)
                             versions.append(version)
diff --git a/appendix-A/03_main-chapter-code/DDP-script.py b/appendix-A/03_main-chapter-code/DDP-script.py
index f8557d3..f93ed32 100644
--- a/appendix-A/03_main-chapter-code/DDP-script.py
+++ b/appendix-A/03_main-chapter-code/DDP-script.py
@@ -91,11 +91,11 @@ def prepare_dataset():
     train_loader = DataLoader(
         dataset=train_ds,
         batch_size=2,
-        shuffle=False, # NEW: False because of DistributedSampler below
+        shuffle=False,  # NEW: False because of DistributedSampler below
         pin_memory=True,
         drop_last=True,
         # NEW: chunk batches across GPUs without overlapping samples:
-        sampler=DistributedSampler(train_ds) # NEW
+        sampler=DistributedSampler(train_ds)  # NEW
     )
     test_loader = DataLoader(
         dataset=test_ds,
@@ -108,14 +108,14 @@ def prepare_dataset():
 # NEW: wrapper
 def main(rank, world_size, num_epochs):
 
-    ddp_setup(rank, world_size) # NEW: initialize process groups
+    ddp_setup(rank, world_size)  # NEW: initialize process groups
 
     train_loader, test_loader = prepare_dataset()
     model = NeuralNetwork(num_inputs=2, num_outputs=2)
     model.to(rank)
     optimizer = torch.optim.SGD(model.parameters(), lr=0.5)
 
-    model = DDP(model, device_ids=[rank]) # NEW: wrap model with DDP
+    model = DDP(model, device_ids=[rank])  # NEW: wrap model with DDP
     # the core model is now accessible as model.module
 
     for epoch in range(num_epochs):
@@ -123,15 +123,15 @@ def main(rank, world_size, num_epochs):
         model.train()
         for features, labels in train_loader:
 
-            features, labels = features.to(rank), labels.to(rank) # New: use rank
+            features, labels = features.to(rank), labels.to(rank)  # New: use rank
             logits = model(features)
-            loss = F.cross_entropy(logits, labels) # Loss function
+            loss = F.cross_entropy(logits, labels)  # Loss function
 
             optimizer.zero_grad()
             loss.backward()
             optimizer.step()
 
-            ### LOGGING
+            # LOGGING
             print(f"[GPU{rank}] Epoch: {epoch+1:03d}/{num_epochs:03d}"
                   f" | Batchsize {labels.shape[0]:03d}"
                   f" | Train/Val Loss: {loss:.2f}")
@@ -142,7 +142,7 @@ def main(rank, world_size, num_epochs):
     test_acc = compute_accuracy(model, test_loader, device=rank)
     print(f"[GPU{rank}] Test accuracy", test_acc)
 
-    destroy_process_group() # NEW: cleanly exit distributed mode
+    destroy_process_group()  # NEW: cleanly exit distributed mode
 
 
 def compute_accuracy(model, dataloader, device):
diff --git a/appendix-D/01_main-chapter-code/previous_chapters.py b/appendix-D/01_main-chapter-code/previous_chapters.py
index ba18f50..6297085 100644
--- a/appendix-D/01_main-chapter-code/previous_chapters.py
+++ b/appendix-D/01_main-chapter-code/previous_chapters.py
@@ -36,7 +36,7 @@ class GPTDatasetV1(Dataset):
         return self.input_ids[idx], self.target_ids[idx]
 
 
-def create_dataloader_v1(txt, batch_size=4, max_length=256, 
+def create_dataloader_v1(txt, batch_size=4, max_length=256,
                          stride=128, shuffle=True, drop_last=True):
     # Initialize the tokenizer
     tokenizer = tiktoken.get_encoding("gpt2")
@@ -80,7 +80,7 @@ class MultiHeadAttention(nn.Module):
 
         # We implicitly split the matrix by adding a `num_heads` dimension
         # Unroll last dim: (b, num_tokens, d_out) -> (b, num_tokens, num_heads, head_dim)
-        keys = keys.view(b, num_tokens, self.num_heads, self.head_dim) 
+        keys = keys.view(b, num_tokens, self.num_heads, self.head_dim)
         values = values.view(b, num_tokens, self.num_heads, self.head_dim)
         queries = queries.view(b, num_tokens, self.num_heads, self.head_dim)
 
@@ -102,7 +102,7 @@ class MultiHeadAttention(nn.Module):
         attn_weights = self.dropout(attn_weights)
 
         # Shape: (b, num_tokens, num_heads, head_dim)
-        context_vec = (attn_weights @ values).transpose(1, 2) 
+        context_vec = (attn_weights @ values).transpose(1, 2)
 
         # Combine heads, where self.d_out = self.num_heads * self.head_dim
         context_vec = context_vec.reshape(b, num_tokens, self.d_out)
@@ -135,7 +135,7 @@ class GELU(nn.Module):
 
     def forward(self, x):
         return 0.5 * x * (1 + torch.tanh(
-            torch.sqrt(torch.tensor(2.0 / torch.pi)) * 
+            torch.sqrt(torch.tensor(2.0 / torch.pi)) *
             (x + 0.044715 * torch.pow(x, 3))
         ))
 
@@ -161,7 +161,7 @@ class TransformerBlock(nn.Module):
             d_in=cfg["emb_dim"],
             d_out=cfg["emb_dim"],
             block_size=cfg["ctx_len"],
-            num_heads=cfg["n_heads"], 
+            num_heads=cfg["n_heads"],
             dropout=cfg["drop_rate"],
             qkv_bias=cfg["qkv_bias"])
         self.ff = FeedForward(cfg)
@@ -227,7 +227,7 @@ def generate_text_simple(model, idx, max_new_tokens, context_size):
 
         # Focus only on the last time step
         # (batch, n_token, vocab_size) becomes (batch, vocab_size)
-        logits = logits[:, -1, :]  
+        logits = logits[:, -1, :]
 
         # Get the idx of the vocab entry with the highest logits value
         idx_next = torch.argmax(logits, dim=-1, keepdim=True)  # (batch, 1)
@@ -315,4 +315,4 @@ def text_to_token_ids(text, tokenizer):
 
 def token_ids_to_text(token_ids, tokenizer):
     flat = token_ids.squeeze(0)  # remove batch dimension
-    return tokenizer.decode(flat.tolist())   
\ No newline at end of file
+    return tokenizer.decode(flat.tolist())
diff --git a/ch02/02_bonus_bytepair-encoder/bpe_openai_gpt2.py b/ch02/02_bonus_bytepair-encoder/bpe_openai_gpt2.py
index f3d9575..16e0ee2 100644
--- a/ch02/02_bonus_bytepair-encoder/bpe_openai_gpt2.py
+++ b/ch02/02_bonus_bytepair-encoder/bpe_openai_gpt2.py
@@ -1,39 +1,3 @@
-"""
-Byte pair encoding utilities
-
-Code from https://github.com/openai/gpt-2/blob/master/src/encoder.py
-
-And modified code (download_vocab) from
-https://github.com/openai/gpt-2/blob/master/download_model.py
-
-Modified MIT License
-
-Software Copyright (c) 2019 OpenAI
-
-We don’t claim ownership of the content you create with GPT-2, so it is yours to do with as you please.
-We only ask that you use GPT-2 responsibly and clearly indicate your content was created using GPT-2.
-
-Permission is hereby granted, free of charge, to any person obtaining a copy of this software and
-associated documentation files (the "Software"), to deal in the Software without restriction,
-including without limitation the rights to use, copy, modify, merge, publish, distribute, sublicense,
-and/or sell copies of the Software, and to permit persons to whom the Software is furnished to do so,
-subject to the following conditions:
-
-The above copyright notice and this permission notice shall be included
-in all copies or substantial portions of the Software.
-The above copyright notice and this permission notice need not be included
-with content created by the Software.
-
-THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED,
-INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
-FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
-BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT,
-TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE
-OR OTHER DEALINGS IN THE SOFTWARE.
-
-
-"""
-
 import os
 import json
 import regex as re
@@ -41,6 +5,7 @@ import requests
 from tqdm import tqdm
 from functools import lru_cache
 
+
 @lru_cache()
 def bytes_to_unicode():
     """
@@ -52,20 +17,21 @@ def bytes_to_unicode():
     To avoid that, we want lookup tables between utf-8 bytes and unicode strings.
     And avoids mapping to whitespace/control characters the bpe code barfs on.
     """
-    bs = list(range(ord("!"), ord("~")+1))+list(range(ord("¡"), ord("¬")+1))+list(range(ord("®"), ord("ÿ")+1))
+    bs = list(range(ord("!"), ord("~") + 1)) + list(range(ord("¡"), ord("¬") + 1)) + list(range(ord("®"), ord("ÿ") + 1))
     cs = bs[:]
     n = 0
     for b in range(2**8):
         if b not in bs:
             bs.append(b)
-            cs.append(2**8+n)
+            cs.append(2**8 + n)
             n += 1
     cs = [chr(n) for n in cs]
     return dict(zip(bs, cs))
 
-def get_pairs(word):
-    """Return set of symbol pairs in a word.
 
+def get_pairs(word):
+    """
+    Return set of symbol pairs in a word.
     Word is represented as tuple of symbols (symbols being variable-length strings).
     """
     pairs = set()
@@ -75,17 +41,18 @@ def get_pairs(word):
         prev_char = char
     return pairs
 
+
 class Encoder:
     def __init__(self, encoder, bpe_merges, errors='replace'):
         self.encoder = encoder
-        self.decoder = {v:k for k,v in self.encoder.items()}
-        self.errors = errors # how to handle errors in decoding
+        self.decoder = {v: k for k, v in self.encoder.items()}
+        self.errors = errors  # how to handle errors in decoding
         self.byte_encoder = bytes_to_unicode()
-        self.byte_decoder = {v:k for k, v in self.byte_encoder.items()}
+        self.byte_decoder = {v: k for k, v in self.byte_encoder.items()}
         self.bpe_ranks = dict(zip(bpe_merges, range(len(bpe_merges))))
         self.cache = {}
 
-        # Should haved added re.IGNORECASE so BPE merges can happen for capitalized versions of contractions
+        # Should have added re.IGNORECASE so BPE merges can happen for capitalized versions of contractions
         self.pat = re.compile(r"""'s|'t|'re|'ve|'m|'ll|'d| ?\p{L}+| ?\p{N}+| ?[^\s\p{L}\p{N}]+|\s+(?!\S)|\s+""")
 
     def bpe(self, token):
@@ -98,7 +65,7 @@ class Encoder:
             return token
 
         while True:
-            bigram = min(pairs, key = lambda pair: self.bpe_ranks.get(pair, float('inf')))
+            bigram = min(pairs, key=lambda pair: self.bpe_ranks.get(pair, float('inf')))
             if bigram not in self.bpe_ranks:
                 break
             first, second = bigram
@@ -109,12 +76,12 @@ class Encoder:
                     j = word.index(first, i)
                     new_word.extend(word[i:j])
                     i = j
-                except:
+                except ValueError:
                     new_word.extend(word[i:])
                     break
 
-                if word[i] == first and i < len(word)-1 and word[i+1] == second:
-                    new_word.append(first+second)
+                if word[i] == first and i < len(word) - 1 and word[i + 1] == second:
+                    new_word.append(first + second)
                     i += 2
                 else:
                     new_word.append(word[i])
@@ -141,16 +108,14 @@ class Encoder:
         text = bytearray([self.byte_decoder[c] for c in text]).decode('utf-8', errors=self.errors)
         return text
 
+
 def get_encoder(model_name, models_dir):
     with open(os.path.join(models_dir, model_name, 'encoder.json'), 'r') as f:
         encoder = json.load(f)
     with open(os.path.join(models_dir, model_name, 'vocab.bpe'), 'r', encoding="utf-8") as f:
         bpe_data = f.read()
     bpe_merges = [tuple(merge_str.split()) for merge_str in bpe_data.split('\n')[1:-1]]
-    return Encoder(
-        encoder=encoder,
-        bpe_merges=bpe_merges,
-    )
+    return Encoder(encoder=encoder, bpe_merges=bpe_merges)
 
 
 def download_vocab():
@@ -158,11 +123,10 @@ def download_vocab():
     subdir = 'gpt2_model'
     if not os.path.exists(subdir):
         os.makedirs(subdir)
-    subdir = subdir.replace('\\','/') # needed for Windows
+    subdir = subdir.replace('\\', '/')  # needed for Windows
 
     for filename in ['encoder.json', 'vocab.bpe']:
-
-        r = requests.get("https://openaipublic.blob.core.windows.net/gpt-2/models/117M" + "/" + filename, stream=True)
+        r = requests.get("https://openaipublic.blob.core.windows.net/gpt-2/models/117M/" + filename, stream=True)
 
         with open(os.path.join(subdir, filename), 'wb') as f:
             file_size = int(r.headers["content-length"])
diff --git a/ch03/02_bonus_efficient-multihead-attention/ch03.py b/ch03/02_bonus_efficient-multihead-attention/ch03.py
index 46e4bb2..1797fe3 100644
--- a/ch03/02_bonus_efficient-multihead-attention/ch03.py
+++ b/ch03/02_bonus_efficient-multihead-attention/ch03.py
@@ -8,33 +8,33 @@ class CausalAttention(nn.Module):
         super().__init__()
         self.d_out = d_out
         self.W_query = nn.Linear(d_in, d_out, bias=qkv_bias)
-        self.W_key   = nn.Linear(d_in, d_out, bias=qkv_bias)
+        self.W_key = nn.Linear(d_in, d_out, bias=qkv_bias)
         self.W_value = nn.Linear(d_in, d_out, bias=qkv_bias)
-        self.dropout = nn.Dropout(dropout) # New
-        self.register_buffer('mask', torch.triu(torch.ones(block_size, block_size), diagonal=1)) # New
+        self.dropout = nn.Dropout(dropout)  # New
+        self.register_buffer('mask', torch.triu(torch.ones(block_size, block_size), diagonal=1))  # New
 
     def forward(self, x):
-        b, num_tokens, d_in = x.shape # New batch dimension b
+        b, num_tokens, d_in = x.shape  # New batch dimension b
         keys = self.W_key(x)
         queries = self.W_query(x)
         values = self.W_value(x)
 
-        attn_scores = queries @ keys.transpose(1, 2) # Changed transpose
+        attn_scores = queries @ keys.transpose(1, 2)  # Changed transpose
         attn_scores.masked_fill_(  # New, _ ops are in-place
-            self.mask.bool()[:num_tokens, :num_tokens], -torch.inf) 
+            self.mask.bool()[:num_tokens, :num_tokens], -torch.inf)
         attn_weights = torch.softmax(attn_scores / keys.shape[-1]**0.5, dim=-1)
-        attn_weights = self.dropout(attn_weights) # New
+        attn_weights = self.dropout(attn_weights)  # New
 
         context_vec = attn_weights @ values
         return context_vec
-    
-    
+
+
 class MultiHeadAttentionWrapper(nn.Module):
 
     def __init__(self, d_in, d_out, block_size, dropout, num_heads, qkv_bias=False):
         super().__init__()
         self.heads = nn.ModuleList(
-            [CausalAttention(d_in, d_out, block_size, dropout, qkv_bias) 
+            [CausalAttention(d_in, d_out, block_size, dropout, qkv_bias)
              for _ in range(num_heads)]
         )
         self.out_proj = nn.Linear(d_out*num_heads, d_out*num_heads)
@@ -44,7 +44,6 @@ class MultiHeadAttentionWrapper(nn.Module):
         return self.out_proj(context_vec)
 
 
-
 class MultiHeadAttention(nn.Module):
     def __init__(self, d_in, d_out, block_size, dropout, num_heads, qkv_bias=False):
         super().__init__()
@@ -52,7 +51,7 @@ class MultiHeadAttention(nn.Module):
 
         self.d_out = d_out
         self.num_heads = num_heads
-        self.head_dim = d_out // num_heads # Reduce the projection dim to match desired output dim
+        self.head_dim = d_out // num_heads  # Reduce the projection dim to match desired output dim
 
         self.W_query = nn.Linear(d_in, d_out, bias=qkv_bias)
         self.W_key = nn.Linear(d_in, d_out, bias=qkv_bias)
@@ -70,7 +69,7 @@ class MultiHeadAttention(nn.Module):
 
         # We implicitly split the matrix by adding a `num_heads` dimension
         # Unroll last dim: (b, num_tokens, d_out) -> (b, num_tokens, num_heads, head_dim)
-        keys = keys.view(b, num_tokens, self.num_heads, self.head_dim) 
+        keys = keys.view(b, num_tokens, self.num_heads, self.head_dim)
         values = values.view(b, num_tokens, self.num_heads, self.head_dim)
         queries = queries.view(b, num_tokens, self.num_heads, self.head_dim)
 
@@ -92,10 +91,10 @@ class MultiHeadAttention(nn.Module):
         attn_weights = self.dropout(attn_weights)
 
         # Shape: (b, num_tokens, num_heads, head_dim)
-        context_vec = (attn_weights @ values).transpose(1, 2) 
+        context_vec = (attn_weights @ values).transpose(1, 2)
 
         # Combine heads, where self.d_out = self.num_heads * self.head_dim
         context_vec = context_vec.contiguous().view(b, num_tokens, self.d_out)
-        context_vec = self.out_proj(context_vec) # optional projection
+        context_vec = self.out_proj(context_vec)  # optional projection
 
-        return context_vec
\ No newline at end of file
+        return context_vec
diff --git a/ch04/01_main-chapter-code/gpt.py b/ch04/01_main-chapter-code/gpt.py
index 2c6ca71..33399b1 100644
--- a/ch04/01_main-chapter-code/gpt.py
+++ b/ch04/01_main-chapter-code/gpt.py
@@ -35,7 +35,7 @@ class GPTDatasetV1(Dataset):
         return self.input_ids[idx], self.target_ids[idx]
 
 
-def create_dataloader_v1(txt, batch_size=4, max_length=256, 
+def create_dataloader_v1(txt, batch_size=4, max_length=256,
                          stride=128, shuffle=True, drop_last=True):
     # Initialize the tokenizer
     tokenizer = tiktoken.get_encoding("gpt2")
@@ -78,7 +78,7 @@ class MultiHeadAttention(nn.Module):
 
         # We implicitly split the matrix by adding a `num_heads` dimension
         # Unroll last dim: (b, num_tokens, d_out) -> (b, num_tokens, num_heads, head_dim)
-        keys = keys.view(b, num_tokens, self.num_heads, self.head_dim) 
+        keys = keys.view(b, num_tokens, self.num_heads, self.head_dim)
         values = values.view(b, num_tokens, self.num_heads, self.head_dim)
         queries = queries.view(b, num_tokens, self.num_heads, self.head_dim)
 
@@ -100,7 +100,7 @@ class MultiHeadAttention(nn.Module):
         attn_weights = self.dropout(attn_weights)
 
         # Shape: (b, num_tokens, num_heads, head_dim)
-        context_vec = (attn_weights @ values).transpose(1, 2) 
+        context_vec = (attn_weights @ values).transpose(1, 2)
 
         # Combine heads, where self.d_out = self.num_heads * self.head_dim
         context_vec = context_vec.contiguous().view(b, num_tokens, self.d_out)
@@ -132,7 +132,7 @@ class GELU(nn.Module):
 
     def forward(self, x):
         return 0.5 * x * (1 + torch.tanh(
-            torch.sqrt(torch.tensor(2.0 / torch.pi)) * 
+            torch.sqrt(torch.tensor(2.0 / torch.pi)) *
             (x + 0.044715 * torch.pow(x, 3))
         ))
 
@@ -158,7 +158,7 @@ class TransformerBlock(nn.Module):
             d_in=cfg["emb_dim"],
             d_out=cfg["emb_dim"],
             block_size=cfg["ctx_len"],
-            num_heads=cfg["n_heads"], 
+            num_heads=cfg["n_heads"],
             dropout=cfg["drop_rate"],
             qkv_bias=cfg["qkv_bias"])
         self.ff = FeedForward(cfg)
@@ -224,7 +224,7 @@ def generate_text_simple(model, idx, max_new_tokens, context_size):
 
         # Focus only on the last time step
         # (batch, n_token, vocab_size) becomes (batch, vocab_size)
-        logits = logits[:, -1, :]  
+        logits = logits[:, -1, :]
 
         # Get the idx of the vocab entry with the highest logits value
         idx_next = torch.argmax(logits, dim=-1, keepdim=True)  # (batch, 1)
diff --git a/ch04/01_main-chapter-code/previous_chapters.py b/ch04/01_main-chapter-code/previous_chapters.py
index ec8c3c7..5e067a4 100644
--- a/ch04/01_main-chapter-code/previous_chapters.py
+++ b/ch04/01_main-chapter-code/previous_chapters.py
@@ -27,7 +27,7 @@ class GPTDatasetV1(Dataset):
         return self.input_ids[idx], self.target_ids[idx]
 
 
-def create_dataloader_v1(txt, batch_size=4, max_length=256, 
+def create_dataloader_v1(txt, batch_size=4, max_length=256,
                          stride=128, shuffle=True, drop_last=True):
     # Initialize the tokenizer
     tokenizer = tiktoken.get_encoding("gpt2")
@@ -49,7 +49,7 @@ class MultiHeadAttention(nn.Module):
 
         self.d_out = d_out
         self.num_heads = num_heads
-        self.head_dim = d_out // num_heads # Reduce the projection dim to match desired output dim
+        self.head_dim = d_out // num_heads  # Reduce the projection dim to match desired output dim
 
         self.W_query = nn.Linear(d_in, d_out, bias=qkv_bias)
         self.W_key = nn.Linear(d_in, d_out, bias=qkv_bias)
@@ -61,13 +61,13 @@ class MultiHeadAttention(nn.Module):
     def forward(self, x):
         b, num_tokens, d_in = x.shape
 
-        keys = self.W_key(x) # Shape: (b, num_tokens, d_out)
+        keys = self.W_key(x)  # Shape: (b, num_tokens, d_out)
         queries = self.W_query(x)
         values = self.W_value(x)
 
         # We implicitly split the matrix by adding a `num_heads` dimension
         # Unroll last dim: (b, num_tokens, d_out) -> (b, num_tokens, num_heads, head_dim)
-        keys = keys.view(b, num_tokens, self.num_heads, self.head_dim) 
+        keys = keys.view(b, num_tokens, self.num_heads, self.head_dim)
         values = values.view(b, num_tokens, self.num_heads, self.head_dim)
         queries = queries.view(b, num_tokens, self.num_heads, self.head_dim)
 
@@ -84,15 +84,15 @@ class MultiHeadAttention(nn.Module):
 
         # Use the mask to fill attention scores
         attn_scores.masked_fill_(mask_bool, -torch.inf)
-        
+
         attn_weights = torch.softmax(attn_scores / keys.shape[-1]**0.5, dim=-1)
         attn_weights = self.dropout(attn_weights)
 
         # Shape: (b, num_tokens, num_heads, head_dim)
-        context_vec = (attn_weights @ values).transpose(1, 2) 
-        
+        context_vec = (attn_weights @ values).transpose(1, 2)
+
         # Combine heads, where self.d_out = self.num_heads * self.head_dim
         context_vec = context_vec.contiguous().view(b, num_tokens, self.d_out)
-        context_vec = self.out_proj(context_vec) # optional projection
+        context_vec = self.out_proj(context_vec)  # optional projection
 
-        return context_vec
\ No newline at end of file
+        return context_vec
diff --git a/ch05/01_main-chapter-code/previous_chapters.py b/ch05/01_main-chapter-code/previous_chapters.py
index 610f6f4..996d0bb 100644
--- a/ch05/01_main-chapter-code/previous_chapters.py
+++ b/ch05/01_main-chapter-code/previous_chapters.py
@@ -100,7 +100,7 @@ class MultiHeadAttention(nn.Module):
         attn_weights = self.dropout(attn_weights)
 
         # Shape: (b, num_tokens, num_heads, head_dim)
-        context_vec = (attn_weights @ values).transpose(1, 2) 
+        context_vec = (attn_weights @ values).transpose(1, 2)
 
         # Combine heads, where self.d_out = self.num_heads * self.head_dim
         context_vec = context_vec.reshape(b, num_tokens, self.d_out)
@@ -132,7 +132,7 @@ class GELU(nn.Module):
 
     def forward(self, x):
         return 0.5 * x * (1 + torch.tanh(
-            torch.sqrt(torch.tensor(2.0 / torch.pi)) * 
+            torch.sqrt(torch.tensor(2.0 / torch.pi)) *
             (x + 0.044715 * torch.pow(x, 3))
         ))
 
@@ -158,7 +158,7 @@ class TransformerBlock(nn.Module):
             d_in=cfg["emb_dim"],
             d_out=cfg["emb_dim"],
             block_size=cfg["ctx_len"],
-            num_heads=cfg["n_heads"], 
+            num_heads=cfg["n_heads"],
             dropout=cfg["drop_rate"],
             qkv_bias=cfg["qkv_bias"])
         self.ff = FeedForward(cfg)
@@ -224,7 +224,7 @@ def generate_text_simple(model, idx, max_new_tokens, context_size):
 
         # Focus only on the last time step
         # (batch, n_token, vocab_size) becomes (batch, vocab_size)
-        logits = logits[:, -1, :]  
+        logits = logits[:, -1, :]
 
         # Get the idx of the vocab entry with the highest logits value
         idx_next = torch.argmax(logits, dim=-1, keepdim=True)  # (batch, 1)
diff --git a/ch05/02_bonus_hparam_tuning/hparam_search.py b/ch05/02_bonus_hparam_tuning/hparam_search.py
index 3e5ccfd..46199fd 100644
--- a/ch05/02_bonus_hparam_tuning/hparam_search.py
+++ b/ch05/02_bonus_hparam_tuning/hparam_search.py
@@ -159,7 +159,7 @@ if __name__ == "__main__":
                 stride=GPT_CONFIG_124M["ctx_len"],
                 drop_last=False,
                 shuffle=False
-                )
+            )
 
             model = GPTModel(GPT_CONFIG_124M)
             model.to(device)
@@ -199,4 +199,4 @@ if __name__ == "__main__":
     if not interrupted:
         print("Hyperparameter search completed.")
         print(f"Best hyperparameters: {best_hparams}")
-        print(f"Best Val loss: {best_val_loss} | Training loss {train_loss}")
\ No newline at end of file
+        print(f"Best Val loss: {best_val_loss} | Training loss {train_loss}")
diff --git a/ch05/02_bonus_hparam_tuning/previous_chapters.py b/ch05/02_bonus_hparam_tuning/previous_chapters.py
index 2c6ca71..33399b1 100644
--- a/ch05/02_bonus_hparam_tuning/previous_chapters.py
+++ b/ch05/02_bonus_hparam_tuning/previous_chapters.py
@@ -35,7 +35,7 @@ class GPTDatasetV1(Dataset):
         return self.input_ids[idx], self.target_ids[idx]
 
 
-def create_dataloader_v1(txt, batch_size=4, max_length=256, 
+def create_dataloader_v1(txt, batch_size=4, max_length=256,
                          stride=128, shuffle=True, drop_last=True):
     # Initialize the tokenizer
     tokenizer = tiktoken.get_encoding("gpt2")
@@ -78,7 +78,7 @@ class MultiHeadAttention(nn.Module):
 
         # We implicitly split the matrix by adding a `num_heads` dimension
         # Unroll last dim: (b, num_tokens, d_out) -> (b, num_tokens, num_heads, head_dim)
-        keys = keys.view(b, num_tokens, self.num_heads, self.head_dim) 
+        keys = keys.view(b, num_tokens, self.num_heads, self.head_dim)
         values = values.view(b, num_tokens, self.num_heads, self.head_dim)
         queries = queries.view(b, num_tokens, self.num_heads, self.head_dim)
 
@@ -100,7 +100,7 @@ class MultiHeadAttention(nn.Module):
         attn_weights = self.dropout(attn_weights)
 
         # Shape: (b, num_tokens, num_heads, head_dim)
-        context_vec = (attn_weights @ values).transpose(1, 2) 
+        context_vec = (attn_weights @ values).transpose(1, 2)
 
         # Combine heads, where self.d_out = self.num_heads * self.head_dim
         context_vec = context_vec.contiguous().view(b, num_tokens, self.d_out)
@@ -132,7 +132,7 @@ class GELU(nn.Module):
 
     def forward(self, x):
         return 0.5 * x * (1 + torch.tanh(
-            torch.sqrt(torch.tensor(2.0 / torch.pi)) * 
+            torch.sqrt(torch.tensor(2.0 / torch.pi)) *
             (x + 0.044715 * torch.pow(x, 3))
         ))
 
@@ -158,7 +158,7 @@ class TransformerBlock(nn.Module):
             d_in=cfg["emb_dim"],
             d_out=cfg["emb_dim"],
             block_size=cfg["ctx_len"],
-            num_heads=cfg["n_heads"], 
+            num_heads=cfg["n_heads"],
             dropout=cfg["drop_rate"],
             qkv_bias=cfg["qkv_bias"])
         self.ff = FeedForward(cfg)
@@ -224,7 +224,7 @@ def generate_text_simple(model, idx, max_new_tokens, context_size):
 
         # Focus only on the last time step
         # (batch, n_token, vocab_size) becomes (batch, vocab_size)
-        logits = logits[:, -1, :]  
+        logits = logits[:, -1, :]
 
         # Get the idx of the vocab entry with the highest logits value
         idx_next = torch.argmax(logits, dim=-1, keepdim=True)  # (batch, 1)
diff --git a/ch05/03_bonus_pretraining_on_gutenberg/prepare_dataset.py b/ch05/03_bonus_pretraining_on_gutenberg/prepare_dataset.py
index 5548b58..1503511 100644
--- a/ch05/03_bonus_pretraining_on_gutenberg/prepare_dataset.py
+++ b/ch05/03_bonus_pretraining_on_gutenberg/prepare_dataset.py
@@ -63,4 +63,4 @@ if __name__ == "__main__":
     target_dir = "path_to_your_large_files"
     print(f"{len(all_files)} files to process.")
 
-    combine_files(all_files, args.output_dir)
\ No newline at end of file
+    combine_files(all_files, args.output_dir)
diff --git a/ch05/03_bonus_pretraining_on_gutenberg/pretraining_simple.py b/ch05/03_bonus_pretraining_on_gutenberg/pretraining_simple.py
index d1763da..14a26f7 100644
--- a/ch05/03_bonus_pretraining_on_gutenberg/pretraining_simple.py
+++ b/ch05/03_bonus_pretraining_on_gutenberg/pretraining_simple.py
@@ -99,7 +99,7 @@ def train_model_simple(model, optimizer, device, n_epochs,
                     max_length=GPT_CONFIG_124M["ctx_len"],
                     stride=GPT_CONFIG_124M["ctx_len"]
                 )
-                print(f"Training ...")
+                print("Training ...")
                 model.train()
                 for input_batch, target_batch in train_loader:
                     optimizer.zero_grad()
diff --git a/ch05/03_bonus_pretraining_on_gutenberg/previous_chapters.py b/ch05/03_bonus_pretraining_on_gutenberg/previous_chapters.py
index 4641ba4..fbe05ee 100644
--- a/ch05/03_bonus_pretraining_on_gutenberg/previous_chapters.py
+++ b/ch05/03_bonus_pretraining_on_gutenberg/previous_chapters.py
@@ -9,11 +9,11 @@ from torch.utils.data import Dataset, DataLoader
 import matplotlib.pyplot as plt
 
 
-
 #####################################
 # Chapter 2
 #####################################
 
+
 class GPTDatasetV1(Dataset):
     def __init__(self, txt, tokenizer, max_length, stride):
         self.tokenizer = tokenizer
@@ -310,5 +310,3 @@ def text_to_token_ids(text, tokenizer):
 def token_ids_to_text(token_ids, tokenizer):
     flat = token_ids.squeeze(0)  # remove batch dimension
     return tokenizer.decode(flat.tolist())
-
-