Update app.py

app.py

@@ -13,7 +13,7 @@ df = pd.read_csv(url)
 
 # Tokenizer
 class ScratchTokenizer:
-    def _init_(self):
+    def __init__(self):
         self.word2idx = {"<PAD>": 0, "<SOS>": 1, "<EOS>": 2, "<UNK>": 3}
         self.idx2word = {0: "<PAD>", 1: "<SOS>", 2: "<EOS>", 3: "<UNK>"}
         self.vocab_size = 4
@@ -43,7 +43,7 @@ tokenizer.build_vocab(train_data["instruction"].tolist() + train_data["response"
 
 # Dataset Class
 class TextDataset(Dataset):
-    def _init_(self, data, tokenizer, max_len=200):
+    def __init__(self, data, tokenizer, max_len=200):
         self.data = data
         self.tokenizer = tokenizer
         self.max_len = max_len
@@ -60,7 +60,7 @@ class TextDataset(Dataset):
 
 # Model
 class GPTModel(nn.Module):
-    def _init_(self, vocab_size, embed_size=256, num_heads=8, num_layers=6, max_len=200):
+    def __init__(self, vocab_size, embed_size=256, num_heads=8, num_layers=6, max_len=200):
         super(GPTModel, self)._init_()
         self.embedding = nn.Embedding(vocab_size, embed_size)
         self.pos_embedding = nn.Parameter(torch.randn(1, max_len, embed_size))
@@ -136,7 +136,7 @@ df = pd.read_csv(url)
 
 # Tokenizer
 class ScratchTokenizer:
-    def _init_(self):
+    def __init__(self):
         self.word2idx = {"<PAD>": 0, "<SOS>": 1, "<EOS>": 2, "<UNK>": 3}
         self.idx2word = {0: "<PAD>", 1: "<SOS>", 2: "<EOS>", 3: "<UNK>"}
         self.vocab_size = 4
@@ -166,7 +166,7 @@ tokenizer.build_vocab(train_data["instruction"].tolist() + train_data["response"
 
 # Dataset Class
 class TextDataset(Dataset):
-    def _init_(self, data, tokenizer, max_len=200):
+    def __init__(self, data, tokenizer, max_len=200):
         self.data = data
         self.tokenizer = tokenizer
         self.max_len = max_len
@@ -183,7 +183,7 @@ class TextDataset(Dataset):
 
 # Model
 class GPTModel(nn.Module):
-    def _init_(self, vocab_size, embed_size=256, num_heads=8, num_layers=6, max_len=200):
+    def __init__(self, vocab_size, embed_size=256, num_heads=8, num_layers=6, max_len=200):
         super(GPTModel, self)._init_()
         self.embedding = nn.Embedding(vocab_size, embed_size)
         self.pos_embedding = nn.Parameter(torch.randn(1, max_len, embed_size))