Update model.py

model.py

@@ -10,6 +10,54 @@ import torch
 import torch.nn as nn
 from torch.nn import functional as F
 
+
+
+# hyperparameters
+batch_size = 16 # how many independent sequences will we process in parallel?
+block_size = 32 # what is the maximum context length for predictions?
+max_iters = 5000
+eval_interval = 100
+learning_rate = 1e-3
+device = 'cuda' if torch.cuda.is_available() else 'cpu'
+eval_iters = 200
+n_embd = 64
+n_head = 4
+n_layer = 4
+dropout = 0.0
+# ------------
+
+torch.manual_seed(1337)
+
+# wget https://raw.githubusercontent.com/karpathy/char-rnn/master/data/tinyshakespeare/input.txt
+with open('input.txt', 'r', encoding='utf-8') as f:
+    text = f.read()
+
+# here are all the unique characters that occur in this text
+chars = sorted(list(set(text)))
+vocab_size = len(chars)
+# create a mapping from characters to integers
+stoi = { ch:i for i,ch in enumerate(chars) }
+itos = { i:ch for i,ch in enumerate(chars) }
+encode = lambda s: [stoi[c] for c in s] # encoder: take a string, output a list of integers
+decode = lambda l: ''.join([itos[i] for i in l]) # decoder: take a list of integers, output a string
+
+# Train and test splits
+data = torch.tensor(encode(text), dtype=torch.long)
+n = int(0.9*len(data)) # first 90% will be train, rest val
+train_data = data[:n]
+val_data = data[n:]
+
+# data loading
+def get_batch(split):
+    # generate a small batch of data of inputs x and targets y
+    data = train_data if split == 'train' else val_data
+    ix = torch.randint(len(data) - block_size, (batch_size,))
+    x = torch.stack([data[i:i+block_size] for i in ix])
+    y = torch.stack([data[i+1:i+block_size+1] for i in ix])
+    x, y = x.to(device), y.to(device)
+    return x, y
+
+
 class LayerNorm(nn.Module):
     """ LayerNorm but with an optional bias. PyTorch doesn't support simply bias=False """