app update

app.py

@@ -22,50 +22,6 @@ dropout = 0.0
 
 torch.manual_seed(1337)
 
-
-# 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
-
-# @torch.no_grad()
-# def estimate_loss():
-#     out = {}
-#     model.eval()
-#     for split in ['train', 'val']:
-#         losses = torch.zeros(eval_iters)
-#         for k in range(eval_iters):
-#             X, Y = get_batch(split)
-#             logits, loss = model(X, Y)
-#             losses[k] = loss.item()
-#         out[split] = losses.mean()
-#     model.train()
-#     return out
-
 class Head(nn.Module):
     """ one head of self-attention """
 
@@ -138,7 +94,6 @@ class Block(nn.Module):
         x = x + self.ffwd(self.ln2(x))
         return x
 
-# super simple bigram model
 # super simple bigram model
 class BigramLanguageModel(nn.Module):
     def __init__(self, dataset_text, n_embd):
@@ -256,13 +211,16 @@ def generate_wikipedia_outputs(prompt=None, max_new_tokens=2000):
     
 
 title = "Nano GPT"
-description = "Nano GPT trained on Shakespeare and Wikipedia datasets. It is trained on a very small amount of data to understand how GPT's are trained and built. <a href='https://github.com/karpathy/nanoGPT'>The implementation can be found here </a>"
+
+description1 = "Nano GPT trained on Shakespeare dataset. It is trained on a very small amount of data to understand how GPT's are trained and built. The implementation can be found <a href='https://github.com/karpathy/nanoGPT'>here.</a>"
 
 shakespeare_interface = gr.Interface(generate_shakespeare_outputs,
                     inputs=[gr.Textbox(label="Enter any prompt ", type="text", value="Once upon a time,"),
                             gr.Slider(minimum=100, maximum=5000, step=100, value=2000, label="Max new tokens")],
                     outputs=gr.Textbox(label="Output generated", type="text"), description=description)
 
+description2 = "Nano GPT trained on Wikipedia dataset. It is trained on a very small amount of data to understand how GPT's are trained and built. The implementation can be found <a href='https://github.com/karpathy/nanoGPT'>here.</a>"
+
 wiki_interface = gr.Interface(generate_wikipedia_outputs,
                     inputs=[gr.Textbox(label="Enter any prompt ", type="text", value="James Bond"),
                             gr.Slider(minimum=100, maximum=5000, step=100, value=2000, label="Max new tokens")],