Spaces:

nkanungo
/

tinygpt

Runtime error

App Files Files Community

nkanungo commited on Oct 27, 2023

Commit

4581574

1 Parent(s): cc1a589

Upload 4 files

Browse files

Files changed (4) hide show

app.py +127 -0
nano_gpt_inferencing.py +197 -0
nano_gpt_model.pth +3 -0
requirements.txt +2 -0

app.py ADDED Viewed

	@@ -0,0 +1,127 @@

+#!/usr/bin/env python
+# coding: utf-8
+# In[2]:
+import gradio as gr
+import torch
+from torch import nn
+from torch.nn import functional as F
+from nano_gpt_inferencing import generate_paragraph
+HTML_TEMPLATE = """
+     <style>
+        body {
+            font-family: 'Arial', sans-serif;
+            background: #3498db; /* Blue background color */
+            margin: 0;
+            padding: 0;
+        }
+        #app-header {
+            text-align: center;
+            background: rgba(255, 255, 255, 0.7); /* Semi-transparent white */
+            padding: 20px;
+            border-radius: 10px;
+            box-shadow: 0 4px 6px rgba(0, 0, 0, 0.1);
+            position: relative; /* To position the artifacts */
+            margin: 30px auto;
+            max-width: 600px;
+        }
+        #app-header h1 {
+            color: #FF0000;
+            font-size: 2.5em;
+            margin-bottom: 10px;
+        }
+        .header-images {
+            display: flex;
+            justify-content: center;
+            align-items: center;
+            margin: 20px 0;
+        }
+        .header-image {
+            width: 100px;
+            height: 100px;
+            margin: 0 10px;
+            background: #fff;
+            border-radius: 50%;
+            display: flex;
+            justify-content: center;
+            align-items: center;
+            box-shadow: 0 4px 6px rgba(0, 0, 0, 0.2);
+        }
+        .header-image img {
+            max-width: 80px;
+            max-height: 80px;
+            border-radius: 50%;
+        }
+        .concept-description {
+            position: absolute;
+            bottom: -30px;
+            left: 50%;
+            transform: translateX(-50%);
+            background-color: #4CAF50;
+            color: white;
+            padding: 5px 10px;
+            border-radius: 5px;
+            opacity: 0;
+            transition: opacity 0.3s;
+        }
+        .concept:hover .concept-description {
+            opacity: 1;
+        }
+    </style>
+</head>
+<body>
+<div id="app-header">
+    <!-- Header Images -->
+    <div class="header-images">
+        <div class="header-image">
+            <img src="https://github.com/nkanungo/ERAS20/blob/main/images/ss1.jpg?raw=true" alt="Image 1">
+        </div>
+        <div class="header-image">
+            <img src="https://github.com/nkanungo/ERAS20/blob/main/images/ss1.jpg?raw=true" alt="Image 2">
+        </div>
+    </div>
+    <!-- Content -->
+    <h1>Paragraph Auto Completion like Shakespeare </h1>
+    <p>Generate dialogue using the intellignece from Shakespeare Dataset .</p>
+    <p>Model: GPT, Dataset: Tiny Shakespeare, Token limit: User input ,Input Text: User input.</p>
+</div>
+"""
+with gr.Blocks(theme=gr.themes.Glass()) as interface:
+    gr.HTML(value=HTML_TEMPLATE, show_label=False)
+    with gr.Row(scale=1):
+        inputs = [
+            gr.Textbox(label="Input Text Prompt"),
+            gr.Textbox(label="Token Limit")
+        ]
+        outputs = gr.Textbox(
+            label="Generated Paragraph"
+        )
+    with gr.Column(scale=1):
+        button = gr.Button("Generate")
+        button.click(generate_paragraph, inputs=inputs, outputs=outputs)
+if __name__ == "__main__":
+    interface.launch(enable_queue=True)
+# In[ ]:

nano_gpt_inferencing.py ADDED Viewed

	@@ -0,0 +1,197 @@

+#!/usr/bin/env python
+# coding: utf-8
+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 = 64 # what is the maximum context length for predictions?
+max_iters = 20000
+eval_interval = 100
+learning_rate = 1e-3
+device = 'cuda' if torch.cuda.is_available() else 'cpu'
+eval_iters = 200
+n_embd = 64
+n_head = 8
+n_layer = 8
+dropout = 0.2
+# ------------
+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
+@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 """
+    def __init__(self, head_size):
+        super().__init__()
+        self.key = nn.Linear(n_embd, head_size, bias=False)
+        self.query = nn.Linear(n_embd, head_size, bias=False)
+        self.value = nn.Linear(n_embd, head_size, bias=False)
+        self.register_buffer('tril', torch.tril(torch.ones(block_size, block_size)))
+        self.dropout = nn.Dropout(dropout)
+    def forward(self, x):
+        B,T,C = x.shape
+        k = self.key(x)   # (B,T,C)
+        q = self.query(x) # (B,T,C)
+        # compute attention scores ("affinities")
+        wei = q @ k.transpose(-2,-1) * C**-0.5 # (B, T, C) @ (B, C, T) -> (B, T, T)
+        wei = wei.masked_fill(self.tril[:T, :T] == 0, float('-inf')) # (B, T, T)
+        wei = F.softmax(wei, dim=-1) # (B, T, T)
+        wei = self.dropout(wei)
+        # perform the weighted aggregation of the values
+        v = self.value(x) # (B,T,C)
+        out = wei @ v # (B, T, T) @ (B, T, C) -> (B, T, C)
+        return out
+class MultiHeadAttention(nn.Module):
+    """ multiple heads of self-attention in parallel """
+    def __init__(self, num_heads, head_size):
+        super().__init__()
+        self.heads = nn.ModuleList([Head(head_size) for _ in range(num_heads)])
+        self.proj = nn.Linear(n_embd, n_embd)
+        self.dropout = nn.Dropout(dropout)
+    def forward(self, x):
+        out = torch.cat([h(x) for h in self.heads], dim=-1)
+        out = self.dropout(self.proj(out))
+        return out
+class FeedFoward(nn.Module):
+    """ a simple linear layer followed by a non-linearity """
+    def __init__(self, n_embd):
+        super().__init__()
+        self.net = nn.Sequential(
+            nn.Linear(n_embd, 4 * n_embd),
+            nn.ReLU(),
+            nn.Linear(4 * n_embd, n_embd),
+            nn.Dropout(dropout),
+        )
+    def forward(self, x):
+        return self.net(x)
+class Block(nn.Module):
+    """ Transformer block: communication followed by computation """
+    def __init__(self, n_embd, n_head):
+        # n_embd: embedding dimension, n_head: the number of heads we'd like
+        super().__init__()
+        head_size = n_embd // n_head
+        self.sa = MultiHeadAttention(n_head, head_size)
+        self.ffwd = FeedFoward(n_embd)
+        self.ln1 = nn.LayerNorm(n_embd)
+        self.ln2 = nn.LayerNorm(n_embd)
+    def forward(self, x):
+        x = x + self.sa(self.ln1(x))
+        x = x + self.ffwd(self.ln2(x))
+        return x
+# super simple bigram model
+class BigramLanguageModel(nn.Module):
+    def __init__(self):
+        super().__init__()
+        # each token directly reads off the logits for the next token from a lookup table
+        self.token_embedding_table = nn.Embedding(vocab_size, n_embd)
+        self.position_embedding_table = nn.Embedding(block_size, n_embd)
+        self.blocks = nn.Sequential(*[Block(n_embd, n_head=n_head) for _ in range(n_layer)])
+        self.ln_f = nn.LayerNorm(n_embd) # final layer norm
+        self.lm_head = nn.Linear(n_embd, vocab_size)
+    def forward(self, idx, targets=None):
+        B, T = idx.shape
+        # idx and targets are both (B,T) tensor of integers
+        tok_emb = self.token_embedding_table(idx) # (B,T,C)
+        pos_emb = self.position_embedding_table(torch.arange(T, device=device)) # (T,C)
+        x = tok_emb + pos_emb # (B,T,C)
+        x = self.blocks(x) # (B,T,C)
+        x = self.ln_f(x) # (B,T,C)
+        logits = self.lm_head(x) # (B,T,vocab_size)
+        if targets is None:
+            loss = None
+        else:
+            B, T, C = logits.shape
+            logits = logits.view(B*T, C)
+            targets = targets.view(B*T)
+            loss = F.cross_entropy(logits, targets)
+        return logits, loss
+    def generate(self, idx, max_new_tokens):
+        # idx is (B, T) array of indices in the current context
+        for _ in range(max_new_tokens):
+            # crop idx to the last block_size tokens
+            idx_cond = idx[:, -block_size:]
+            # get the predictions
+            logits, loss = self(idx_cond)
+            # focus only on the last time step
+            logits = logits[:, -1, :] # becomes (B, C)
+            # apply softmax to get probabilities
+            probs = F.softmax(logits, dim=-1) # (B, C)
+            # sample from the distribution
+            idx_next = torch.multinomial(probs, num_samples=1) # (B, 1)
+            # append sampled index to the running sequence
+            idx = torch.cat((idx, idx_next), dim=1) # (B, T+1)
+        return idx
+def generate_paragraph(initial_text,max_token):
+    model = BigramLanguageModel()
+    model.load_state_dict(torch.load('nano_gpt_model.pth'))
+    final_model = model.to(device)
+    encoded_text= encode(initial_text)
+    encoded_text_tensor = torch.tensor(encoded_text).view(1, -1)
+    return decode(final_model.generate(encoded_text_tensor, max_new_tokens=int(max_token))[0].tolist())

nano_gpt_model.pth ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:2007cc588e3cb9df071ee89a38153c9f38857f7da86c436cda60d5ce3c6d09d7
+size 2793298

requirements.txt ADDED Viewed

	@@ -0,0 +1,2 @@


1	+ gradio
2	+ torch