First commit

app.py

@@ -0,0 +1,58 @@
+import torch
+import gradio as gr
+from model import BigramLanguageModel
+
+cuda = torch.cuda.is_available()
+device = 'cuda' if cuda else 'cpu'
+
+model = BigramLanguageModel()
+model.load_state_dict(torch.load("model.pth", map_location=torch.device(device)), strict=False)
+
+# read text file
+with open('input.txt', 'r', encoding='utf-8') as f:
+    text = f.read()
+
+# collect all the unique characters that occur in this text
+chars = sorted(list(set(text)))
+vocab_size = len(chars)
+
+# create a maaping from charaters that occur in this text
+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 
+
+def inference(input_text, max_new_tokens=500):
+    context = torch.tensor(encode(input_text), dtype=torch.long, device=device)
+    
+    output_text = decode(model.generate(context, max_new_tokens=max_new_tokens)[0].tolist())
+    
+    return output_text
+
+title = "NanoGPT trained on Shakespeare Plays dataset"
+description = "A simple Gradio interface to generate text from gpt model trained on Shakespeare Plays"
+examples = [["Shape", 500], 
+           ["Answer", 500], 
+           ["Ideology", 500], 
+           ["Absorb", 500], 
+           ["Triangle", 500], 
+           ["Listen", 500], 
+           ["Census", 500], 
+           ["Balance", 500], 
+           ["Representative", 500], 
+           ["Cinema", 500], 
+           ]
+demo = gr.Interface(
+    inference, 
+    inputs = [
+        gr.Textbox(label="Enter any word", type="text"),
+        gr.Slider(minimum=100, maximum=10000, step=100, value=500, label="Max character to generate")
+        ], 
+    outputs = [
+        gr.Textbox(label="Output", type="text")
+        ],
+    title = title,
+    description = description,
+    examples = examples,
+)
+demo.launch()

model.py

@@ -0,0 +1,149 @@
+import torch
+import torch.nn as nn
+import torch.nn.functional as F
+
+n_embd = 384
+block_size = 256
+dropout = 0.1
+n_head = 8
+n_layer = 6
+
+# read text file
+with open('input.txt', 'r', encoding='utf-8') as f:
+    text = f.read()
+
+# collect all the unique characters that occur in this text
+chars = sorted(list(set(text)))
+vocab_size = len(chars)
+
+cuda = torch.cuda.is_available()
+device = 'cuda' if cuda else 'cpu'
+
+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('trill', 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)
+        q = self.query(x)
+        # compute attention scores ("affinities")
+        wei = q @ k.transpose(-2, -1) * C**-0.5
+        wei = wei.masked_fill(self.trill[:T, :T] == 0, float('-inf'))
+        wei = F.softmax(wei, dim=-1)
+        wei = self.dropout(wei)
+        # perform the weighted aggregation of the values
+        v = self.value(x)
+        out = wei @ v
+        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 FeedForward(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) -> None:
+
+        super().__init__()
+        head_size = n_embd // n_head
+        self.sa = MultiHeadAttention(n_head, head_size)
+        self.ffwd = FeedForward(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)
+
+
+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.sa_head = MultiHeadAttention(4, n_embd//4)
+        # self.ffwd = FeedForward(n_embd)
+        # self.blocks = nn.Sequential(
+        #     Block(n_embd, n_head=4),
+        #     Block(n_embd, n_head=4),
+        #     Block(n_embd, n_head=4),
+        #     nn.LayerNorm(n_embd)
+        # )
+        self.blocks = nn.Sequential(*[Block(n_embd, n_head) for _ in range (n_layer)])
+        self.ln_f = nn.LayerNorm(n_embd)
+        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))
+        x = tok_emb + pos_emb
+        # x = self.sa_head(x)
+        # x = self.ffwd(x)
+        x = self.blocks(x)
+        x = self.ln_f(x)
+        logits = self.lm_head(x)
+
+        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):
+            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

nanogpt.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf87f20f3e71ff9fbd3781c4f4969cbeebe0f73ec85838b7edac1c2e7f86dd29
+size 55835502

requirements.txt

@@ -0,0 +1,81 @@
+aiofiles==23.2.1
+altair==5.3.0
+annotated-types==0.7.0
+anyio==4.4.0
+attrs==23.2.0
+certifi==2024.6.2
+charset-normalizer==3.3.2
+click==8.1.7
+colorama==0.4.6
+contourpy==1.2.1
+cycler==0.12.1
+dnspython==2.6.1
+email_validator==2.1.1
+fastapi==0.111.0
+fastapi-cli==0.0.4
+ffmpy==0.3.2
+filelock==3.13.1
+fonttools==4.53.0
+fsspec==2024.2.0
+gradio==4.36.1
+gradio_client==1.0.1
+h11==0.14.0
+httpcore==1.0.5
+httptools==0.6.1
+httpx==0.27.0
+huggingface-hub==0.23.4
+idna==3.7
+importlib_resources==6.4.0
+intel-openmp==2021.4.0
+Jinja2==3.1.3
+jsonschema==4.22.0
+jsonschema-specifications==2023.12.1
+kiwisolver==1.4.5
+markdown-it-py==3.0.0
+MarkupSafe==2.1.5
+matplotlib==3.9.0
+mdurl==0.1.2
+mkl==2021.4.0
+mpmath==1.3.0
+networkx==3.2.1
+numpy==1.26.3
+orjson==3.10.5
+packaging==24.1
+pandas==2.2.2
+pillow==10.2.0
+pydantic==2.7.4
+pydantic_core==2.18.4
+pydub==0.25.1
+Pygments==2.18.0
+pyparsing==3.1.2
+python-dateutil==2.9.0.post0
+python-dotenv==1.0.1
+python-multipart==0.0.9
+pytz==2024.1
+PyYAML==6.0.1
+referencing==0.35.1
+requests==2.32.3
+rich==13.7.1
+rpds-py==0.18.1
+ruff==0.4.9
+semantic-version==2.10.0
+shellingham==1.5.4
+six==1.16.0
+sniffio==1.3.1
+starlette==0.37.2
+sympy==1.12
+tbb==2021.11.0
+tomlkit==0.12.0
+toolz==0.12.1
+torch==2.3.1
+torchaudio==2.3.1
+torchvision==0.18.1
+tqdm==4.66.4
+typer==0.12.3
+typing_extensions==4.9.0
+tzdata==2024.1
+ujson==5.10.0
+urllib3==2.2.1
+uvicorn==0.30.1
+watchfiles==0.22.0
+websockets==11.0.3