update app.py

app.py

@@ -1,63 +1,84 @@
+import torch
+import torch.nn as nn
 import gradio as gr
-from huggingface_hub import InferenceClient
-
-"""
-For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
-"""
-client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
-
-
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
-    messages = [{"role": "system", "content": system_message}]
-
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
-
-    messages.append({"role": "user", "content": message})
-
-    response = ""
-
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
-        temperature=temperature,
-        top_p=top_p,
-    ):
-        token = message.choices[0].delta.content
-
-        response += token
-        yield response
-
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
-demo = gr.ChatInterface(
-    respond,
-    additional_inputs=[
-        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
-        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
-        gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
-        gr.Slider(
-            minimum=0.1,
-            maximum=1.0,
-            value=0.95,
-            step=0.05,
-            label="Top-p (nucleus sampling)",
-        ),
-    ],
-)
-
-
-if __name__ == "__main__":
-    demo.launch()
+from torch.nn import functional as F
+
+# Define your model and any necessary helper functions here
+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):
+        for _ in range(max_new_tokens):
+            idx_cond = idx[:, -block_size:]
+            logits, loss = self(idx_cond)
+            logits = logits[:, -1, :]
+            probs = F.softmax(logits, dim=-1)
+            idx_next = torch.multinomial(probs, num_samples=1)
+            idx = torch.cat((idx, idx_next), dim=1)
+        return idx
+
+# Initialize model
+device = 'cuda' if torch.cuda.is_available() else 'cpu'
+vocab_size = 65  # Update this with the correct vocab size
+n_embd = 64
+n_head = 4
+n_layer = 4
+block_size = 32
+
+model = BigramLanguageModel()
+model.load_state_dict(torch.load('bigram_language_model.pth', map_location=device))
+model.to(device)
+model.eval()
+
+# Character mappings (ensure these match your training setup)
+stoi = {ch: i for i, ch in enumerate(chars)}
+itos = {i: ch for i, ch in enumerate(chars)}
+
+def encode(s):
+    return [stoi[c] for c in s]
+
+def decode(l):
+    return ''.join([itos[i] for i in l])
+
+def generate_text(input_text):
+    idx = torch.tensor(encode(input_text), dtype=torch.long).unsqueeze(0).to(device)
+    generated_idx = model.generate(idx, max_new_tokens=200)
+    generated_text = decode(generated_idx[0].tolist())
+    return generated_text
+
+# Create Gradio Interface
+iface = gr.Interface(fn=generate_text,
+                     inputs=gr.inputs.Textbox(lines=5, label="Input Text"),
+                     outputs=gr.outputs.Textbox(label="Generated Text"),
+                     title="Shakespeare-like Text Generator",
+                     description="Enter some text and the model will generate Shakespeare-like text.")
+
+iface.launch()