Upload app.py

app.py

@@ -1,64 +1,149 @@
-import gradio as gr
-from huggingface_hub import InferenceClient
+# -*- coding: utf-8 -*-
+"""app
 
+Automatically generated by Colab.
+
+Original file is located at
+    https://colab.research.google.com/drive/1OBF9xRogFp1BlMVFwZX6R-0jD8yU_tEk
 """
-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")
 
+import torch
+import torch.nn as nn
+from torch.nn import functional as F
+import gradio as gr
+
+# hyperparameters
+batch_size = 16
+block_size = 32
+n_embd = 64
+n_head = 4
+n_layer = 4
+dropout = 0.0
+device = 'cuda' if torch.cuda.is_available() else 'cpu'
 
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
-    messages = [{"role": "system", "content": system_message}]
+# Load Book of Mormon text
+with open('Book of Mormon.txt', 'r', encoding='utf-8') as f:
+    text = f.read()
 
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
+# Tokenizer setup
+chars = sorted(list(set(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]
+decode = lambda l: ''.join([itos[i] for i in l])
 
-    messages.append({"role": "user", "content": message})
+# Model definition
+class BigramLanguageModel(nn.Module):
+    def __init__(self):
+        super().__init__()
+        self.token_embedding_table = nn.Embedding(len(chars), 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)
+        self.lm_head = nn.Linear(n_embd, len(chars))
 
-    response = ""
+    def forward(self, idx, targets=None):
+        tok_emb = self.token_embedding_table(idx)
+        pos_emb = self.position_embedding_table(torch.arange(idx.shape[1], device=device))
+        x = tok_emb + pos_emb
+        x = self.blocks(x)
+        x = self.ln_f(x)
+        logits = self.lm_head(x)
+        loss = F.cross_entropy(logits.view(-1, logits.size(-1)), targets.view(-1)) if targets is not None else None
+        return logits, loss
 
-    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
+    def generate(self, idx, max_new_tokens):
+        for _ in range(max_new_tokens):
+            idx_cond = idx[:, -block_size:]
+            logits, _ = 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
 
-        response += token
-        yield response
+class Block(nn.Module):
+    def __init__(self, n_embd, n_head):
+        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
 
-"""
-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)",
-        ),
-    ],
+class MultiHeadAttention(nn.Module):
+    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 Head(nn.Module):
+    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)))
+
+    def forward(self, x):
+        k, q, v = self.key(x), self.query(x), self.value(x)
+        wei = q @ k.transpose(-2, -1) * (k.size(-1) ** -0.5)
+        wei = wei.masked_fill(self.tril[:x.size(1), :x.size(1)] == 0, float('-inf'))
+        wei = F.softmax(wei, dim=-1)
+        return wei @ v
+
+class FeedForward(nn.Module):
+    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)
+
+# Load pre-trained model
+model = BigramLanguageModel()
+model.load_state_dict(torch.load('model.pth', map_location=device))
+model.eval()
+
+# Gradio functions
+def ask_question(question, max_new_tokens=100):
+    context_text = f"Q: {question}\nA:"
+    context_tokens = torch.tensor(encode(context_text), dtype=torch.long, device=device).unsqueeze(0)
+    generated_tokens = model.generate(context_tokens, max_new_tokens=max_new_tokens)
+    generated_text = decode(generated_tokens[0].tolist())
+    return generated_text.split("A:")[1].strip()
+
+def chatbot_response(question):
+    try:
+        return ask_question(question)
+    except Exception as e:
+        return f"Error: {e}"
+
+# Gradio Interface
+demo = gr.Interface(
+    fn=chatbot_response,
+    inputs="text",
+    outputs="text",
+    title="Religious Chatbot",
+    description="Ask questions about the Book of Mormon."
 )
 
+# Launch the app
+demo.launch()
 
-if __name__ == "__main__":
-    demo.launch()