few changes added

app.py

@@ -1,21 +1,139 @@
 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")
+import torch
+import torch.nn as nn
+import torch.functional as F
 
+n_embd = 64
+dropout = 0.0
+block_size = 32
+vocab_size = 65
+n_head = 4
+n_layer = 4
+
+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)))
+
+        self.dropout = nn.Dropout(dropout)
+
+    def forward(self, x):
+        B,T,C = x.shape
+        k = self.key(x)   
+        q = self.query(x) 
+        wei = q @ k.transpose(-2,-1) * C**-0.5 
+        wei = wei.masked_fill(self.tril[:T, :T] == 0, float('-inf')) 
+        wei = F.softmax(wei, dim=-1) 
+        wei = self.dropout(wei)
+
+        v = self.value(x)
+        out = wei @ v
+        return out
+
+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 FeedFoward(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)
+
+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 = 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
+
+class BigramLanguageModel(nn.Module):
+
+    def __init__(self):
+        super().__init__()
+        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) 
+        self.lm_head = nn.Linear(n_embd, vocab_size)
+
+    def forward(self, idx, targets=None):
+        B, T = idx.shape
+
+        tok_emb = self.token_embedding_table(idx) 
+        pos_emb = self.position_embedding_table(torch.arange(T)) 
+        x = tok_emb + pos_emb 
+        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):
+        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
+
+
+chars = "\n !$&',-.3:;?ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz"
+itos = { i:ch for i,ch in enumerate(chars) }
+stoi = { ch:i for i,ch in enumerate(chars) }
+
+decode = lambda l: ''.join([itos[i] for i in l])
+encode = lambda s: [stoi[c] for c in s]
+
+model = BigramLanguageModel()
 
 def respond(
     message,
     history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
 ):
-    messages = [{"role": "system", "content": system_message}]
+    messages = [{"role": "system", "content": "Cocaine"}]
 
     for val in history:
         if val[0]:
@@ -27,36 +145,23 @@ def respond(
 
     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)",
-        ),
-    ],
-)
+    input_txt = encode(message)
+    context = torch.tensor(input_txt).unsqueeze(0)
+    # response = decode(model.generate(context, max_new_tokens=2000)[0].tolist())
+
+    idx = context
+    for _ in range(2000):
+
+        idx_cond = idx[:, -block_size:]
+        logits = model(idx_cond).logits
+        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) 
+
+        yield decode(idx_next[0].tolist())
+
+demo = gr.ChatInterface(respond)
 
 
 if __name__ == "__main__":