Fix: Moved the Files around due to imports not working right

Feat: Phoebe replies but it's gibbish
This is a version break because of the file structure change.

phoebe/train_gpt_model.py

@@ -0,0 +1,130 @@
+import torch
+import mmap
+import random
+from gpt_model import GPT, encode, decode
+
+device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+
+# Hyperparameters
+batch_size = 64
+block_size = 256
+max_iters = 500
+learning_rate = 2e-5
+eval_iters = 250
+dropout = 0.2
+
+chars = ""
+with open("vocab.txt", "r", encoding="utf-8") as f:
+    text = f.read()
+    chars = sorted(list(set(text)))
+
+# Ensure that space and other special characters are included
+# Ensure that space and other special characters are included
+required_chars = " \n\r\t"
+for char in required_chars:
+    if char not in chars:
+        chars.append(char)
+
+# Add a special token for unknown characters
+special_token = "<unk>"
+if special_token not in chars:
+    chars.append(special_token)
+
+vocab_size = len(chars)
+string_to_int = {ch: i for i, ch in enumerate(chars)}
+int_to_string = {i: ch for i, ch in enumerate(chars)}
+
+
+def get_random_chunk(split):
+    filename = "train_split.txt" if split == "train" else "eval_split.txt"
+    with open(filename, "rb") as f:
+        with mmap.mmap(f.fileno(), length=0, access=mmap.ACCESS_READ) as mm:
+            file_size = len(mm)
+            start = random.randint(0, file_size - block_size * batch_size)
+            mm.seek(start)
+            block = mm.read(block_size * batch_size - 1)
+            decoded_block = block.decode("utf-8", errors="ignore").replace(
+                "\r", ""
+            )
+            data = torch.tensor(
+                encode(decoded_block, string_to_int), dtype=torch.long
+            )
+            return data
+
+
+def get_batch(split):
+    data = get_random_chunk(split)
+    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
+
+
+model = GPT(vocab_size).to(device)
+
+
+@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().item()
+    model.train()
+    return out
+
+
+def train_model():
+    optimizer = torch.optim.AdamW(model.parameters(), lr=learning_rate)
+    for iter in range(max_iters):
+        if iter % eval_iters == 0:
+            losses = estimate_loss()
+            print(
+                f"step {iter}: train loss {losses['train']:.3f}, "
+                f"val loss {losses['val']:.3f}"
+            )
+        xb, yb = get_batch("train")
+        logits, loss = model(xb, yb)
+        optimizer.zero_grad(set_to_none=True)
+        loss.backward()
+        optimizer.step()
+
+    print(loss.item())
+    torch.save(model.state_dict(), "phoebe_model.pt")
+    print("Model Saved!")
+
+
+def check_input_chars(s, string_to_int):
+    unknown_chars = [c for c in s if c not in string_to_int]
+    if unknown_chars:
+        print(f"Unknown characters in input: {unknown_chars}")
+    return unknown_chars
+
+
+def process_message(message):
+    if not message.strip():
+        return "Message is empty or invalid."
+
+    # Check for unknown characters
+    unknown_chars = check_input_chars(message, string_to_int)
+    if unknown_chars:
+        return f"Message contains unknown characters: {unknown_chars}"
+
+    encoded_text = torch.tensor(
+        [encode(message, string_to_int)], dtype=torch.long
+    ).to(device)
+    print(f"Encoded text shape: {encoded_text.shape}")  # Debug print
+    if encoded_text.size(1) == 0:
+        return "Message could not be processed."
+
+    response = model.generate(encoded_text, max_new_tokens=50)
+    decoded_response = decode(response[0].tolist(), int_to_string)
+    return decoded_response
+
+
+# train_model()