Update app.py

app.py

@@ -1,70 +1,43 @@
+import torch
 import gradio as gr
-from huggingface_hub import InferenceClient
-
-
-def respond(
-    message,
-    history: list[dict[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-    hf_token: gr.OAuthToken,
-):
-    """
-    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(token=hf_token.token, model="openai/gpt-oss-20b")
-
-    messages = [{"role": "system", "content": system_message}]
-
-    messages.extend(history)
-
-    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,
-    ):
-        choices = message.choices
-        token = ""
-        if len(choices) and choices[0].delta.content:
-            token = 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
-"""
-chatbot = gr.ChatInterface(
-    respond,
-    type="messages",
-    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)",
-        ),
-    ],
-)
-
-with gr.Blocks() as demo:
-    with gr.Sidebar():
-        gr.LoginButton()
-    chatbot.render()
-
-
-if __name__ == "__main__":
-    demo.launch()
+from transformers import GPT2Config
+from safetensors.torch import load_file
+from model import GPT2LMHeadModel
+
+# ---- LOAD YOUR MODEL ----
+MODEL_REPO = "Hai929/The_GuageLLM_12M"
+
+config = GPT2Config.from_pretrained(MODEL_REPO)
+model = GPT2LMHeadModel(config)
+
+state = load_file("model.safetensors")
+model.load_state_dict(state, strict=False)
+model.eval()
+
+# ---- TOKENIZER (CHAR LEVEL) ----
+def encode(text):
+    return torch.tensor([[ord(c) % 256 for c in text]], dtype=torch.long)
+
+def decode(tokens):
+    return "".join(chr(int(t)) for t in tokens)
+
+# ---- GENERATION ----
+@torch.no_grad()
+def chat(message, history):
+    ids = encode(message)
+
+    for _ in range(32):
+        logits = model(ids).logits[:, -1, :]
+        probs = torch.softmax(logits, dim=-1)
+        next_token = torch.multinomial(probs, 1)
+        ids = torch.cat([ids, next_token], dim=1)
+
+    text = decode(ids[0])
+    return text.split(".")[0] + "."
+
+# ---- UI ----
+gr.ChatInterface(
+    fn=chat,
+    title="GuageLLM",
+    description="A small language model trained from scratch."
+).launch()