Update app.py

app.py

@@ -1,69 +1,63 @@
 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)
+import torch
+from transformers import AutoModelForCausalLM, AutoTokenizer, TextIteratorStreamer
+from threading import Thread
+
+# 1. Point the script directly to your uploaded Hugging Face model
+MODEL_ID = "Cydercoder/qwen2.5-coder-3b"
+
+print("Loading tokenizer...")
+tokenizer = AutoTokenizer.from_pretrained(MODEL_ID)
+print("Loading model on CPU (Free Tier)...")
+# We load in 8-bit or float32 to fit inside the free 16GB CPU RAM limit safely
+model = AutoModelForCausalLM.from_pretrained(
+    MODEL_ID,
+    torch_dtype=torch.float32,
+    low_cpu_mem_usage=True
+)
 
+def chat_function(message, history):
+    # Construct formatting conversation list matrices
+    messages = [
+        {"role": "system", "content": "You are an expert full-stack developer assistant."}
+    ]
+    
+    # Re-insert existing browser chat history logs
+    for user_msg, bot_msg in history:
+        messages.append({"role": "user", "content": user_msg})
+        messages.append({"role": "assistant", "content": bot_msg})
+        
     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,
-    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)",
-        ),
-    ],
+    
+    # Process tokens safely
+    inputs = tokenizer.apply_chat_template(messages, add_generation_prompt=True, return_tensors="pt")
+    
+    # Set up a dynamic background streamer so answers appear word-by-word in browser
+    streamer = TextIteratorStreamer(tokenizer, skip_prompt=True, skip_special_tokens=True)
+    
+    generation_kwargs = dict(
+        input_ids=inputs,
+        streamer=streamer,
+        max_new_tokens=512,
+        temperature=0.6,
+    )
+    
+    # Run text generation in a separate background processor thread
+    thread = Thread(target=model.generate, kwargs=generation_kwargs)
+    thread.start()
+    
+    partial_text = ""
+    for new_text in streamer:
+        partial_text += new_text
+        yield partial_text
+
+# 4. Initialize the gorgeous, interactive native Gradio browser interface
+demo = gr.ChatInterface(
+    fn=chat_function,
+    title="🤖 Cydercoder Qwen 3B AI Chatbot",
+    description="Your custom fine-tuned assistant running 24/7 in the cloud for free.",
+    examples=["Write a login form using React and Tailwind.", "Fix this code error: Cannot read properties of undefined"]
 )
 
-with gr.Blocks() as demo:
-    with gr.Sidebar():
-        gr.LoginButton()
-    chatbot.render()
-
-
 if __name__ == "__main__":
     demo.launch()