Create app.py

app.py

@@ -1,64 +1,46 @@
 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")
-
-
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
-    messages = [{"role": "system", "content": system_message}]
-
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
-
-    messages.append({"role": "user", "content": message})
-
-    response = ""
+import torch
+from transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig, pipeline
+
+# Model ID
+model_id = "large-traversaal/Alif-1.0-8B-Instruct"
+
+# 4-bit quantization configuration
+quantization_config = BitsAndBytesConfig(
+    load_in_4bit=True,
+    bnb_4bit_compute_dtype=torch.float16,
+    bnb_4bit_use_double_quant=True,
+    bnb_4bit_quant_type="nf4"
+)
 
-    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
+# Load tokenizer and model in 4-bit
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+model = AutoModelForCausalLM.from_pretrained(
+    model_id,
+    quantization_config=quantization_config,
+    device_map="auto"
+)
 
-        response += token
-        yield response
+# Create text generation pipeline
+chatbot = pipeline("text-generation", model=model, tokenizer=tokenizer, device_map="auto")
 
+# Function to generate responses
+def chat(message):
+    response = chatbot(message, max_new_tokens=100, do_sample=True, temperature=0.3)
+    return response[0]["generated_text"]
 
-"""
-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)",
-        ),
-    ],
-)
+# Gradio UI
+with gr.Blocks() as demo:
+    gr.Markdown("# 🤖 Alif Chatbot - Urdu Language AI Model")
+    with gr.Row():
+        user_input = gr.Textbox(label="User Input", placeholder="اپنا سوال یہاں لکھیں...")
+    with gr.Row():
+        submit_btn = gr.Button("Send")
+    with gr.Row():
+        bot_response = gr.Textbox(label="AI Response")
 
+    submit_btn.click(fn=chat, inputs=user_input, outputs=bot_response)
 
+# Launch the app
 if __name__ == "__main__":
     demo.launch()