Added chat interface

app.py

@@ -1,63 +1,28 @@
+from transformers import AutoModelForCausalLM, AutoTokenizer
+from huggingface_hub import login
 import gradio as gr
-from huggingface_hub import InferenceClient
+import torch
 
-"""
-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("meta-llama/Llama-3.2-11B-Vision-Instruct")
+login(token = os.getenv('HF_TOKEN'))
 
+# Load the tokenizer and model
+tokenizer = AutoTokenizer.from_pretrained("meta-llama/Llama-3.2-11B-Vision-Instruct")
+model = AutoModelForCausalLM.from_pretrained(
+    "meta-llama/Llama-3.2-11B-Vision-Instruct",
+    device_map="auto",
+    torch_dtype="auto",
+)
 
-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 = ""
-
-    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
+def generate_response(message, history):
+    inputs = tokenizer(message['text'], return_tensors="pt").to("cpu")
+    with torch.no_grad():
+        outputs = model.generate(inputs.input_ids, max_length=100)
+    return tokenizer.decode(outputs[0], skip_special_tokens=True)
 
-"""
-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)",
-        ),
-    ],
+    fn=generate_response, 
+    examples=[{"text": "Hello", "files": []}], 
+    title="LLAMA 3.2 Chat", 
+    multimodal=True
 )
-
-
-if __name__ == "__main__":
-    demo.launch()
+demo.launch(debug = True)