Update space

app.py

@@ -1,17 +1,64 @@
-from transformers import AutoModelForCausalLM, AutoTokenizer
+import gradio as gr
+from huggingface_hub import InferenceClient
 
-model_name = "emeses/lab2_model"
-# Load the model with 8-bit quantization (works better on CPU)
-model = AutoModelForCausalLM.from_pretrained(model_name, quantization_config={"load_in_8bit": True})
-tokenizer = AutoTokenizer.from_pretrained(model_name)
-model = model.to("cpu")
+"""
+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-3.2-3B-Instruct")
 
-# Function for Gradio interface
-def generate_text(prompt):
-    inputs = tokenizer(prompt, return_tensors="pt")
-    outputs = model.generate(inputs["input_ids"], max_length=50)
-    return tokenizer.decode(outputs[0], skip_special_tokens=True)
 
-# Gradio interface
-import gradio as gr
-gr.Interface(fn=generate_text, inputs="text", outputs="text").launch()
+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
+
+
+"""
+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)",
+        ),
+    ],
+)
+
+
+if __name__ == "__main__":
+    demo.launch()