Update app.py

app.py

@@ -1,12 +1,21 @@
+from unsloth import FastLanguageModel
 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")
+# Declare necessary variables
+max_seq_length = 2048  # Choose any! We auto support RoPE Scaling internally!
+dtype = None  # None for auto detection. Float16 for Tesla T4, V100, Bfloat16 for Ampere+
+load_in_4bit = True  # Use 4bit quantization to reduce memory usage. Can be False.
 
+# Load the model and tokenizer
+model, tokenizer = FastLanguageModel.from_pretrained(
+    model_name="abdfajar707/llama3_8B_lora_model_rkp_pn2025_v3",  # YOUR MODEL YOU USED FOR TRAINING
+    max_seq_length=max_seq_length,
+    dtype=dtype,
+    load_in_4bit=load_in_4bit,
+)
+FastLanguageModel.for_inference(model)  # Enable native 2x faster inference
 
+# Define the respond function
 def respond(
     message,
     history: list[tuple[str, str]],
@@ -27,23 +36,20 @@ def respond(
 
     response = ""
 
-    for message in client.chat_completion(
+    for msg in model.chat_completion(
         messages,
         max_tokens=max_tokens,
         stream=True,
         temperature=temperature,
         top_p=top_p,
     ):
-        token = message.choices[0].delta.content
-
+        token = msg.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
-"""
+# Create the Gradio interface
 demo = gr.ChatInterface(
-    respond,
+    fn=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"),
@@ -58,6 +64,6 @@ demo = gr.ChatInterface(
     ],
 )
 
-
+# Launch the Gradio interface
 if __name__ == "__main__":
-    demo.launch()
+    demo.launch()