Update app.py

app.py

@@ -4,8 +4,24 @@ 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("abdfajar707/rkp_lora_model")
+model = InferenceClient("abdfajar707/rkp_lora_model")
 
+def get_completion(query: str, model, tokenizer) -> str:
+  device = "cuda:0"
+  prompt_template = """
+  <start_of_turn>user
+  Below is an instruction that describes a task. Write a response that appropriately completes the request.
+  {query}
+  <end_of_turn>\\n<start_of_turn>model
+  
+  """
+  prompt = prompt_template.format(query=query)
+  encodeds = tokenizer(prompt, return_tensors="pt", add_special_tokens=True)
+  model_inputs = encodeds.to(device)
+  generated_ids = model.generate(**model_inputs, max_new_tokens=1000, do_sample=True, pad_token_id=tokenizer.eos_token_id)
+  # decoded = tokenizer.batch_decode(generated_ids)
+  decoded = tokenizer.decode(generated_ids[0], skip_special_tokens=True)
+  return (decoded)
 
 def respond(
     message,
@@ -27,7 +43,7 @@ def respond(
 
     response = ""
 
-    for message in client.chat_completion(
+    for message in model.chat_completion(
         messages,
         max_tokens=max_tokens,
         stream=True,
@@ -43,7 +59,7 @@ def respond(
 For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
 """
 demo = gr.ChatInterface(
-    respond,
+    get_completion,
     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"),