Update app.py

app.py

@@ -1,20 +1,12 @@
 import gradio as gr
-from huggingface_hub import InferenceClient
+from peft import AutoPeftModelForCausalLM
+from transformers import AutoTokenizer
 
 """
 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("eforse01/lora_model")
 
-
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
+def respond(message, history: list[tuple[str, str]], system_message, max_tokens, temperature, min_p,):
     messages = [{"role": "system", "content": system_message}]
 
     for val in history:
@@ -25,20 +17,24 @@ def respond(
 
     messages.append({"role": "user", "content": message})
 
-    response = ""
+    model = AutoPeftModelForCausalLM.from_pretrained(
+        "eforse01/lora_model", 
+    )
 
-    for message in client.chat_completion(
+    tokenizer = AutoTokenizer.from_pretrained("eforse01/lora_model")
+    inputs = tokenizer.apply_chat_template(
         messages,
-        max_tokens=max_tokens,
-        stream=True,
-        temperature=temperature,
-        top_p=top_p,
-    ):
-        token = message.choices[0].delta.content
+        tokenize = True,
+        add_generation_prompt = True, 
+        return_tensors = "pt",
+    )
 
-        response += token
-        yield response
+    output = model.generate(input_ids = inputs, max_new_tokens = max_tokens,
+                    use_cache = True, temperature = temperature, min_p = min_p)
+    
+    response = tokenizer.batch_decode(output, skip_special_tokens=True)[0]
 
+    yield response.split('assistant')[-1]
 
 """
 For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
@@ -47,18 +43,17 @@ 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=1, maximum=2048, value=2048, step=1, label="Max new tokens"),
+        gr.Slider(minimum=0.1, maximum=4.0, value=1.5, step=0.1, label="Temperature"),
         gr.Slider(
             minimum=0.1,
             maximum=1.0,
-            value=0.95,
-            step=0.05,
-            label="Top-p (nucleus sampling)",
+            value=0.99,
+            step=0.01,
+            label="Min-p",
         ),
     ],
 )
 
-
 if __name__ == "__main__":
-    demo.launch()
+    demo.launch()