Update app.py

app.py

@@ -1,6 +1,9 @@
 import gradio as gr
 from huggingface_hub import InferenceClient
+from transformers import AutoTokenizer, AutoModelForCausalLM
 
+tokenizer = AutoTokenizer.from_pretrained("google/gemma-2-2b")
+model = AutoModelForCausalLM.from_pretrained("google/gemma-2-2b")
 """
 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
 """
@@ -24,20 +27,24 @@ def respond(
             messages.append({"role": "assistant", "content": val[1]})
 
     messages.append({"role": "user", "content": message})
-
     response = ""
+    inputs = tokenizer(message, return_tensors="pt")
+    
+    generate_ids = model.generate(inputs.input_ids, max_length=30)
+    response = tokenizer.batch_decode(generate_ids, skip_special_tokens=True, clean_up_tokenization_spaces=False)[0]
+    # Load model directly
+    yield 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
 
-    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
+    #     response += token
+    #     yield response
 
 """
 For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface