Update app.py

app.py

@@ -1,11 +1,9 @@
 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")
+from transformers import AutoTokenizer, AutoModelForCausalLM
 
+# Load model directly
+tokenizer = AutoTokenizer.from_pretrained("Leo022/Gemma_QA_For_Telegram_Bot")
+model = AutoModelForCausalLM.from_pretrained("Leo022/Gemma_QA_For_Telegram_Bot")
 
 def respond(
     message,
@@ -25,23 +23,20 @@ def respond(
 
     messages.append({"role": "user", "content": message})
 
-    response = ""
+    input_ids = tokenizer.encode(messages, return_tensors="pt")
 
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
+    output = model.generate(
+        input_ids,
+        max_length=max_tokens,
         temperature=temperature,
         top_p=top_p,
-    ):
-        token = message.choices[0].delta.content
+        do_sample=True,
+    )
+
+    response = tokenizer.decode(output[0], skip_special_tokens=True)
 
-        response += token
-        yield response
+    return 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=[
@@ -58,6 +53,5 @@ demo = gr.ChatInterface(
     ],
 )
 
-
 if __name__ == "__main__":
     demo.launch()