Update app.py

app.py

@@ -1,11 +1,11 @@
 import gradio as gr
-from huggingface_hub import InferenceClient
+#from huggingface_hub import InferenceClient
 from transformers import pipeline
 
 """
 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")
+#client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
 
 modelpath = "distilgpt2"
 
@@ -42,19 +42,26 @@ def respond(
 
     messages.append({"role": "user", "content": message})
 
-    response = ""
-
-    for message in client.chat_completion(
+    response = pipe(
         messages,
-        max_tokens=max_tokens,
-        stream=True,
+        max_new_tokens=max_tokens,
         temperature=temperature,
         top_p=top_p,
-    ):
-        token = message.choices[0].delta.content
+    )[0]["generated_text"]
+    yield response
+    #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
 
-        response += token
-        yield response
+    #    response += token
+    #    yield response
 
 
 """