Update app.py

app.py

@@ -1,10 +1,14 @@
 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")
+# pip install bitsandbytes accelerate
+from transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig
+# to use 4bit use `load_in_4bit=True` instead
+quantization_config = BitsAndBytesConfig(load_in_8bit=True)
+checkpoint = "HuggingFaceTB/SmolLM-135M"
+tokenizer = AutoTokenizer.from_pretrained(checkpoint)
+model = AutoModelForCausalLM.from_pretrained(checkpoint, quantization_config=quantization_config)
+
 
 
 def respond(
@@ -27,17 +31,11 @@ def respond(
 
     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
+    inputs = tokenizer.encode(messages, return_tensors="pt").to("cuda")
+    outputs = model.generate(inputs)
+    print(tokenizer.decode(outputs[0]))
+
+    return tokenizer.decode(outputs[0])
 
 """
 For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface