Update app.py

app.py

@@ -6,8 +6,15 @@ 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")
-client = InferenceClient("unsloth/Llama-3.2-11B-Vision-Instruct")
-
+client = InferenceClient("unsloth/Llama-3.2-3B-Instruct")
+
+model, tokenizer = FastLanguageModel.from_pretrained(
+    model_name = "unsloth/mistral-7b-bnb-4bit", # Choose ANY! eg teknium/OpenHermes-2.5-Mistral-7B
+    max_seq_length = max_seq_length,
+    dtype = dtype,
+    load_in_4bit = load_in_4bit,
+    # token = "hf_...", # use one if using gated models like meta-llama/Llama-2-7b-hf
+)
 
 def respond(
     message,