Update app.py

app.py

@@ -7,10 +7,7 @@ import torch
 import random
 from transformers import AutoTokenizer, AutoModelForCausalLM
 
-max_seq_length = 2048 # Choose any! We auto support RoPE Scaling internally!
-dtype = None # None for auto detection. Float16 for Tesla T4, V100, Bfloat16 for Ampere+
-
-model, tokenizer = AutoModelForCausalLM.from_pretrained("unsloth/Qwen2-1.5B-bnb-4bit", max_seq_length = max_seq_length, dtype = dtype)
+model, tokenizer = AutoModelForCausalLM.from_pretrained("unsloth/Qwen2-1.5B-bnb-4bit")
 model = PeftModel.from_pretrained(model, "RandomNameAnd6/Phi-3-Mini-Dhar-Mann-Adapters-BOS")
 
 def generate_text(prompt):