Update app.py

app.py

@@ -1,14 +1,26 @@
 import os
-os.system("pip install torch gradio transformers")
+os.system("pip install -q gradio")
+os.system('pip install "unsloth[colab-new] @ git+https://github.com/unslothai/unsloth.git"')
+os.system('pip install --no-deps xformers "trl<0.9.0" peft accelerate bitsandbytes')
 
 import gradio as gr
 import torch
 import random
-from transformers import GPT2Tokenizer, GPT2LMHeadModel
+from unsloth import FastLanguageModel
+from peft import PeftModel
 
+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+
+load_in_4bit = True # Use 4bit quantization to reduce memory usage. Can be False.
 
-tokenizer = GPT2Tokenizer.from_pretrained("gpt2-medium")
-model = GPT2LMHeadModel.from_pretrained("RandomNameAnd6/DharGPT-Small")
+model, tokenizer = FastLanguageModel.from_pretrained(
+    model_name = "Qwen/Qwen2-1.5B",
+    max_seq_length = max_seq_length,
+    dtype = dtype,
+    load_in_4bit = load_in_4bit
+)
+
+model = PeftModel.from_pretrained(model, "RandomNameAnd6/Phi-3-Mini-Dhar-Mann-Adapters-BOS")
 
 def generate_text(prompt):
   input_ids = tokenizer.encode(prompt, return_tensors="pt")