added import bitsandbytes and accelerate

app.py

@@ -1,5 +1,9 @@
 import gradio as gr
 from transformers import AutoModelForCausalLM, AutoTokenizer
+import bitsandbytes as bnb
+import accelerate
+print("Bitsandbytes version:", bnb.__version__)
+print("Accelerate version:", accelerate.__version__)
 
 # Load the original model
 original_model = AutoModelForCausalLM.from_pretrained("unsloth/DeepSeek-R1-Distill-Llama-8B-unsloth-bnb-4bit")

requirements.txt

@@ -2,4 +2,4 @@ torch
 transformers
 gradio
 accelerate>=0.26.0
-bitsandbytes>=0.42.0 --extra-index-url https://download.pytorch.org/whl/cu118
+bitsandbytes