added accelarate support

app.py

@@ -5,7 +5,7 @@ import torch
 # Load your model and tokenizer
 model_name = "modelsmafia/punjabi_Gemma-2B"  # Replace with your model name
 tokenizer = AutoTokenizer.from_pretrained(model_name)
-model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.float16, device_map="auto", trust_remote_code=True)
+model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.float16, device_map="cpu",low_cpu_mem_usage=True,  trust_remote_code=True)
 
 # Create a chat function
 def chat_with_model(message, history):

requirements.txt

@@ -1,4 +1,5 @@
 huggingface_hub==0.25.2
 gradio
 transformers
-torch
+torch
+accelerate>=0.26.0