Update app.py

app.py

@@ -17,7 +17,7 @@ demo.launch()
 #!pip install accelerate
 #!pip install -i 
 
-"""
+
 
 import gradio as gr
 import torch
@@ -29,17 +29,17 @@ from transformers import AutoModelForCausalLM, AutoTokenizer
 peft_model_id = "charansr/llama2-7b-chat-hf-therapist"
 
 config = PeftConfig.from_pretrained(peft_model_id,
-                                   use_auth_token="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", load_in_8bit=True, device_map='auto',)
+                                   use_auth_token="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", load_in_8bit=True, device_map='cpu',)
 
-newmodel = AutoModelForCausalLM.from_pretrained(config.base_model_name_or_path, return_dict=True, load_in_8bit=True, device_map='auto',
+newmodel = AutoModelForCausalLM.from_pretrained(config.base_model_name_or_path, return_dict=True, load_in_8bit=True, device_map='cpu',
                                                 use_auth_token="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")
 
 newtokenizer = AutoTokenizer.from_pretrained(config.base_model_name_or_path,
-                                            use_auth_token="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", load_in_8bit=True, device_map='auto',)
+                                            use_auth_token="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", load_in_8bit=True, device_map='cpu',)
 
 # Load the Lora model
 newmodel = PeftModel.from_pretrained(newmodel, peft_model_id,
-                                    use_auth_token="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", load_in_8bit=True, device_map='auto')
+                                    use_auth_token="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", load_in_8bit=True, device_map='cpu')
 
 def givetext(input_text,lmodel,ltokenizer):
   eval_prompt_pt1 = "\nBelow is an instruction that describes a task. Write a response that appropriately completes the request.\n### Instruction: Act like a therapist and respond\n\n### Input: "
@@ -62,7 +62,6 @@ demo.launch()
 
 """
 
-
 import gradio as gr
 import torch
 from peft import PeftModel, PeftConfig
@@ -93,3 +92,5 @@ def mental_chat(message, history):
 demo = gr.ChatInterface(mental_chat)
 
 demo.launch()
+
+"""