Update app.py

app.py

@@ -1,17 +1,17 @@
 import re
 import spaces
 import gradio as gr
-from transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig
+from transformers import AutoTokenizer, AutoModel, BitsAndBytesConfig
 import torch
-from peft import PeftModel, PeftConfig
+# from peft import PeftModel, PeftConfig
 
 
-tokenizer = AutoTokenizer.from_pretrained("FlawedLLM/BhashiniLLM")
-quantization_config = BitsAndBytesConfig(
-        load_in_4bit=True,
-        bnb_4bit_use_double_quant=True,
-        bnb_4bit_quant_type="nf4",  
-        bnb_4bit_compute_dtype=torch.float16)
+tokenizer = AutoTokenizer.from_pretrained("FlawedLLM/Bhashini")
+# quantization_config = BitsAndBytesConfig(
+#         load_in_4bit=True,
+#         bnb_4bit_use_double_quant=True,
+#         bnb_4bit_quant_type="nf4",  
+#         bnb_4bit_compute_dtype=torch.float16)
 # model = AutoModelForCausalLM.from_pretrained("FlawedLLM/BhashiniLLM",
 #                                              device_map="auto",
 #                                              quantization_config=quantization_config, 
@@ -34,9 +34,7 @@ quantization_config = BitsAndBytesConfig(
 
 
 
-config = PeftConfig.from_pretrained("FlawedLLM/BhashiniLLM")
-base_model = AutoModelForCausalLM.from_pretrained("unsloth/llama-3-8b-bnb-4bit",  device_map='auto', quantization_config=quantization_config)
-model = PeftModel.from_pretrained(base_model, "FlawedLLM/BhashiniLLM")
+model = AutoModel.from_pretrained("FlawedLLM/Bhashini",device_map='auto')
 
 
 @spaces.GPU(duration=300)