Update app.py

app.py

@@ -4,11 +4,19 @@ import gradio as gr
 from peft import PeftModel, PeftConfig
 from peft import AutoPeftModelForCausalLM
 from transformers import AutoTokenizer
-model = AutoPeftModelForCausalLM.from_pretrained(
-        "FlawedLLM/BhashiniLLM", # YOUR MODEL YOU USED FOR TRAINING
+# model = AutoPeftModelForCausalLM.from_pretrained(
+#         "FlawedLLM/BhashiniLLM", # YOUR MODEL YOU USED FOR TRAINING
+#         load_in_4bit = True,
+# )
+# tokenizer = AutoTokenizer.from_pretrained("FlawedLLM/BhashiniLLM")
+from unsloth import FastLanguageModel
+model, tokenizer = FastLanguageModel.from_pretrained(
+        model_name = "FlawedLLM/BhashiniLLM", # YOUR MODEL YOU USED FOR TRAINING
+        max_seq_length = 2048,
+        dtype = None,
         load_in_4bit = True,
 )
-tokenizer = AutoTokenizer.from_pretrained("FlawedLLM/BhashiniLLM")
+FastLanguageModel.for_inference(model)
 @spaces.GPU(duration=300)
 def chunk_it(input_command):