Update app.py

app.py

@@ -1,17 +1,13 @@
 import re
 from unsloth import FastLanguageModel
+from peft import PeftModel, PeftConfig
+from transformers import AutoModelForCausalLM
 
-
-if True:
-    from unsloth import FastLanguageModel
-    model, tokenizer = FastLanguageModel.from_pretrained(
-        model_name = "FlawedLLM/BhashiniLLM", # YOUR MODEL YOU USED FOR TRAINING
-        max_seq_length = max_seq_length,
-        dtype = dtype,
-        load_in_4bit = load_in_4bit,
-    )
-    FastLanguageModel.for_inference(model) # Enable native 2x faster inference
-
+config = PeftConfig.from_pretrained("FlawedLLM/BhashiniLLM")
+base_model = AutoModelForCausalLM.from_pretrained("unsloth/llama-3-8b-bnb-4bit")
+model = PeftModel.from_pretrained(base_model, "FlawedLLM/BhashiniLLM")
+FastLanguageModel.for_inference(model) # Enable native 2x faster inference
+tokenizer = AutoTokenizer.from_pretrained("FlawedLLM/BhashiniLLM")
 @spaces.GPU
 def chunk_it(input_command):
     inputs = tokenizer(