Update app.py

app.py

@@ -45,10 +45,10 @@ import torch
 # tokenizer = AutoTokenizer.from_pretrained("FlawedLLM/Bhashini")
 from unsloth import FastLanguageModel
 model, tokenizer = FastLanguageModel.from_pretrained(
-        model_name = "BhashiniLLama", # YOUR MODEL YOU USED FOR TRAINING
-        max_seq_length = max_seq_length,
-        dtype = dtype,
-        load_in_4bit = load_in_4bit,)
+        model_name = "FlawedLLM/Bhashini_2", # YOUR MODEL YOU USED FOR TRAINING
+        max_seq_length = 2048,
+        dtype = torch.float16,
+        load_in_4bit = True,)
 FastLanguageModel.for_inference(model)
 
 @spaces.GPU(duration=300)