Update app.py

app.py

@@ -2,29 +2,17 @@ import gradio as gr
 from transformers import AutoTokenizer, AutoModelForCausalLM
 import torch
 model_id = "Mohammed-Altaf/Medical-ChatBot"
-model = AutoModelForCausalLM.from_pretrained(
-    model_id,
-    torch_dtype=torch.bfloat16,
-    trust_remote_code=True,
-    device_map="auto",
-    low_cpu_mem_usage=True,
-)
+model = AutoModelForCausalLM.from_pretrained(model_id)
 tokenizer = AutoTokenizer.from_pretrained(model_id)
 
 
 def generate_text(input_text):
     input_ids = tokenizer.encode(input_text, return_tensors="pt")
-    attention_mask = torch.ones(input_ids.shape)
 
     output = model.generate(
         input_ids,
-        attention_mask=attention_mask,
         max_length=200,
-        do_sample=True,
-        top_k=10,
-        num_return_sequences=1,
-        eos_token_id=tokenizer.eos_token_id,
-    )
+        )
 
     output_text = tokenizer.decode(output[0], skip_special_tokens=True)
     print(output_text)