Update app.py

app.py

@@ -1,44 +1,34 @@
 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,
+)
+tokenizer = AutoTokenizer.from_pretrained(model_id)
 
-model_id = None 
 
-if model_id:
-
-    model = AutoModelForCausalLM.from_pretrained(
-        model_id,
-        torch_dtype=torch.bfloat16,
-        trust_remote_code=True,
-        device_map="auto",
-        low_cpu_mem_usage=True,
+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,
     )
-    tokenizer = AutoTokenizer.from_pretrained(model_id)
-else:
-    model = 'We have not downloaded model yet'
-    tokenizer = 'we have not downloaded the tokenizer yet'
 
+    output_text = tokenizer.decode(output[0], skip_special_tokens=True)
+    print(output_text)
 
-def generate_text(input_text):
-    if model_id:
-        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)
-    else:
-        output_text = model
-        print(model)
     # Remove Prompt Echo from Generated Text
     cleaned_output_text = output_text.replace(input_text, "")
     return cleaned_output_text
@@ -50,5 +40,5 @@ text_generation_interface = gr.Interface(
         gr.inputs.Textbox(label="Input Text"),
     ],
     outputs=gr.inputs.Textbox(label="Generated Text"),
-    title="Falcon-7B Instruct",
+    title="Medical ChatBot",
 ).launch()