Update app.py

app.py

@@ -23,16 +23,17 @@
 # iface.launch(share=True)
 
 import gradio as gr
-from transformers import pipeline
+from transformers import AutoModelForCausalLM, AutoTokenizer
 
-# Load the question answering pipeline
-qa_pipeline = pipeline("question-answering", model="distilbert-base-cased-distilled-squad", tokenizer="distilbert-base-cased")
+model_name = "abacusai/Smaug-72B-v0.1"
+model = AutoModelForCausalLM.from_pretrained(model_name)
+tokenizer = AutoTokenizer.from_pretrained(model_name)
 
-# Define a function to generate answer for the given question
 def generate_answer(question):
-    # Call the question answering pipeline
-    result = qa_pipeline(question=question, context=None)
-    return result["answer"]
+    inputs = tokenizer.encode("Question: " + question, return_tensors="pt")
+    outputs = model.generate(inputs, max_length=100, num_return_sequences=1, early_stopping=True, do_sample=True)
+    answer = tokenizer.decode(outputs[0], skip_special_tokens=True)
+    return answer
 
 iface = gr.Interface(
     fn=generate_answer,
@@ -44,3 +45,21 @@ iface = gr.Interface(
 
 iface.launch(share=True)  # Deploy the interface
 
+
+# from transformers import AutoModelForCausalLM, AutoTokenizer
+
+# model_name = "abacusai/Smaug-72B-v0.1"
+# model = AutoModelForCausalLM.from_pretrained(model_name)
+# tokenizer = AutoTokenizer.from_pretrained(model_name)
+
+
+
+
+
+# def generate_answer(question):
+#     inputs = tokenizer.encode("Question: " + question, return_tensors="pt")
+#     outputs = model.generate(inputs, max_length=100, num_return_sequences=1, early_stopping=True, do_sample=True)
+#     answer = tokenizer.decode(outputs[0], skip_special_tokens=True)
+#     return answer
+
+