stableLM

question_paper.py

@@ -11,12 +11,12 @@ MODEL = None
 TOKENIZER = None
 
 @app.get("/")
-def llama():
-    prompt = [{'role': 'user', 'content': 'List 3 synonyms for the word "tiny"'}]
+def llama(input):
+    prompt = [{'role': 'user', 'content': input}]
     inputs = TOKENIZER.apply_chat_template( prompt, add_generation_prompt=True,     return_tensors='pt' )
 
     tokens = MODEL.generate( inputs.to(MODEL.device), max_new_tokens=1024, temperature=0.3, do_sample=True)
-    
+
     tresponse = TOKENIZER.decode(tokens[0], skip_special_tokens=False)
     print(tresponse)