Update app.py

app.py

@@ -18,8 +18,8 @@ instruct_pipeline_falcon = pipeline(model="tiiuae/falcon-7b-instruct", tokenizer
 instruct_pipeline_llama = pipeline(model="HuggingFaceH4/llama-7b-ift-ds-save-test4", torch_dtype=torch.bfloat16, trust_remote_code=True, device_map="auto", use_auth_token=TOKEN)
 
 def generate(query, temperature, top_p, top_k, max_new_tokens): 
-    return [instruct_pipeline_falcon(query, temperature=temperature, top_p=top_p, top_k=top_k, max_new_tokens=max_new_tokens), 
-            instruct_pipeline_llama(query, temperature=temperature, top_p=top_p, top_k=top_k, max_new_tokens=max_new_tokens)]
+    return [instruct_pipeline_falcon(query, temperature=temperature, top_p=top_p, top_k=top_k, max_new_tokens=max_new_tokens)[0]["generated_text"], 
+            instruct_pipeline_llama(query, temperature=temperature, top_p=top_p, top_k=top_k, max_new_tokens=max_new_tokens)[0]["generated_text"]]