Update app.py

app.py

@@ -33,7 +33,7 @@ completion_tfidf_vectorizer = joblib.load('completion_vectorizer.pkl')
 completion_tfidf_matrix = joblib.load('completion_tfidf_matrix.pkl')
 
 # specify the model's ids
-model_id = "nicholasKluge/Aira-2-124M"
+model_id = "nicholasKluge/Aira-OPT-125M"
 rewardmodel_id = "nicholasKluge/RewardModel"
 toxicitymodel_id = "nicholasKluge/ToxicityModel"
 
@@ -64,11 +64,11 @@ toxiciyTokenizer = AutoTokenizer.from_pretrained(toxicitymodel_id)
 intro = """
 ## What is `Aira`?
 
-[`Aira`](https://huggingface.co/nicholasKluge/Aira-Instruct-124M) is a series of open-domain chatbots (Portuguese and English) achieved via `instruction-tuning` and `RLHF`. The Aira-Instruct series was developed to help researchers explore the challenges related to the Alignment problem.
+[`Aira`](https://huggingface.co/nicholasKluge/Aira-OPT-125M) is a series of open-domain chatbots (Portuguese and English) achieved via `instruction-tuning` and `RLHF`. Aira-2 is the second version of the Aira series. The Aira series was developed to help researchers explore the challenges related to the Alignment problem.
 
 ## Limitations
 
-We developed our open-domain conversational chatbots via conditional text generation/instruction-tuning. This approach has a lot of limitations. Even though we can make a chatbot that can answer questions about anything, forcing the model to produce good-quality responses is hard. And by good, we mean **factual** and **nontoxic**  text. This leads us to two of the most common problems with generative models used in conversational applications:
+We developed our open-domain conversational chatbots via instruction-tuning. This approach has a lot of limitations. Even though we can make a chatbot that can answer questions about anything, forcing the model to produce good-quality responses is hard. And by good, we mean **factual** and **nontoxic**  text. This leads us to two of the most common problems with generative models used in conversational applications:
 
 🤥 Generative models can perpetuate the generation of pseudo-informative content, that is, false information that may appear truthful.
 
@@ -76,11 +76,11 @@ We developed our open-domain conversational chatbots via conditional text genera
 
 ## Intended Use
 
-`Aira` is intended only for academic research. For more information, read our [model card](https://huggingface.co/nicholasKluge/Aira-2-124M) to see how we developed `Aira`.
+`Aira` is intended only for academic research. For more information, read our [model card](https://huggingface.co/nicholasKluge/Aira-OPT-125M) to see how we developed `Aira`.
 
 ## How this demo works?
 
-For this demo, we use the lighter model we have trained (`Aira-2-124M`). This demo employs a [`reward model`](https://huggingface.co/nicholasKluge/RewardModel) and a [`toxicity model`](https://huggingface.co/nicholasKluge/ToxicityModel) to evaluate the score of each candidate's response, considering its alignment with the user's message and its level of toxicity. The generation function arranges the candidate responses in order of their reward scores and eliminates any responses deemed toxic or harmful. Subsequently, the generation function returns the candidate response with the highest score that surpasses the safety threshold, or a default message if no safe candidates are identified.
+For this demo, we use the lighter model we have trained from the OPT series (`Aira-OPT-125M`). This demo employs a [`reward model`](https://huggingface.co/nicholasKluge/RewardModel) and a [`toxicity model`](https://huggingface.co/nicholasKluge/ToxicityModel) to evaluate the score of each candidate's response, considering its alignment with the user's message and its level of toxicity. The generation function arranges the candidate responses in order of their reward scores and eliminates any responses deemed toxic or harmful. Subsequently, the generation function returns the candidate response with the highest score that surpasses the safety threshold, or a default message if no safe candidates are identified.
 """
 
 search_intro ="""