Update README.md

README.md

@@ -47,7 +47,7 @@ co2_eq_emissions:
 ---
 # Aira-2-124M-DPO
 
-`Aira-2` is the second version of the Aira instruction-tuned series. `Aira-2-124M-DPO` is an instruction-tuned model further fine-tuned via DPO based on [Aira-2-124M](https://huggingface.co/nicholasKluge/Aira-2-124M). The model was first trained with supervised fine-tuning (STF) with a dataset composed of prompts and completions generated synthetically by prompting already-tuned models (ChatGPT, Llama, Open-Assistant, etc). Secondly, the model was fine-tuned again via DPO using a reward dataset created by the [`Aira-RewardModel`](https://huggingface.co/nicholasKluge/RewardModel).
+Aira-2 is the second version of the Aira instruction-tuned series. Aira-2-124M-DPO is an instruction-tuned model further fine-tuned via DPO based on [Aira-2-124M](https://huggingface.co/nicholasKluge/Aira-2-124M). The model was first trained with supervised fine-tuning (STF) with a dataset composed of prompts and completions generated synthetically by prompting already-tuned models (ChatGPT, Llama, Open-Assistant, etc). Secondly, the model was fine-tuned again via DPO using a reward dataset created by the [`Aira-RewardModel`](https://huggingface.co/nicholasKluge/RewardModel).
 
 Check our gradio-demo in [Spaces](https://huggingface.co/spaces/nicholasKluge/Aira-Demo).
 
@@ -108,9 +108,11 @@ The model will output something like:
 
 ## Limitations
 
-🤥 Generative models can perpetuate the generation of pseudo-informative content, that is, false information that may appear truthful.
+- **Hallucinations:** This model can produce content that can be mistaken for truth but is, in fact, misleading or entirely false, i.e., hallucination.
 
-🤬 In certain types of tasks, generative models can produce harmful and discriminatory content inspired by historical stereotypes.
+- **Biases and Toxicity:** This model inherits the social and historical stereotypes from the data used to train it. Given these biases, the model can produce toxic content, i.e., harmful, offensive, or detrimental to individuals, groups, or communities.
+
+- **Repetition and Verbosity:** The model may get stuck on repetition loops (especially if the repetition penalty during generations is set to a meager value) or produce verbose responses unrelated to the prompt it was given.
 
 ## Evaluation
 
@@ -146,4 +148,4 @@ The model will output something like:
 
 ## License
 
-The `Aira-2-124M-DPO` is licensed under the Apache License, Version 2.0. See the [LICENSE](LICENSE) file for more details.
+Aira-2-124M-DPO is licensed under the Apache License, Version 2.0. See the [LICENSE](LICENSE) file for more details.