nicholasKluge commited on
Commit
d6cfb51
1 Parent(s): 6ed2f9d

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +6 -4
README.md CHANGED
@@ -39,7 +39,7 @@ co2_eq_emissions:
39
  ---
40
  # Aira-OPT-125M
41
 
42
- `Aira-2` is the second version of the Aira instruction-tuned series. `Aira-OPT-125M` is an instruction-tuned model based on [OPT](https://huggingface.co/facebook/opt-125m). The model was trained with a dataset composed of prompts and completions generated synthetically by prompting already-tuned models (ChatGPT, Llama, Open-Assistant, etc).
43
 
44
  Check our gradio-demo in [Spaces](https://huggingface.co/spaces/nicholasKluge/Aira-Demo).
45
 
@@ -99,9 +99,11 @@ The model will output something like:
99
 
100
  ## Limitations
101
 
102
- 🤥 Generative models can perpetuate the generation of pseudo-informative content, that is, false information that may appear truthful.
103
 
104
- 🤬 In certain types of tasks, generative models can produce harmful and discriminatory content inspired by historical stereotypes.
 
 
105
 
106
  ## Evaluation
107
 
@@ -134,4 +136,4 @@ The model will output something like:
134
 
135
  ## License
136
 
137
- The `Aira-OPT-125M` is licensed under the OPT-175B License Agreement, Copyright (c) Meta Platforms, Inc. All Rights Reserved. See the [LICENSE](LICENSE.md) file for more details.
 
39
  ---
40
  # Aira-OPT-125M
41
 
42
+ Aira-2 is the second version of the Aira instruction-tuned series. Aira-OPT-125M is an instruction-tuned model based on [OPT](https://huggingface.co/facebook/opt-125m). The model was trained with a dataset composed of prompts and completions generated synthetically by prompting already-tuned models (ChatGPT, Llama, Open-Assistant, etc).
43
 
44
  Check our gradio-demo in [Spaces](https://huggingface.co/spaces/nicholasKluge/Aira-Demo).
45
 
 
99
 
100
  ## Limitations
101
 
102
+ - **Hallucinations:** This model can produce content that can be mistaken for truth but is, in fact, misleading or entirely false, i.e., hallucination.
103
 
104
+ - **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.
105
+
106
+ - **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.
107
 
108
  ## Evaluation
109
 
 
136
 
137
  ## License
138
 
139
+ Aira-OPT-125M is licensed under the OPT-175B License Agreement, Copyright (c) Meta Platforms, Inc. All Rights Reserved. See the [LICENSE](LICENSE.md) file for more details.