nicholasKluge
commited on
Commit
•
3256e4b
1
Parent(s):
ac1136c
Update README.md
Browse files
README.md
CHANGED
@@ -41,7 +41,7 @@ co2_eq_emissions:
|
|
41 |
---
|
42 |
# Aira-2-portuguese-1B7
|
43 |
|
44 |
-
`Aira-2
|
45 |
|
46 |
Check our gradio-demo in [Spaces](https://huggingface.co/spaces/nicholasKluge/Aira-Demo-Portuguese).
|
47 |
|
@@ -119,7 +119,7 @@ The model will output something like:
|
|
119 |
|
120 |
@misc{nicholas22aira,
|
121 |
doi = {10.5281/zenodo.6989727},
|
122 |
-
url = {https://huggingface.co/nicholasKluge/Aira-2-portuguese-
|
123 |
author = {Nicholas Kluge Corrêa},
|
124 |
title = {Aira},
|
125 |
year = {2023},
|
|
|
41 |
---
|
42 |
# Aira-2-portuguese-1B7
|
43 |
|
44 |
+
`Aira-2` is the second version of the Aira instruction-tuned series. `Aira-2-portuguese-1B7` is an instruction-tuned GPT-style model based on [BLOOM](https://huggingface.co/bigscience/bloom-1b7). The model was trained with a dataset composed of prompts and completions generated synthetically by prompting already-tuned models (ChatGPT, Llama, Open-Assistant, etc).
|
45 |
|
46 |
Check our gradio-demo in [Spaces](https://huggingface.co/spaces/nicholasKluge/Aira-Demo-Portuguese).
|
47 |
|
|
|
119 |
|
120 |
@misc{nicholas22aira,
|
121 |
doi = {10.5281/zenodo.6989727},
|
122 |
+
url = {https://huggingface.co/nicholasKluge/Aira-2-portuguese-1B7},
|
123 |
author = {Nicholas Kluge Corrêa},
|
124 |
title = {Aira},
|
125 |
year = {2023},
|