Update README.md
Browse files
README.md
CHANGED
|
@@ -86,11 +86,11 @@ This QLoRA was trained on a Lambda Labs 1x H100 80GB GPU instance.
|
|
| 86 |
|
| 87 |
## Citation
|
| 88 |
|
| 89 |
-
Llama 2 (Meta AI) for the base model.
|
| 90 |
-
Farouk E / Far El: https://twitter.com/far__el for helping with all my silly questions about QLoRA
|
| 91 |
-
Lambda Labs for the compute. The model itself only took a few hours to train, but it took me days to learn how to tie everything together.
|
| 92 |
-
Tim Dettmers, Artidoro Pagnoni, Ari Holtzman, Luke Zettlemoyer for QLoRA + implementation on github: https://github.com/artidoro/qlora/
|
| 93 |
-
@eugene-yh and @jinyongyoo on Github + @ChrisHayduk for the QLoRA merge: https://gist.github.com/ChrisHayduk/1a53463331f52dca205e55982baf9930
|
| 94 |
|
| 95 |
|
| 96 |
## Model Card Contact
|
|
|
|
| 86 |
|
| 87 |
## Citation
|
| 88 |
|
| 89 |
+
- Llama 2 (Meta AI) for the base model.
|
| 90 |
+
- Farouk E / Far El: https://twitter.com/far__el for helping with all my silly questions about QLoRA
|
| 91 |
+
- Lambda Labs for the compute. The model itself only took a few hours to train, but it took me days to learn how to tie everything together.
|
| 92 |
+
- Tim Dettmers, Artidoro Pagnoni, Ari Holtzman, Luke Zettlemoyer for QLoRA + implementation on github: https://github.com/artidoro/qlora/
|
| 93 |
+
- @eugene-yh and @jinyongyoo on Github + @ChrisHayduk for the QLoRA merge: https://gist.github.com/ChrisHayduk/1a53463331f52dca205e55982baf9930
|
| 94 |
|
| 95 |
|
| 96 |
## Model Card Contact
|