Update README.md
Browse files
README.md
CHANGED
|
@@ -12,12 +12,14 @@ datasets:
|
|
| 12 |
|
| 13 |
*Brahe* is an analytical LLM for multilingual literature fine-tuned from llama-13B. Given any text, Brahe will generate a list of potentially twenty annotations. Brahe is intended to be used by computational humanities project, similarly to BookNLP.
|
| 14 |
|
| 15 |
-
*Brahe* has been trained on 8,000 excerpts of literature in the public domain and on a set of synthetic and manual annotations. Half of the excerpts are in English and half in other languages (mostly French, German, Italian…).
|
| 16 |
|
| 17 |
Thanks to the native multilinual capacity of llama-13B, *Brahe* has been proven to work on languages that were not part of its original corpus, such as the Gascon variety of Occitan.
|
| 18 |
|
| 19 |
*Brahe* is a reversed companion of *[Epstein](https://huggingface.co/Pclanglais/epstein)*, a generative AI model to create new literary texts by submitting annotated prompts (for now in English-only). Both models are named after the protagonists of the philosophical novel of Daniele del Giudice, *Atlante occidentale*. Brahe is a scientist working at the CERN on quantum physics, Epstein is a novelist and they both confront their different views of reality.
|
| 20 |
|
|
|
|
|
|
|
| 21 |
## Running Brahe
|
| 22 |
|
| 23 |
The best way to test Brahe is to use the [official demo](https://colab.research.google.com/drive/1asOBSChi56V2U1HOvKwN-Ilqfct8gXlR?usp=sharing) on Google Colab.
|
|
|
|
| 12 |
|
| 13 |
*Brahe* is an analytical LLM for multilingual literature fine-tuned from llama-13B. Given any text, Brahe will generate a list of potentially twenty annotations. Brahe is intended to be used by computational humanities project, similarly to BookNLP.
|
| 14 |
|
| 15 |
+
*Brahe* has been trained on.Jean Zay (compute plan AD011014736) on 8,000 excerpts of literature in the public domain and on a set of synthetic and manual annotations. Half of the excerpts are in English and half in other languages (mostly French, German, Italian…).
|
| 16 |
|
| 17 |
Thanks to the native multilinual capacity of llama-13B, *Brahe* has been proven to work on languages that were not part of its original corpus, such as the Gascon variety of Occitan.
|
| 18 |
|
| 19 |
*Brahe* is a reversed companion of *[Epstein](https://huggingface.co/Pclanglais/epstein)*, a generative AI model to create new literary texts by submitting annotated prompts (for now in English-only). Both models are named after the protagonists of the philosophical novel of Daniele del Giudice, *Atlante occidentale*. Brahe is a scientist working at the CERN on quantum physics, Epstein is a novelist and they both confront their different views of reality.
|
| 20 |
|
| 21 |
+
|
| 22 |
+
|
| 23 |
## Running Brahe
|
| 24 |
|
| 25 |
The best way to test Brahe is to use the [official demo](https://colab.research.google.com/drive/1asOBSChi56V2U1HOvKwN-Ilqfct8gXlR?usp=sharing) on Google Colab.
|