Update README.md
Browse files
README.md
CHANGED
@@ -21,7 +21,9 @@ tags:
|
|
21 |
|
22 |
This model is part of the CroissantLLM initiative, and corresponds to the checkpoint after 190k steps (2.99 T) tokens and a final Chat finetuing phase.
|
23 |
|
24 |
-
|
|
|
|
|
25 |
|
26 |
```python
|
27 |
CHAT = """<|im_start|>user
|
@@ -41,7 +43,14 @@ This work enriches the NLP landscape, breaking away from previous English-centri
|
|
41 |
Our work can be cited as:
|
42 |
|
43 |
```bash
|
44 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
45 |
```
|
46 |
|
47 |
## Usage
|
|
|
21 |
|
22 |
This model is part of the CroissantLLM initiative, and corresponds to the checkpoint after 190k steps (2.99 T) tokens and a final Chat finetuing phase.
|
23 |
|
24 |
+
https://arxiv.org/abs/2402.00786
|
25 |
+
|
26 |
+
For best performance, it should be used with a temperature of above 0.4, and with the exact template described below:
|
27 |
|
28 |
```python
|
29 |
CHAT = """<|im_start|>user
|
|
|
43 |
Our work can be cited as:
|
44 |
|
45 |
```bash
|
46 |
+
@misc{faysse2024croissantllm,
|
47 |
+
title={CroissantLLM: A Truly Bilingual French-English Language Model},
|
48 |
+
author={Manuel Faysse and Patrick Fernandes and Nuno Guerreiro and António Loison and Duarte Alves and Caio Corro and Nicolas Boizard and João Alves and Ricardo Rei and Pedro Martins and Antoni Bigata Casademunt and François Yvon and André Martins and Gautier Viaud and Céline Hudelot and Pierre Colombo},
|
49 |
+
year={2024},
|
50 |
+
eprint={2402.00786},
|
51 |
+
archivePrefix={arXiv},
|
52 |
+
primaryClass={cs.CL}
|
53 |
+
}
|
54 |
```
|
55 |
|
56 |
## Usage
|