Update README.md
Browse files
README.md
CHANGED
@@ -13,20 +13,22 @@ tags:
|
|
13 |
|
14 |
## Model Card for Model ID
|
15 |
|
16 |
-
Chocolatine v1.0 8B params. Llama3-8B arch.
|
|
|
|
|
17 |
Base model : mlabonne/NeuralDaredevil-8B-abliterated
|
18 |
|
19 |
![image/jpeg](https://github.com/jpacifico/French-Alpaca/blob/main/Assets/chocolatine.png?raw=true)
|
20 |
|
21 |
### Model Description
|
22 |
|
23 |
-
fine-tuned with the 12k DPO Intel/orca_dpo_pairs translated in French AIffl/french_orca_dpo_pairs.
|
24 |
Chocolatine is a general model and can itself be finetuned to be specialized for specific use cases.
|
25 |
-
More infos & Benchmarks very soon ^^
|
26 |
|
27 |
### Limitations
|
28 |
|
29 |
-
Chocolatine is a quick demonstration that a base 8B model can be easily fine-tuned to specialize in a particular language.
|
30 |
It does not have any moderation mechanisms.
|
31 |
|
32 |
- **Developed by:** Jonathan Pacifico, 2024
|
|
|
13 |
|
14 |
## Model Card for Model ID
|
15 |
|
16 |
+
Chocolatine v1.0 8B params. Llama3-8B arch.
|
17 |
+
The delicious model for mastering French 😋
|
18 |
+
|
19 |
Base model : mlabonne/NeuralDaredevil-8B-abliterated
|
20 |
|
21 |
![image/jpeg](https://github.com/jpacifico/French-Alpaca/blob/main/Assets/chocolatine.png?raw=true)
|
22 |
|
23 |
### Model Description
|
24 |
|
25 |
+
fine-tuned with the 12k DPO Intel/orca_dpo_pairs translated in French : AIffl/french_orca_dpo_pairs.
|
26 |
Chocolatine is a general model and can itself be finetuned to be specialized for specific use cases.
|
27 |
+
More infos & Benchmarks very soon ^^
|
28 |
|
29 |
### Limitations
|
30 |
|
31 |
+
Chocolatine is a quick demonstration that a base 8B model can be easily fine-tuned to specialize in a particular language.
|
32 |
It does not have any moderation mechanisms.
|
33 |
|
34 |
- **Developed by:** Jonathan Pacifico, 2024
|