Create README.md
Browse files
README.md
ADDED
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: transformers
|
3 |
+
license: apache-2.0
|
4 |
+
language:
|
5 |
+
- fr
|
6 |
+
- en
|
7 |
+
datasets:
|
8 |
+
- jpacifico/French-Alpaca-dataset-Instruct-110K
|
9 |
+
---
|
10 |
+
|
11 |
+
## Model Card for Model ID
|
12 |
+
|
13 |
+
A 7B language model. Good in French.
|
14 |
+
|
15 |
+
### Model Description
|
16 |
+
|
17 |
+
French-Alpaca is a 7.24B params LLM model based on the mlabonne/AlphaMonarch-7B merged model(Mistral-7B base),
|
18 |
+
fine-tuned from the original French-Alpaca-dataset entirely generated with OpenAI GPT-3.5-turbo.
|
19 |
+
|
20 |
+
This quantized GGUF version can be used on a CPU device, compatible with llama.cpp and LM Studio.
|
21 |
+
|
22 |
+
The fine-tuning method is inspired from https://crfm.stanford.edu/2023/03/13/alpaca.html
|
23 |
+
|
24 |
+
### Limitations
|
25 |
+
|
26 |
+
The French-Alpaca beta model is a quick demonstration that a base 7B model can be easily fine-tuned to specialize in a particular language.
|
27 |
+
It does not have any moderation mechanisms.
|
28 |
+
|
29 |
+
- **Developed by:** Jonathan Pacifico, 2024
|
30 |
+
- **Model type:** LLM
|
31 |
+
- **Language(s) (NLP):** French
|
32 |
+
- **License:** Apache 2.0
|
33 |
+
- **Finetuned from model :** mlabonne/AlphaMonarch-7B
|