DavidDutour
commited on
Commit
•
4ddbec2
1
Parent(s):
f28165b
Update README.md
Browse files
README.md
CHANGED
@@ -8,14 +8,13 @@ tags:
|
|
8 |
---
|
9 |
# French Pro model
|
10 |
This version aims to be a multilingual model (EN 🇺🇸 + FR🇫🇷) to refine the specific professional tasks in French.
|
11 |
-
This model is adapted to professional tasks with advanced RAG contexts.
|
12 |
|
13 |
# Dataset
|
14 |
EnnoAi-Pro has been trained on a French dataset to enhance its analysis and response quality.
|
15 |
The dataset contains ~275K high-quality training samples of professional and general strategic themes.
|
16 |
|
17 |
# Tuning
|
18 |
-
We
|
19 |
|
20 |
# Prompt Format
|
21 |
We use the default ChatML format with `system` role support.
|
|
|
8 |
---
|
9 |
# French Pro model
|
10 |
This version aims to be a multilingual model (EN 🇺🇸 + FR🇫🇷) to refine the specific professional tasks in French.
|
|
|
11 |
|
12 |
# Dataset
|
13 |
EnnoAi-Pro has been trained on a French dataset to enhance its analysis and response quality.
|
14 |
The dataset contains ~275K high-quality training samples of professional and general strategic themes.
|
15 |
|
16 |
# Tuning
|
17 |
+
We use specific recipes with QLora methods to increase accuracy in advanced RAG contexts.
|
18 |
|
19 |
# Prompt Format
|
20 |
We use the default ChatML format with `system` role support.
|