willyninja30
commited on
Commit
•
818c606
1
Parent(s):
5067875
Update README.md
Browse files
README.md
CHANGED
@@ -14,7 +14,9 @@ tags:
|
|
14 |
- data
|
15 |
- education
|
16 |
- languages
|
|
|
17 |
pipeline_tag: text-generation
|
|
|
18 |
---
|
19 |
ARIA is the last version of Llama 2 70B finetuned over 50.000 high quality french tokens. We built our own dataset for training doing an extract of the French Dataset from Enno and removing Alpaca style translated text from english.
|
20 |
|
@@ -85,4 +87,4 @@ We are also applying rope scalling as experimental approach used by several othe
|
|
85 |
**Evaluation of fine-tuned LLMs on different safety datasets.** Same metric definitions as above.
|
86 |
|
87 |
## Ethical Considerations and Limitations
|
88 |
-
ARIA is a new technology that carries risks with use.
|
|
|
14 |
- data
|
15 |
- education
|
16 |
- languages
|
17 |
+
- legal
|
18 |
pipeline_tag: text-generation
|
19 |
+
inference: true
|
20 |
---
|
21 |
ARIA is the last version of Llama 2 70B finetuned over 50.000 high quality french tokens. We built our own dataset for training doing an extract of the French Dataset from Enno and removing Alpaca style translated text from english.
|
22 |
|
|
|
87 |
**Evaluation of fine-tuned LLMs on different safety datasets.** Same metric definitions as above.
|
88 |
|
89 |
## Ethical Considerations and Limitations
|
90 |
+
ARIA is a new technology that carries risks with use.
|