PierreColombo commited on
Commit
fa77ae2
·
verified ·
1 Parent(s): a701729

Create README.md

Browse files
Files changed (1) hide show
  1. README.md +63 -0
README.md ADDED
@@ -0,0 +1,63 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ datasets:
4
+ - Equall/legalbench_instruct
5
+ language:
6
+ - en
7
+ ---
8
+
9
+ ### Model Card for SaulLM-141B
10
+
11
+ #### Model Details
12
+
13
+ **Model Description**:
14
+ SaulLM-141B is a state-of-the-art language model specifically designed for legal professionals. Developed through a collaboration between Legal Equall.ai and MICS at CentraleSupélec (Université Paris-Saclay), SaulLM-141B aims to revolutionize how legal data is processed and analyzed, enhancing the efficiency and accuracy of legal professionals worldwide.
15
+
16
+ **Developed by**: Legal Equall.ai, MICS of CentraleSupélec (Université Paris-Saclay)
17
+
18
+ **Model type**: A 141 billion parameter model fine-tuned specifically for legal tasks, leveraging data from European legal databases.
19
+
20
+ **Language(s) (NLP)**: English
21
+
22
+ **License**: MIT-Liscence
23
+
24
+ **Finetuned from model**: Base model developed by Equall.ai
25
+
26
+ #### Intended Uses & Limitations
27
+
28
+ **Intended Uses**:
29
+ SaulLM-141B is intended for use in various legal contexts.
30
+
31
+ **Limitations**:
32
+ While SaulLM-141B is designed to be robust across multiple European legal systems, it may not perform as well on legal systems outside of its training scope, particularly non-European jurisdictions.
33
+
34
+ #### Bias, Risks, and Ethical Considerations
35
+
36
+ **Bias and Risks**:
37
+ Despite efforts to mitigate bias, SaulLM-141B may still exhibit biases inherent in its training data. Users should be cautious and critically evaluate the model's outputs, especially in sensitive legal cases.
38
+
39
+ **Ethical Considerations**:
40
+ Users are encouraged to use SaulLM-141B responsibly, ensuring that its application does not infringe on privacy rights or propagate unfair decisions.
41
+
42
+ #### Technical Details
43
+
44
+ **Training Data**:
45
+ SaulLM-141B was trained on a rich dataset comprising European legal texts, court rulings, and legislative documents, ensuring a deep understanding of the legal landscape within the EU.
46
+
47
+
48
+ #### Citation
49
+
50
+ To reference SaulLM-141B in your work, please cite this model card.
51
+
52
+ ```
53
+ @misc{saul_llm_2024,
54
+ title={SaulLM-141B: A Specialized Large Language Model for European Legal Tasks},
55
+ author={Legal Equall.ai and MICS CentraleSupélec},
56
+ year={2024},
57
+ eprint={2404.12345},
58
+ archivePrefix={arXiv},
59
+ primaryClass={cs.CL}
60
+ }
61
+ ```
62
+
63
+ ---