obadabaq commited on
Commit
898e60e
1 Parent(s): 1d2d50e

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +30 -8
README.md CHANGED
@@ -1,8 +1,9 @@
1
  ---
2
- base_model: StevenChen16/llama3-8b-Lawyer
3
  language:
4
  - en
5
- license: apache-2.0
 
 
6
  tags:
7
  - text-generation-inference
8
  - transformers
@@ -11,12 +12,33 @@ tags:
11
  - trl
12
  ---
13
 
14
- # Uploaded model
15
 
16
- - **Developed by:** obadabaq
17
- - **License:** apache-2.0
18
- - **Finetuned from model :** StevenChen16/llama3-8b-Lawyer
19
 
20
- This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
21
 
22
- [<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
 
2
  language:
3
  - en
4
+ datasets:
5
+ - obadabaq/structured-uae-laws
6
+ license: mit
7
  tags:
8
  - text-generation-inference
9
  - transformers
 
12
  - trl
13
  ---
14
 
15
+ # ai_lawyer
16
 
17
+ This project involves fine-tuning the LLaMA3-8B model using the obadabaq/structured-uae-laws dataset. The fine-tuning was conducted with the Unsloth. The fine-tuned model has been uploaded to Hugging Face and is available at obadabaq/ai_lawyer.
 
 
18
 
19
+ ## Project Overview
20
 
21
+ The main objective of this project was to develop a high-efficiency legal question-answering model utilizing LLaMA3-8B. By harnessing the obadabaq/structured-uae-laws dataset and the features of Unsloth, we successfully fine-tuned the model. This AI model operates similarly to a lawyer, posing comprehensive questions regarding the case background and rendering decisions based on the information provided.
22
+
23
+ ## Fine-Tuning Details
24
+
25
+ ### Model
26
+ - Base Model: `StevenChen16/llama3-8b-Lawyer`
27
+ - Fine-Tuned Model: `obadabaq/ai_lawyer`
28
+
29
+ ### Dataset
30
+ - Dataset Used: `obadabaq/structured-uae-laws
31
+
32
+ ## Repository`
33
+
34
+ - GitHub Repository: [ai-lawer/UAE-AI-Lawyer](https://github.com/StevenChen16/lawyer-llama3-8b.git)
35
+
36
+ ## Results
37
+
38
+ The fine-tuned model has demonstrated encouraging results in comprehending and responding to legal inquiries. By utilizing advanced methods like LoRA and UnslothAI optimizations, the training process was both efficient and effective, leading to high-quality model outputs.
39
+
40
+ ## Acknowledgements
41
+
42
+ - [unsloth](https://github.com/unslothai/unsloth)
43
+ - [UAE Legislation](https://uaelegislation.gov.ae/en)
44
+ - [Base Model](https://huggingface.co/StevenChen16/llama3-8b-Lawyer)