Commit
•
c532c7b
1
Parent(s):
1563075
Update README.md
Browse files
README.md
CHANGED
@@ -1,6 +1,7 @@
|
|
1 |
---
|
2 |
language:
|
3 |
- en
|
|
|
4 |
license: apache-2.0
|
5 |
tags:
|
6 |
- text-generation-inference
|
@@ -9,8 +10,38 @@ tags:
|
|
9 |
- llama
|
10 |
- gguf
|
11 |
base_model: unsloth/llama-3-8b-Instruct-bnb-4bit
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
12 |
---
|
13 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
14 |
# Uploaded model
|
15 |
|
16 |
- **Developed by:** ahmedheakl
|
@@ -19,4 +50,4 @@ base_model: unsloth/llama-3-8b-Instruct-bnb-4bit
|
|
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 |
+
- ar
|
5 |
license: apache-2.0
|
6 |
tags:
|
7 |
- text-generation-inference
|
|
|
10 |
- llama
|
11 |
- gguf
|
12 |
base_model: unsloth/llama-3-8b-Instruct-bnb-4bit
|
13 |
+
datasets:
|
14 |
+
- ahmedheakl/arzen-llm-dataset
|
15 |
+
metrics:
|
16 |
+
- bleu
|
17 |
+
- meteor
|
18 |
+
- bertscore
|
19 |
+
library_name: transformers
|
20 |
---
|
21 |
|
22 |
+
**Please see paper & code for more information:**
|
23 |
+
- https://github.com/ahmedheakl/arazn-llm
|
24 |
+
- https://arxiv.org/abs/2406.18120
|
25 |
+
|
26 |
+
|
27 |
+
## Citation
|
28 |
+
|
29 |
+
**BibTeX:**
|
30 |
+
```
|
31 |
+
@article{heakl2024arzen,
|
32 |
+
title={ArzEn-LLM: Code-Switched Egyptian Arabic-English Translation and Speech Recognition Using LLMs},
|
33 |
+
author={Heakl, Ahmed and Zaghloul, Youssef and Ali, Mennatullah and Hossam, Rania and Gomaa, Walid},
|
34 |
+
journal={arXiv preprint arXiv:2406.18120},
|
35 |
+
year={2024}
|
36 |
+
}
|
37 |
+
```
|
38 |
+
|
39 |
+
|
40 |
+
## Model Card Authors
|
41 |
+
|
42 |
+
- Email: ahmed.heakl@ejust.edu.eg
|
43 |
+
- Linkedin: https://linkedin.com/in/ahmed-heakl
|
44 |
+
|
45 |
# Uploaded model
|
46 |
|
47 |
- **Developed by:** ahmedheakl
|
|
|
50 |
|
51 |
This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
|
52 |
|
53 |
+
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
|