Create README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,44 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
language:
|
| 3 |
+
- en
|
| 4 |
+
- de
|
| 5 |
+
- fr
|
| 6 |
+
- zh
|
| 7 |
+
- pt
|
| 8 |
+
- nl
|
| 9 |
+
- ru
|
| 10 |
+
- ko
|
| 11 |
+
- it
|
| 12 |
+
- es
|
| 13 |
+
license: cc-by-nc-4.0
|
| 14 |
+
metrics:
|
| 15 |
+
- comet
|
| 16 |
+
pipeline_tag: translation
|
| 17 |
+
---
|
| 18 |
+
# Model Card for TowerInstruct-WMT24-Chat-7B
|
| 19 |
+
|
| 20 |
+
## Model Details
|
| 21 |
+
|
| 22 |
+
### Model Description
|
| 23 |
+
|
| 24 |
+
TowerInstruct-WMT24-Chat-7B is is a language model that results from fine-tuning TowerBase on TowerBlocks and the WMT24 Chat MT Shared task training set.
|
| 25 |
+
|
| 26 |
+
It is specifically tailoured for context-aware translation of customer support chats.
|
| 27 |
+
|
| 28 |
+
Check out our [paper](https://aclanthology.org/2024.wmt-1.100/) for more details and information on training and data.
|
| 29 |
+
|
| 30 |
+
Information on model usage, out-of-scope usages, risks, etc... from the model cards of the TowerInstruct models applies here.
|
| 31 |
+
|
| 32 |
+
## Citation
|
| 33 |
+
|
| 34 |
+
```bibtex
|
| 35 |
+
@inproceedings{pombal2024improving,
|
| 36 |
+
title={Improving Context Usage for Translating Bilingual Customer Support Chat with Large Language Models},
|
| 37 |
+
author={Pombal, Jos{\'e} and Agrawal, Sweta and Martins, Andr{\'e} FT},
|
| 38 |
+
booktitle={Proceedings of the Ninth Conference on Machine Translation},
|
| 39 |
+
pages={993--1003},
|
| 40 |
+
year={2024}
|
| 41 |
+
}
|
| 42 |
+
```
|
| 43 |
+
|
| 44 |
+
[<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl)
|