Update README.md
Browse files
README.md
CHANGED
|
@@ -43,7 +43,7 @@ Llama-2-7B-EAX is a language model specifically enhanced for inter non-English l
|
|
| 43 |
The model is built on top of Llama 2, following a two-stage training approach: first, an English-centric parallel data supervised fine-tuning stage (the SFT model is available at [Llama-2-7b-MT-SFT](https://huggingface.co/double7/Llama-2-7b-MT-SFT)), followed by a dedicated x2x optimization stage.
|
| 44 |
This approach strategically leverages the established English-centric capabilities of large language models to bootstrap comprehensive multilingual translation capabilities.
|
| 45 |
|
| 46 |
-
<img src="imgs/pref_overview_llama_comet.png" alt="performance overview" style="width:
|
| 47 |
|
| 48 |
|
| 49 |
- **Model type:** A 7B parameter translation model built on top of Llama 2, enhanced for x2x language pairs through specialized optimization.
|
|
|
|
| 43 |
The model is built on top of Llama 2, following a two-stage training approach: first, an English-centric parallel data supervised fine-tuning stage (the SFT model is available at [Llama-2-7b-MT-SFT](https://huggingface.co/double7/Llama-2-7b-MT-SFT)), followed by a dedicated x2x optimization stage.
|
| 44 |
This approach strategically leverages the established English-centric capabilities of large language models to bootstrap comprehensive multilingual translation capabilities.
|
| 45 |
|
| 46 |
+
<img src="imgs/pref_overview_llama_comet.png" alt="performance overview" style="width:800px; height:auto;">
|
| 47 |
|
| 48 |
|
| 49 |
- **Model type:** A 7B parameter translation model built on top of Llama 2, enhanced for x2x language pairs through specialized optimization.
|