Update README.md
Browse files
README.md
CHANGED
|
@@ -25,7 +25,7 @@ This modelcard aims to be a base template for new models. It has been generated
|
|
| 25 |
|
| 26 |
### Model Description
|
| 27 |
|
| 28 |
-
TowerInstruct is a language model that results from fine-tuning TowerBase on the
|
| 29 |
The model is trained to handle several translation-related tasks, such as general machine translation (e.g., sentence- and document-level translation, terminology-aware translation, context-aware translation), automatic post edition, named-entity recognition, gramatical error correction, and paraphrase generation.
|
| 30 |
We will release more details in the upcoming technical report.
|
| 31 |
|
|
@@ -38,7 +38,7 @@ We will release more details in the upcoming technical report.
|
|
| 38 |
|
| 39 |
## Intended uses & limitations
|
| 40 |
|
| 41 |
-
The model was initially fine-tuned on a filtered and preprocessed supervised fine-tuning dataset (
|
| 42 |
- Translation
|
| 43 |
- Automatic Post Edition
|
| 44 |
- Machine Translation Evaluation
|
|
@@ -50,7 +50,7 @@ The model was initially fine-tuned on a filtered and preprocessed supervised fin
|
|
| 50 |
- Synthetic Chat data
|
| 51 |
- Code instructions
|
| 52 |
|
| 53 |
-
You can find the dataset and all data sources of
|
| 54 |
|
| 55 |
### Direct Use
|
| 56 |
|
|
|
|
| 25 |
|
| 26 |
### Model Description
|
| 27 |
|
| 28 |
+
TowerInstruct is a language model that results from fine-tuning TowerBase on the TowerBlocks supervised fine-tuning dataset. TowerInstruct v0.1 is the first model in the series.
|
| 29 |
The model is trained to handle several translation-related tasks, such as general machine translation (e.g., sentence- and document-level translation, terminology-aware translation, context-aware translation), automatic post edition, named-entity recognition, gramatical error correction, and paraphrase generation.
|
| 30 |
We will release more details in the upcoming technical report.
|
| 31 |
|
|
|
|
| 38 |
|
| 39 |
## Intended uses & limitations
|
| 40 |
|
| 41 |
+
The model was initially fine-tuned on a filtered and preprocessed supervised fine-tuning dataset (TowerBlocks), which contains a diverse range of data sources:
|
| 42 |
- Translation
|
| 43 |
- Automatic Post Edition
|
| 44 |
- Machine Translation Evaluation
|
|
|
|
| 50 |
- Synthetic Chat data
|
| 51 |
- Code instructions
|
| 52 |
|
| 53 |
+
You can find the dataset and all data sources of TowerBlocks here.
|
| 54 |
|
| 55 |
### Direct Use
|
| 56 |
|