Update README.md
Browse files
README.md
CHANGED
|
@@ -123,7 +123,7 @@ translator("Translate to Zulu: The cow is eating grass.")
|
|
| 123 |
|
| 124 |
#### Preprocessing [optional]
|
| 125 |
|
| 126 |
-
|
| 127 |
|
| 128 |
|
| 129 |
#### Training Hyperparameters
|
|
@@ -187,12 +187,6 @@ Look at the repo to find out how the dataset clean up and preparation code in py
|
|
| 187 |
**OMT-LR-Mistral7b** fine-tunes **Mistral-7B-v0.1** using custom prompt engineering for **low-resource African languages**, specifically **English to Zulu and Xhosa** translation. It was trained for 31 GPU days using a multilingual dataset to improve translation accuracy for morphologically rich languages.
|
| 188 |
|
| 189 |
|
| 190 |
-
## Model Examination [optional]
|
| 191 |
-
|
| 192 |
-
<!-- Relevant interpretability work for the model goes here -->
|
| 193 |
-
|
| 194 |
-
[More Information Needed]
|
| 195 |
-
|
| 196 |
## Environmental Impact
|
| 197 |
|
| 198 |
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
|
|
|
| 123 |
|
| 124 |
#### Preprocessing [optional]
|
| 125 |
|
| 126 |
+
Please check out the repo above to get the dataset cleanup and preparation code.
|
| 127 |
|
| 128 |
|
| 129 |
#### Training Hyperparameters
|
|
|
|
| 187 |
**OMT-LR-Mistral7b** fine-tunes **Mistral-7B-v0.1** using custom prompt engineering for **low-resource African languages**, specifically **English to Zulu and Xhosa** translation. It was trained for 31 GPU days using a multilingual dataset to improve translation accuracy for morphologically rich languages.
|
| 188 |
|
| 189 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 190 |
## Environmental Impact
|
| 191 |
|
| 192 |
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|