Updated images
Browse files
README.md
CHANGED
|
@@ -123,7 +123,9 @@ The existing Indic benchmarks are not natively in Indian languages, rather, they
|
|
| 123 |
### Qualitative Results
|
| 124 |
Below are the results from manual evaluation of prompt-response pairs across languages and task categories. Scores are between 1-5 (higher the better). Model names were anonymised during the evaluation.
|
| 125 |
|
| 126 |
-
<
|
|
|
|
|
|
|
| 127 |
|
| 128 |
## Usage
|
| 129 |
To use the model, you can load it with `AutoModelForCausalLM` as follows:
|
|
|
|
| 123 |
### Qualitative Results
|
| 124 |
Below are the results from manual evaluation of prompt-response pairs across languages and task categories. Scores are between 1-5 (higher the better). Model names were anonymised during the evaluation.
|
| 125 |
|
| 126 |
+
<img src="images/cumulative_score_category.png" alt="cumulative_score_category" width="600" height="400" />
|
| 127 |
+
<img src="images/cumulative_score_langauge.png" alt="cumulative_score_langauge" width="600" height="400" />
|
| 128 |
+
|
| 129 |
|
| 130 |
## Usage
|
| 131 |
To use the model, you can load it with `AutoModelForCausalLM` as follows:
|