Update README.md
Browse files
README.md
CHANGED
|
@@ -29,6 +29,8 @@ After fine-tuning, the model underwent Direct Preference Optimization (DPO) to e
|
|
| 29 |
|
| 30 |
The model delivers best-in-class performance across Indic tasks and a promising performance on English benchmarks equivalent to models 5-10x the size. We present details of the model architecture, pre-training, post-training and evaluation results. We also publicly release the post-trained versions of the model. We are continuously improving the model through post-training techniques such as RLHF.
|
| 31 |
|
|
|
|
|
|
|
| 32 |
## Key Features
|
| 33 |
- 12B parameter dense transformer model leading to better generalization compared to Krutrim-1 7B;
|
| 34 |
- Supports context up to 128K tokens making it suitable for long multi-turn conversations, long-form generations, document translations and others;
|
|
|
|
| 29 |
|
| 30 |
The model delivers best-in-class performance across Indic tasks and a promising performance on English benchmarks equivalent to models 5-10x the size. We present details of the model architecture, pre-training, post-training and evaluation results. We also publicly release the post-trained versions of the model. We are continuously improving the model through post-training techniques such as RLHF.
|
| 31 |
|
| 32 |
+
[](https://www.youtube.com/watch?v=beqXNHq67xg)
|
| 33 |
+
|
| 34 |
## Key Features
|
| 35 |
- 12B parameter dense transformer model leading to better generalization compared to Krutrim-1 7B;
|
| 36 |
- Supports context up to 128K tokens making it suitable for long multi-turn conversations, long-form generations, document translations and others;
|