Update README.md
Browse files
README.md
CHANGED
|
@@ -11,6 +11,8 @@ The final checkpoint of `sarvam-2b` will be released soon, and it will be traine
|
|
| 11 |
|
| 12 |
The current checkpoint has not undergone any post-training. You can see the capabilities of the current checkpoint in [this video](https://www.youtube.com/watch?v=DFtAS1BCKvk).
|
| 13 |
|
|
|
|
|
|
|
| 14 |
Getting started:
|
| 15 |
```
|
| 16 |
from transformers import pipeline
|
|
@@ -39,7 +41,4 @@ Here is a comparison of fertility scores between `sarvam-2b` and other popular m
|
|
| 39 |
|tel_Telu|2.14 |13.3 |4.57 |3.06 |
|
| 40 |
|**Average** |**2.08** |**9.34** |**4.01** |**3.00** |
|
| 41 |
|
| 42 |
-
|
| 43 |
-
This model is trained on the NeMo stack on Nvidia H100s on the Yotta data center.
|
| 44 |
-
|
| 45 |
More technical details like evaluations and benchmarking will be posted soon.
|
|
|
|
| 11 |
|
| 12 |
The current checkpoint has not undergone any post-training. You can see the capabilities of the current checkpoint in [this video](https://www.youtube.com/watch?v=DFtAS1BCKvk).
|
| 13 |
|
| 14 |
+
The model was trained with NVIDIA NeMo™ Framework on the Yotta Shakti Cloud using HGX H100 systems.
|
| 15 |
+
|
| 16 |
Getting started:
|
| 17 |
```
|
| 18 |
from transformers import pipeline
|
|
|
|
| 41 |
|tel_Telu|2.14 |13.3 |4.57 |3.06 |
|
| 42 |
|**Average** |**2.08** |**9.34** |**4.01** |**3.00** |
|
| 43 |
|
|
|
|
|
|
|
|
|
|
| 44 |
More technical details like evaluations and benchmarking will be posted soon.
|