| GPT2 model for Sanskrit language, one of the oldest in world. | |
| heads=12 layers=6. | |
| This is a bit smaller version, since I trained it on my laptop with smaller gpu. | |
| GPT2 model for Sanskrit language, one of the oldest in world. | |
| heads=12 layers=6. | |
| This is a bit smaller version, since I trained it on my laptop with smaller gpu. | |