Device: cuda Loaded 97270379 characters from Wikipedia Vocabulary size: 1976 Parameters: 98,424 (~1K) Step 0 | Loss: 7.6146 Step 300 | Loss: 2.5528 Step 600 | Loss: 2.4822 Step 900 | Loss: 2.4557 Step 1200 | Loss: 2.4927 Step 1500 | Loss: 2.4626 Step 1800 | Loss: 2.5529 Step 2100 | Loss: 2.4207 Step 2400 | Loss: 2.5079 Step 2700 | Loss: 2.4675 ✅ Model saved!

Sample generation: Ela e e e e e e e e e e e e e e e e e e e e e e e e e e e e e e e e e e e e e e e e e e e e e e e e e e e e e e e e e e e e e e e e e e e e e e e e e e e e e e e e e e e e e e e e e e e e e e e e e e e

Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Dataset used to train HyxLabs/Hyx-100K-V1-Spanish

Collection including HyxLabs/Hyx-100K-V1-Spanish