prog-love/rostam

Update README.md

Update README.md

Update README.md

Update README.md

Update README.md

Final Upgrade: 36 layers complete training on 150k-300k Alpaca dataset

Training in progress, step 14730, checkpoint

Training in progress, step 14730

Training in progress, step 12000, checkpoint

Training in progress, step 12000

Training in progress, step 8000, checkpoint

Training in progress, step 8000

Training in progress, step 4000, checkpoint

Training in progress, step 4000

Update README.md

Update README.md

Update README.md

Update README.md

Update README.md

Update README.md

Upload 2 files

Create images/file.txt

Upgrade: Expanded to 24 layers and trained on 50k-150k Alpaca rows

Upgrade: Instruct-tuned on 50k Persian Alpaca rows

Upgrade: Scaled model to 48M+ parameters and fine-tuned on Ganjoor classical poetry dataset

Upgrade: Synced Fast Tokenizer configs for Rostam V2

Upgrade: Scaled model to 48M+ parameters and fine-tuned on Ganjoor classical poetry dataset

Initial commit: Custom Persian ByteLevel BPE Tokenizer

Initial commit: Trained Rostam model on Shahnameh

initial commit