rugpt3xl
Model was trained with 512 sequence length using Deepspeed and Megatron code by SberDevices team, on 80B tokens dataset for 4 epochs. After that model was finetuned 1 epoch with sequence length 2048.
Note! Model has sparse attention blocks.
Total training time was around 10 days on 256 GPUs.
Final perplexity on test set is 12.05.
Model parameters: 1.3B.
Inference Providers
NEW
This model is not currently available via any of the supported Inference Providers.
The model cannot be deployed to the HF Inference API:
The model has no library tag.