RetNet legacy

Pre-0.5B generations, archived from the local workspace before deletion. Each file is a raw torch.save state dict (or a safetensors export for 100m_chat); they are not from_pretrained-ready repositories, only weight dumps.

100m_chat/model.safetensors - 100M chat fine-tune
97m_wikitext103/model.pt - 97M wikitext103 baseline
23m/best_model.pt - 23M smoke-test model (may contain optimizer state)

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