smart-sun-31 / README.md
quik-models's picture
Upload autoresearch experiment (val_bpb=0.778052)
ed064c1 verified
|
Raw
History Blame Contribute Delete
346 Bytes
metadata
library_name: autoresearch
tags:
  - autoresearch
  - nanochat-tokenizer

autoresearch experiment

This checkpoint uses the 16,384-token nanochat-compatible BPE tokenizer. Load model.pt with this repository's GPT class and config.json.

W&B run URL: https://wandb.ai/dustinsdelivery-delivery-ai/autoresearch/runs/a6aekama