| language: en | |
| library_name: transformers | |
| tags: | |
| - text-generation | |
| - kronlstm | |
| # void.2 | |
| Private training checkpoints for the 97.9M-parameter KronLSTM model. | |
| Training: 4096-byte byte-level sequences; ClimbMix/DCLM/OpenMathInstruct-2 50/30/20. | |
| Use `latest.json` to locate a full resumable checkpoint containing optimizer masters, AdamW state, RNG state, and stream cursors. FLA/KronLSTM is required for inference. | |