| num_blocks: 4 | |
| embedding_dim: 64 | |
| mlstm_block: | |
| mlstm: | |
| num_heads: 4 | |
| slstm_block: | |
| slstm: | |
| num_heads: 4 | |
| slstm_at: | |
| - 2 | |
| context_length: 4096 | |
| vocab_size: 178 | |
| num_blocks: 4 | |
| embedding_dim: 64 | |
| mlstm_block: | |
| mlstm: | |
| num_heads: 4 | |
| slstm_block: | |
| slstm: | |
| num_heads: 4 | |
| slstm_at: | |
| - 2 | |
| context_length: 4096 | |
| vocab_size: 178 | |