Loading weights:   0%|          | 0/473 [00:00<?, ?it/s]Loading weights:  51%|█████     | 240/473 [00:00<00:00, 2399.29it/s]Loading weights: 100%|██████████| 473/473 [00:00<00:00, 4072.51it/s]
[transformers] `causal_conv1d_fn` is falling back to its reference PyTorch implementation because `causal_conv1d` is not installed. This is correct but much slower; install `causal_conv1d` for the optimized kernel.
[transformers] `chunk_gated_delta_rule` is falling back to its reference PyTorch implementation because `flash-linear-attention` is not installed. This is correct but much slower; install `flash-linear-attention` for the optimized kernel.
[transformers] `causal_conv1d_update` is falling back to its reference PyTorch implementation because `causal_conv1d` is not installed. This is correct but much slower; install `causal_conv1d` for the optimized kernel.
[transformers] `fused_recurrent_gated_delta_rule` is falling back to its reference PyTorch implementation because `flash-linear-attention` is not installed. This is correct but much slower; install `flash-linear-attention` for the optimized kernel.
{'mode': 'existing', 'inferred': 64, 'total': 5615, 'seconds': 7}
{'mode': 'existing', 'inferred': 576, 'total': 5615, 'seconds': 57}
{'mode': 'existing', 'inferred': 1088, 'total': 5615, 'seconds': 106}
{'mode': 'existing', 'inferred': 1600, 'total': 5615, 'seconds': 156}
{'mode': 'existing', 'inferred': 2112, 'total': 5615, 'seconds': 207}
{'mode': 'existing', 'inferred': 2624, 'total': 5615, 'seconds': 255}
{'mode': 'existing', 'inferred': 3136, 'total': 5615, 'seconds': 305}
{'mode': 'existing', 'inferred': 3648, 'total': 5615, 'seconds': 352}
{'mode': 'existing', 'inferred': 4160, 'total': 5615, 'seconds': 402}
{'mode': 'existing', 'inferred': 4672, 'total': 5615, 'seconds': 450}
{'mode': 'existing', 'inferred': 5184, 'total': 5615, 'seconds': 498}
{'state': 'description_inference_complete', 'mode': 'existing', 'targets': 5615, 'schema_valid': 6}
