LICENSE
README.md
pyproject.toml
src/levanter/__init__.py
src/levanter/checkpoint.py
src/levanter/config.py
src/levanter/distributed.py
src/levanter/eval.py
src/levanter/eval_harness.py
src/levanter/grad_accum.py
src/levanter/lora.py
src/levanter/schedule.py
src/levanter/shapes.py
src/levanter/tensorstore_serialization.py
src/levanter/trainer.py
src/levanter/trainer_state.py
src/levanter/visualization.py
src/levanter.egg-info/PKG-INFO
src/levanter.egg-info/SOURCES.txt
src/levanter.egg-info/dependency_links.txt
src/levanter.egg-info/requires.txt
src/levanter.egg-info/top_level.txt
src/levanter/analysis/__init__.py
src/levanter/analysis/entropy.py
src/levanter/analysis/tree_stats.py
src/levanter/analysis/visualization.py
src/levanter/callbacks/__init__.py
src/levanter/callbacks/_core.py
src/levanter/callbacks/_metrics.py
src/levanter/callbacks/watch.py
src/levanter/compat/__init__.py
src/levanter/compat/hf_checkpoints.py
src/levanter/data/__init__.py
src/levanter/data/_preprocessor.py
src/levanter/data/_prp.py
src/levanter/data/audio.py
src/levanter/data/dataset.py
src/levanter/data/loader.py
src/levanter/data/metrics_monitor.py
src/levanter/data/mixture.py
src/levanter/data/packing.py
src/levanter/data/passthrough_tokenizer.py
src/levanter/data/permutation.py
src/levanter/data/sharded_datasource.py
src/levanter/data/text.py
src/levanter/data/utils.py
src/levanter/infra/__init__.py
src/levanter/infra/cli_helpers.py
src/levanter/infra/docker.py
src/levanter/infra/ray_tpu.py
src/levanter/infra/tpus.py
src/levanter/layers/__init__.py
src/levanter/layers/attention.py
src/levanter/layers/normalization.py
src/levanter/layers/rotary.py
src/levanter/main/cache_dataset.py
src/levanter/main/eval_lm.py
src/levanter/main/export_lm_to_hf.py
src/levanter/main/lora_lm.py
src/levanter/main/sft.py
src/levanter/main/sft_mixture.py
src/levanter/main/train_asr.py
src/levanter/main/train_lm.py
src/levanter/main/viz_logprobs.py
src/levanter/models/__init__.py
src/levanter/models/asr_model.py
src/levanter/models/flash_attention.py
src/levanter/models/gemma.py
src/levanter/models/gpt2.py
src/levanter/models/gpt2_hyena.py
src/levanter/models/hyena.py
src/levanter/models/llama.py
src/levanter/models/lm_model.py
src/levanter/models/loss.py
src/levanter/models/mistral.py
src/levanter/models/mixtral.py
src/levanter/models/olmo.py
src/levanter/models/qwen.py
src/levanter/models/rotary.py
src/levanter/models/whisper.py
src/levanter/optim/__init__.py
src/levanter/optim/adam_mini.py
src/levanter/optim/adopt.py
src/levanter/optim/cautious.py
src/levanter/optim/clip_update_norm.py
src/levanter/optim/config.py
src/levanter/optim/kron.py
src/levanter/optim/mars.py
src/levanter/optim/model_averaging.py
src/levanter/optim/muon.py
src/levanter/optim/rmsprop.py
src/levanter/optim/scion.py
src/levanter/optim/skipstep.py
src/levanter/optim/soap.py
src/levanter/optim/sophia.py
src/levanter/optim/util.py
src/levanter/store/__init__.py
src/levanter/store/cache.py
src/levanter/store/jagged_array.py
src/levanter/store/tree_store.py
src/levanter/tracker/__init__.py
src/levanter/tracker/helpers.py
src/levanter/tracker/histogram.py
src/levanter/tracker/tensorboard.py
src/levanter/tracker/tracker.py
src/levanter/tracker/tracker_fns.py
src/levanter/tracker/wandb.py
src/levanter/utils/__init__.py
src/levanter/utils/activation.py
src/levanter/utils/background_iterable.py
src/levanter/utils/cloud_utils.py
src/levanter/utils/datetime_utils.py
src/levanter/utils/flop_utils.py
src/levanter/utils/fsspec_utils.py
src/levanter/utils/hf_utils.py
src/levanter/utils/index.py
src/levanter/utils/jax_utils.py
src/levanter/utils/json_utils.py
src/levanter/utils/logging.py
src/levanter/utils/py_utils.py
src/levanter/utils/ray_utils.py
src/levanter/utils/stat_utils.py
src/levanter/utils/thread_utils.py
src/levanter/utils/tree_utils.py
src/levanter/utils/types.py
tests/test_attention.py
tests/test_audio.py
tests/test_background_iterable.py
tests/test_checkpoint.py
tests/test_config.py
tests/test_datetime_utils.py
tests/test_distributed.py
tests/test_eval_harness.py
tests/test_eval_lm.py
tests/test_export_to_hf.py
tests/test_flash_attention.py
tests/test_gemma.py
tests/test_grad_accum.py
tests/test_hf_checkpoints.py
tests/test_hf_gpt2_serialize.py
tests/test_hf_utils.py
tests/test_histogram.py
tests/test_hyena.py
tests/test_jagged_array.py
tests/test_jax_utils.py
tests/test_llama.py
tests/test_llama3.py
tests/test_logging.py
tests/test_lora.py
tests/test_loss.py
tests/test_mistral.py
tests/test_mixtral.py
tests/test_mixture.py
tests/test_new_cache.py
tests/test_new_loader.py
tests/test_newdataset.py
tests/test_olmo.py
tests/test_optimizer_config.py
tests/test_packing.py
tests/test_prp.py
tests/test_py_utils.py
tests/test_qwen2.py
tests/test_qwen3.py
tests/test_ray_tpu.py
tests/test_rotary.py
tests/test_scheduler.py
tests/test_sft.py
tests/test_sharded_dataset.py
tests/test_skip_step.py
tests/test_sophia.py
tests/test_supervised.py
tests/test_tensorboard.py
tests/test_tensorstore_serialization.py
tests/test_text.py
tests/test_torch_serialization.py
tests/test_tracker.py
tests/test_train_asr.py
tests/test_train_lm.py
tests/test_tree_store.py
tests/test_utils.py
tests/test_varying_mixture.py
tests/test_viz_lm.py
tests/test_weight_decay_mask.py