.gitignore
LICENSE
MANIFEST.in
README.md
pyproject.toml
requirements-dev.txt
requirements.txt
.github/workflows/publish.yml
.github/workflows/test.yml
assets/GleamLM.png
assets/train_loss.jpg
assets/val.jpg
configs/base.yaml
configs/lite.yaml
configs/nano.yaml
configs/pro.yaml
data/.gitkeep
data/raw/.gitkeep
data_tools/build_dataset.py
data_tools/clean_sft_data.py
data_tools/clean_text.py
data_tools/dedup_text.py
data_tools/download_data.py
data_tools/extract_parquet.py
data_tools/filter_qa.py
data_tools/gen_sft.py
data_tools/generate_rejected.py
data_tools/generate_sft_data.py
data_tools/generate_sft_data_full.py
data_tools/make_small_nano.py
data_tools/prepare_data.py
gleamlm/__init__.py
gleamlm/types.py
gleamlm-lite/.gitignore
gleamlm-lite/dpo.py
gleamlm-lite/infer.py
gleamlm-lite/make_small_data.py
gleamlm-lite/sft.py
gleamlm-lite/test_train.py
gleamlm-lite/train.py
gleamlm-lite/checkpoints/.gitkeep
gleamlm-lite/evaluation/generate_samples.py
gleamlm-lite/evaluation/perplexity.py
gleamlm-lite/tests/__init__.py
gleamlm-lite/tests/_run_tests.py
gleamlm-lite/tests/smoke_test.py
gleamlm-lite/tests/test_dataset.py
gleamlm-lite/tests/test_model.py
gleamlm-nano/dpo.py
gleamlm-nano/infer.py
gleamlm-nano/make_small_data.py
gleamlm-nano/quantize.py
gleamlm-nano/quick_test_sft_dpo.py
gleamlm-nano/sft.py
gleamlm-nano/train.py
gleamlm-nano/checkpoints/.gitkeep
gleamlm-nano/evaluation/generate_samples.py
gleamlm-nano/evaluation/perplexity.py
gleamlm-nano/tests/__init__.py
gleamlm-nano/tests/_run_tests.py
gleamlm-nano/tests/test_dataset.py
gleamlm-nano/tests/test_model.py
gleamlm-nano/tests/test_tokenizer.py
gleamlm-pro/.gitkeep
gleamlm.egg-info/PKG-INFO
gleamlm.egg-info/SOURCES.txt
gleamlm.egg-info/dependency_links.txt
gleamlm.egg-info/requires.txt
gleamlm.egg-info/scm_file_list.json
gleamlm.egg-info/scm_version.json
gleamlm.egg-info/top_level.txt
gleamlm/dataset/__init__.py
gleamlm/dataset/dataset.py
gleamlm/evaluation/__init__.py
gleamlm/evaluation/benchmark.py
gleamlm/evaluation/knowledge.py
gleamlm/evaluation/ppl.py
gleamlm/evaluation/runner.py
gleamlm/inference/__init__.py
gleamlm/inference/generate.py
gleamlm/inference/sampler.py
gleamlm/inference/streamer.py
gleamlm/models/__init__.py
gleamlm/models/config.py
gleamlm/models/model.py
gleamlm/tokenizer/__init__.py
gleamlm/tokenizer/tokenizer.py
gleamlm/tokenizer/checkpoints/bbpe_12k/bbpe_tokenizer.json
gleamlm/utils/__init__.py
gleamlm/utils/config.py
gleamlm/utils/logging.py
gleamlm/utils/torch_utils.py
scripts/_check_fanti.py
scripts/_check_stats.py
scripts/_read_tb.py
scripts/check_ckpt.py
scripts/eval_knowledge.py
scripts/eval_layer_dropout.py
scripts/eval_ppl.py
scripts/quick_run.py
scripts/verify_both.py
scripts/verify_lite.py
scripts/verify_paths.py
tests/__init__.py
tests/conftest.py
tests/test_dataset.py
tests/test_evaluation.py
tests/test_model.py
tests/test_sampler.py
tests/test_tokenizer.py
tests/test_utils_config.py
tests/verify_flash_attn.py