.gitignore
LICENSE
MANIFEST.in
README.md
classifiers.txt
dataset_loader.py
eval_mteb.py
find_mteb.sh
pyproject.toml
setup.py
train.py
wordllama.png
.github/workflows/ci.yml
.github/workflows/publish.yml
benchmark/inference_benchmark.png
benchmark/inference_benchmarks.py
build_tools/build_wheels.sh
tests/test_functional.py
tests/test_inference.py
tests/test_kmeans.py
tests/test_minima_functions.py
tests/test_semantic_splitter.py
tests/test_splitting_functions.py
tests/test_vector_similarity.py
tests/test_wordllama.py
tutorials/extract_token_embeddings.md
tutorials/blog/semantic_split/output_12_0.png
tutorials/blog/semantic_split/output_15_0.png
tutorials/blog/semantic_split/output_17_1.png
tutorials/blog/semantic_split/output_19_0.png
tutorials/blog/semantic_split/output_23_0.png
tutorials/blog/semantic_split/output_26_1.png
tutorials/blog/semantic_split/output_6_0.png
tutorials/blog/semantic_split/wl_semantic_blog.ipynb
tutorials/blog/semantic_split/wl_semantic_blog.md
wordllama/RESULTS.md
wordllama/__init__.py
wordllama/_version.py
wordllama/inference.py
wordllama/mode_decorators.py
wordllama/wordllama.py
wordllama.egg-info/PKG-INFO
wordllama.egg-info/SOURCES.txt
wordllama.egg-info/dependency_links.txt
wordllama.egg-info/not-zip-safe
wordllama.egg-info/requires.txt
wordllama.egg-info/top_level.txt
wordllama/adapters/__init__.py
wordllama/adapters/avg_pool.py
wordllama/adapters/binarizer.py
wordllama/adapters/mlp.py
wordllama/adapters/projector.py
wordllama/adapters/weighted_mlp.py
wordllama/adapters/weighted_projector.py
wordllama/algorithms/__init__.py
wordllama/algorithms/deduplicate_helpers.c
wordllama/algorithms/deduplicate_helpers.pyx
wordllama/algorithms/find_local_minima.cpp
wordllama/algorithms/find_local_minima.pyx
wordllama/algorithms/kmeans.c
wordllama/algorithms/kmeans.pyx
wordllama/algorithms/semantic_splitter.py
wordllama/algorithms/splitter.cpp
wordllama/algorithms/splitter.pyx
wordllama/algorithms/vector_similarity.c
wordllama/algorithms/vector_similarity.pxd
wordllama/algorithms/vector_similarity.pyx
wordllama/config/__init__.py
wordllama/config/models.py
wordllama/config/train/command_rplus.toml
wordllama/config/train/dbrx.toml
wordllama/config/train/deberta_v3_large.toml
wordllama/config/train/deepseekv2.toml
wordllama/config/train/gemma2_27B.toml
wordllama/config/train/l2_supercat.toml
wordllama/config/train/l2p3.toml
wordllama/config/train/l2p3_lg.toml
wordllama/config/train/l3_supercat.toml
wordllama/config/train/llama2_70B.toml
wordllama/config/train/llama3_70B.toml
wordllama/config/train/llama3_8B.toml
wordllama/config/train/llamaguard.toml
wordllama/config/train/miqu.toml
wordllama/config/train/mixtral.toml
wordllama/config/train/mixtral_8x22B.toml
wordllama/config/train/openelm_3B.toml
wordllama/config/train/phi3_medium.toml
wordllama/config/train/qwen2_72B.toml
wordllama/config/train/yi_1v5_34B.toml
wordllama/embedding/__init__.py
wordllama/embedding/word_llama_embedding.py
wordllama/extract/__init__.py
wordllama/extract/extract_hf.py
wordllama/extract/extract_llama_70B.py
wordllama/extract/extract_safetensors.py
wordllama/tokenizers/__init__.py
wordllama/tokenizers/l2_supercat_tokenizer_config.json
wordllama/trainers/__init__.py
wordllama/trainers/reduce_dimension.py
wordllama/weights/l2_supercat_256.safetensors