.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
build_tools/build_wheels.sh
tests/test_functional.py
tests/test_inference.py
tests/test_kmeans.py
tests/test_wordllama.py
tutorials/extract_token_embeddings.md
wordllama/RESULTS.md
wordllama/__init__.py
wordllama/_version.py
wordllama/inference.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/hamming_distance.c
wordllama/algorithms/hamming_distance.pyx
wordllama/algorithms/kmeans.c
wordllama/algorithms/kmeans.pyx
wordllama/algorithms/splitter.c
wordllama/algorithms/splitter.pyx
wordllama/config/__init__.py
wordllama/config/command_rplus.toml
wordllama/config/dbrx.toml
wordllama/config/deberta_v3_large.toml
wordllama/config/deepseekv2.toml
wordllama/config/gemma2_27B.toml
wordllama/config/l2_supercat.toml
wordllama/config/l2p3.toml
wordllama/config/l2p3_lg.toml
wordllama/config/l3_supercat.toml
wordllama/config/llama2_70B.toml
wordllama/config/llama3_70B.toml
wordllama/config/llama3_8B.toml
wordllama/config/llamaguard.toml
wordllama/config/miqu.toml
wordllama/config/mixtral.toml
wordllama/config/mixtral_8x22B.toml
wordllama/config/openelm_3B.toml
wordllama/config/phi3_medium.toml
wordllama/config/qwen2_72B.toml
wordllama/config/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