reparam-discrete-diffusion

(★ 108)

Reparameterized Discrete Diffusion Models for Text Generation

File Explorer

Download Latest Version (.zip)

- - __init__.py
  - absorbing_diffusion.py
  - discrete_diffusion_base.py
  - multinomial_diffusion.py
  - reparam_absorbing_diffusion.py
  - reparam_multinomial_diffusion.py
  - utils.py
- setup.py
- - __init__.py
  - diffusion_generator.py
  - time_sampler.py
  - utils.py
  - vocab.txt
- - .gitignore
  - __init__.py
- - diffuseq_generate.sh
  - diffuseq_train.sh
  - mt_generate.sh
  - mt_train.sh
- - __init__.py
  - binarizer.py
  - checkpoint_utils.py
  - file_chunker_utils.py
  - file_io.py
  - file_utils.py
  - hub_utils.py
  - incremental_decoding_utils.py
  - iterative_refinement_generator.py
  - nan_detector.py
  - ngram_repeat_block.py
  - options.py
  - pdb.py
  - quantization_utils.py
  - registry.py
  - search.py
  - sequence_generator.py
  - sequence_scorer.py
  - speech_generator.py
  - token_generation_constraints.py
  - tokenizer.py
  - trainer.py
  - utils.py
  - version.txt
- - __init__.py
  - eval_lm.py
  - generate.py
  - hydra_train.py
  - interactive.py
  - preprocess.py
  - score.py
  - train.py
  - validate.py
- - __init__.py
  - average_checkpoints.py
  - build_sym_alignment.py
  - compare_namespaces.py
  - compound_split_bleu.sh
  - convert_dictionary.lua
  - convert_model.lua
  - count_docs.py
  - read_binarized.py
  - rm_pt.py
  - sacrebleu.sh
  - shard_docs.py
  - split_train_valid_docs.py
  - spm_decode.py
  - spm_encode.py
  - spm_train.py
  - test_fsdp.sh
- - __init__.py
  - test_activation_checkpointing.py
  - test_amp_optimizer.py
  - test_average_checkpoints.py
  - test_backtranslation_dataset.py
  - test_binaries.py
  - test_character_token_embedder.py
  - test_checkpoint_utils.py
  - test_concat_dataset.py
  - test_constraints.py
  - test_convtbc.py
  - test_data_utils.py
  - test_dataclass_utils.py
  - test_dataset.py
  - test_dictionary.py
  - test_ema.py
  - test_export.py
  - test_file_chunker_utils.py
  - test_file_io.py
  - test_fp16_optimizer.py
  - test_huffman.py
  - test_inference_dropout.py
  - test_iopath.py
  - test_iterators.py
  - test_label_smoothing.py
  - test_lm_context_window.py
  - test_lstm_jitable.py
  - test_memory_efficient_fp16.py
  - test_metrics.py
  - test_multi_corpus_dataset.py
  - test_multi_corpus_sampled_dataset.py
  - test_multihead_attention.py
  - test_noising.py
  - test_online_backtranslation.py
  - test_plasma_utils.py
  - test_reproducibility.py
  - test_resampling_dataset.py
  - test_roberta.py
  - test_sequence_generator.py
  - test_sequence_scorer.py
  - test_sparse_multihead_attention.py
  - test_token_block_dataset.py
  - test_train.py
  - test_transformer.py
  - test_utils.py
  - test_valid_subset_checks.py
  - utils.py
- .isort.cfg
- .pre-commit-config.yaml
- CODE_OF_CONDUCT.md
- CONTRIBUTING.md
- hubconf.py
- LICENSE
- pyproject.toml
- README.md
- setup.cfg
- setup.py
- train.py
.gitignore
LICENSE
README.md
requirements.txt

# Installation Guide

1. Get the code

git clone https://github.com/HKUNLP/reparam-discrete-diffusion

Downloads the entire project code from GitHub to your computer.

cd reparam-discrete-diffusion

Moves into the project folder you just downloaded.

2. Python

Easy Recommended

Prerequisites

Git Needed to download the project code from GitHub.
Python 3 On Windows, be sure to check 'Add Python to PATH' during installation.

pip install -r requirements.txt

Installs the Python libraries listed in requirements.txt (or similar).

pip install -e discrete_diffusion

Installs the Python libraries listed in requirements.txt (or similar).

✅ If it runs without errors and prints output in the terminal, it worked.

Pulled directly from this repo's README.