### Install Project Dependencies

Source: https://github.com/shark-nlp/diffuseq/blob/main/README.md

Installs all necessary Python packages listed in the requirements.txt file using pip. This command is essential for setting up the project environment.

```bash
pip install -r requirements.txt
```

--------------------------------

### Run DiffuSeq Training Script

Source: https://github.com/shark-nlp/diffuseq/blob/main/README.md

Navigates to the 'scripts' directory and executes the main training script using bash. This script initiates the DiffuSeq model training process with specified arguments.

```bash
cd scripts
bash train.sh
```

--------------------------------

### Accelerate DiffuSeq Decoding with DPM-Solver++

Source: https://github.com/shark-nlp/diffuseq/blob/main/README.md

Utilizes a customized DPM-Solver++ implementation to speed up the sampling process for DiffuSeq models. Navigate to the 'scripts' directory and execute 'run_decode_solver.sh'.

```bash
cd scripts
bash run_decode_solver.sh
```

--------------------------------

### Train DiffuSeq Models with Distributed Launch

Source: https://github.com/shark-nlp/diffuseq/blob/main/README.md

Commands to initiate distributed training for DiffuSeq models across various datasets like QQP, QG, and Dialogue. Specifies parameters such as learning rate, batch size, and noise schedule.

```python
python -m torch.distributed.launch --nproc_per_node=4 --master_port=12233 --use_env run_train.py --diff_steps 2000 --lr 0.0001 --learning_steps 50000 --save_interval 10000 --seed 102 --noise_schedule sqrt --hidden_dim 128 --bsz 2048 --dataset qqp --data_dir {datasets/QQP} --vocab bert --seq_len 128 --schedule_sampler lossaware --notes qqp

python -m torch.distributed.launch --nproc_per_node=4 --master_port=12233 --use_env run_train.py --diff_steps 2000 --lr 0.0001 --learning_steps 40000 --save_interval 2000 --seed 102 --noise_schedule sqrt --hidden_dim 128 --bsz 2048 --microbatch 64 --dataset qg --data_dir {datasets/QG} --vocab bert --seq_len 128 --schedule_sampler lossaware --notes qg

python -m torch.distributed.launch --nproc_per_node=7 --master_port=12233 --use_env run_train.py --diff_steps 2000 --lr 0.0001 --learning_steps 140000 --save_interval 20000 --seed 102 --noise_schedule sqrt --hidden_dim 128 --bsz 2048 --microbatch 64 --dataset dialogue --data_dir {datasets/Conversation} --vocab bert --seq_len 128 --schedule_sampler lossaware --notes dialogue

python -m torch.distributed.launch --nproc_per_node=8 --master_port=12233 --use_env run_train.py --diff_steps 2000 --lr 0.0001 --learning_steps 80000 --save_interval 20000 --seed 102 --noise_schedule sqrt --hidden_dim 128 --bsz 2048 --microbatch 64 --dataset dialogue --data_dir {datasets/TS} --vocab bert --seq_len 128 --schedule_sampler lossaware --notes ts
```

--------------------------------

### Decode DiffuSeq Models

Source: https://github.com/shark-nlp/diffuseq/blob/main/README.md

Executes the decoding process for trained DiffuSeq models. Requires navigating to the 'scripts' directory and running the 'run_decode.sh' script.

```bash
cd scripts
bash run_decode.sh
```

--------------------------------

### DiffuSeq Citation Information

Source: https://github.com/shark-nlp/diffuseq/blob/main/README.md

Provides BibTeX entries for citing the DiffuSeq project and its associated research papers, including the original ICLR 2023 publication and the DiffuSeq-v2 arXiv preprint.

```bibtex
@inproceedings{gong2022diffuseq,
  author = {Gong, Shansan and Li, Mukai and Feng, Jiangtao and Wu, Zhiyong and Kong, Lingpeng},
  booktitle = {International Conference on Learning Representations, ICLR},
  title = {{DiffuSeq}: Sequence to Sequence Text Generation with Diffusion Models},
  year = 2023
}

@article{gong2023diffuseqv2,
  title={DiffuSeq-v2: Bridging Discrete and Continuous Text Spaces for Accelerated Seq2Seq Diffusion Models},
  author={Gong, Shansan and Li, Mukai and Feng, Jiangtao and Wu, Zhiyong and Kong, Lingpeng},
  journal={arXiv preprint arXiv:2310.05793},
  year={2023}
}
```

--------------------------------

### Evaluate DiffuSeq Outputs and MBR Decoding

Source: https://github.com/shark-nlp/diffuseq/blob/main/README.md

Evaluates the quality and diversity of decoded texts generated by DiffuSeq models. The script computes diversity scores or performs MBR decoding based on the '--mbr' flag and requires specifying the folder containing decoded files.

```python
cd scripts
python eval_seq2seq.py --folder ../{your-path-to-outputs} --mbr
```

=== COMPLETE CONTENT === This response contains all available snippets from this library. No additional content exists. Do not make further requests.