initial commit

dataset/download_LibriSpeech.sh

+# Training sets
+wget https://www.openslr.org/resources/12/train-clean-100.tar.gz
+tar xvzf train-clean-100.tar.gz
+wget https://www.openslr.org/resources/12/train-clean-360.tar.gz
+tar xvzf train-clean-360.tar.gz
+wget https://www.openslr.org/resources/12/train-other-500.tar.gz
+tar xvzf train-other-500.tar.gz
+
+# Development sets
+wget https://www.openslr.org/resources/12/dev-clean.tar.gz
+tar xvzf dev-clean.tar.gz
+wget https://www.openslr.org/resources/12/dev-other.tar.gz
+tar xvzf dev-other.tar.gz
+
+# Test sets
+wget https://www.openslr.org/resources/12/test-clean.tar.gz
+tar xvzf test-clean.tar.gz
+wget https://www.openslr.org/resources/12/test-other.tar.gz
+tar xvzf test-other.tar.gz
+

docker/Dockerfile

+FROM image.sourcefind.cn:5000/dcu/admin/base/pytorch:2.1.0-ubuntu20.04-dtk24.04.1-py3.8
+RUN source/opt/dtk/env.sh
\ No newline at end of file

fairseq/CODE_OF_CONDUCT.md

+# Code of Conduct
+
+## Our Pledge
+
+In the interest of fostering an open and welcoming environment, we as
+contributors and maintainers pledge to make participation in our project and
+our community a harassment-free experience for everyone, regardless of age, body
+size, disability, ethnicity, sex characteristics, gender identity and expression,
+level of experience, education, socio-economic status, nationality, personal
+appearance, race, religion, or sexual identity and orientation.
+
+## Our Standards
+
+Examples of behavior that contributes to creating a positive environment
+include:
+
+* Using welcoming and inclusive language
+* Being respectful of differing viewpoints and experiences
+* Gracefully accepting constructive criticism
+* Focusing on what is best for the community
+* Showing empathy towards other community members
+
+Examples of unacceptable behavior by participants include:
+
+* The use of sexualized language or imagery and unwelcome sexual attention or
+  advances
+* Trolling, insulting/derogatory comments, and personal or political attacks
+* Public or private harassment
+* Publishing others' private information, such as a physical or electronic
+  address, without explicit permission
+* Other conduct which could reasonably be considered inappropriate in a
+  professional setting
+
+## Our Responsibilities
+
+Project maintainers are responsible for clarifying the standards of acceptable
+behavior and are expected to take appropriate and fair corrective action in
+response to any instances of unacceptable behavior.
+
+Project maintainers have the right and responsibility to remove, edit, or
+reject comments, commits, code, wiki edits, issues, and other contributions
+that are not aligned to this Code of Conduct, or to ban temporarily or
+permanently any contributor for other behaviors that they deem inappropriate,
+threatening, offensive, or harmful.
+
+## Scope
+
+This Code of Conduct applies within all project spaces, and it also applies when
+an individual is representing the project or its community in public spaces.
+Examples of representing a project or community include using an official
+project e-mail address, posting via an official social media account, or acting
+as an appointed representative at an online or offline event. Representation of
+a project may be further defined and clarified by project maintainers.
+
+## Enforcement
+
+Instances of abusive, harassing, or otherwise unacceptable behavior may be
+reported by contacting the project team at <conduct@pytorch.org>. All
+complaints will be reviewed and investigated and will result in a response that
+is deemed necessary and appropriate to the circumstances. The project team is
+obligated to maintain confidentiality with regard to the reporter of an incident.
+Further details of specific enforcement policies may be posted separately.
+
+Project maintainers who do not follow or enforce the Code of Conduct in good
+faith may face temporary or permanent repercussions as determined by other
+members of the project's leadership.
+
+## Attribution
+
+This Code of Conduct is adapted from the [Contributor Covenant][homepage], version 1.4,
+available at https://www.contributor-covenant.org/version/1/4/code-of-conduct.html
+
+[homepage]: https://www.contributor-covenant.org
+
+For answers to common questions about this code of conduct, see
+https://www.contributor-covenant.org/faq
+

fairseq/CONTRIBUTING.md

+# Contributing to Facebook AI Research Sequence-to-Sequence Toolkit (fairseq)
+We want to make contributing to this project as easy and transparent as
+possible.
+
+## Pull Requests
+We actively welcome your pull requests.
+
+1. Fork the repo and create your branch from `master`.
+2. If you've added code that should be tested, add tests.
+3. If you've changed APIs, update the documentation.
+4. Ensure the test suite passes.
+5. Make sure your code lints.
+6. If you haven't already, complete the Contributor License Agreement ("CLA").
+
+## Contributor License Agreement ("CLA")
+In order to accept your pull request, we need you to submit a CLA. You only need
+to do this once to work on any of Facebook's open source projects.
+
+Complete your CLA here: <https://code.facebook.com/cla>
+
+## Issues
+We use GitHub issues to track public bugs. Please ensure your description is
+clear and has sufficient instructions to be able to reproduce the issue.
+
+## License
+By contributing to Facebook AI Research Sequence-to-Sequence Toolkit (fairseq),
+you agree that your contributions will be licensed under the LICENSE file in
+the root directory of this source tree.

fairseq/LICENSE

+MIT License
+
+Copyright (c) Facebook, Inc. and its affiliates.
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

fairseq/README.md

+# Fairseq
+
+Fairseq(-py)是一个序列建模工具包，允许研究人员和开发人员训练自定义模型，用于翻译、摘要、语言建模和其他文本生成任务。
+
+## 安装步骤
+
+按照如下步骤，下载并安装好torch相关的库文件，并安装fairseq安装依赖的环境，并进行编译安装
+
+```
+wget https://cancon.hpccube.com:65024/directlink/4/pytorch/dtk22.10/torch-1.10.0a0+git2040069.dtk2210-cp38-cp38-manylinux2014_x86_64.whl
+
+wget https://cancon.hpccube.com:65024/directlink/4/vision/dtk22.10/torchvision-0.10.0a0+e04d001.dtk2210-cp38-cp38-manylinux2014_x86_64.whl
+
+wget https://cancon.hpccube.com:65024/directlink/4/torchaudio/dtk22.10/torchaudio-0.10.0+git9dcc7a1.dtk2210-cp38-cp38-manylinux2014_x86_64.whl
+
+pip3 install torch-1.10.0a0+git2040069.dtk2210-cp38-cp38-manylinux2014_x86_64.whl
+
+pip3 install torchvision-0.10.0a0+e04d001.dtk2210-cp38-cp38-manylinux2014_x86_64.whl
+
+pip3 install torchaudio-0.10.0+git9dcc7a1.dtk2210-cp38-cp38-manylinux2014_x86_64.whl
+
+pip3 install requirements.txt
+
+cd fairseq
+pip3 install --editable ./
+```
+
+
+

fairseq/README_origin.md

+<p align="center">
+  <img src="docs/fairseq_logo.png" width="150">
+  <br />
+  <br />
+  <a href="https://github.com/pytorch/fairseq/blob/master/LICENSE"><img alt="MIT License" src="https://img.shields.io/badge/license-MIT-blue.svg" /></a>
+  <a href="https://github.com/pytorch/fairseq/releases"><img alt="Latest Release" src="https://img.shields.io/github/release/pytorch/fairseq.svg" /></a>
+  <a href="https://github.com/pytorch/fairseq/actions?query=workflow:build"><img alt="Build Status" src="https://github.com/pytorch/fairseq/workflows/build/badge.svg" /></a>
+  <a href="https://fairseq.readthedocs.io/en/latest/?badge=latest"><img alt="Documentation Status" src="https://readthedocs.org/projects/fairseq/badge/?version=latest" /></a>
+</p>
+
+--------------------------------------------------------------------------------
+
+Fairseq(-py) is a sequence modeling toolkit that allows researchers and
+developers to train custom models for translation, summarization, language
+modeling and other text generation tasks.
+We provide reference implementations of various sequence modeling papers:
+
+<details><summary>List of implemented papers</summary><p>
+
+- **Convolutional Neural Networks (CNN)**
+  - [Language Modeling with Gated Convolutional Networks (Dauphin et al., 2017)](examples/language_model/conv_lm/README.md)
+  - [Convolutional Sequence to Sequence Learning (Gehring et al., 2017)](examples/conv_seq2seq/README.md)
+  - [Classical Structured Prediction Losses for Sequence to Sequence Learning (Edunov et al., 2018)](https://github.com/pytorch/fairseq/tree/classic_seqlevel)
+  - [Hierarchical Neural Story Generation (Fan et al., 2018)](examples/stories/README.md)
+  - [wav2vec: Unsupervised Pre-training for Speech Recognition (Schneider et al., 2019)](examples/wav2vec/README.md)
+- **LightConv and DynamicConv models**
+  - [Pay Less Attention with Lightweight and Dynamic Convolutions (Wu et al., 2019)](examples/pay_less_attention_paper/README.md)
+- **Long Short-Term Memory (LSTM) networks**
+  - Effective Approaches to Attention-based Neural Machine Translation (Luong et al., 2015)
+- **Transformer (self-attention) networks**
+  - Attention Is All You Need (Vaswani et al., 2017)
+  - [Scaling Neural Machine Translation (Ott et al., 2018)](examples/scaling_nmt/README.md)
+  - [Understanding Back-Translation at Scale (Edunov et al., 2018)](examples/backtranslation/README.md)
+  - [Adaptive Input Representations for Neural Language Modeling (Baevski and Auli, 2018)](examples/language_model/transformer_lm/README.md)
+  - [Lexically constrained decoding with dynamic beam allocation (Post & Vilar, 2018)](examples/constrained_decoding/README.md)
+  - [Mixture Models for Diverse Machine Translation: Tricks of the Trade (Shen et al., 2019)](examples/translation_moe/README.md)
+  - [RoBERTa: A Robustly Optimized BERT Pretraining Approach (Liu et al., 2019)](examples/roberta/README.md)
+  - [Facebook FAIR's WMT19 News Translation Task Submission (Ng et al., 2019)](examples/wmt19/README.md)
+  - [Jointly Learning to Align and Translate with Transformer Models (Garg et al., 2019)](examples/joint_alignment_translation/README.md )
+  - [Multilingual Denoising Pre-training for Neural Machine Translation (Liu et at., 2020)](examples/mbart/README.md)
+  - [Neural Machine Translation with Byte-Level Subwords (Wang et al., 2020)](examples/byte_level_bpe/README.md)
+  - [Unsupervised Quality Estimation for Neural Machine Translation (Fomicheva et al., 2020)](examples/unsupervised_quality_estimation/README.md)
+  - [wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations (Baevski et al., 2020)](examples/wav2vec/README.md)
+  - [Generating Medical Reports from Patient-Doctor Conversations Using Sequence-to-Sequence Models (Enarvi et al., 2020)](examples/pointer_generator/README.md)
+  - [Linformer: Self-Attention with Linear Complexity (Wang et al., 2020)](examples/linformer/README.md)
+  - [Cross-lingual Retrieval for Iterative Self-Supervised Training (Tran et al., 2020)](examples/criss/README.md)
+  - [Deep Transformers with Latent Depth (Li et al., 2020)](examples/latent_depth/README.md)
+- **Non-autoregressive Transformers**
+  - Non-Autoregressive Neural Machine Translation (Gu et al., 2017)
+  - Deterministic Non-Autoregressive Neural Sequence Modeling by Iterative Refinement (Lee et al. 2018)
+  - Insertion Transformer: Flexible Sequence Generation via Insertion Operations (Stern et al. 2019)
+  - Mask-Predict: Parallel Decoding of Conditional Masked Language Models (Ghazvininejad et al., 2019)
+  - [Levenshtein Transformer (Gu et al., 2019)](examples/nonautoregressive_translation/README.md)
+- **Finetuning**
+  - [Better Fine-Tuning by Reducing Representational Collapse (Aghajanyan et al. 2020)](examples/rxf/README.md)
+
+</p></details>
+
+### What's New:
+
+- October 2020: [Added R3F/R4F (Better Fine-Tuning) code](examples/rxf/README.md)
+- October 2020: [Deep Transformer with Latent Depth code released](examples/latent_depth/README.md)
+- October 2020: [Added CRISS models and code](examples/criss/README.md)
+- September 2020: [Added Linformer code](examples/linformer/README.md)
+- September 2020: [Added pointer-generator networks](examples/pointer_generator/README.md)
+- August 2020: [Added lexically constrained decoding](examples/constrained_decoding/README.md)
+- August 2020: [wav2vec2 models and code released](examples/wav2vec/README.md)
+- July 2020: [Unsupervised Quality Estimation code released](examples/unsupervised_quality_estimation/README.md)
+- May 2020: [Follow fairseq on Twitter](https://twitter.com/fairseq)
+- April 2020: [Monotonic Multihead Attention code released](examples/simultaneous_translation/README.md)
+- April 2020: [Quant-Noise code released](examples/quant_noise/README.md)
+- April 2020: [Initial model parallel support and 11B parameters unidirectional LM released](examples/megatron_11b/README.md)
+<details><summary>Previous updates</summary><p>
+
+- March 2020: [Byte-level BPE code released](examples/byte_level_bpe/README.md)
+- February 2020: [mBART model and code released](examples/mbart/README.md)
+- February 2020: [Added tutorial for back-translation](https://github.com/pytorch/fairseq/tree/master/examples/backtranslation#training-your-own-model-wmt18-english-german)
+- December 2019: [fairseq 0.9.0 released](https://github.com/pytorch/fairseq/releases/tag/v0.9.0)
+- November 2019: [VizSeq released (a visual analysis toolkit for evaluating fairseq models)](https://facebookresearch.github.io/vizseq/docs/getting_started/fairseq_example)
+- November 2019: [CamemBERT model and code released](examples/camembert/README.md)
+- November 2019: [BART model and code released](examples/bart/README.md)
+- November 2019: [XLM-R models and code released](examples/xlmr/README.md)
+- September 2019: [Nonautoregressive translation code released](examples/nonautoregressive_translation/README.md)
+- August 2019: [WMT'19 models released](examples/wmt19/README.md)
+- July 2019: fairseq relicensed under MIT license
+- July 2019: [RoBERTa models and code released](examples/roberta/README.md)
+- June 2019: [wav2vec models and code released](examples/wav2vec/README.md)
+
+</p></details>
+
+### Features:
+
+- multi-GPU training on one machine or across multiple machines (data and model parallel)
+- fast generation on both CPU and GPU with multiple search algorithms implemented:
+  - beam search
+  - Diverse Beam Search ([Vijayakumar et al., 2016](https://arxiv.org/abs/1610.02424))
+  - sampling (unconstrained, top-k and top-p/nucleus)
+  - lexically constrained decoding ([Post & Vilar, 2018](examples/constrained_decoding/README.md))
+- large mini-batch training even on a single GPU via delayed updates
+- mixed precision training (trains faster with less GPU memory on [NVIDIA tensor cores](https://developer.nvidia.com/tensor-cores))
+- extensible: easily register new models, criterions, tasks, optimizers and learning rate schedulers
+
+We also provide [pre-trained models for translation and language modeling](#pre-trained-models-and-examples)
+with a convenient `torch.hub` interface:
+```python
+en2de = torch.hub.load('pytorch/fairseq', 'transformer.wmt19.en-de.single_model')
+en2de.translate('Hello world', beam=5)
+# 'Hallo Welt'
+```
+See the PyTorch Hub tutorials for [translation](https://pytorch.org/hub/pytorch_fairseq_translation/)
+and [RoBERTa](https://pytorch.org/hub/pytorch_fairseq_roberta/) for more examples.
+
+# Requirements and Installation
+
+* [PyTorch](http://pytorch.org/) version >= 1.5.0
+* Python version >= 3.6
+* For training new models, you'll also need an NVIDIA GPU and [NCCL](https://github.com/NVIDIA/nccl)
+* **To install fairseq** and develop locally:
+```bash
+git clone https://github.com/pytorch/fairseq
+cd fairseq
+pip install --editable ./
+
+# on MacOS:
+# CFLAGS="-stdlib=libc++" pip install --editable ./
+```
+* **For faster training** install NVIDIA's [apex](https://github.com/NVIDIA/apex) library:
+```bash
+git clone https://github.com/NVIDIA/apex
+cd apex
+pip install -v --no-cache-dir --global-option="--cpp_ext" --global-option="--cuda_ext" \
+  --global-option="--deprecated_fused_adam" --global-option="--xentropy" \
+  --global-option="--fast_multihead_attn" ./
+```
+* **For large datasets** install [PyArrow](https://arrow.apache.org/docs/python/install.html#using-pip): `pip install pyarrow`
+* If you use Docker make sure to increase the shared memory size either with
+`--ipc=host` or `--shm-size` as command line options to `nvidia-docker run`.
+
+
+# Getting Started
+
+The [full documentation](https://fairseq.readthedocs.io/) contains instructions
+for getting started, training new models and extending fairseq with new model
+types and tasks.
+
+# Pre-trained models and examples
+
+We provide pre-trained models and pre-processed, binarized test sets for several tasks listed below,
+as well as example training and evaluation commands.
+
+- [Translation](examples/translation/README.md): convolutional and transformer models are available
+- [Language Modeling](examples/language_model/README.md): convolutional and transformer models are available
+
+We also have more detailed READMEs to reproduce results from specific papers:
+- [Cross-lingual Retrieval for Iterative Self-Supervised Training (Tran et al., 2020)](examples/criss/README.md)
+- [wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations (Baevski et al., 2020)](examples/wav2vec/README.md)
+- [Unsupervised Quality Estimation for Neural Machine Translation (Fomicheva et al., 2020)](examples/unsupervised_quality_estimation/README.md)
+- [Training with Quantization Noise for Extreme Model Compression ({Fan*, Stock*} et al., 2020)](examples/quant_noise/README.md)
+- [Neural Machine Translation with Byte-Level Subwords (Wang et al., 2020)](examples/byte_level_bpe/README.md)
+- [Multilingual Denoising Pre-training for Neural Machine Translation (Liu et at., 2020)](examples/mbart/README.md)
+- [Reducing Transformer Depth on Demand with Structured Dropout (Fan et al., 2019)](examples/layerdrop/README.md)
+- [Jointly Learning to Align and Translate with Transformer Models (Garg et al., 2019)](examples/joint_alignment_translation/README.md)
+- [Levenshtein Transformer (Gu et al., 2019)](examples/nonautoregressive_translation/README.md)
+- [Facebook FAIR's WMT19 News Translation Task Submission (Ng et al., 2019)](examples/wmt19/README.md)
+- [RoBERTa: A Robustly Optimized BERT Pretraining Approach (Liu et al., 2019)](examples/roberta/README.md)
+- [wav2vec: Unsupervised Pre-training for Speech Recognition (Schneider et al., 2019)](examples/wav2vec/README.md)
+- [Mixture Models for Diverse Machine Translation: Tricks of the Trade (Shen et al., 2019)](examples/translation_moe/README.md)
+- [Pay Less Attention with Lightweight and Dynamic Convolutions (Wu et al., 2019)](examples/pay_less_attention_paper/README.md)
+- [Understanding Back-Translation at Scale (Edunov et al., 2018)](examples/backtranslation/README.md)
+- [Classical Structured Prediction Losses for Sequence to Sequence Learning (Edunov et al., 2018)](https://github.com/pytorch/fairseq/tree/classic_seqlevel)
+- [Hierarchical Neural Story Generation (Fan et al., 2018)](examples/stories/README.md)
+- [Scaling Neural Machine Translation (Ott et al., 2018)](examples/scaling_nmt/README.md)
+- [Convolutional Sequence to Sequence Learning (Gehring et al., 2017)](examples/conv_seq2seq/README.md)
+- [Language Modeling with Gated Convolutional Networks (Dauphin et al., 2017)](examples/language_model/conv_lm/README.md)
+
+# Join the fairseq community
+
+* Twitter: https://twitter.com/fairseq
+* Facebook page: https://www.facebook.com/groups/fairseq.users
+* Google group: https://groups.google.com/forum/#!forum/fairseq-users
+
+# License
+
+fairseq(-py) is MIT-licensed.
+The license applies to the pre-trained models as well.
+
+# Citation
+
+Please cite as:
+
+```bibtex
+@inproceedings{ott2019fairseq,
+  title = {fairseq: A Fast, Extensible Toolkit for Sequence Modeling},
+  author = {Myle Ott and Sergey Edunov and Alexei Baevski and Angela Fan and Sam Gross and Nathan Ng and David Grangier and Michael Auli},
+  booktitle = {Proceedings of NAACL-HLT 2019: Demonstrations},
+  year = {2019},
+}
+```

fairseq/config/config.yaml

+defaults:
+  - params: training_params
+  - task: language_modeling
+  - model: transformer_lm
+  - criterion: cross_entropy
+  - optimizer: adam
+  - lr_scheduler: inverse_sqrt

fairseq/config/config_eval_lm.yaml

+defaults:
+  - params: eval_lm_params
+  - task: language_modeling
+  - model: transformer_lm
+  - criterion: cross_entropy
+  - optimizer: adam
+  - lr_scheduler: inverse_sqrt

fairseq/config/criterion/adaptive_loss.yaml

+# @package _group_
+sentence_avg: ${params.optimization.sentence_avg}
+ddp_backend: ${params.distributed_training.ddp_backend}

fairseq/config/criterion/cross_entropy.yaml

+# @package _group_
+sentence_avg: ${params.optimization.sentence_avg}
+ddp_backend: ${params.distributed_training.ddp_backend}

fairseq/config/lr_scheduler/cosine.yaml

+# @package _group_
+warmup_updates: 0
+warmup_init_lr: -1
+max_lr: 1.0
+t_mult: 1.0
+lr_period_updates: -1
+lr_shrink: 0.1

fairseq/config/lr_scheduler/inverse_sqrt.yaml

+# @package _group_
+warmup_updates: 4000
+warmup_init_lr: -1

fairseq/config/model/transformer_lm.yaml

+# @package _group_
+activation_fn: "relu"
+dropout: 0.1
+attention_dropout: 0.0
+activation_dropout: 0.0
+relu_dropout: 0.0
+decoder_embed_dim: 512
+decoder_output_dim: 512
+decoder_input_dim: 512
+decoder_ffn_embed_dim: 2048
+decoder_layers: 6
+decoder_attention_heads: 8
+decoder_normalize_before: true
+no_decoder_final_norm: false
+adaptive_softmax_cutoff: null
+adaptive_softmax_dropout: 0
+adaptive_softmax_factor: 4
+no_token_positional_embeddings: false
+share_decoder_input_output_embed: false
+character_embeddings: false
+character_filters: "[(1, 64), (2, 128), (3, 192), (4, 256), (5, 256), (6, 256), (7, 256)]"
+character_embedding_dim: 4
+char_embedder_highway_layers: 2
+adaptive_input: false
+adaptive_input_factor: 4
+adaptive_input_cutoff: null
+tie_adaptive_weights: false
+tie_adaptive_proj: false
+decoder_learned_pos: false
+decoder_layerdrop: 0
+decoder_layers_to_keep: null
+layernorm_embedding: false
+no_scale_embedding: false
+quant_noise_pq: 0
+quant_noise_pq_block_size: 8
+quant_noise_scalar: 0

fairseq/config/model/transformer_lm_baevski_gbw.yaml

+# @package _group_
+activation_fn: "relu"
+dropout: 0.1
+attention_dropout: 0.1
+activation_dropout: 0.0
+relu_dropout: 0.0
+decoder_embed_dim: 512
+decoder_output_dim: 512
+decoder_input_dim: 512
+decoder_ffn_embed_dim: 4096
+decoder_layers: 12
+decoder_attention_heads: 16
+decoder_normalize_before: true
+no_decoder_final_norm: true
+adaptive_softmax_cutoff: null
+adaptive_softmax_dropout: 0
+adaptive_softmax_factor: 4
+no_token_positional_embeddings: false
+share_decoder_input_output_embed: false
+character_embeddings: false
+character_filters: "[(1, 64), (2, 128), (3, 192), (4, 256), (5, 256), (6, 256), (7, 256)]"
+character_embedding_dim: 4
+char_embedder_highway_layers: 2
+adaptive_input: false
+adaptive_input_factor: 4
+adaptive_input_cutoff: null
+tie_adaptive_weights: false
+tie_adaptive_proj: false
+decoder_learned_pos: false
+decoder_layerdrop: 0
+decoder_layers_to_keep: null
+layernorm_embedding: false
+no_scale_embedding: false
+quant_noise_pq: 0
+quant_noise_pq_block_size: 8
+quant_noise_scalar: 0

fairseq/config/model/transformer_lm_baevski_wiki103.yaml

+# @package _group_
+activation_fn: "relu"
+dropout: 0.3
+attention_dropout: 0.1
+activation_dropout: 0.1
+relu_dropout: 0.1
+decoder_embed_dim: 1024
+decoder_output_dim: 1024
+decoder_input_dim: 1024
+decoder_ffn_embed_dim: 4096
+decoder_layers: 16
+decoder_attention_heads: 8
+decoder_normalize_before: true
+no_decoder_final_norm: true
+adaptive_softmax_cutoff: "20000,60000"
+adaptive_softmax_dropout: 0.2
+adaptive_softmax_factor: 4
+no_token_positional_embeddings: false
+share_decoder_input_output_embed: false
+character_embeddings: false
+character_filters: "[(1, 64), (2, 128), (3, 192), (4, 256), (5, 256), (6, 256), (7, 256)]"
+character_embedding_dim: 4
+char_embedder_highway_layers: 2
+adaptive_input: true
+adaptive_input_factor: 4
+adaptive_input_cutoff: "20000,60000"
+tie_adaptive_weights: true
+tie_adaptive_proj: true
+decoder_learned_pos: false
+decoder_layerdrop: 0
+decoder_layers_to_keep: null
+layernorm_embedding: false
+no_scale_embedding: false
+quant_noise_pq: 0
+quant_noise_pq_block_size: 8
+quant_noise_scalar: 0