Shanghai(CN) & Sydney(AU)

Liam Liang Ding

Expert
@alphadl

AI researcher & builder

lookahead.pytorch. lookahead optimizer (Lookahead Optimizer: k steps forward, 1 step back) for pytorch

336

proxifier_code. several free registration code for PROXIFIER

273

darts.pytorch1.1. Implementation with latest PyTorch (v1.1) for multi-gpu differentiable architecture search https://arxiv.org/abs/1806.09055

83

R1. 🚀enhanced GRPO with more verifiable rewards and real-time evaluators

37

mobi_ebooks. personal taste mobi books for kindle, mainly in Chinese version. welcome rp/ fork/ star ...

31

Neural-Machine-Translation. Several basic neural machine translation models implemented by PyTorch & TensorFlow

29

OOP-eval. The first Object-Oriented Programming (OOP) Evaluation Benchmark for LLMs

27

SafeLLM_with_IntentionAnalysis. Towards Safe LLM with our simple-yet-highly-effective Intention Analysis Prompting

21

self-attention. Transformer

11

corpus_filter. Scripts for machine translation corpora filtering/ 机器翻译平行语料过滤的脚本

9

inspiring_papers. Papers related to Machine Translation (continuously updating & welcome Star/Fork/PR)

7

EasyBLEU. An effective and simple tool to calculate SacreBLEU, Token-BLEU, BLEU w/ compound splitting for fairseq

7

LCNAT. LCNAT: Lexical choice in NAT - ICLR 2021

7

keywords_extract. Python

7

CodeGen-USCD. Code Gen with "Uncertainty Aware Selective Contrastive Decoding"

6

RLFW-NAT. RLFW-NAT: Rejuvenating low-frequency words (parallel data) - ACL 2021

5

LanguageAware_Tuning. language-aware tuning for building accurate cross-lingual LLMs

4

NMT-MultiModel-EnsembleDecoder. Extended multi-model ensemble decoding function based on ONMT

4

GD-optimization-algorithms. gradient descent optimization algorithms

3

RLFW-NAT.mono. RLFW-NAT.mono: Redistributing low-frequency words (monolingual data) - ACL 2022

3

DeepLearning-500-questions. 深度学习500问，以问答形式对常用的概率知识、线性代数、机器学习、深度学习、计算机视觉等热点问题进行阐述，以帮助自己及有需要的读者。 全书分为18个章节，50余万字。由于水平有限，书中不妥之处恳请广大读者批评指正。 未完待续............ 如有意合作，联系scutjy2015@163.com 版权所有，违权必究 Tan 2018.06

3

VRNN.tensorflow. A novel RNN cell named VRNN, which consumes less parameters and training time but gain comparable performance as LSTM/GRU

3

pyltp. pyltp: the python extension for LTP

2

SafeVLM_with_AMIA. Towards Safe LVM with Automatic Masking and Joint Intention Analysis

2

Dive-into-DL-PyTorch. 本项目将《动手学深度学习》(Dive into Deep Learning)原书中的MXNet实现改为PyTorch实现。

1

awesome-ensemble-learning. Ensemble learning related books, papers, videos, and toolboxes

1

CMU-CS11-747. hw for CMU cs11-747, neural networks for NLP

1

MT-scorer. several evaluation metrics for Machine Translation

1

WMT_scripts. Some helpful scripts for the WMT

1

rapid-adaptation. Reproduction instructions for "Rapid Adaptation of Neural Machine Translation to New Languages"

1

Awesome-LLM-Compression. Awesome LLM compression research papers and tools.

1

AlignLLMHumanSurvey. Aligning Large Language Models with Human: A Survey

1

sentence_prob_lstm. Calculating the sentence probability through lstm language model

1

deep_learning_curriculum. Language model alignment-focused deep learning curriculum

1

graph-generation. GraphRNN: Generating Realistic Graphs with Deep Auto-regressive Models

1

PyTorch-BigGraph. Software used for generating embeddings from large-scale graph-structured data.

1

llm-course. Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.

1

Efficient-LLMs-Survey. Efficient Large Language Models: A Survey

1

Awesome-Knowledge-Distillation-of-LLMs. This repository collects papers for "A Survey on Knowledge Distillation of Large Language Models". It includes KD Algorithms (Labeling, Self-Knowledge, Self-Rewarding, SFT, etc.) leveraging data augmentation or synthesis for getting knowledge, Skill Distillation (e.g. instruction following), and specialized applications (law, healthcare).

1

arxiv-sanity-preserver. Web interface for browsing, search and filtering recent arxiv submissions

1

cakechat. CakeChat: Emotional Generative Dialog System

1

text2sql-data. A collection of datasets that pair questions with SQL queries.

1

deeplearningbook-chinese. Deep Learning Book Chinese Translation

1
43
Apply