Beijing

Zheng Yuan

Elite
@GanjinZero

Ph.D. from THU Center of Statistical Science. Ex: Qwen. Focus on Alignment, Reasoning and Medical in NLP.

awesome_Chinese_medical_NLP. 中文医学NLP公开资源整理:术语集/语料库/词向量/预训练模型/知识图谱/命名实体识别/QA/信息抽取/模型/论文/etc

2.6k

RRHF. [NIPS2023] RRHF & Wombat

806

ChineseEHRBert. A Chinese EHR Bert Pretrained Model.

271

CODER. CODER: Knowledge infused cross-lingual medical term embedding for term normalization. [JBI, ACL-BioNLP 2022]

80

Tenpai_prediction. 用深层神经网络预测日本麻将立直听牌

71

KeBioLM. Improving Biomedical Pretrained Language Models with Knowledge [BioNLP 2021]

65

math401-llm. Source codes and datasets for How well do Large Language Models perform in Arithmetic tasks?

57

ICD-MSMN. Code Synonyms Do Matter: Multiple Synonyms Matching Network for Automatic ICD Coding [ACL 2022]

56

BioBART. BioBART: Pretraining and Evaluation of A Biomedical Generative Language Model [ACL-BioNLP 2022]

52

Triaffine-nested-ner. Fusing Heterogeneous Factors with Triaffine Mechanism for Nested Named Entity Recognition [ACL 2022 Findings]

44

CHIP2020_term_normalization. CHIP2020 Task 3 术语标准化任务

31

RAMM. Codes and Pre-trained models for RAMM: Retrieval-augmented Biomedical Visual Question Answering with Multi-modal Pre-training [ACM MM 2023]

29

GTS. Code for Unsupervised multi-granular Chinese word segmentation and term discovery via graph partition [JBI]

16

bios_re. Relation Extraction for BIOS

7

pyserverchan. Server-chan for python. / Server酱python版。

7

HMDB51_CNN. Use CNN to classify HMDB51.

7

Deep-Learning-Playground. A playground for Deep Learning

6

Moleformer. Codes for Molecular Geometry-aware Transformer for accurate 3D Atomic System modeling

4

ACG_translator. Train a jp2zh NMT model with ACG parallel corpus.

4

stealer. Calculate the preflop 3bet steal range in NLHE.

4

embedding_script. 大文档计算word2vec,glove,ngram的脚本

3

Quora-Insincere-Questions-Classification. Detect toxic content to improve online conversations

3

GanjinZero.github.io. HTML

3

Awesome-Code-LLM. 👨‍💻 An awesome & curated list of best code-LLM for research.

3

GenBioEL. Generative Biomedical Entity Linking via Knowledge Base-Guided Pre-training and Synonyms-Aware Fine-tuning[NAACL 2022]

2

gsm8k-ScRel. Codes and Data for Scaling Relationship on Learning Mathematical Reasoning with Large Language Models

2

dangdang_gpt2. Python

2

wana. python, R, linux, tensorflow, pytorch, numpy, pandas, etc. 踩坑记录

2

GTO_study. Some notes on GTO result.

2

FindTheChatGPTer. 汇总那些ChatGPT的平替们

2

Ace-Blocker. Calculate MTT EV, variance, VAR, min buyin, ...

2

Haiku_generator. Generate Haiku by seq2seq.

1

Qwen-7B. Python

1
33
Apply