allanj
NLP Scientist at AI Lab, ByteDance, Singapore. Ph.D. from SUTD. Working on Semantic parsing, Dependency parsing and Named Entity Recognition
Salesforce ResearchSingapore
Pinned Repositories
Deductive-MWP
dynamic-pal
Leveraging training data for few-shot prompting
LayoutLMv3-DocVQA
Example codebase for fine-tuning layoutLMv3 on DocVQA
ner_incomplete_annotation
ner_with_dependency
neural-partialCRF
Neural (LSTM) version of the partial CRF model
phd-thesis
Phd thesis
pytorch_neural_crf
Pytorch implementation of LSTM/BERT-CRF for named entity recognition
repo-level-codegen-papers
Repo-Level Code generation papers
statnlp-neural
statnlp-neural
allanj's Repositories
allanj/pytorch_neural_crf
Pytorch implementation of LSTM/BERT-CRF for named entity recognition
allanj/ner_incomplete_annotation
allanj/repo-level-codegen-papers
Repo-Level Code generation papers
allanj/ner_with_dependency
allanj/Deductive-MWP
allanj/LayoutLMv3-DocVQA
Example codebase for fine-tuning layoutLMv3 on DocVQA
allanj/dynamic-pal
Leveraging training data for few-shot prompting
allanj/phd-thesis
Phd thesis
allanj/LLaMA-Factory
Unified Efficient Fine-Tuning of 100+ LLMs (ACL 2024)
allanj/LLMDebugger
LDB: A Large Language Model Debugger via Verifying Runtime Execution Step by Step
allanj/allanj
allanj/allanj.github.io
allanj/awesome-readme-template
An awesome README template for your projects!
allanj/init_setup
allanj/K-Wu.github.io
A beautiful, simple, clean, and responsive Jekyll theme for academics
allanj/layoutlm_experiments
forked branch to reproduce
allanj/lightseq
LightSeq: A High Performance Library for Sequence Processing and Generation
allanj/LOMO_for_math
LOMO: LOw-Memory Optimization for math word problem
allanj/mathematics_in_lean
The user home repository for the Mathematics in Lean tutorial.
allanj/mwp_ReFT
allanj/OpenRLHF
An Easy-to-use, Scalable and High-performance RLHF Framework (70B+ PPO Full Tuning & Iterative DPO & LoRA & RingAttention)
allanj/Pretrained-Pix2Seq
Replication of Pix2Seq with Pretrained Model
allanj/pycharm_setting
allanj/reflexion
[NeurIPS 2023] Reflexion: Language Agents with Verbal Reinforcement Learning
allanj/rxrw
xixi
allanj/shizhediao
allanj/statnlp-core
allanj/transformers
🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.
allanj/transformers-bloom-inference
Fast Inference Solutions for BLOOM
allanj/trl
Train transformer language models with reinforcement learning.