Yong Zheng-Xin's repositories
adapter-transformers
Huggingface Transformers + Adapters = ❤️
multilingual-t0
Multilingual extension of T0
acl-anthology
Data and software for building the ACL Anthology.
alfred
Toolbox for integrating Large Pretrained Models into Weak Supervision
archive-yongzx.github.io
Personal website
concept-erasure
Erasing concepts from neural representations with provable guarantees
cs2951o-boolsat
Project 1 for CSCI 2951O - Prescriptive Analytics
csci2390-assignments
CSCI 2390 assignment stencil code
dpo_toxic
A Mechanistic Understanding of Alignment Algorithms: A Case Study on DPO and Toxicity.
eai-alignment-handbook
Robust recipes for to align language models with human and AI preferences
elk
Keeping language models honest by directly eliciting knowledge encoded in their activations. Building on "Discovering latent knowledge in language models without supervision" (Burns et al. 2022)
eval_t0_deepspeed
Evaluate T0 with DeepSpeed
fairseq
Facebook AI Research Sequence-to-Sequence Toolkit written in Python.
labelmodels
Lightweight implementations of generative label models for weakly supervised machine learning
LLMTest_NeedleInAHaystack
Doing simple retrieval from LLM models at various context lengths to measure accuracy
lm-evaluation-harness
A framework for few-shot evaluation of autoregressive language models.
LMOps
General technology for enabling AI capabilities w/ LLMs and Generative AI models
promptsource
Toolkit for collecting and applying templates of prompting instances
seacrowd-datahub
A collaborative project to collect datasets in SEA languages, SEA regions, or SEA cultures.
t-zero
Reproduce results and replicate training fo T0 (Multitask Prompted Training Enables Zero-Shot Task Generalization)
transformers
🤗 Transformers: State-of-the-art Natural Language Processing for Pytorch, TensorFlow, and JAX.
yong-life-in-weeks
Visualise your life 🎩✨