Skip to content
View wuwangzhang1216's full-sized avatar
🎯
Focusing
🎯
Focusing

Organizations

@Lightning-Goods

Block or report wuwangzhang1216

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don't include any personal information such as legal names or email addresses. Markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
wuwangzhang1216/README.md

Hey, I'm Steve Neal πŸ‘‹

AI Engineer & LLM Researcher

Building AI-native tools that actually ship. Obsessed with making large language models more useful, more controllable, and more open.


πŸš€ What I'm Working On

  • 🧠 LLM alignment research β€” abliteration, representation engineering & steering vectors
  • πŸ” Vector search engines & RAG pipelines at scale
  • πŸ€– Multi-agent orchestration β€” built from scratch, no heavy frameworks
  • πŸ“ AI-native writing & knowledge systems
  • 🦬 Working on OpenYak β€” open-source AI desktop app
  • πŸ”¬ Publishing fine-tuned & abliterated models on HuggingFace

πŸ›  Tech Stack

Languages
Python C++ CUDA TypeScript

AI/ML & Deep Learning
PyTorch Transformers HuggingFace PEFT DeepSpeed vLLM

Research & Techniques
RepEng Abliteration RLHF Quantization FlashAttention KnowledgeDistillation MoE

LLM APIs & Inference
OpenAI Anthropic Ollama

Vector Databases & Retrieval
FAISS pgvector Milvus

Full Stack
FastAPI Next.js React PostgreSQL Redis

Infra
Docker AWS Linux


πŸŽ“ Background

  • πŸ’Ό 10+ years in Databases, LLMs & AI Agent Systems

HuggingFace

Pinned Loading

  1. openyak/desktop openyak/desktop Public

    An open-source desktop AI agent that handles your documents, files, and daily workflows β€” locally, with any model.

    Python 519 71

  2. abliterix abliterix Public

    Fully automatic censorship removal for language models. LoRA abliteration + Optuna TPE optimization.

    Python 42 8

  3. doXmind/Docs doXmind/Docs Public

    MDX