Skip to content
View m4vic's full-sized avatar
9 followers · 10 following

Block or report m4vic

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
m4vic/README.md

ideas, tools, systems, experiments.
Anything that mixes creativity, curiosity, and technology.

Building Neural-alchemy - secure, reliable, long-term AI systems focused on safety, reasoning, and developer tooling.

Pinned Loading

  1. TinyMobileLLM TinyMobileLLM Public

    on-mobile-llm is a research-style project that evaluates how well small language models (0.5B–2B parameters) run fully offline on an Android smartphone using GGUF + llama.cpp + Termux. The goal is …

    Shell 5

  2. Train-Transformers-encoder-decoder-models Train-Transformers-encoder-decoder-models Public

    Building a mini LLM from scratch. Embedding, positional encoding , encoder decoder , GPT

    Jupyter Notebook 4

  3. Neural-alchemy/promptshield Neural-alchemy/promptshield Public

    "Universal AI security framework - Protect LLM applications from prompt injection, jailbreaks, and adversarial attacks. Works with OpenAI, Anthropic, LangChain, and any LLM."

    Python 4 3

  4. Neural-alchemy/promptxploit Neural-alchemy/promptxploit Public

    LLM Penetration Testing Framework - Discover vulnerabilities in AI applications before attackers do. 100attacks + AI-powered adaptive mode.

    Python 2 2