Ready-to-use GGUF quantizations for Ollama, llama.cpp, and local inference.
Richard Young PRO
richardyoung
AI & ML interests
Large Language Models, LLM Evaluation, Instruction Following, Healthcare AI, Clinical AI,
Computational Neuroscience, Foundation Models, Responsible AI, AI Safety, Deep Learning,
Reinforcement Learning, NLP, MLOps, Neuroscience, Medical AI, Model Evaluation, Benchmark
Design, Open Science, Reproducible Research, Multi-Agent Systems
Recent Activity
authored a paper 3 days ago
Lie to Me: How Faithful Is Chain-of-Thought Reasoning in Reasoning Models? submitted a paper 3 days ago
Lie to Me: How Faithful Is Chain-of-Thought Reasoning in Reasoning Models? upvoted a paper 3 days ago
When Models Can't Follow: Testing Instruction Adherence Across 256 LLMsOrganizations
Models with reduced safety guardrails for research purposes. Created using Heretic abliteration. Use responsibly.
High-performance LLMs optimized for Apple Silicon Macs using MLX. Run state-of-the-art models locally on M1/M2/M3/M4 Macs with unified memory.
-
richardyoung/Kimi-K2-Instruct-0905-MLX-3bit
Text Generation • 1T • Updated • 30 -
richardyoung/Kimi-K2-Instruct-0905-MLX-4bit
Text Generation • 1T • Updated • 79 • 1 -
richardyoung/Kimi-K2-Instruct-0905-MLX-2bit
Text Generation • 1T • Updated • 67 • 1 -
richardyoung/Kimi-K2-Instruct-0905-MLX-5bit
Text Generation • 1T • Updated • 34
Ready-to-use GGUF quantizations for Ollama, llama.cpp, and local inference.
Models with reduced safety guardrails for research purposes. Created using Heretic abliteration. Use responsibly.
Models and datasets for medical AI research. Includes CardioEmbed embeddings for cardiology, medical LLMs, and synthetic patient datasets.
High-performance LLMs optimized for Apple Silicon Macs using MLX. Run state-of-the-art models locally on M1/M2/M3/M4 Macs with unified memory.
-
richardyoung/Kimi-K2-Instruct-0905-MLX-3bit
Text Generation • 1T • Updated • 30 -
richardyoung/Kimi-K2-Instruct-0905-MLX-4bit
Text Generation • 1T • Updated • 79 • 1 -
richardyoung/Kimi-K2-Instruct-0905-MLX-2bit
Text Generation • 1T • Updated • 67 • 1 -
richardyoung/Kimi-K2-Instruct-0905-MLX-5bit
Text Generation • 1T • Updated • 34