ML Application · Python
Mark-AI
Sparse Neural Architectures (DeepSeek2 Native GGUF, Multi-Head Latent Attention & 3D MoE in Non-Linear 4-Bit IQ4_NL) engineered for 8GB Consumer GPUs.
What it is
Mark-AI is a repository implementing Sparse Transformer architectures (Multi-Head Latent Attention and Mixture-of-Experts) with quantization to GGUF format for efficient local inference on consumer GPUs, including training scripts, export tools, and a retrieval-augmented generation component.
- deepseek2
- gguf
- mixture-of-experts
- multi-head-latent-attention
- pytorch
- quantization
Where it counts
- NLP & LLMs95%
- Machine Learning90%
- MLOps40%
- Data Science20%
- Computer Vision10%
- AI Agents10%
How much of the project is about each field, as scoring counts it. It ranks in the field it is most about.
Around it on the NLP & LLMs board
Whole board- 36, shared ranksnap-cite-livive-netAI Developer Tool · Python57.4ImplementationJarad PeckenpaughNLP & LLMs
- 36, shared ranktactilesqlML Application · JavaScript57.4ImplementationMurat GençNLP & LLMs
- 38, shared rankorionOther AI Project · TypeScript57.0ImplementationNepheriusNLP & LLMs
- 38, shared rankMark-AIML Application · Python57.0ImplementationMice WorksNLP & LLMs
- 40ollama-webui-personalML Application · Svelte56.4ImplementationPetr SovadinaNLP & LLMs
