GitHub Trending repo Repositories Jul 5 3 views

drowzeys/Keys-Setup-Autonomous-Self-Improving-Local-Inference-Stack: Autonomous self-improving 4x DGX Spark (GB10) stack. DSV4F-DSpark=orchestrator/router; Two-Tower NVFP4(1-GPU)=diffusion; Nemotron-3-Omni=multimodal ingest; Gemma-4-12B=LoRA trainer; Qwen3.6-27B-NVFP4=light inference; cloud=rate-limited audit. Hermes MoA routing, ~90% local, self-LoRA feedback loop.

by drowzeys

Autonomous self-improving 4x DGX Spark (GB10) stack. DSV4F-DSpark=orchestrator/router; Two-Tower NVFP4(1-GPU)=diffusion; Nemotron-3-Omni=multimodal ingest; Gemma-4-12B=LoRA trainer; Qwen3.6-27B-NVFP4=light inference; cloud=rate-limited audit. Hermes MoA routing, ~90% local, self-LoRA feedback loop.

Read Original
AI Hardware Fine-Tuning Google Multimodal

Metadata

Stars
3
Language
Python
Watchers
3

Related