deepseek

Production-grade recipe for DeepSeek-V4-Flash-0731 (284B MoE) on 2x NVIDIA DGX Spark: self-healing 2-node vLLM cluster, reboot-verified, tuned DSpark speculative decoding (~75 tok/s), full benchmarks, OpenAI Codex CLI integration

CyberBrain_Model is an advanced AI project designed for fine-tuning the model `DeepSeek-R1-Distill-Qwen-14B` specifically for cyber security tasks.

A straightforward explanation of how DeepSeek R1 works

Build Fullstack GenAI apps and AI Agents

Official GitHub repository for Phison aiDAPTIV. NAND cache memory-boosted AI inference and LLM fine-tuning platform.

Practical guide to fine-tuning LLMs like Gemma, LLaMA, and Mistral on custom datasets using popular frameworks.

A low-token visual evidence compiler for text-only coding agents. Convert images into compact Visual Evidence Packets (VEP) for DeepSeek, Codex, Claude Code, and other text-only models.

Codex Skill：让纯文本模型（DeepSeek）借助 StepFun step-3.7-flash 获得看图能力 | Give text-only Codex models (DeepSeek) image understanding via StepFun step-3.7-flash

10 legit ways to access major AI models (GPT, Claude, Llama, DeepSeek & more) for FREE — step-by-step guides, no subscription, no card.

Running Large Language Model easily.

Local AI for Apple Silicon. Chat with open LLMs (Qwen, Gemma, DeepSeek, Mistral, Llama…) fully offline on your Mac via Apple MLX — private by design, zero telemetry.

Run DeepSeek-V4-Flash 304B on a single NVIDIA GB10 / DGX Spark - 2-bit MoE planes, FP4 quality recovery, speculative decoding

DeepSeek-V4-Flash-0731 tuned on 4x DGX Spark (GB10) at TP=4 — 123.13 tok/s decode. Every variable measured one at a time, with the values that lost.

Dsh-visual-plugin.Give your text-only model eyes: forward user images to any OpenAI-compatible vision model and see the results in a Web UI right panel

Extend LLM context windows beyond GPU memory limits with disk-backed KV cache.

Reproducible kit to deploy DeepSeek-V4-Flash-DSpark on a 2× NVIDIA DGX Spark (GB10) cluster: vLLM TP=2 over QSFP 200GbE, NVFP4 KV, DSpark speculative decoding, 1M context, systemd self-heal. Apache-2.0.