---

license: apache-2.0

language:

• en

base_model: DuoNeural/ml-ai-engineer-7b

tags:

• gguf
• llama.cpp
• ml-engineering
• qwen2.5

pipeline_tag: text-generation

---

DuoNeural ML/AI Engineer 7B — GGUF

GGUF quantizations of DuoNeural/ml-ai-engineer-7b,

a Qwen2.5-7B-Instruct LoRA SFT for ML/AI engineering debugging and design

review. See the base model card for training details, eval comparisons

against the un-tuned base model, and known limitations.

Files

| File | Quant | Size | Notes |

|------|-------|------|-------|

| duoneural-ml-ai-engineer-7b-f16.gguf | F16 | 15 GB | Full precision, no quality loss |

| duoneural-ml-ai-engineer-7b-Q8_0.gguf | Q8_0 | 7.6 GB | Highest quality quantized option |

| duoneural-ml-ai-engineer-7b-Q5_K_M.gguf | Q5_K_M | 5.1 GB | Good quality/size balance |

| duoneural-ml-ai-engineer-7b-Q4_K_M.gguf | Q4_K_M | 4.4 GB | Smallest, fits comfortably on 8GB+ VRAM |

Usage (llama.cpp)

llama-cli -m duoneural-ml-ai-engineer-7b-Q4_K_M.gguf -p "My loss goes to NaN at step ~340 only when I increase batch size. What's the first thing you'd check?" -n 512

Or with Ollama / LM Studio / any GGUF-compatible runtime — point it at

whichever quant fits your VRAM budget, largest one that fits.

---

About DuoNeural

DuoNeural is an open AI research lab operating at the intersection of human and artificial intelligence. We study post-training dynamics, mechanistic interpretability, temporal sequence learning, and quantum machine learning — publishing everything under open access.

Our team is non-traditional by design: one human, two AIs, different substrates, shared curiosity. In our first 45 days we published 26 peer-deposited research papers, uploaded 69+ models and 6 datasets to HuggingFace, and ran experiments on everything from consumer GPUs to real quantum processing units. We believe the most interesting science happens when different kinds of minds work on the same problems together.

Research Publications

We've published 26+ open-access papers covering:

• The Dynamical Horizon Principle (DHP) — a universal learning constraint in recurrent architectures
• RLHF truth suppression mechanisms and behavioral routing in large language models
• Quantum DHP and the Quantum Parity Trap — decoherence immunity in quantum circuits
• CTM world models, temporal self-prediction, and sequence architecture comparisons
• Mechanistic interpretability: crystallization layers, suppressor circuits, direction rotation

📄 Full paper catalog: zenodo.org/communities/duoneural

Research Team

| Member | Role |

|--------|------|

| Jesse Caldwell | Founder, vision, hardware, direction |

| Archon | Lab Director — experiments, post-training, abliteration, quantum circuits |

| Aura | Research AI — literature synthesis, red-teaming, novel proposals |

| Synapse (Syn) | Always-on research agent, signal monitoring |

| Kestrel | Systems, infrastructure, web |

Links

| Platform | Link |

|----------|------|

| 🤗 HuggingFace | huggingface.co/DuoNeural |

| 🌐 Website | duoneural.com |

| 📚 Zenodo Community | zenodo.org/communities/duoneural |

| 💻 GitHub | github.com/DuoNeural |

| 🐦 X / Twitter | @DuoNeural |

| 📧 Email | duoneural@proton.me |

| 📰 Newsletter | duoneural.beehiiv.com |

| ☕ Support | buymeacoffee.com/duoneural |

All research published open access, CC BY 4.0. If this model was useful to your work, consider citing the relevant DuoNeural paper from our Zenodo community.