DualMind-GGUF

GGUF quantizations of DualMind for local inference via llama.cpp, Ollama, LM Studio, and other GGUF-compatible runtimes.

Convergent Intelligence LLC: Research Division

Available Quantizations

File	Quant	Size	Use Case
`DualMind-f16.gguf`	F16	~3.4 GB	Full precision, reference quality
`DualMind-Q8_0.gguf`	Q8_0	~1.8 GB	Near-lossless, recommended for GPU
`DualMind-Q5_K_M.gguf`	Q5_K_M	~1.3 GB	Balanced quality/size
`DualMind-Q4_K_M.gguf`	Q4_K_M	~1.1 GB	Best for CPU/edge deployment

What Is DualMind?

DualMind is a 1.7B parameter model that implements a dual-cognition reasoning architecture:

<explore>  — unconstrained reasoning, derivation, speculation
<examine>  — adversarial self-critique, error detection
<response> — clean synthesis from the internal dialogue

The model learns to reason freely, then critique its own reasoning, then produce a final answer. Multi-model dialectics collapsed into shared weights.

Training lineage: Qwen3-1.7B → DistilQwen3 (uncensored) → Disctil (DISC-refined) → TKD from Qwen3-30B-A3B-Thinking → DualMind SFT on LogicInference_OA dataset.

Quick Start

Ollama:

# Already published:
ollama run reaperdoesntrun/DualMinded-1.7B

# Or from GGUF:
ollama create dualmind -f Modelfile

llama.cpp:

./llama-cli -m DualMind-Q4_K_M.gguf \
  -p "##USER:\nProve that every convergent sequence is Cauchy.\n\n<explore>\n" \
  --temp 0.6 --top-p 0.9 --repeat-penalty 1.3 -n 512

Recommended parameters:

temperature: 0.6
top_p: 0.9
repeat_penalty: 1.3 (important — prevents enumeration loops)
num_predict: 512–1024

DualMind — source model (SafeTensors)
DualMinded-Qwen3-1.7B — Opus-trained variant
DualMind_Methodolgy — methodology paper (DOI: 10.57967/hf/8184)
DualMind Collection
DistilQwen Collection — the full distillation chain

Mathematical Foundations

This is a GGUF-quantized variant. The mathematical foundations (Discrepancy Calculus, Topological Knowledge Distillation) are documented in the source model's card. The discrepancy operator $Df(x)$ and BV decomposition that inform the training pipeline are preserved through quantization — the structural boundaries detected by DISC during training are baked into the weights, not dependent on precision.

Citation

@misc{colca2026dualmind,
  title={From Three Teachers to Dual Cognition},
  author={Colca, Roy S.},
  year={2026},
  publisher={HuggingFace},
  url={https://doi.org/10.57967/hf/8184}
}

Convergent Intelligence LLC: Research Division — Apache 2.0