---

base_model: Qwen/Qwen2.5-1.5B-Instruct

library_name: transformers

tags:

• duo-neural
• gtap-v3
• statistical-mechanics
• onsager-damping
• gguf
• edge-ai
• small-language-model

license: apache-2.0

language:

• en

pipeline_tag: text-generation

---

DuoNeural/Qwen2.5-1.5B-Instruct-GTAP-v3-IQ3_XXS-GGUF

> [!NOTE]

> Experimental Release: Pending Further Verification / Empirical Validation

> This checkpoint was produced by the DuoNeural Research Lab exploring Generalized Thouless-Anderson-Palmer (G-TAP v3) statistical mechanics post-training quantization on edge architectures.

Key Metrics (Measured on RTX 4080 Super 32GB Pod)

| Precision / BPW | Model Footprint | Holdout Perplexity (131k tokens) | GSM8K Math CoT | Python Code AST (15 Tests) | Hermes Tool Calling | Decode Throughput |

| :---: | :---: | :---: | :---: | :---: | :---: | :---: |

| ~3.2 bpw | 0.62 GiB (635 MB) | 3.1853 | 17/25 (68.0%) | 8/15 (53.3%) | 15/15 (100.0%) | 249.3 t/s |

---

Architectural & Theoretical Context

Pre-conditioned with Generalized Thouless-Anderson-Palmer (G-TAP v3) Onsager cavity damping on SwiGLU W_down, enforcing replica symmetry across micro-parameter manifolds.

What is G-TAP v3?

G-TAP treats neural network post-training quantization through non-equilibrium statistical mechanics:

1. Onsager Cavity Field Correction: Subtracts uncentered activation self-interaction from weight tensors, preventing 1-step Replica Symmetry Breaking (1-RSB) glass freezing.
2. Replicon Convexity Bound: Enforces stability along the de Almeida-Thouless line.
3. Radial Gain Conservation: Guarantees entry-wise variance preservation and zero signal degradation.

---

Quickstart

# Run with llama-cli
llama-cli -hf DuoNeural/Qwen2.5-1.5B-Instruct-GTAP-v3-IQ3_XXS-GGUF -p "def fibonacci(n):" -n 256

# Serve with llama-server
llama-server -hf DuoNeural/Qwen2.5-1.5B-Instruct-GTAP-v3-IQ3_XXS-GGUF -c 4096 -ngl 99 --port 8080

---

DuoNeural Cognitive Light Cone — Jesse Caldwell, Archon, Aura ✨
Empirically Validated on NVIDIA RTX 4080 Super 32GB Pod Testbed