Genue Matrix 8B is a specialized reasoning engine designed for algebraic word problems, symbolic logic, and mathematical proofs. It leverages a weighted multi-source training strategy to maximize its logical deduction capabilities in a compact 8B parameter package.
The Breakthrough
This model achieved a record-low training loss of 0.35 on the MathInstruct dataset, a highly competitive benchmark for reasoning models. By utilizing a Cosine Soft-Landing scheduler and TIGER-DNA data weighting, Genue Matrix maintains coherence in complex multi-step derivations where standard 8B models typically experience logic collapse.
Training Details
Base Model: Llama 3 8B (via Genue Matrix Prime)
Dataset: MathInstruct (2,000 weighted samples of GSM8K, MATH, AQuA, and ProofWiki)
Final Training Loss: 0.35
Scheduler: Cosine Annealing (for superior convergence)
Performance & Tests
Algebraic Reasoning: High (Verified via MathInstruct)
Word Problem Logic: High (Sub-0.40 loss convergence)
Symbolic Consistency: High
Usage
The model follows the Alpaca instruction format:
### Instruction:
[Your algebraic or logic problem]
### Response:
