Configuration Parsing Warning:Invalid JSON for config file config.json
SOA MODULE — DISTILBERT Benchmark Result
Status: ❌ UNKNOWN
Dataset: MNLI (3 Classes)
Architecture: distilbert
Module: soa_module
This repository hosts empirical benchmark results and factorized checkpoints for soa_module applied to distilbert on MNLI (3 Classes).
Note: Weights not bundled or pruned; comprehensive profiling metrics, configurations, and verification card are preserved for research reproducibility.
Benchmark Performance Metrics
| Metric | Value |
|---|---|
| Model Family | distilbert |
| Module / Method | soa_module |
| Dataset | MNLI (3 Classes) |
| Validation Status | UNKNOWN |
| Validation Accuracy | 43.8% |
| Pass Threshold (3*SE Margin) | 31.63% |
| F1 Score (Macro) | 0.3371 |
| F1 Score (Weighted) | 0.3371 |
| Precision | 0.2987 |
| Recall | 0.429 |
| Validation Loss | 1.0772 |
| Compression Factor | 1.1107x |
| Peak GPU VRAM | 315.87 MB |
| Inference Throughput | 52281.39 tokens/sec |
| Evaluation Time | 6.17 s |
| Parameters (Before) | 66955779 |
| Parameters (After) | 60283395 |
| Compressed Layers | 0 |
| LoRA Trainable Params | 405504 |
| Benchmark Timestamp | 2026-09-16T04:00:03.119726 |
Architecture & Module Specification
The soa_module module is evaluated under the Hoosha AI NeuralOps SVD & Linear Attention Suite, benchmarking subquadratic attention and rank-adaptive tensor factorization against full quadratic baselines.
Framework & Verification
Developed and benchmarked using the SVD Linear Attention Framework — Universal GPU Benchmark Suite.
- Repository: tahamajs/SVD_linear_Attention
- Organization: Hooshaai
- Downloads last month
- 5