Text Classification
Transformers
English
Indonesian
code
security
code-review
static-analysis
vulnerability-detection
sarif
sliding-window-attention
spark
cpp
avx2
awq
experimental
Instructions to use wxsys/spark-servitor with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use wxsys/spark-servitor with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="wxsys/spark-servitor")# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("wxsys/spark-servitor", device_map="auto") - Notebooks
- Google Colab
- Kaggle
docs: add available model variants (Slim 1.3GB & Baseline 1.6GB)
Browse files
README.md
CHANGED
|
@@ -119,12 +119,21 @@ The generative projection head (`lm_head`, 311M parameters) has been removed. Ra
|
|
| 119 |
| **Output Gating** | Headwise Sigmoid Projection (`g_proj`) |
|
| 120 |
| **Context Window** | Up to 1,048,576 tokens via circular SWA buffer |
|
| 121 |
| **Decision Mechanism** | Dual-Softmax Differential Cortex Head (`DiffCAMQPCortexHead`) |
|
| 122 |
-
| **Format & Quantization** | Outlier-Preserved AWQ INT4 / W8A8 (1.
|
| 123 |
| **Resident Memory** | 4.08 MB VmRSS (C++ daemon via UNIX domain socket) |
|
| 124 |
| **Inference Latency** | 0.044 ms per diff (CPU Intel AVX2 SIMD) |
|
| 125 |
|
| 126 |
---
|
| 127 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 128 |
## Core Capabilities
|
| 129 |
|
| 130 |
### 1. Single-Pass 3-Way Verdict Gate
|
|
|
|
| 119 |
| **Output Gating** | Headwise Sigmoid Projection (`g_proj`) |
|
| 120 |
| **Context Window** | Up to 1,048,576 tokens via circular SWA buffer |
|
| 121 |
| **Decision Mechanism** | Dual-Softmax Differential Cortex Head (`DiffCAMQPCortexHead`) |
|
| 122 |
+
| **Format & Quantization** | Outlier-Preserved AWQ INT4 / W8A8 (1.3 GB Slim & 1.6 GB Baseline) |
|
| 123 |
| **Resident Memory** | 4.08 MB VmRSS (C++ daemon via UNIX domain socket) |
|
| 124 |
| **Inference Latency** | 0.044 ms per diff (CPU Intel AVX2 SIMD) |
|
| 125 |
|
| 126 |
---
|
| 127 |
|
| 128 |
+
## Available Model Variants
|
| 129 |
+
|
| 130 |
+
| Variant | Path in Repository | Size on Disk | Embedding Precision | Verdict Parity vs Baseline | Description |
|
| 131 |
+
|---|---|---|---|---|---|
|
| 132 |
+
| **Spark-Servitor Slim (Recommended)** | `slim/spark-servitor-slim.servitor` | **1.3 GB** (~1,312 MB) | INT8 Quantized (Cosine: 0.999966) | **100% Identical** ($\Delta r^* = 0.0000$) | Recommended for production. Saves ~300 MB on disk while maintaining full 151k vocabulary and zero quality loss. |
|
| 133 |
+
| **Spark-Servitor Baseline** | `int4/spark-servitor-awq_int4.servitor` | **1.6 GB** (~1,608 MB) | FP16 High-Precision | Baseline Standard | Golden uncompressed-embedding checkpoint preserving full FP16 token lookup representations. |
|
| 134 |
+
|
| 135 |
+
---
|
| 136 |
+
|
| 137 |
## Core Capabilities
|
| 138 |
|
| 139 |
### 1. Single-Pass 3-Way Verdict Gate
|