Downloads · 30 days
31
27% of all-time downloads
beam-q4_K_M
torchsight/beam-q4_K_M
beam-q4_K_M is a machine learning model from torchsight. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
Cybersecurity document classifier. LoRA fine-tune of Qwen 3.5 27B, quantized to q4KM. Approximately 17 GB GGUF.
All-time downloads
116
Public
Repo size
16.5 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.gguf16.5 GB · 100%
At a glance
- License
- apache-2.0
- Access
- Public
- Created
- Mar 15, 2026
- Updated
- May 12, 2026
- SHA
- 4e83dd45
Base models
Model card
From the Hugging Face model README
TorchSight Beam q4_K_M
Cybersecurity document classifier. LoRA fine-tune of Qwen 3.5 27B, quantized to q4_K_M. Approximately 17 GB GGUF.
Recommended hardware: 32 GB unified memory (e.g. M-series Mac) or 24 GB GPU.
This is the default quantization for the TorchSight system — released alongside:
Dobrovolskyi, I. Security Document Classification with a Fine-Tuned Local Large Language Model: Benchmark Data and an Open-Source System. Journal of Information Security and Applications, 2026.
Benchmark results
Evaluated under identical methodology (alpaca prompt, Ollama /api/generate,
temperature = 0, num_predict = 2048) on the companion dataset
torchsight/cybersecurity-classification-benchmark.
Canonical numbers live in that repo's BENCHMARK_NUMBERS.md.
Primary — eval-1000-synthetic (n = 1,000)
| Model | Type | Cat. acc [95% CI] | Subcat. acc |
|---|---|---|---|
| Beam q4_K_M | Local (LoRA) | 95.0% [93.5, 96.2] | 48.2% |
| Beam f16 | Local (LoRA) | 93.2% [91.5, 94.6] | 51.1% |
| Beam q8_0 | Local (LoRA) | 93.0% [91.2, 94.4] | 51.4% |
| Claude Sonnet 4 | Commercial API | 79.9% [77.3, 82.3] | 23.0% |
| Claude Opus 4 | Commercial API | 79.9% [77.3, 82.3] | 22.5% |
| GPT-5 | Commercial API | 76.9% [74.2, 79.4] | 11.6% |
| Gemini 2.5 Pro | Commercial API | 75.4% [72.6, 78.0] | 21.0% |
| Qwen 3.5 27B base | Local (no LoRA) | 86.3% [84.0, 88.3] | 19.0% |
| Regex (48 patterns) | Rule-based | 52.7% [49.6, 55.8] | — |
95% confidence intervals are Wilson-score. Beam q4_K_M's advantage over every commercial baseline is significant under pairwise McNemar's tests after Bonferroni correction (α = 0.05).
External — eval-500-external (n = 500)
| Model | Cat. acc [95% CI] | Δ vs. primary |
|---|---|---|
| Beam q4_K_M | 93.8% [91.3, 95.6] | −1.2 pp |
| Beam f16 | 91.2% [88.4, 93.4] | −2.0 pp |
| Beam q8_0 | 91.2% [88.4, 93.4] | −1.8 pp |
| Claude Sonnet 4 | 86.4% [83.1, 89.1] | +6.5 pp |
| Gemini 2.5 Pro | 82.0% [78.4, 85.1] | +6.6 pp |
| Qwen 3.5 27B base | 86.6% [83.3, 89.3] | +0.3 pp |
| GPT-5 | 65.8% [61.5, 69.8] | −11.1 pp |
| Regex baseline | 29.6% [25.8, 33.7] | −23.1 pp |
Usage with Ollama
ollama pull torchsight/beam-q4_K_M
ollama run torchsight/beam-q4_K_M
Or via the TorchSight CLI for full document-scanning workflow:
./install.sh
torchsight /path/to/scan
Training
- Base: Qwen 3.5 27B (dense)
- Method: LoRA (r = 128, α = 256), bf16, 5 epochs
- Dataset: 78,358 balanced samples — see
torchsight/beam-training-data - Hardware: 8× NVIDIA A100 80GB SXM4, 10.5 hours
License
Apache 2.0. The base model (Qwen 3.5 27B) carries its own license; consult upstream terms for use.
- License
- apache-2.0
- Created
- Mar 15, 2026
- Updated
- May 12, 2026