Add README with quantization metadata
Browse files
README.md
ADDED
|
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: fdtn-ai/Foundation-Sec-8B-Instruct
|
| 3 |
+
tags:
|
| 4 |
+
- quantized
|
| 5 |
+
- nvfp4
|
| 6 |
+
- tensorrt
|
| 7 |
+
- foundation-sec-8b-instruct
|
| 8 |
+
- cybersecurity
|
| 9 |
+
---
|
| 10 |
+
|
| 11 |
+
# Foundation-Sec-8B-Instruct-NVFP4-quantized
|
| 12 |
+
|
| 13 |
+
This repository contains an NVFP4 quantized version of the
|
| 14 |
+
[fdtn-ai/Foundation-Sec-8B-Instruct](https://huggingface.co/fdtn-ai/Foundation-Sec-8B-Instruct) model, optimized for NVIDIA Spark using TensorRT Model Optimizer.
|
| 15 |
+
|
| 16 |
+
## Quantization Details
|
| 17 |
+
- Quantization Method: NVFP4
|
| 18 |
+
- Base Model: [fdtn-ai/Foundation-Sec-8B-Instruct](https://huggingface.co/fdtn-ai/Foundation-Sec-8B-Instruct)
|
| 19 |
+
- Tool: NVIDIA TensorRT Model Optimizer
|
| 20 |
+
- Environment: NVIDIA Spark
|
| 21 |
+
|
| 22 |
+
## Loading
|
| 23 |
+
Refer to TensorRT-LLM or your deployment stack for loading NVFP4 artifacts.
|
| 24 |
+
|
| 25 |
+
## License
|
| 26 |
+
(Inherit from base model if applicable, or specify your own)
|