Update README.md
Browse files
README.md
CHANGED
|
@@ -24,7 +24,7 @@ LLMSIEM/logem is a specialized language model fine-tuned for Security Informatio
|
|
| 24 |
|
| 25 |
LLMSIEM/logem is a fine-tuned version of Qwen3-0.6B, specifically optimized for cybersecurity applications. The model demonstrates that targeted fine-tuning can dramatically improve performance on domain-specific tasks, achieving superior results compared to much larger general-purpose models.
|
| 26 |
|
| 27 |
-
- **Developed by:** [
|
| 28 |
- **Model type:** Causal Language Model (Fine-tuned)
|
| 29 |
- **Language(s):** English
|
| 30 |
- **License:** Apache 2.0
|
|
@@ -34,8 +34,6 @@ LLMSIEM/logem is a fine-tuned version of Qwen3-0.6B, specifically optimized for
|
|
| 34 |
|
| 35 |
### Model Sources
|
| 36 |
|
| 37 |
-
- **Repository:** [Your GitHub Repository]
|
| 38 |
-
- **Paper:** [Research Paper Link if available]
|
| 39 |
- **Blog Post:** [LinkedIn/Blog Series Link]
|
| 40 |
|
| 41 |
## Performance Highlights
|
|
@@ -206,7 +204,7 @@ Dataset characteristics:
|
|
| 206 |
|
| 207 |
Training a specialized 0.6B parameter model requires significantly less computational resources compared to training larger models from scratch:
|
| 208 |
|
| 209 |
-
- **Hardware Type:** NVIDIA GPU (
|
| 210 |
- **Training approach:** Fine-tuning (more efficient than training from scratch)
|
| 211 |
- **Base model efficiency:** Starting from pre-trained Qwen3-0.6B reduces carbon footprint
|
| 212 |
- **Production efficiency:** Smaller model size reduces inference energy consumption
|
|
|
|
| 24 |
|
| 25 |
LLMSIEM/logem is a fine-tuned version of Qwen3-0.6B, specifically optimized for cybersecurity applications. The model demonstrates that targeted fine-tuning can dramatically improve performance on domain-specific tasks, achieving superior results compared to much larger general-purpose models.
|
| 26 |
|
| 27 |
+
- **Developed by:** [Hassan Shehata]
|
| 28 |
- **Model type:** Causal Language Model (Fine-tuned)
|
| 29 |
- **Language(s):** English
|
| 30 |
- **License:** Apache 2.0
|
|
|
|
| 34 |
|
| 35 |
### Model Sources
|
| 36 |
|
|
|
|
|
|
|
| 37 |
- **Blog Post:** [LinkedIn/Blog Series Link]
|
| 38 |
|
| 39 |
## Performance Highlights
|
|
|
|
| 204 |
|
| 205 |
Training a specialized 0.6B parameter model requires significantly less computational resources compared to training larger models from scratch:
|
| 206 |
|
| 207 |
+
- **Hardware Type:** NVIDIA GPU (RTX3060)
|
| 208 |
- **Training approach:** Fine-tuning (more efficient than training from scratch)
|
| 209 |
- **Base model efficiency:** Starting from pre-trained Qwen3-0.6B reduces carbon footprint
|
| 210 |
- **Production efficiency:** Smaller model size reduces inference energy consumption
|