Update README.md
Browse files
README.md
CHANGED
|
@@ -7,4 +7,13 @@ A Llama3 based model fine-tuned for cybersecurity domain.
|
|
| 7 |
The model was finetuned over https://huggingface.co/datasets/unibuc-cs/CyberGuardianDataset.
|
| 8 |
While the Llama3 original perplexity on the dataset started ~21.9, we managed to fine-tune to ~7.8 on this dataset, still preserving the general language abilities.
|
| 9 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 10 |
Refer to our github page for details: https://github.com/unibuc-cs/CyberGuardian
|
|
|
|
| 7 |
The model was finetuned over https://huggingface.co/datasets/unibuc-cs/CyberGuardianDataset.
|
| 8 |
While the Llama3 original perplexity on the dataset started ~21.9, we managed to fine-tune to ~7.8 on this dataset, still preserving the general language abilities.
|
| 9 |
|
| 10 |
+
You can load the model and see its LoRA config as below:
|
| 11 |
+
```
|
| 12 |
+
from peft import get_peft_model, AutoPeftModelForCausalLM, PeftModel, PeftConfig
|
| 13 |
+
from transformers import AutoModel
|
| 14 |
+
config = PeftConfig.from_pretrained("unibuc-cs/CyberGuardian")
|
| 15 |
+
model = AutoModel.from_pretrained(config.base_model_name_or_path)
|
| 16 |
+
```
|
| 17 |
+
|
| 18 |
+
|
| 19 |
Refer to our github page for details: https://github.com/unibuc-cs/CyberGuardian
|