Downloads · 30 days
10
32% of all-time downloads
llama-3.2-1b-incident-json-lora
hassanabdel/llama-3.2-1b-incident-json-lora
llama-3.2-1b-incident-json-lora is a machine learning model from hassanabdel. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for peft.
LoRA adapter trained to convert short incident narratives into JSON.
All-time downloads
31
Public
Repo size
1.1 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pt723 MB · 56%
At a glance
- Library
- peft
- Access
- Public
- Created
- Aug 17, 2026
- Updated
- Aug 17, 2026
- SHA
- 118717d9
Base models
Model card
From the Hugging Face model README
Llama 3.2 1B Incident JSON LoRA
LoRA adapter trained to convert short incident narratives into JSON.
Output schema
{
"severity": "low | medium | high | critical",
"entities": {
"actors": [],
"locations": [],
"assets": []
},
"summary": "One-sentence incident summary",
"recommended_action": "One-sentence recommended action"
}
Base model
meta-llama/Llama-3.2-1B-Instruct
Training
- Method: QLoRA / LoRA
- Quantization: 4-bit
- Dataset: 2,040 training examples, 360 validation examples
- Epochs: 3
- Final train loss: 0.1732
Important limitation
This is an adapter, not a standalone model. Load it with the exact base model above.
- Library
- peft
- Created
- Aug 17, 2026
- Updated
- Aug 17, 2026