|
--- |
|
library_name: transformers |
|
datasets: |
|
- ahmed000000000/cybersec |
|
- dzakwan/cybersec |
|
language: |
|
- en |
|
tags: |
|
- conversational |
|
--- |
|
# Model Card for Model ID |
|
|
|
Works as a cyber assistant. |
|
|
|
|
|
|
|
## Model Details |
|
|
|
### Model Description |
|
|
|
<!-- Provide a longer summary of what this model is. --> |
|
|
|
This is the model card of a 🤗 transformers model that has been pushed on the Hub. |
|
|
|
- **Developed by:** <a href="https://github.com/Zardian18">Zardian18</a> |
|
- **Model type:** GPT2 |
|
- **Language(s) (NLP):** English |
|
- **Finetuned from model [optional]:** <a href="https://huggingface.co/openai-community/gpt2-medium">OpenAi GPT2-medium</a> |
|
|
|
### Model Sources [optional] |
|
|
|
<!-- Provide the basic links for the model. --> |
|
|
|
- **Repository:** <a href="https://github.com/Zardian18/CyberAssist">Github repo</a> |
|
|
|
## Uses |
|
|
|
Can be used to handle and solve basic cybersec queries. |
|
|
|
|
|
## Bias, Risks, and Limitations |
|
|
|
Currently it is fine-tuned on GPT2, which is good but not comparable to state of the art LLMs and Transformers. Moreover, the dataset is small. |
|
|
|
[More Information Needed] |
|
|
|
|
|
## How to Get Started with the Model |
|
|
|
```# Use a pipeline as a high-level helper |
|
from transformers import pipeline |
|
|
|
pipe = pipeline("text-generation", model="Zardian/Cyber_assist3.0") |
|
|
|
``` |
|
```# Load model directly |
|
from transformers import AutoTokenizer, AutoModelForCausalLM |
|
|
|
tokenizer = AutoTokenizer.from_pretrained("Zardian/Cyber_assist3.0") |
|
model = AutoModelForCausalLM.from_pretrained("Zardian/Cyber_assist3.0") |
|
|
|
``` |
|
|
|
## Training Details |
|
|
|
### Training Data |
|
|
|
<a href="https://huggingface.co/datasets/ahmed000000000/cybersec">Cybersec queries and responses dataset</a> consisting of 12k enteries. |
|
|
|
<a href="https://huggingface.co/datasets/dzakwan/cybersec">Cybersec dataset with instructions and output</a> consisting of 14k enteries. |
