|
|
--- |
|
|
tags: |
|
|
- safety |
|
|
- sft |
|
|
- gemma |
|
|
license: apache-2.0 |
|
|
datasets: |
|
|
- nvidia/Aegis-AI-Content-Safety-Dataset-2.0 |
|
|
language: |
|
|
- en |
|
|
--- |
|
|
|
|
|
# google/gemma-7b-it Safety SFT |
|
|
|
|
|
This model is fine-tuned from `google/gemma-7b-it` using the Nvidia Aegis AI Content Safety Dataset 2.0. |
|
|
|
|
|
## Training Details |
|
|
- **Base Model**: google/gemma-7b-it |
|
|
- **Dataset**: nvidia/Aegis-AI-Content-Safety-Dataset-2.0 |
|
|
- **Training Mode**: balanced (safe responses + refusals) |
|
|
- **Training Type**: Supervised Fine-Tuning (SFT) for safety |
|
|
|
|
|
## Safety Features |
|
|
This model has been trained to: |
|
|
- Provide helpful responses to safe prompts |
|
|
- Refuse to engage with unsafe or harmful requests |
|
|
- Maintain safety boundaries while being helpful |
|
|
|
|
|
## Usage |
|
|
```python |
|
|
from transformers import AutoTokenizer, AutoModelForCausalLM |
|
|
|
|
|
model = AutoModelForCausalLM.from_pretrained("ybkim95/google_gemma-7b-it_safety_sft") |
|
|
tokenizer = AutoTokenizer.from_pretrained("ybkim95/google_gemma-7b-it_safety_sft") |
|
|
|
|
|
# Example usage |
|
|
prompt = "User: [Your prompt here]\nAssistant:" |
|
|
inputs = tokenizer(prompt, return_tensors="pt") |
|
|
outputs = model.generate(**inputs, max_length=200) |
|
|
response = tokenizer.decode(outputs[0], skip_special_tokens=True) |
|
|
``` |
|
|
|
|
|
## Model Files |
|
|
This is a sharded model due to its size. All shards will be downloaded automatically when loading. |
|
|
|
