hacking-instruct-exp-72B

This is a experimental fine-tuned version of Qwen2.5-72B-Instruct on cybersecurity datasets.

Model Details

• Base Model: Qwen/Qwen2.5-72B-Instruct
• Fine-tuning Method: Supervised Fine-Tuning (SFT)
• Training Data: Cybersecurity instruction datasets
• Checkpoint: checkpoint-2424

Usage

from transformers import AutoTokenizer, AutoModelForCausalLM

model_name = "ccss17/hacking-instruct-exp-72B"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype=torch.bfloat16,
    device_map="auto"
)