cyberviser/glasseye-bbp-v1

GlassEye BBP/VDP v1 (LoRA)

GlassEye ? authorized HackerOne Bug Bounty (BBP) / Vulnerability Disclosure (VDP) assistant.

Training

• —Base: mistralai/Mistral-7B-Instruct-v0.3
• —Init: Hancock pentest v4 LoRA (detection-leaning)
• —Data: glasseye_bbp_v1.jsonl (~3740 samples) ? scope, reporting, severity, ethical web methodology
• —Steps: 300 | train_loss ? 0.24 | QLoRA
• —Hardware: glasseye NVIDIA RTX 5070 only (no cloud GPUs)

Intended use

In-scope HackerOne program workflows: policy/scope, report writing, severity rationale, remediation. Not for unauthorized testing or exploit dump recipes.

Load

from peft import PeftModel
from transformers import AutoModelForCausalLM, AutoTokenizer
import torch
base = "mistralai/Mistral-7B-Instruct-v0.3"
tok = AutoTokenizer.from_pretrained(base)
model = AutoModelForCausalLM.from_pretrained(base, torch_dtype=torch.bfloat16, device_map="auto")
model = PeftModel.from_pretrained(model, "cyberviser/glasseye-bbp-v1")

Owner: Johnny Watters (0ai-Cyberviser) / 0AI / GLASSEYE