GlassEye? authorized HackerOne Bug Bounty (BBP) / Vulnerability Disclosure (VDP) assistant. In-scope HackerOne program workflows: policy/scope, report writing, severity rationale, remediation. Not for unauthorized testing or exploit dump recipes.
Model Card
By CyberviserAI, published under apache-2.0, revision 283271b157b4.
GlassEye? authorized HackerOne Bug Bounty (BBP) / Vulnerability Disclosure (VDP) assistant. In-scope HackerOne program workflows: policy/scope, report writing, severity rationale, remediation. Not for unauthorized testing or exploit dump recipes.
Read CyberviserAI's full model card
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
Identity and Version
- Repository
- GLASSEYE/glasseye-bbp-v1
- Publisher
- CyberviserAI
- Task
- Not stated by the source
- Modality
- Other
- Library
- peft
- Parameters
- Not stated by the source
- Languages
- bug-bounty, vdp, bbp
- Revision
- 283271b157b44fbad049a64cacc8439ddafba3b6
- First published
- 2026-09-18
- Last updated
- 2026-09-18
Files and Weights
7 files, 87.6 MB in total. The weights are 1 file totalling 83.9 MB in safetensors.
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| adapter_model.safetensors | Weights | 83.9 MB | 4d0503531f6c |
| adapter_config.json | Configuration | 1.3 KB | — |
| README.md | Documentation | 1.2 KB | — |
| chat_template.jinja | Other | 4.0 KB | — |
| .gitattributes | Repository | 1.5 KB | — |
| tokenizer.json | Tokenizer | 3.7 MB | — |
| tokenizer_config.json | Tokenizer | 462 B | — |
License and Download
- License
- apache-2.0
- Access
- Open weights, no gate
- Download size
- 83.9 MB
Released by CyberviserAI through its official repository on Hugging Face. Read the license.
Built From
- Adapter of mistralai/Mistral-7B-Instruct-v0.3
- Derived from mistralai/Mistral-7B-Instruct-v0.3
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 83.9 MB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
Questions About glasseye-bbp-v1
Can I use glasseye-bbp-v1 commercially?
Yes. glasseye-bbp-v1 is released under Apache License 2.0. The Apache License 2.0 is a permissive open-source license. It permits commercial use, modification and redistribution. It requires keeping the license and copyright notices and any NOTICE file, stating significant changes, and it includes an express patent grant from contributors.