# vext-labs-inc/vext-pentest-7b architecture

> Architecture diagram of the GitHub repository vext-labs-inc/vext-pentest-7b, generated by GitDiagram from its file tree, README and a sample of source files (last updated 2026-10-06). It is an AI-made overview: check details against the source.

- Interactive diagram: https://gitdiagram.com/vext-labs-inc/vext-pentest-7b
- Repository: https://github.com/vext-labs-inc/vext-pentest-7b

## Overview

Vext-labs-7B-v1.1 is a 7B language-model checkpoint for autonomous penetration-testing analysis, distributed with a CLI inference script. The documented workflow is to provide scan or tool output, generate model text, and use it for tool-output interpretation, attack planning, vulnerability classification, or remediation guidance. The sampled script loads a tokenizer and causal language model through Transformers; the README also documents vLLM serving. The repository does not show a pentesting agent or tool-execution runtime. Bundled weights and tokenizer files are identified from the tree; their runtime wiring is not shown in the sampled source.

Main entry points: [`run.py`](https://github.com/vext-labs-inc/vext-pentest-7b/blob/main/run.py) (Inference CLI), [`tokenizer.json`](https://github.com/vext-labs-inc/vext-pentest-7b/blob/main/tokenizer.json) (Tokenizer), [`adapter_model.safetensors`](https://github.com/vext-labs-inc/vext-pentest-7b/blob/main/adapter_model.safetensors) (Model weights)

## Diagram (Mermaid)

```mermaid
flowchart TD

subgraph group_inference["Inference"]
  node_cli["Inference CLI<br/>[run.py]"]
  node_model_output["Pentest analysis<br/>[run.py]"]
end

subgraph group_checkpoint["Model assets"]
  node_tokenizer["Tokenizer<br/>[tokenizer.json]"]
  node_chat_template["Chat template"]
  node_weights["Model weights"]
  node_adapter_config["Adapter config"]
end

node_user(("Analyst"))
node_vllm["vLLM serving"]

node_user -->|"provides prompt"| node_cli
node_cli -->|"tokenizes input"| node_tokenizer
node_cli -->|"generates response"| node_model_output
node_model_output -->|"returns analysis"| node_user
node_vllm -->|"serves checkpoint"| node_weights

click node_cli "https://github.com/vext-labs-inc/vext-pentest-7b/blob/main/run.py"
click node_tokenizer "https://github.com/vext-labs-inc/vext-pentest-7b/blob/main/tokenizer.json"
click node_chat_template "https://github.com/vext-labs-inc/vext-pentest-7b/blob/main/chat_template.jinja"
click node_weights "https://github.com/vext-labs-inc/vext-pentest-7b/blob/main/adapter_model.safetensors"
click node_adapter_config "https://github.com/vext-labs-inc/vext-pentest-7b/blob/main/adapter_config.json"
click node_model_output "https://github.com/vext-labs-inc/vext-pentest-7b/blob/main/run.py"

classDef toneNeutral fill:#f8fafc,stroke:#334155,stroke-width:1.5px,color:#0f172a
classDef toneBlue fill:#dbeafe,stroke:#2563eb,stroke-width:1.5px,color:#172554
classDef toneAmber fill:#fef3c7,stroke:#d97706,stroke-width:1.5px,color:#78350f
classDef toneMint fill:#dcfce7,stroke:#16a34a,stroke-width:1.5px,color:#14532d
classDef toneRose fill:#ffe4e6,stroke:#e11d48,stroke-width:1.5px,color:#881337
classDef toneIndigo fill:#e0e7ff,stroke:#4f46e5,stroke-width:1.5px,color:#312e81
classDef toneTeal fill:#ccfbf1,stroke:#0f766e,stroke-width:1.5px,color:#134e4a
class node_cli,node_model_output toneBlue
class node_tokenizer,node_chat_template,node_weights,node_adapter_config toneAmber
class node_user,node_vllm toneIndigo
```

## Components

### Inference

- [Inference CLI](https://github.com/vext-labs-inc/vext-pentest-7b/blob/main/run.py): `run.py`
- [Pentest analysis](https://github.com/vext-labs-inc/vext-pentest-7b/blob/main/run.py): `run.py`

### Model assets

- [Tokenizer](https://github.com/vext-labs-inc/vext-pentest-7b/blob/main/tokenizer.json): `tokenizer.json`
- [Chat template](https://github.com/vext-labs-inc/vext-pentest-7b/blob/main/chat_template.jinja): `chat_template.jinja`
- [Model weights](https://github.com/vext-labs-inc/vext-pentest-7b/blob/main/adapter_model.safetensors): `adapter_model.safetensors`
- [Adapter config](https://github.com/vext-labs-inc/vext-pentest-7b/blob/main/adapter_config.json): `adapter_config.json`

### Other components

- **Analyst**
- **vLLM serving**

## Connections

- Analyst → Inference CLI: provides prompt (evidence: `README.md`)
- Inference CLI → Tokenizer: tokenizes input (evidence: `run.py`)
- Inference CLI → Pentest analysis: generates response (evidence: `run.py`)
- Pentest analysis → Analyst: returns analysis (evidence: `README.md`)
- vLLM serving → Model weights: serves checkpoint (evidence: `README.md`)
