NetIntel/NetIntelOCR-7B-0925

NetIntel/ NetIntelOCR-7B-0925:latest

230 Downloads Updated 1 year ago

NetIntelOCR model is fine tuned from Qwen2.5-VL-7B-Instruct to support Security and Network extraction for Semantic CMDBs.

vision

ollama run NetIntel/NetIntelOCR-7B-0925

curl http://localhost:11434/api/chat \
  -d '{
    "model": "NetIntel/NetIntelOCR-7B-0925",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from ollama import chat

response = chat(
    model='NetIntel/NetIntelOCR-7B-0925',
    messages=[{'role': 'user', 'content': 'Hello!'}],
)
print(response.message.content)

import ollama from 'ollama'

const response = await ollama.chat({
  model: 'NetIntel/NetIntelOCR-7B-0925',
  messages: [{role: 'user', content: 'Hello!'}],
})
console.log(response.message.content)

Details

Updated 1 year ago

1 year ago

ea2ceaa620c7 · 9.0GB

model

archqwen2vl

parameters7.62B

quantizationQ8_0

8.1GB

projector

archclip

parameters677M

quantizationQ8_0

853MB

system

You are a friendly and informative Network AI assistant, specializing in Network and Security provid

122B

params

{ "temperature": 0.0001, "top_k": 40 }

34B

template

{{- if .System -}} <|im_start|>system {{ .System }}<|im_end|> {{- end -}} {{- range $i, $_ := .Messa

487B

Readme

NetIntel-OCR is a specialized tool designed for network engineers and security professionals to automatically extract, analyze, and convert network diagrams from PDF documents into structured formats. Using advanced OCR and AI technologies, it identifies network topologies, components, and connections, transforming them into actionable intelligence.

Project Details : https://pypi.org/project/netintel-ocr/

Network Intelligence Extraction

Automatic Network Detection: AI-powered identification of network diagrams in documents.
Component Recognition: Identifies routers, switches, firewalls, servers, and other network elements
Connection Mapping: Traces and documents network paths and relationships
Security Architecture Analysis: Extracts security zones, DMZs, and trust boundaries