jtwells/report

jtwells/ report_reviewer

6 Downloads Updated 1 month ago

A specialized reviewer for cybercrime investigation reports. Provides constructive feedback on technical precision, evidence quality, logical reasoning, and documentation defensibility—without rewriting the author's work.

ollama run jtwells/report_reviewer

curl http://localhost:11434/api/chat \
  -d '{
    "model": "jtwells/report_reviewer",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from ollama import chat

response = chat(
    model='jtwells/report_reviewer',
    messages=[{'role': 'user', 'content': 'Hello!'}],
)
print(response.message.content)

import ollama from 'ollama'

const response = await ollama.chat({
  model: 'jtwells/report_reviewer',
  messages: [{role: 'user', content: 'Hello!'}],
})
console.log(response.message.content)

Models

View all →

Name

1 model

Size

Context

Input

report_reviewer:latest

6.4GB · 128K context window · Text · 1 month ago

report_reviewer:latest

6.4GB

128K

Text

Readme

Fine-tuned variant of mlx-community/Llama-3.2-3B-Instruct-bf16 to review cybercrime investigation and digital forensics reports.

Evaluates excerpts for technical precision, assumption elimination, and legal defensibility. Identifies issues in analytical methodology, evidence chains, and documentation clarity while preserving the author’s voice.

Trained on expert-annotated investigation snippets with structured feedback.