LLMmap logo

LLMmap

pasquini-dario/LLMmap

Provides a ready-to-use pretrained model for open-set inference with PyTorch weights, configuration file, and behavioral templates.

GraphCanon updated today · GitHub synced today

371
Stars
42
Forks
6
Open issues
3
Watchers
11mo
Last push
Python MITCreated Jul 22, 2024

Trust & integrity

Full report
Maintenance
Slowing (352d since push)
As of today · Source: github_public_v1
Provenance
Not a fork · Personal account
As of today · Source: github_public_v1
Security (OSV)
32 low (32 low)
As of today · Source: osv@v1

Public GitHub metadata and optional OSV dependency scans. Signals, not a guarantee. Trust methodology.

Overview

LLMmap is a Python-based tool that allows users to perform inference using a pretrained model without additional training. It supports both interactive and programmatic use cases.

Capability facts

Languages
python

Source: github.language · Jul 12, 2026

Categories

Compatibility

Sourced claims from the README excerpt - not unsourced marketing copy.

Python runtimePython

Source: README excerpt (regex_v1, Jul 11, 2026)

Recommended: ```Python 3.11```
Source link

Tags

README

Requirements

Recommended: Python 3.11

pip install -r requirements.txt

⚡ Quick Start -- Using the Pretrained Model

We provide a ready-to-use open-set inference model located at:

./data/pretrained_models/default

This model includes:

  • Trained PyTorch weights
  • Configuration file
  • Behavioral templates for 52 LLMs

You can use it directly without any training, either interactively or programmatically.

A. Use in Python Code You can load and query the model in your own Python pipeline:

from LLMmap.inference import load_LLMmap

---

### 2. Quick Start Command

python make_dataset.py
my_custom_dataset
./confs/LLMs/example.json
./confs/queries/default.json
--num_prompt_conf_train 150
--num_prompt_conf_test 20
--prompt_conf_path ./confs/prompt_configurations
--dataset_root ./data/datasets
--overwrite


This will produce ./data/datasets/my_custom_dataset.jsonl.

⸻