{"data":{"slug":"pasquini-dario-llmmap","name":"LLMmap","tagline":"Provides a ready-to-use pretrained model for open-set inference with PyTorch weights, configuration file, and behavioral templates.","github_url":"https://github.com/pasquini-dario/LLMmap","owner":"pasquini-dario","repo":"LLMmap","owner_avatar_url":"https://avatars.githubusercontent.com/u/44810501?v=4","primary_language":"Python","stars":371,"forks":42,"topics":[],"archived":false,"github_pushed_at":"2025-07-24T13:07:49+00:00","maintenance_label":"Slowing","url":"https://www.graphcanon.com/tools/pasquini-dario-llmmap","markdown_url":"https://www.graphcanon.com/tools/pasquini-dario-llmmap.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/pasquini-dario-llmmap","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=pasquini-dario-llmmap","description":null,"homepage_url":null,"license":"MIT","open_issues":6,"watchers":3,"ai_summary":"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.","readme_excerpt":"## Requirements \n\nRecommended: ```Python 3.11```\n\n```\npip install -r requirements.txt\n```\n\n---\n\n## **⚡ Quick Start -- Using the Pretrained Model**\nWe provide a ready-to-use open-set inference model located at:\n```\n./data/pretrained_models/default\n```\nThis model includes:\n*\tTrained PyTorch weights\n*\tConfiguration file\n*\tBehavioral templates for 52 LLMs\n\nYou can use it directly without any training, either interactively or programmatically.\n\n✅ **A. Use in Python Code**\nYou can load and query the model in your own Python pipeline:\n```\nfrom LLMmap.inference import load_LLMmap\n\n---\n\n### 2. Quick Start Command\n\n```\npython make_dataset.py \\\n    my_custom_dataset \\\n    ./confs/LLMs/example.json \\\n    ./confs/queries/default.json \\\n    --num_prompt_conf_train 150 \\\n    --num_prompt_conf_test 20 \\\n    --prompt_conf_path ./confs/prompt_configurations \\\n    --dataset_root ./data/datasets \\\n    --overwrite\n```\n\nThis will produce ./data/datasets/my_custom_dataset.jsonl.\n\n⸻","github_created_at":"2024-07-22T16:22:11+00:00","created_at":"2026-07-11T23:41:20.006359+00:00","updated_at":"2026-07-12T03:48:11.376657+00:00","categories":[{"slug":"model-training","name":"Model Training","url":"https://www.graphcanon.com/categories/model-training","markdown_url":"https://www.graphcanon.com/categories/model-training.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/model-training"},{"slug":"inference-serving","name":"Inference & Serving","url":"https://www.graphcanon.com/categories/inference-serving","markdown_url":"https://www.graphcanon.com/categories/inference-serving.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/inference-serving"}],"tags":[{"slug":"pretrained-models","name":"pretrained models"},{"slug":"open-set-inference","name":"open-set inference"},{"slug":"llms","name":"llms"},{"slug":"python","name":"python"},{"slug":"pytorch","name":"pytorch"}],"trust":{"provenance":{"is_fork":false,"github_id":832253373,"owner_type":"User","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-07-11T23:41:21.909Z","maintenance":{"label":"Slowing","score":36,"methodology":"github_public_v1","releases_90d":0,"days_since_push":352,"last_release_at":null},"security_summary":{"status":"findings","scanner":"osv@v1","low_count":32,"high_count":0,"last_scan_at":"2026-07-11T23:41:22.617Z","medium_count":0,"scan_profile":"deps","critical_count":0}},"capability_facts":{"scan":{"source":"repo_scan","observed_at":"2026-07-12T03:47:49.063Z"},"languages":{"value":["python"],"source":"github.language","observed_at":"2026-07-12T03:47:49.063Z"},"license_spdx":{"value":"MIT","source":"github.license","observed_at":"2026-07-12T03:47:49.063Z"}},"decision_facts":{"hosting":null,"pricing":null,"requirements":null,"constraints":null,"when_to_use":["When you need immediate model deployment and don't want or can’t afford the time to train a custom model.","For interactive applications where rapid setup with minimal code改动 is required because it provides preconfigured models."],"when_not_to_use":["If your application requires fine-tuning on specific datasets as LLMmap offers only generic pretrained models without out-of-the-box support for further training.","In scenarios needing advanced customization beyond the provided behavioral templates, since LLMmap’s framework might not accommodate extensive model modifications."],"source":"enrich:decision_facts","observed_at":"2026-07-12T03:48:11.162Z"},"constraint_facets":null,"decision_summary":[{"label":"Adopt for","value":"LLMmap is a Python-based tool for quick inference using pretrained models without needing additional training. It includes PyTorch weights, configuration files, and behavioral templates tailored to 52 different LLMs."}]}}