{"data":{"slug":"sakanaai-text-to-lora","name":"text-to-lora","tagline":"Hypernetworks for adapting LLMs to specific tasks via textual descriptions","github_url":"https://github.com/SakanaAI/text-to-lora","owner":"SakanaAI","repo":"text-to-lora","owner_avatar_url":"https://avatars.githubusercontent.com/u/140988036?v=4","primary_language":"Python","stars":1300,"forks":88,"topics":["fine-tuning","hypernetworks","llm","lora","machine-learning"],"archived":false,"github_pushed_at":"2025-06-08T14:42:10+00:00","maintenance_label":"Dormant","stars_delta_30d":6,"url":"https://www.graphcanon.com/tools/sakanaai-text-to-lora","markdown_url":"https://www.graphcanon.com/tools/sakanaai-text-to-lora.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/sakanaai-text-to-lora","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=sakanaai-text-to-lora","description":"Hypernetworks that adapt LLMs for specific benchmark tasks using only textual task description as the input","homepage_url":"https://arxiv.org/abs/2506.06105","license":"Apache-2.0","open_issues":2,"watchers":13,"ai_summary":"This Python-based repository offers tools to fine-tune and adapt large language models (LLMs) using hypernetworks with only text task descriptions as input for benchmark tasks.","readme_excerpt":"# (see https://docs.astral.sh/uv/getting-started/installation/)\nuv self update\nuv venv --python 3.10 --seed\nuv sync\n\n---\n\n# we use the following wheel for installation\n\n---\n\n# you might have to change the wheel to be compatible with your hardware\nuv pip install https://github.com/Dao-AILab/flash-attention/releases/download/v2.6.3/flash_attn-2.6.3+cu123torch2.3cxx11abiFALSE-cp310-cp310-linux_x86_64.whl\nuv pip install src/fishfarm\n```\n\n---\n\n<h1 align=\"center\">🚀 Demo</h1>\n\n***Downloading trained T2L***\n\n:warning: **You need to download the checkpoints before running any of the demos.** :warning:\n\n:warning: **You need a >16GB GPU to handle both models simultaneously to run any of these demos.** :warning:\n```bash\nuv run huggingface-cli login\nuv run huggingface-cli download SakanaAI/text-to-lora --local-dir . --include \"trained_t2l/*\"\n```\n\n***Web UI***\n\nThis demo runs `Mistral-7B-Instruct-v0.2` locally alongside a T2L model.\n```bash","github_created_at":"2025-05-05T09:11:35+00:00","created_at":"2026-07-11T11:39:12.917672+00:00","updated_at":"2026-08-24T00:02:20.742622+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"}],"tags":[{"slug":"fine-tuning","name":"fine-tuning"},{"slug":"hypernetworks","name":"hypernetworks"},{"slug":"llm","name":"llm"},{"slug":"lora","name":"lora"},{"slug":"machine-learning","name":"machine-learning"}],"trust":{"provenance":{"is_fork":false,"github_id":977970140,"owner_type":"Organization","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-08-24T00:02:20.004Z","maintenance":{"label":"Dormant","score":18,"methodology":"github_public_v1","releases_90d":0,"days_since_push":441,"last_release_at":null,"stars_delta_30d":6,"open_issues_delta_30d":0},"security_summary":{"status":"no_lockfile","scanner":null,"low_count":0,"high_count":0,"last_scan_at":"2026-07-11T11:39:14.863Z","medium_count":0,"scan_profile":"none","critical_count":0}},"capability_facts":{"scan":{"source":"repo_scan","observed_at":"2026-08-24T00:02:20.445Z"},"languages":{"value":["python"],"source":"github.language+pyproject.toml","observed_at":"2026-08-24T00:02:20.445Z"},"license_spdx":{"value":"Apache-2.0","source":"github.license","observed_at":"2026-08-24T00:02:20.445Z"}},"decision_facts":{"hosting":null,"pricing":null,"requirements":{"notes":["text-to-lora requires Python and supports model training processes using hypernetwork techniques."]},"constraints":null,"when_to_use":["When you have access to textual descriptions of tasks but lack specific labeled datasets required for fine-tuning.","To efficiently adapt pre-trained language models to new tasks with minimal coding effort, leveraging Python scripts for automation."],"when_not_to_use":["Avoid if your task requires complex decision making that surpasses the capabilities provided by text-based descriptions alone and necessitates detailed labeled datasets.","If real-time performance is critical, since text-to-lora's adaptation process through hypernetworks may not be optimized for low-latency use cases."],"source":"enrich:decision_facts","observed_at":"2026-07-14T21:14:18.433Z"},"constraint_facets":null,"decision_summary":[{"label":"Requirements","value":"text-to-lora requires Python and supports model training processes using hypernetwork techniques."},{"label":"Adopt for","value":"text-to-lora uses hypernetworks to adapt LLMs using only textual task descriptions for benchmark tasks without the need for paired input-output data."},{"label":"License detail","value":"Apache-2.0 License"}]}}