text-to-lora
Hypernetworks for adapting LLMs to specific tasks via textual descriptions
GraphCanon updated 4w · GitHub synced 4w
Decision brief
text-to-lora uses hypernetworks to adapt LLMs using only textual task descriptions for benchmark tasks without the need for paired input-output data.
Good fit when
- 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.
Avoid when
- 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.
- Requirements:
- text-to-lora requires Python and supports model training processes using hypernetwork techniques.
Observed Jul 14, 2026 · Source: enrich:decision_facts
Verify the decision
Maintenance and security
Full trust report- Maintenance
- Dormant (410d since push)
- As of 4w
- Provenance
- Not a fork · Organization account
- As of 4w
- Security (OSV)
- No lockfile
- As of 1mo
Public GitHub metadata and optional OSV scans. Signals, not a guarantee. Trust methodology.
Install
pip install text-to-loraSimilar tools
Same-category neighbours. No typed graph edges are catalogued for this tool yet.
Evidence and technical details
Sourced facts, taxonomy, compatibility claims, README excerpt, and machine-readable endpoints.
Overview
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.
Capability facts
- Languages
- python
Source: github.language+pyproject.toml · Jul 24, 2026
Categories
Compatibility
Sourced claims from the README excerpt - not unsourced marketing copy.
Source: README excerpt (regex_v1, Jul 24, 2026)
uv venv --python 3.10 --seedSource link
Tags
README
(see https://docs.astral.sh/uv/getting-started/installation/)
uv self update uv venv --python 3.10 --seed uv sync
we use the following wheel for installation
you might have to change the wheel to be compatible with your hardware
uv 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 uv pip install src/fishfarm
---
<h1 align="center">🚀 Demo</h1>
***Downloading trained T2L***
:warning: **You need to download the checkpoints before running any of the demos.** :warning:
:warning: **You need a >16GB GPU to handle both models simultaneously to run any of these demos.** :warning:
```bash
uv run huggingface-cli login
uv run huggingface-cli download SakanaAI/text-to-lora --local-dir . --include "trained_t2l/*"
Web UI
This demo runs Mistral-7B-Instruct-v0.2 locally alongside a T2L model.
For agents
This page has a .md twin and JSON over the API.