https://github.com/zphang/hyperllama
https://github.com/zphang/hyperllama
Last synced: 3 months ago
JSON representation
- Host: GitHub
- URL: https://github.com/zphang/hyperllama
- Owner: zphang
- Created: 2024-02-08T04:49:29.000Z (over 1 year ago)
- Default Branch: main
- Last Pushed: 2024-02-27T04:28:39.000Z (over 1 year ago)
- Last Synced: 2025-01-29T13:43:37.294Z (4 months ago)
- Size: 2.93 KB
- Stars: 5
- Watchers: 5
- Forks: 0
- Open Issues: 1
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Investigating the Effectiveness of HyperTuning via Gisting
---
Code for [Investigating the Effectiveness of HyperTuning via Gisting](https://arxiv.org/abs/2402.16817).
Cite:
```
@article{phang2024hyperllama,
author = {Phang, Jason},
title = {{I}nvestigating the {E}ffectiveness of {H}yperTuning via {G}isting},
year = {2024},
journal = {arXiv preprint 2402.16817},
}
```
---
To-do (as of 02/26/2023):
- [ ] Data preparation instructions
- [ ] Tokenization scripts
- [ ] Hyperpretraining script
- [ ] Fine-tuning script
- [ ] Prefix Tuning script
- [ ] Evaluation script
- [ ] Upload model weights to HF Model Hub