QLoRA: Efficient Finetuning of Quantized LLMs
| [Paper](https://arxiv.org/abs/2305.14314) | [Adapter Weights](https://huggingface.co/timdettmers) | [Demo](https://huggingface.co/spaces/uwnlp/guanaco-playground-tgi) |
Explore
129,002 skills indexed with the new KISS metadata standard.
| [Paper](https://arxiv.org/abs/2305.14314) | [Adapter Weights](https://huggingface.co/timdettmers) | [Demo](https://huggingface.co/spaces/uwnlp/guanaco-playground-tgi) |
services:
require_ci_to_pass: yes
type: website
- Can you train StableLM with this? Yes, but only with a single GPU atm. Multi GPU support is coming soon! Just waiting on this [PR](https://github.com/huggingface/transformers/pull/22874)
<picture>
generic skill
configs
python: python3
language: "en-US"
exclude = tests
source = axolotl
[*]
__pycache__/
<img src="https://raw.githubusercontent.com/huggingface/alignment-handbook/main/assets/handbook.png">
> [!NOTE]
- repo: https://github.com/astral-sh/ruff-pre-commit
<div style="text-align: center">
.gitattributes
Everyone is welcome to contribute, and we value everybody's contribution. Code contributions are not the only way to help the community. Answering questions, helping others, and improving the documentation are also immensely valuable.
We as members, contributors, and leaders pledge to make participation in our
__pycache__/
- repo: https://github.com/astral-sh/ruff-pre-commit
Copyright 2023 The HuggingFace Team. All rights reserved.