|
|
@@ -1,6 +1,6 @@
|
|
|
## 🦙🌲🤏 Alpaca-LoRA: Low-Rank LLaMA Instruct-Tuning
|
|
|
|
|
|
-**Try the pretrained model out on Colab [here](https://colab.research.google.com/drive/1eWAmesrW99p7e1nah5bipn0zikMb8XYC)!** _If you have problems with short outputs or very long outputs, please redownload the weights (`force_download=True`) and pull the latest version of the code._
|
|
|
+**Try the pretrained model out on Colab [here](https://colab.research.google.com/drive/1eWAmesrW99p7e1nah5bipn0zikMb8XYC)!**
|
|
|
|
|
|
This repository contains code for reproducing the [Stanford Alpaca](https://github.com/tatsu-lab/stanford_alpaca) results using [low-rank adaptation (LoRA)](https://arxiv.org/pdf/2106.09685.pdf).
|
|
|
We provide an Instruct model of similar quality to `text-davinci-003` that can run [on a Raspberry Pi](https://twitter.com/miolini/status/1634982361757790209) (for research),
|
|
|
@@ -14,6 +14,8 @@ as well as Tim Dettmers' [bitsandbytes](https://github.com/TimDettmers/bitsandby
|
|
|
|
|
|
Without hyperparameter tuning or validation-based checkpointing, the LoRA model produces outputs comparable to the Stanford Alpaca model. (Please see the outputs included below.) Further tuning might be able to achieve better performance; I invite interested users to give it a try and report their results.
|
|
|
|
|
|
+For discussion and support, users have created a dedicated Discord server [here](https://discord.gg/prbq284xX5).
|
|
|
+
|
|
|
### Setup
|
|
|
|
|
|
1. Install dependencies
|
|
|
@@ -38,9 +40,10 @@ PRs adapting this code to support larger models are always welcome.
|
|
|
### Checkpoint export (`export_*_checkpoint.py`)
|
|
|
|
|
|
These files contain scripts that merge the LoRA weights back into the base model
|
|
|
-for export to Hugging Face format and to PyTorch `state_dicts`,
|
|
|
-which should help users who want to export LlamaModel-shaped weights or
|
|
|
-use the model with projects like [llama.cpp](https://github.com/ggerganov/llama.cpp).
|
|
|
+for export to Hugging Face format and to PyTorch `state_dicts`.
|
|
|
+They should help users
|
|
|
+who want to run inference in projects like [llama.cpp](https://github.com/ggerganov/llama.cpp)
|
|
|
+or [alpaca.cpp](https://github.com/antimatter15/alpaca.cpp).
|
|
|
|
|
|
### Dataset
|
|
|
|
Eric J. Wang