LLaMA-LoRA-Tuner
AlpacaDataCleaned
LLaMA-LoRA-Tuner | AlpacaDataCleaned | |
---|---|---|
6 | 14 | |
426 | 1,394 | |
- | - | |
7.9 | 7.6 | |
12 months ago | about 1 year ago | |
Python | Python | |
- | Apache License 2.0 |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
LLaMA-LoRA-Tuner
- [P] Uptraining a pretrained model using company data?
- (HELP) Token Issue on Generation
- Help with Random Characters and Words on Output
-
Fine-tuning LLaMA for research without Meta license
I would like to fine-tune LLaMA using this tuner for a research paper, but I am wondering if it is legal to do so. If it isn't, does anyone have suggestions for alternatives which are similarly user-friendly as the one above, since I am not a good programmer? Any advice would be greatly appreciated, thank you!
-
Why run LLMs locally?
The bad news is that, as far as I know, it does require a GPU. The good news is that I've gotten training done with a 7b model on both google colab and kaggle with free accounts. Both have 'just' enough vram to make it work as long as you use load the model in 8bit. Like --load-in-8bit on the command line with oobabooga. The Lora Tuner frontend even has a colab notebook set up to simplify things even more. Though the frontend keeps the LoRA Rank and LoRA Alpha values capped pretty low. Thankfully that's just set in the GUI though. I think it was one of the files in its UI directory. Pretty easy to just hand edit it to allow for higher values if desired.
- How can I train my custom dataset on top of Vicuna?
AlpacaDataCleaned
-
While training LoRA I get 'Failed to read file... JSON parse error'
I tried using the default alpaca_data_cleaned.json training dataset as mentioned here: https://github.com/gururise/AlpacaDataCleaned/blob/main/alpaca_data_cleaned.json. Does anyone know why I could be getting this error? The file must be in correct format since it is the default file they have shown in their example.
-
Why run LLMs locally?
This cleaned alpaca dataset gives a good idea of how data is formatted for the standard alpaca json format. Personally, I'd handle making your own datasets by using gpt4 to format the data into a dataset. You can do it by hand or use a llama model, but I've personally just found using chatgpt to be the most efficient way to get the highest possible output. I'm trying to go for quality over quantity.
-
New llama LoRA trained on WizardLM dataset
I created a dataset merge based on the following very high quality datasets:
- [P] Finetuning a commercially viable open source LLM (Flan-UL2) using Alpaca, Dolly15K and LoRA
-
Stability AI Launches the First of Its StableLM Suite of Language Models
That dataset is licensed under CC BY NC 4.0, which is not open. It also has a bunch of garbage in it; see https://github.com/gururise/AlpacaDataCleaned
- Alpacino-13B
-
GPT4-X-Alpaca 30B 4-bit, by MetaIX based on LoRA by chansung
The alpaca cleaned dataset has integrated the Microsoft GPT-4 dataset and cleaned many of the issues.
-
Alpaca, LLaMa, Vicuna [D]
13b Alpaca Cleaned (trained on the cleaned dataset) is very impressive and works well as an instruct model w/o any censorship.
-
Is there a good place to post datasets for the community?
There's already a community maintained Alpaca with cleaned data. https://github.com/gururise/AlpacaDataCleaned And a huge amount of work has already been done.
-
Dirty data sets and LLaMA/ALPACA...
this might be what you're looking for: https://github.com/gururise/AlpacaDataCleaned
What are some alternatives?
CodeCapybara - Open-source Self-Instruction Tuning Code LLM
StableLM - StableLM: Stability AI Language Models
CodeCapypara - [Moved to: https://github.com/FSoft-AI4Code/CodeCapybara]
safetensors - Simple, safe way to store and distribute tensors
BELLE - BELLE: Be Everyone's Large Language model Engine(开源中文对话大模型)
koboldcpp - A simple one-file way to run various GGML and GGUF models with KoboldAI's UI
lora - Train Large Language Models (LLM) using LoRA
simpleAI - An easy way to host your own AI API and expose alternative models, while being compatible with "open" AI clients.
GPT-4-LLM - Instruction Tuning with GPT-4
simple-llm-finetuner - Simple UI for LLM Model Finetuning
txtinstruct - 📚 Datasets and models for instruction-tuning