LoRA
LyCORIS
Our great sponsors
LoRA | LyCORIS | |
---|---|---|
34 | 13 | |
9,046 | 1,966 | |
8.6% | - | |
5.4 | 9.6 | |
about 2 months ago | 7 days ago | |
Python | Python | |
MIT License | 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.
LoRA
-
DECT NR+: A technical dive into non-cellular 5G
This seems to be an order of magnitude better than LoRa (https://lora-alliance.org/ not https://arxiv.org/abs/2106.09685). LoRa doesn't have all the features this one does like OFDM, TDM, FDM, and HARQ. I didn't know there's spectrum dedicated for DECT use.
-
Training LLMs Taking Too Much Time? Technique you need to know to train it faster
So to solve this, we tried researching into some optimization techniques and we found LoRA, Which stands for Low-Rank Adaptation of Large Language Models.
-
OpenAI employee: GPT-4.5 rumor was a hallucination
> Anyone have any ideas / knowledge on how they deploy little incremental fixes to exploited jailbreaks, etc?
LoRa[1] would be my guess.
For detailed explanation I recommend the paper. But the short explanation is that it is a trick which lets you train a smaller, lower dimensional model which when you add to the original model it gets you the result you want.
1: https://arxiv.org/abs/2106.09685
-
Can a LoRa be used on models other than Stable Diffusion?
LoRA was initially developed for large language models, https://arxiv.org/abs/2106.09685 (2021). It was later that people discovered that it worked REALLY well for diffusion models.
-
StyleTTS2 – open-source Eleven Labs quality Text To Speech
Curious if we'll see a Civitai-style LoRA[1] marketplace for text-to-speech models.
1 = https://github.com/microsoft/LoRA
-
Andreessen Horowitz Invests in Civitai, Which Profits from Nonconsensual AI Porn
From https://arxiv.org/abs/2106.09685:
> LoRA: Low-Rank Adaptation of Large Language Models
> An important paradigm of natural language processing consists of large-scale pre-training on general domain data and adaptation to particular tasks or domains. As we pre-train larger models, full fine-tuning, which retrains all model parameters, becomes less feasible. Using GPT-3 175B as an example -- deploying independent instances of fine-tuned models, each with 175B parameters, is prohibitively expensive. We propose Low-Rank Adaptation, or LoRA, which freezes the pre-trained model weights and injects trainable rank decomposition matrices into each layer of the Transformer architecture, greatly reducing the number of trainable parameters for downstream tasks. Compared to GPT-3 175B fine-tuned with Adam, LoRA can reduce the number of trainable parameters by 10,000 times and the GPU memory requirement by 3 times. LoRA performs on-par or better than fine-tuning in model quality on RoBERTa, DeBERTa, GPT-2, and GPT-3, despite having fewer trainable parameters, a higher training throughput, and, unlike adapters, no additional inference latency.
-
Is supervised learning dead for computer vision?
Yes, your understanding is correct. However, instead of adding a head on top of the network, most fine-tuning is currently done with LoRA (https://github.com/microsoft/LoRA). This introduces low-rank matrices between different layers of your models, those are then trained using your training data while the rest of the models' weights are frozen.
-
Run LLMs at home, BitTorrent‑style
Somewhat yes. See "LoRA": https://arxiv.org/abs/2106.09685
They're not composable in the sense that you can take these adaptation layers and arbitrarily combine them, but training different models while sharing a common base of weights is a solved problem.
-
New LoRa RF distance record: 1336 km / 830 mi
With all the naive AI zealotry on HN can you really fault me?
They're referring to this:
https://arxiv.org/abs/2106.09685
-
Open-source Fine-Tuning on Codebase with Refact
It's possible to fine-tune all parameters (called "full fine-tune"), but recently PEFT methods became popular. PEFT stands for Parameter-Efficient Fine-Tuning. There are several methods available, the most popular so far is LoRA (2106.09685) that can train less than 1% of the original weights. LoRA has one important parameter -- tensor size, called lora_r. It defines how much information LoRA can add to the network. If your codebase is small, the fine-tuning process will see the same data over and over again, many times in a loop. We found that for a smaller codebase small LoRA tensors work best because it won't overfit as much -- the tensors just don't have the capacity to fit the limited training set exactly. As the codebase gets bigger, tensors should become bigger as well. We also unfreeze token embeddings at a certain codebase size. To pick all the parameters automatically, we have developed a heuristic that calculates a score based on the source files it sees. This score is then used to determine the appropriate LoRA size, number of finetuning steps, and other parameters. We have tested this heuristic on several beta test clients, small codebases of several files, and large codebases like the Linux kernel (consisting of about 50,000 useful source files). If the heuristic doesn't work for you for whatever reason, you can set all the parameters yourself.
LyCORIS
-
LoRA (LyCORIS) iA3 is amazing (info in 1st comment)
Lycoris is another implementation of LoRA done by KohakuBlueleaf: https://github.com/KohakuBlueleaf/LyCORIS
-
Training LORAs locally guide in text form?
Most guides focus on LoRa training as that has been around for longer. But I think LoHa can give better results. But the training is about half as fas it/s and it requires different training settings.
-
Guide to DreamBooth / LORA / LyCORIS
I've read in some tutorials that it is best that the value should be 64 or below, also here they suggest to not go over 64 ( https://github.com/KohakuBlueleaf/LyCORIS )
-
LyCORIS doesn't work with inpainting models
Does anyone know how to make LyCORIS models (https://github.com/KohakuBlueleaf/LyCORIS) work with inpainting models?
- wtf is a lycoris?
- I wonder what to do with this?
-
I'm the creator of LoRA. How can I make it better?
I think it was linked already but this is also relevant for LoRa: https://github.com/KohakuBlueleaf/LyCORIS Nice work!
-
LoRA: Low-Rank Adaptation of Large Language Models
There are some WIP evolutions of SD Lora in the works, like locon and lycoris.
https://github.com/KohakuBlueleaf/LyCORIS
- What the hell is a Locon/Loha model?
-
SD fine-tuning methods compared: a benchmark
You might want to expand LoRA to include LoCon and LoHa, (and also add a column for VRAM requirements) (Think of it as a more complete LoRA that works for the kernels in the convolutional units rather than just the weights for the feed-forward network), support is still quite limited, but it's starting to pick up steam https://github.com/KohakuBlueleaf/LyCORIS
What are some alternatives?
ComfyUI - The most powerful and modular stable diffusion GUI, api and backend with a graph/nodes interface.
lora - Using Low-rank adaptation to quickly fine-tune diffusion models.
ControlNet - Let us control diffusion models!
peft - 🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.
sd-webui-additional-networks
alpaca-lora - Instruct-tune LLaMA on consumer hardware
kohya_ss
LLaMA-Adapter - [ICLR 2024] Fine-tuning LLaMA to follow Instructions within 1 Hour and 1.2M Parameters
StableTuner - Finetuning SD in style.
LoRA_Easy_Training_Scripts - A UI made in Pyside6 to make training LoRA/LoCon and other LoRA type models in sd-scripts easy