RWKV-LM
civitai
RWKV-LM | civitai | |
---|---|---|
84 | 639 | |
11,657 | 5,626 | |
- | 2.1% | |
8.8 | 10.0 | |
8 days ago | 4 days ago | |
Python | TypeScript | |
Apache License 2.0 | 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.
RWKV-LM
-
Do LLMs need a context window?
https://github.com/BlinkDL/RWKV-LM#rwkv-discord-httpsdiscord... lists a number of implementations of various versions of RWKV.
https://github.com/BlinkDL/RWKV-LM#rwkv-parallelizable-rnn-w... :
> RWKV: Parallelizable RNN with Transformer-level LLM Performance (pronounced as "RwaKuv", from 4 major params: R W K V)
> RWKV is an RNN with Transformer-level LLM performance, which can also be directly trained like a GPT transformer (parallelizable). And it's 100% attention-free. You only need the hidden state at position t to compute the state at position t+1. You can use the "GPT" mode to quickly compute the hidden state for the "RNN" mode.
> So it's combining the best of RNN and transformer - great performance, fast inference, saves VRAM, fast training, "infinite" ctx_len, and free sentence embedding (using the final hidden state).
> "Our latest version is RWKV-6,*
- People who've used RWKV, whats your wishlist for it?
- Paving the way to efficient architectures: StripedHyena-7B
-
Understanding Deep Learning
That is not true. There are RNNs with transformer/LLM-like performance. See https://github.com/BlinkDL/RWKV-LM.
-
Q-Transformer: Scalable Reinforcement Learning via Autoregressive Q-Functions
This is what RWKV (https://github.com/BlinkDL/RWKV-LM) was made for, and what it will be good at.
Wow. Pretty darn cool! <3 :'))))
-
Personal GPT: A tiny AI Chatbot that runs fully offline on your iPhone
Thanks for the support! Two weeks ago, I'd have said longer contexts on small on-device LLMs are at least a year away, but developments from last week seem to indicate that it's well within reach. Once the low hanging product features are done, I think it's a worthy problem to spend a couple of weeks or perhaps even months on. Speaking of context lengths, recurrent models like RWKV technically have infinite context lengths, but in practice the context slowly fades away after a few thousands of tokens.
-
"If you see a startup claiming to possess top-secret results leading to human level AI, they're lying or delusional. Don't believe them!" - Yann LeCun, on the conspiracy theories of "X company has reached AGI in secret"
This is the reason there are only a few AI labs, and they show little of the theoretical and scientific understanding you believe is required. Go check their code, there's nothing there. Even the transformer with it's heads and other architectural elements turns out to not do anything and it is less efficient than RNNs. (see https://github.com/BlinkDL/RWKV-LM)
-
The Secret Sauce behind 100K context window in LLMs: all tricks in one place
I've been pondering the same thing, as simply extending the context window in a straightforward manner would lead to a significant increase in computational resources. I've had the opportunity to experiment with Anthropics' 100k model, and it's evident that they're employing some clever techniques to make it work, albeit with some imperfections. One interesting observation is that their prompt guide recommends placing instructions after the reference text when inputting lengthy text bodies. I noticed that the model often disregarded the instructions if placed beforehand. It's clear that the model doesn't allocate the same level of "attention" to all parts of the input across the entire context window.
Moreover, the inability to cache transformers makes the use of large context windows quite costly, as all previous messages must be sent with each call. In this context, the RWKV-LM project on GitHub (https://github.com/BlinkDL/RWKV-LM) might offer a solution. They claim to achieve performance comparable to transformers using an RNN, which could potentially handle a 100-page document and cache it, thereby eliminating the need to process the entire document with each subsequent query. However, I suspect RWKV might fall short in handling complex tasks that require maintaining multiple variables in memory, such as mathematical computations, but it should suffice for many scenarios.
On a related note, I believe Anthropics' Claude is somewhat underappreciated. In some instances, it outperforms GPT4, and I'd rank it somewhere between GPT4 and Bard overall.
-
Meta's plan to offer free commercial AI models puts pressure on Google, OpenAI
> The only reason open-source LLMs have a heartbeat is they’re standing on Meta’s weights.
Not necessarily.
RWKV, for example, is a different architecture that wasn't based on Facebook's weights whatsoever. I don't know where BlinkDL (the author) got the training data, but they seem to have done everything mostly independently otherwise.
https://github.com/BlinkDL/RWKV-LM
disclaimer: I've been doing a lot of work lately on an implementation of CPU inference for this model, so I'm obviously somewhat biased since this is the model I have the most experience in.
-
Eliezer Yudkowsky - open letter on AI
I think the main concern is that, due to the resources put into LLM research for finding new ways to refine and improve them, that work can then be used by projects that do go the extra mile and create things that are more than just LLMs. For example, RWKV is similar to an LLM but will actually change its own model after every processed token, thus letting it remember things longer-term without the use of 'context tokens'.
civitai
-
Washington's Lottery forced to pull site after creating AI porn of lotto user
I find it quite funny, especially if you realize that something like 90% of the Stable Diffusion model fine-tunes out there are actually made for generating porn or images of females. Go to the website that has the most image generation models to verify this for yourself: https://civitai.com
WARNING don't visit this site on your work computer.
-
JavaScript Bloat in 2024
Remember The Website Obesity Crisis [1] article from 2015, since then [2] things only got worse, and it is been almost 10 years already (at the end of 2024).
Is it foolish to say that in 10 more years you wont be able to navigate the web on a circa 2015 PC ? If nothing changes seems like it.
My old macbook from 2013 with latest Firefox is already can not handle loading https://civitai.com web page with 23.98 MB of JavaScript, it is just hangs for half a minute while trying to render this disaster of web frontend.
[1] https://idlewords.com/talks/website_obesity.htm
[2] https://hn.algolia.com/?dateRange=all&page=0&prefix=true&que...
-
Generate Unlimited AI Images for Free Online
One of the most popular free AI image generators right now is Civitai. Civitai uses a cutting-edge AI model to turn text prompts into photorealistic images in seconds.
-
Ask HN: Those making $500/month on side projects in 2024 – Show and tell
Soz, I don't like to cross link my accounts, especially with all this TSWift shenanigans going around. But, if you look at https://civitai.com/ plenty of people have links to their ko-fi accounts where you can commission them (heck you may even find me somewhere on there).
- Google Imagen 2
-
Help with finding an AI art site.
civitai.com ?
-
Prompts?
all the samples images on models at https://civitai.com/ have prompts included. I used to have a bunch of sites that list prompts bookmarked, but I lost all my bookmarks recently :(
-
not sure how to set up conterfiet modal
https://civitai.com/ most people grab models here these days I think. At least I do. And yeah, make sure to put checkpoints in the model folder, and lora in the lora folder, and hit the refresh button and it should show up.
-
Online AI instagram model with stable diffusion Attempt 1(support needed, like desperately, like really bad)
Go to civitai.com, look for images that look realistic, study their prompts and the models used to generate them.
-
‘Nudify’ Apps That Use AI to ‘Undress’ Women in Photos Are Soaring in Popularity
Tons of models to pick from on Civitai. I have a bunch downloaded for making NPCs for DnD.
What are some alternatives?
llama - Inference code for Llama models
stable-diffusion-webui-colab - stable diffusion webui colab
alpaca-lora - Instruct-tune LLaMA on consumer hardware
huggingface_hub - The official Python client for the Huggingface Hub.
flash-attention - Fast and memory-efficient exact attention
stable-diffusion-webui - Stable Diffusion web UI
koboldcpp - A simple one-file way to run various GGML and GGUF models with KoboldAI's UI
stable-diffusion-ui - Easiest 1-click way to install and use Stable Diffusion on your computer. Provides a browser UI for generating images from text prompts and images. Just enter your text prompt, and see the generated image. [Moved to: https://github.com/easydiffusion/easydiffusion]
gpt4all - gpt4all: run open-source LLMs anywhere
InvokeAI - InvokeAI is a leading creative engine for Stable Diffusion models, empowering professionals, artists, and enthusiasts to generate and create visual media using the latest AI-driven technologies. The solution offers an industry leading WebUI, supports terminal use through a CLI, and serves as the foundation for multiple commercial products.
RWKV-CUDA - The CUDA version of the RWKV language model ( https://github.com/BlinkDL/RWKV-LM )
stable.art - Photoshop plugin for Stable Diffusion with Automatic1111 as backend (locally or with Google Colab)