EQTransformer VS RWKV-LM

Here is a specific idea that would be interesting to test. SCITS released a ML P&S picker that supposedly is pretty good. They put the code on github (https://github.com/smousavi05/EQTransformer). I think a really easy idea would be to put it to the test against USGS picks in different areas. You can get IRIS data and run this in a different area that doesn't normally get much attention and see how it compares to the published catalog. Software like this always makes bold claims, so it would be nice to have independent, verified tests of it. You would just need to download the package (it's already on pypi so you can pip it), learn how to run it, and test against some real data. Would make for a decent paper actually.

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,*

That is not true. There are RNNs with transformer/LLM-like performance. See https://github.com/BlinkDL/RWKV-LM.

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 :'))))

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.

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)

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.

> 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.

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'.