Viewing profile — rhdunn

I knew it... Wuthering Heights was written by AI and Lucy Maud Montgomery, Edgar Allan Poe, et. al. were AI bots churning out content! Or maybe -- just maybe -- using dashes isn't …

The what happened section mentions the addition of the `setup.mjs` and `Math_Symbol.js`, along with a change in `package.json` to add `"preinstall": "node setup.mjs"`, so presumabl…

On my 4090 setup I'm getting 86t/s on a 12B Q6_K quantized model running entirely in VRAM. The current GPUs are optimized for processing huge numbers of triangles per second. There…

There are several aspects to this: 1. Better hardware optimized for matrix operations and other ML/NN specific workflows (NVIDIA hardware, Apple M4/M5 chips, Intel AI Boost, other …

Various libraries (e.g. Python's `re` library) support comments and whitespace as an option allowing you to format the regex on multiple lines with commenting to document what each…

Unless they are building a podcast application which is predominantly RSS 2.0 based with some extensions from itunes and others to provide additional podcast-specific metadata such…

XSLT 3 (via XPath 3.1) has support for maps, arrays, and parsing JSON to/from those or an XML representation. The XML representation is easier to work with in 3. There's a draft ve…

C++ has had smart pointers for memory (and other resource) management for a long time now (see e.g. the Windows ATL classes for working with COM objects and resources). There are a…

A common writing tool is to use a story grid. You have chapters/similar along the Y axis and title, characters, plot elements, etc. along the X axis. That way you can keep track of…

This has happened with other accelerants in various media/fields: 1. easy access to video recording and editing equipment has made it a lot easier to produce videos on sites like Y…

IIUC, the main problem with the current Li batteries is that the two plates can over time grow material that will 1) degrade performance; and 2) make it more likely to short circui…

In the linked "Kimi-K3 Technical Report [pdf]" paper, section 2.3 (Stable LatentMoE, p6) has the table with those equations on (top of p7, using β_1 for the gate branch and β_2 for…

From the paper (page 6 with a comparison to GLU and SwiGLU) they are not using tanh directly (i.e. f(x) = tanh(x)) but: f_gate(b,x) = b * tanh(x / b) * sigmoid(x) f_up(b,x) = b * t…

Maybe they are in the process of uploading the weights and git history and have taken down the holding page/project to not have the "coming soon" in the git history.

I was talking about running this on a server, hence my comments re 1xB200. Obviously, the more hardware/VRAM you have the better/faster you can run these large models. But if you a…

Yes, that's what I was saying w.r.t. expert offloading, i.e. ensuring that the GPU could fit the active parameters not all the parameters.

If it is a mixture of experts (MoE) model like the 2.x models, won't this reduce the hardware needed to run the model? The Kimi-K2.6 model is 1.1T parameters with 32B active parame…

It can be useful for checking input token usage before sending it to the model, e.g. preventing calls above a given token bound or grouping requests into batches. It can also be us…

Firefox has had profiles for a long time (via about:profiles and a command-line argument). Unfortunately, the new profiles are not compatible with the old ones and cannot be migrat…

1. https://www.uea.ac.uk/about/news/article/fresh-evidence-of-c... -- (2023) Fresh evidence of ChatGPTs political bias revealed by comprehensive new study 2. https://www.ox.ac.uk/n…

I think you're right with the current LLM/transformer architecture. There are several factors that affect model size: - The number of token values supported by the model ("n_vocab"…

Does anyone know if they intend on releasing open source/weights variants for 3.8 or whether 3.6 was the last model they are/were doing that for?

A parachuting flamingo? An aardvark driving a bus? It should be easy to randomize the animal and the mode of transport (or vary it with animal playing a sport) to create images not…

Possibly. Telephone (电话) is electricity/electronic (电) + talking/speech (话). In Japanese there's the Japanese possessive ('no') which can also be a modifier/qualifier in text like …

Have you tried the https://huggingface.co/LatitudeGames models? They are used by the https://play.aidungeon.com website, but can also be downloaded and used with llama-server in co…