Llama.ttf: A font which is also an LLM
The llama.ttf font file acts as a language model and inference engine for text generation in Wasm-enabled HarfBuzz-based applications. Users can download and integrate the font for local text generation.
Read original article
The llama.ttf font file serves a dual purpose as a large language model (LLM) and an inference engine for that model. This unique functionality allows users to run the LLM and generate text within Wasm-enabled HarfBuzz-based applications like text editors or email clients without waiting for additional features to be included by vendors. By utilizing the font, users can engage in text generation locally without the need for external servers. To experience this font in action, users can download the llama.ttf file and integrate it into applications built with Wasm support. This innovative approach showcases the potential for unconventional uses of fonts and LLMs, such as creating playable games or formatting text creatively. Additionally, the font's capabilities are demonstrated in various projects like tom7's text formatting language and Erk's presentation on programmable fonts with HarfBuzz-Wasm.
Related
Tetris Font (2020)
The Tetris Font, designed by Erik and Martin Demaine, features letters made of Tetris pieces, challenging users with puzzle elements. Created in 2020, it showcases the complexity of Tetris in a unique typographic experience.
Font as Tetris [video]
The video discusses font evolution from clay tablets to digital fonts, covering styles, typography progress, ligatures, OTF and TTF formats. It mentions Metafont, hinting techniques, and Half Bus C++ library integration.
GitHub – Karpathy/LLM101n: LLM101n: Let's Build a Storyteller
The GitHub repository "LLM101n: Let's build a Storyteller" offers a course on creating a Storyteller AI Large Language Model using Python, C, and CUDA. It caters to beginners, covering language modeling, deployment, programming, data types, deep learning, and neural nets. Additional chapters and appendices are available for further exploration.
How to run an LLM on your PC, not in the cloud, in less than 10 minutes
You can easily set up and run large language models (LLMs) on your PC using tools like Ollama, LM Suite, and Llama.cpp. Ollama supports AMD GPUs and AVX2-compatible CPUs, with straightforward installation across different systems. It offers commands for managing models and now supports select AMD Radeon cards.
Detecting hallucinations in large language models using semantic entropy
Researchers devised a method to detect hallucinations in large language models like ChatGPT and Gemini by measuring semantic entropy. This approach enhances accuracy by filtering unreliable answers, improving model performance significantly.
43 commentsI was wondering why this was never used for an simpler autocorrect, but i guess that's why.
Also perhaps someone more educated on LLMs could tell me; this wouldn't always be consistent right? Like "once upon a time _____" wouldn't always output the same thing, yes? If so even copying and pasting in your own system using the correct font could change the content.
Has there already been a proposal to add scripting functionality to Unicode itself? Seems to me we're not very far from that anymore...
Right?
In that case could you ship a live demo of this that's a web page with the font embedded in the page as a web font, such that Chrome and Firefox users can try it out without installing anything else?
It'd be lovely if someone embedded the font in a website form to save us all the trouble of demoing it
Oh, this can't be used for nefarious purposes. What could POSSIBLY go wrong?!
As an aside, I originally thought this was going to generate a new font "style" that matched the text. So for example, "once upon a time" would look like a storybook style font or if you wrote something computer science-related, it would look like a tech manual font. I wonder if that's possible.
You could also use this to make animated fonts. An excuse to hook up a diffusion model next?
So we could expect latex.ttf very soon?
Related
Tetris Font (2020)
The Tetris Font, designed by Erik and Martin Demaine, features letters made of Tetris pieces, challenging users with puzzle elements. Created in 2020, it showcases the complexity of Tetris in a unique typographic experience.
Font as Tetris [video]
The video discusses font evolution from clay tablets to digital fonts, covering styles, typography progress, ligatures, OTF and TTF formats. It mentions Metafont, hinting techniques, and Half Bus C++ library integration.
GitHub – Karpathy/LLM101n: LLM101n: Let's Build a Storyteller
The GitHub repository "LLM101n: Let's build a Storyteller" offers a course on creating a Storyteller AI Large Language Model using Python, C, and CUDA. It caters to beginners, covering language modeling, deployment, programming, data types, deep learning, and neural nets. Additional chapters and appendices are available for further exploration.
How to run an LLM on your PC, not in the cloud, in less than 10 minutes
You can easily set up and run large language models (LLMs) on your PC using tools like Ollama, LM Suite, and Llama.cpp. Ollama supports AMD GPUs and AVX2-compatible CPUs, with straightforward installation across different systems. It offers commands for managing models and now supports select AMD Radeon cards.
Detecting hallucinations in large language models using semantic entropy
Researchers devised a method to detect hallucinations in large language models like ChatGPT and Gemini by measuring semantic entropy. This approach enhances accuracy by filtering unreliable answers, improving model performance significantly.