History LLMs: Models trained exclusively on pre-1913 texts(github.com)

826 points by iamwil 10 months ago | 396 comments

GitHub repository serving as an information hub for a project training large language models exclusively on historical texts published before 1913.

Zlob.h 100% POSIX and glibc compatible globbing lib that is faste and better(github.com)

17 points by neogoose 8 months ago | 10 comments

Common Lisp SDK for the Datastar Hypermedia Framework(github.com)

70 points by fsmunoz 9 months ago | 8 comments

Show HN: Yet another memory system for LLMs(github.com)

144 points by blackmanta 1 year ago | 38 comments

Show HN: A MitM proxy to see what your LLM tools are sending(github.com)

200 points by jmuncor 9 months ago | 104 comments

Dr. TVAM – Inverse Rendering for Tomographic Volumetric Additive Manufacturing(github.com)

54 points by roflmaostc 1 year ago | 9 comments

Train Your Own LLM from Scratch(github.com)

376 points by kristianpaul 5 months ago | 43 comments

GitHub repository by angelos-p providing code and docs for training your own large language model from scratch.

Llm.c – LLM training in simple, pure C/CUDA(github.com)

810 points by tosh 2 years ago | 134 comments

GitHub repository for llm.c, Andrej Karpathy's project for training LLMs like GPT-2 in simple, raw C/CUDA.

LLM4Decompile: Decompiling Binary Code with LLM(github.com)

373 points by Davidbrcz 2 years ago | 120 comments

GitHub repository for LLM4Decompile, a project using large language models to decompile binary code, with evaluation scripts and samples.

SmolGPT: A minimal PyTorch implementation for training a small LLM from scratch(github.com)

415 points by amrrs 1 year ago | 52 comments

GitHub repository for smolGPT, a minimal PyTorch implementation for training a small GPT-style language model from scratch.

RustGPT: A pure-Rust transformer LLM built from scratch(github.com)

357 points by amazonhut 1 year ago | 170 comments

GitHub repository for RustGPT, a transformer-based large language model written entirely in Rust from scratch.

Show HN: LLMs can generate valid JSON 100% of the time(github.com)

776 points by remilouf 3 years ago | 263 comments

GitHub repository for Outlines, a Python library by Normal Computing for guided LLM text generation that guarantees output matching regexes or JSON schemas.