This is stars and forks stats for /karpathy/nanoGPT repository. As of 19 Apr, 2024 this repository has 25133 stars and 3429 forks.
nanoGPT The simplest, fastest repository for training/finetuning medium-sized GPTs. It is a rewrite of minGPT that prioritizes teeth over education. Still under active development, but currently the file train.py reproduces GPT-2 (124M) on OpenWebText, running on a single 8XA100 40GB node in about 4 days of training. The code itself is plain and readable: train.py is a ~300-line boilerplate training loop and model.py a ~300-line GPT model definition, which can optionally load the GPT-2 weights from...
nanoGPT The simplest, fastest repository for training/finetuning medium-sized GPTs. It is a rewrite of minGPT that prioritizes teeth over education. Still under active development, but currently the file train.py reproduces GPT-2 (124M) on OpenWebText, running on a single 8XA100 40GB node in about 4 days of training. The code itself is plain and readable: train.py is a ~300-line boilerplate training loop and model.py a ~300-line GPT model definition, which can optionally load the GPT-2 weights from...
repo | techs | stars | weekly | forks | weekly |
---|---|---|---|---|---|
kuca-belludo/urnas | Python | 92 | 0 | 17 | 0 |
apachecn/ailearning | PythonJavaScriptCSS | 36.6k | 0 | 11.3k | 0 |
Aeternalis-Ingenium/FastAPI-Backend-Template | PythonDockerfileOther | 446 | 0 | 66 | 0 |
AsYetUntitled/Framework | SQFC++Python | 237 | 0 | 316 | 0 |
ilaria-manco/multimodal-ml-music | TeXPython | 243 | 0 | 10 | 0 |
corkami/pocs | AssemblyPythonBatchfile | 1.4k | 0 | 202 | 0 |
DFHack/dfhack | C++LuaC | 1.8k | 0 | 459 | 0 |
mwidera/iac-labs | CSSHTMLJavaScript | 0 | 0 | 34 | 0 |
LazyDeveloperr/Mogneius | DockerfilePythonShell | 2 | 0 | 23 | 0 |
lihop/godot-xterm | GDScriptC++Python | 73 | 0 | 11 | 0 |