Not a fine-tune. Not an adapter. Random weights, a real corpus, and a real loss curve you watch fall in real time — from a browser tab, on our GPUs.
Signing in opens NanoDex full screen — Hugging Face's login page can't run inside an embedded frame.
Four architectures, from 492k to 8.1M parameters. That's the real total — embeddings included, no asterisk.
Anywhere from {{ min_tokens // 10**6 }}M to 1.5 billion tokens of fineweb-edu. More tokens, sharper model, longer wait.
Your run joins the queue. Live loss curve, throughput, logs — then the weights land in your own Hugging Face account.
Every finished run is pushed to your Hugging Face namespace: config.json, model.safetensors, the tokenizer, a training_run.json with the full recipe, and a generated model card. Load it with transformers like anything else on the Hub.
At a few hundred thousand parameters, a model learns word shapes, common collocations and a little syntax. It will produce English-looking text with no facts in it. That's the correct outcome — and watching cross-entropy fall from 7.6 (uniform noise over 2,048 tokens) to somewhere near 4 is the whole point.
Sign in with Hugging Face — no separate account, no password.