Downloads · 30 days
0
federico-anastasi/nicu-9m
nicu-9m is a text generation model from federico-anastasi. Use it when you need the model to write or continue text. The card lists the license as cc-by-nc-4.0.
Nicu is a 9M-parameter language model trained from scratch (no pretrained base) that plays a single character: a friendly guy from Catania, Sicily. He knows his small world — the sea, the grill, his friends, Sant'Agat…
Downloads · 30 days
0
Access
Public
Updated Jul 4, 2026
Repo size
107 MB
Likes
0
Public
Click a slice to open those files.
.onnx58.1 MB · 54%
From the Hugging Face model README
Nicu is a 9M-parameter language model trained from scratch (no pretrained base) that plays a single character: a friendly guy from Catania, Sicily. He knows his small world — the sea, the grill, his friends, Sant'Agata — and deflects instead of hallucinating on everything else. That's the design: a model this small can't hold facts about the world, so it stays in character and dodges, usually with a joke.
Try it live: nicu.chat — the model runs entirely on your device (ONNX Runtime Web, WASM). No inference server.
This is the v1.0 release, part of a three-size family trained on the same final corpus for size-scaling comparison: nicu-5m · nicu-9m · nicu-20m
A large teacher LLM generated ~565k synthetic in-character dialogues from a "character sheet" (identity, voice, boundaries). After quality filtering, a ByteLevel-BPE tokenizer (vocab 6000) and this nanoGPT-style decoder were trained from random initialization on the resulting 38M tokens.
| Parameters | 9.6M |
| Layers / heads / embd | 10 / 8 / 256 |
| Vocab | 6,000 (ByteLevel BPE) |
| Context | 512 tokens |
| Precision | fp32 (+ dynamic-int8 ONNX) |
Blind LLM-judge over a 204-case character-fidelity suite (identity, substance, multi-turn coherence, boundary handling): 64.2% case pass rate. The int8 ONNX was judged blind against fp32 on the full suite: no measurable quality loss (the live site serves int8).
model.onnx — fp32 ONNX export (opset 17), for onnxruntime-web/onnxruntimemodel.int8.onnx — dynamic-int8 quantized ONNX (what nicu.chat serves)tokenizer.json — ByteLevel BPE tokenizer (HF tokenizers format)checkpoint.pt — PyTorch weights + config ({'model_state', 'cfg', ...})Plain dialogue text, no special tokens beyond <|endoftext|> (id 0):
Utente: Ciao Nicu! Chi sei?
Nicu:
Sample with repetition penalty ~1.15 (current turn only), temperature 1.0,
top-p 0.92; stop on <|endoftext|> or on a generated \nUtente: / \nNicu: line.
Weights: CC-BY-NC-4.0 (non-commercial). Contact the author for other uses.