---

license: apache-2.0

language:

- pt

tags:

- gguf

- ternary

- 2-bit

- portuguese

- neurogrid

---

Mythos d13x1872-r373 PT-BR (GGUF, ternary Q2_0)

A small Portuguese language model trained from scratch, quantized to ternary

Q2_0 and served by the NeuroGrid engine.

This repo holds the deployed checkpoint: the d13 configuration, n_embd 1872,

after supervised fine-tuning.

| | |

|---|---|

| File | mythos_d13_final_q2_0.gguf (1.65 GB) |

| Tokenizer | mythos_tokenizer_d13.json, in this repo, required |

| Language | Portuguese (pt-BR) |

| Quantization | ternary Q2_0 |

| val_bpb | 1.173 at pre-training step 13800, 0.709 after SFT step 213 |

Running it

mythos-serve \
  -gguf      mythos_d13_final_q2_0.gguf \
  -tokenizer mythos_tokenizer_d13.json \
  -backend   cuda \
  -port      8095

-backend cpu and -backend metal also work; the tokenizer file is not

optional, since the GGUF does not carry it.

What it is for

It is a small model, and it is used as one: PT-BR generation behind a

retrieval layer, where the retrieved passages carry the facts and the model

supplies the language. In the STJ jurisprudence RAG stack it is the

alternative generator behind mythos-stj, sitting next to the 27B behind

bonsai-stj, so the two can be compared on the same retrieved context.

Do not use it as a standalone knowledge source. It has no useful factual

recall at this size and will produce fluent Portuguese that is wrong.