GGUF quantizations of nanoBeard Sloop — a tiny 14M GPT-2-style pirate text model (completion, no chat turns), loaded via llama.cpp's gpt2 arch (14M params), for on-device inference with llama.cpp and the NanoBeard mobile app. Val loss ≈ 4.282.

Files

file	quant	size	use
`sloop-14M.Q4_K_M.gguf`	Q4_K_M	11.1 MB	default — phones
`sloop-14M.Q8_0.gguf`	Q8_0	14.7 MB	quality fallback

Q4_K_M is the default for phones (smallest + fastest). Q8_0 is a near-lossless fallback when you have the storage and want max quality.

Chat format

Plain-text turns (no chat template). Build the prompt as:

User: <your message>
Pirate:

Turns are separated by a single newline; stop generation at the <|endoftext|> token. Example with llama.cpp:

bash

llama-completion -m sloop-14M.Q4_K_M.gguf \
  -p $'User: Tell me about the sea.\nPirate:' -n 80 --temp 0.8 --top-k 40

Tokenizer

Custom 16,384-token byte-level BPE (GPT-2-style pre-tokenizer), embedded in the GGUF. No external tokenizer file required.

younissk/nanoBeard-sloop-14M-GGUF

nanoBeard Sloop 14M (pirate, GPT-2)

Files

Chat format

Tokenizer

younissk/
nanoBeard-sloop-14M-GGUF