--- license: apache-2.0 base_model: Lucasgitguy-co/wiki-model-tiny base_model_relation: quantized library_name: gguf pipeline_tag: text-generation language: en tags: - gguf - llama.cpp - wikipedia - facts --- # wiki-model-tiny GGUF GGUF files of [Lucasgitguy-co/wiki-model-tiny](https://huggingface.co/Lucasgitguy-co/wiki-model-tiny), a 12.5M-parameter model trained from scratch. It runs in llama.cpp as a normal `llama` model. | File | Type | Size (GB) | | --- | --- | ---: | | `wiki-model-tiny-F16.gguf` | F16, same output as the original | 0.025 | | `wiki-model-tiny-Q8_0.gguf` | Q8_0 | 0.014 | There are no K-quants: the model width (320) isn't a multiple of 256. ## Use The prompt tags are ` topic `, ` question `, ` claim `, and an optional ` text ` in front. The context window is 384 tokens. ```bash hf download Lucasgitguy-co/wiki-model-tiny-GGUF wiki-model-tiny-F16.gguf --local-dir . llama-completion -m wiki-model-tiny-F16.gguf -no-cnv --temp 0 -n 80 -c 384 \ -p " Mount Everest is Earth's highest mountain, in the Himalayas. Where is Mount Everest? " ``` The Python package's `--grounded` BM25 index isn't included, so supply the context yourself. Without context this model mostly makes things up. ## How these were made and tested - The original is plain PyTorch, so `convert_tiny.py` writes the GGUF directly with gguf-py: - The fused `qkv` and `gate_up` weights are split. - RoPE is kept as is, because the model already uses llama.cpp's interleaved layout. - The byte-level BPE tokenizer is stored as `gpt2` with the `gpt-2` pre-tokenizer. - Tested 2026-11-16 with llama.cpp 1.0.0 (build 12359): - Token ids match the original tokenizer on all three prompt formats. - Greedy output (F32 and F16) is identical to the PyTorch model on 4 prompts, up to the end-of-answer token. - Q8_0 was spot-checked on one prompt. ## Licence Apache-2.0, the same as the source model. Wikipedia-derived training data is CC BY-SA 4.0.