pionus-0.5b-v0.1
A fine-tune of Qwen/Qwen2.5-Coder-0.5B-Instruct that writes git commit messages in the repository's style, for pionus, a CLI that runs a small model locally (Intel NPU, GPU or CPU). Version 0.1: the first published model, while the training recipe still changes.
It is trained on pionus's own prompt, byte for byte: a system prompt with the rules (subject of at most 72 columns, imperative mood, Conventional Commits when the repository uses them) and a user prompt with the changed files, the compacted diff and up to 5 recent subjects of the repository. Other prompts are untested.
Files
| File | What | SHA-256 |
|---|---|---|
model.safetensors (+ config and tokenizer) |
merged weights, bf16 | bb95863256956bd51e106042ea03e5f5b8d28a42dd1df53ba52289dfd15afef3 |
pionus-0.5b-v0.1-q4_k_m.gguf |
Q4_K_M for llama.cpp, 398 MB | 83b9acfc91e67cba1a2b669a0afe59ddc1b3ce5909617355b88d3a2ff6e66c11 |
Use with pionus
hf download LucasBRT/pionus-0.5b-v0.1 pionus-0.5b-v0.1-q4_k_m.gguf --local-dir ~/models
PIONUS_GGUF=~/models/pionus-0.5b-v0.1-q4_k_m.gguf pionus
It runs on pionus's llama.cpp devices (CPU and Vulkan GPUs). For the OpenVINO devices (Intel NPU and GPU), the safetensors can be exported with pionus's export scripts; that export is not validated yet for this model.
Evaluation
eval-v1: 500 commits from the
test split of CommitChronicle (repositories never seen in training), 250
following Conventional Commits and 250 free-form; eval-short: 197 commits
from young repositories (1–5 earlier subjects). Greedy decoding, pionus
at db389c2, Vulkan, with its retry and file-list fallback.
| Model | type_match | scope_known | first_try | fallback | word_f1 | word_f1 (free) | fallback (young repos) |
|---|---|---|---|---|---|---|---|
| Qwen2.5-Coder-0.5B-Instruct, upstream Q4_K_M | 0.168 | 0.756 | 0.392 | 0.400 | 0.133 | 0.101 | 0.345 |
| same, re-quantized like this model (control) | 0.236 | 0.880 | 0.424 | 0.512 | 0.153 | 0.098 | 0.386 |
| pionus-0.5b-v0.1 | 0.640 | 0.856 | 0.980 | 0.012 | 0.342 | 0.233 | 0.091 |
- type_match: same Conventional type as the real commit. The base model
answers
fixto most changes; answeringfixalways would score 0.41. - scope_known: no scope, or one the repository already used.
- first_try: the first reply was usable; fallback: no reply was, and pionus wrote the message from the file list.
- word_f1: word overlap with the real subject, a rough proxy for content.
All the numbers, the learning curve behind the choice of 40k examples and the method are in training/HYPOTHESES.md (H3). For reference, 324 s for the 500 commits of eval-v1 on an Intel Arc iGPU (Core Ultra 5 225H), retries included. See also pionus-1.5b-v0.1: the 1.5B version writes closer to the real messages and falls back less on young repositories.
Training
- Data: 39,985 commits from the train split of
CommitChronicle
(revision
5fd076e), each with at least 10 earlier subjects of its repository; prompts built by pionus itself, the real subject as the target (examples file sha2567495c85514a53985…). - Method: LoRA r=16, alpha=32, dropout 0.05 on all linear layers, lr 2e-4 cosine, warmup 3%, batch 4 × 4, 1 epoch, seed 0, loss on the reply only; 4-bit NF4 base with fp16 compute (QLoRA) on a Kaggle Tesla T4, 147 minutes. torch 2.11.0, transformers 5.20.1, peft 0.21.2.
- Export: merged into the bf16 base and quantized to Q4_K_M with llama.cpp
b11381 (
training/export_gguf.py --merged).
Training on a GPU is not bit-for-bit reproducible; generation is (greedy). The recipe, the data selection and the scripts are in training/.
Limitations
- English messages only (the training data is English).
- Young repositories: with fewer than 10 earlier commits it sometimes repeats or paraphrases one of them, or the reply is unusable and pionus falls back to the file list (0.091 of eval-short).
- It can invent details the diff does not show (a version, a file's purpose), and it does not know when the staged changes are several commits.
- Trained on prompts without pionus's map of where each scope is used, added later; with that map in the prompt it was not re-evaluated on eval-v1.
Licence and attribution
The weights are released under Apache-2.0, like the base model.
CommitChronicle (JetBrains Research) has no single licence: it gathers
commits from repositories under MIT, Apache-2.0 and BSD-3-Clause, and asks
that uses follow their terms, attribution included. The dataset records the
repository and licence of every commit (repo and license fields), which is
the provenance of the training data.