Instructions to use pointbreaklab/knot-scribe with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use pointbreaklab/knot-scribe with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("unsloth/qwen2.5-coder-7b-instruct-bnb-4bit") model = PeftModel.from_pretrained(base_model, "pointbreaklab/knot-scribe") - Notebooks
- Google Colab
- Kaggle
Knot Scribe
On-device model that writes your git commit messages. Give it a diff, get a correctly-typed Conventional-Commit message back. Runs 100% on your machine, no API, no code leaving your device.
Part of the Knot AI family, alongside Knot Delta (which reads a change and writes a grounded report). Knot Scribe is the model behind Knot's hands-free auto-commit, released standalone here.
Renamed: this repo was formerly
pointbreaklab/knot-ai. The old URL redirects here.
A LoRA fine-tune of Qwen2.5-Coder-7B-Instruct (Apache-2.0), trained only on public commit history. No user data, no private code.
Benchmark โ v5
Sixty hand-reviewed commits (gold-v1), balanced across all eleven
conventional-commit types. Head-to-head of the previous release (v4) and the
current model (v5).
| metric | v4 | v5 |
|---|---|---|
| Type accuracy | 48.3% | 60.0% |
| Scope accuracy | 68.3% | 75.0% |
| Title word-overlap | 27.2% | 19.1% |
| Exact title | 6.7% | 0.0% |
| Generation errors / 60 | 7 | 4 |
Type accuracy across releases: v3 40% โ v4 55% โ v5 60%. v3/v4 were scored on an earlier JS/TS-only set; v5 on the harder balanced set above, where v4 re-scores 48.3% โ so v5's real gain over v4 is +11.7 points.
Honest read: v5 lifts type accuracy and scope and nearly halves the format
errors. Title word-overlap and exact-title fall because v5 paraphrases: it
writes its own titles, often more descriptive than the single human reference
it is scored against, which exact string-match penalizes. build and revert
remain hard.
Use it
Ollama
ollama run pointbreaklab/knot-scribe "$(git diff --staged)"
llama.cpp (base + this LoRA)
llama-server --model qwen2.5-coder-7b-instruct-q4_k_m.gguf \
--lora knot-scribe-lora.gguf
Output is JSON {"title": "...", "body": "..."} โ a correctly-typed
Conventional-Commit subject and body.
Training
- Base: Qwen2.5-Coder-7B-Instruct ยท Apache-2.0
- Method: QLoRA (4-bit), completion-only SFT (loss on the message only)
- Data: diff โ message pairs mined from permissive open-source commit history (JS/TS, Python, Rust, Go)
- Privacy: public commit history only โ no user data, no private code
- License: Apache-2.0 (derivative of Qwen2.5-Coder-7B)
- Downloads last month
- 112
We're not able to determine the quantization variants.