GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
pointbreaklab
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Run this model inference with full control and performance in your environment.
Model Details
Model Provider
pointbreaklab
Model Tree
Qwen/Qwen2.5-Coder-7B-Instruct
Input Modalities
Output Modalities
Supported Functionality
Knot AI does one thing well: turn a diff into a clear, correctly-typed Conventional-Commit message. It is not a chat assistant or a general coding model - feed it a diff, get a message. That focus is the point: a small, private, owned specialist you run on your own hardware.
Inference: git diff (+ light file context) → prompt → Qwen2.5-Coder-7B + Knot AI LoRA → commit message
Training: permissively-licensed public repos → mine (diff→message pairs) → filter + rebalance → QLoRA SFT → LoRA adapter → GGUF
Two held-out gold sets of 60 hand-reviewed commits each (the model never saw them), scored through the shipping GGUF path. Three models compared under one identical harness:
| Metric | Base Qwen | Knot AI v3 | Knot AI (v4) |
|---|---|---|---|
| Type accuracy | 0.0% | 40.0% | 55.0% |
| Title word-overlap | 0.4% | 18.3% | 30.3% |
| Exact title | 0.0% | 0.0% | 6.7% |
| Exact full message | 0.0% | 0.0% |
The base model is not "bad at commits" - zero-shot with the same prompt it returns unstructured prose 59 times out of 60, so it can't be wired into an automated pipeline at all. Fine-tuning's first job is to make the reply reliably parseable (59 → 4 → 0 errors); its second is to pick the right type.
| Type | n | Base | v3 | Knot AI (v4) |
|---|---|---|---|---|
| chore | 6 | 0% | 83% | 100% |
| ci | 6 | 0% | 67% | 100% |
| feat | 6 | 0% | 33% | 83% |
Honest read: strong on the high-signal types (chore, ci, feat, fix, test); still developing on the inherently ambiguous ones - refactor vs feat, build vs chore, style, revert - which is exactly what v5 targets.
| Language | n | Base | v3 | Knot AI (v4) |
|---|---|---|---|---|
| Rust | 20 | 0% | 10% | 55% |
| Go | 20 | 0% | 55% | 45% |
| Python | 20 | 0% | 55% | 60% |
The added multilingual training pays off: Knot AI holds ~53% type accuracy overall on this separate Rust/Go/Python set - close to its 55% JS/TS score - and lifts Rust from 10% → 55%, where the base model still scores 0% (unparseable).
Note: these are single-reference metrics - they compare to one human label, though a commit has many valid messages and a change can honestly be
fixorrefactor. So the scores understate real usefulness; sample outputs below are representative.
Sample outputs
| Change | Knot AI |
|---|---|
| Added a divide-by-zero guard | fix: prevent division by zero |
| Added a new function | feat: add divide function |
sh
ollama run pointbreaklab/knot-ai "$(git diff --staged)"
sh
llama-server --model qwen2.5-coder-7b-instruct-q4_k_m.gguf \--lora knot-ai-lora-f16.gguf
python
from transformers import AutoModelForCausalLM, AutoTokenizerfrom peft import PeftModelbase = "Qwen/Qwen2.5-Coder-7B-Instruct"tok = AutoTokenizer.from_pretrained(base)model = AutoModelForCausalLM.from_pretrained(base, device_map="auto")model = PeftModel.from_pretrained(model, "pointbreaklab/knot-ai")
This is v1 (built on Knot AI's v4 adapter). A v5 is planned - a larger, higher-quality corpus for better accuracy and closer matching, with a focus on the ambiguous types (refactor / build / style / revert). Knot AI improves in the open.
Built on Qwen2.5-Coder-7B-Instruct (Apache-2.0) by Alibaba Qwen. Knot AI is a LoRA fine-tune by PointBreakLab, trained only on permissively-licensed public commit history.
| Scope accuracy | 0.0% | 70.0% | 75.0% |
| Unparseable replies / 60 | 59 | 4 | 0 |
| fix |
| 6 |
| 0% |
| 67% |
| 83% |
| test | 5 | 0% | 80% | 80% |
| docs | 6 | 0% | 83% | 67% |
| perf | 6 | 0% | 0% | 50% |
| build | 5 | 0% | 0% | 0% |
| refactor | 6 | 0% | 0% | 0% |
| style | 6 | 0% | 0% | 0% |
| revert | 2 | 0% | 0% | 0% |