Downloads · 30 days
4
14% of all-time downloads
phi-4-minecraft-advisor-qlora-sft
trentnorth/phi-4-minecraft-advisor-qlora-sft
phi-4-minecraft-advisor-qlora-sft is a machine learning model from trentnorth. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for peft. The card lists the license as mit.
QLoRA SFT adapter for microsoft/phi-4 trained on an ecological advisor corpus for Minecraft Alive mod.
All-time downloads
29
Public
Repo size
446 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors446 MB · 98%
At a glance
- Library
- peft
- License
- mit
- Access
- Public
- Created
- Jun 9, 2026
- Updated
- Jun 9, 2026
- SHA
- 8a27b02a
Base models
Model card
From the Hugging Face model README
phi-4-minecraft-advisor-qlora-sft
QLoRA SFT adapter for microsoft/phi-4 trained on an ecological advisor corpus for Minecraft Alive mod.
Eval results (104-prompt advisor eval, Claude judge)
| Metric | Score | Gate | |
|---|---|---|---|
| TP recall | 0.972 | ≥0.90 | PASS |
| TN precision | 0.958 | ≥0.85 | PASS |
| Joint F | 0.965 | ≥0.88 | PASS |
| Edge accuracy | 1.000 | ≥0.75 | PASS |
| Mechanism mean | 1.84/2.0 | ≥1.50 | PASS |
Zero-shot phi-4 baseline: TP=1.000, TN=0.667 (over-alerts on every scenario).
Training details
- Base model: microsoft/phi-4
- Task: QLoRA SFT, 3 epochs, r=32, alpha=64, target_modules=all-linear, NF4 4-bit
- Corpus: 1384 train / 154 val scenarios
Framework versions
- PEFT 0.13.0
- Library
- peft
- License
- mit
- Created
- Jun 9, 2026
- Updated
- Jun 9, 2026