---
base_model: Qwen/Qwen3-4B-Instruct-2507
library_name: peft
license: other
tags:
- unsloth
- lora
- sft
- completion-only
- struct-eval
- hard-filter
model-index:
- name: main_rev2_sft04
  results: []
---

# main_rev2_sft04

This is a **Safe SFT** LoRA adapter (REV2 SFT04).
It uses **Completion-only Training** and **Hard SFT Filtering**.

## Base Model
Qwen/Qwen3-4B-Instruct-2507

## Training Data (Mixed 65:35)
- 65%: daichira/structured-hard-sft-4k (Filtered High Quality)
- 35%: u-10bei/structured_data_with_cot_dataset_512_v4 (Filtered Output-only)

## Hard Filter Applied
- Length Limit (Format-wise)
- Anti-Log/Audit Keywords
- Repetition Check (Tokens, Lines, Gases)

## Method
- **Completion-only**: User prompts are masked (-100 output label).
- **Marker**: `
### OUTPUT
` inserted before assistant output.
- **Config**: 1 Epoch, Max Seq Length 4096.