Upload README.md with huggingface_hub

README.md

@@ -1,22 +1,39 @@
 ---
-base_model: unsloth/qwen3-4b-instruct-2507-unsloth-bnb-4bit
+base_model: Qwen/Qwen3-4B-Instruct-2507
+library_name: peft
+license: other
 tags:
-- text-generation-inference
-- transformers
 - unsloth
-- qwen3
-- trl
-license: apache-2.0
-language:
-- en
+- lora
+- sft
+- completion-only
+- struct-eval
+- hard-filter
+model-index:
+- name: main_rev2_sft04
+  results: []
 ---
 
-# Uploaded  model
+# main_rev2_sft04
 
-- **Developed by:** fieldvalley-llm2025
-- **License:** apache-2.0
-- **Finetuned from model :** unsloth/qwen3-4b-instruct-2507-unsloth-bnb-4bit
+This is a **Safe SFT** LoRA adapter (REV2 SFT04).
+It uses **Completion-only Training** and **Hard SFT Filtering**.
 
-This qwen3 model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
+## Base Model
+Qwen/Qwen3-4B-Instruct-2507
 
-[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
+## 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.