初始化项目，由ModelHub XC社区提供模型

Model: bmle/Qwen3-4B-Instruct_NSFW-V2.1
Source: Original Platform

README.md

@@ -0,0 +1,26 @@
+---
+license: apache-2.0
+language:
+- en
+base_model: Qwen/Qwen3-4B-Instruct-2507
+pipeline_tag: text-generation
+tags:
+- qwen
+- qwen3
+- instruct
+- math
+- merged
+- causal-lm
+- nsfw
+---
+
+# Qwen2.5-Math-1.5B Merged Fine-Tune
+
+Merged full model fine-tuned from `Qwen/Qwen2.5-Math-1.5B-Instruct`.
+
+## Base model
+- Qwen/Qwen3-4B-Instruct-2507
+
+## Notes
+- This repo contains the merged full model.
+- Suitable for direct inference without separately loading a LoRA adapter.