license: apache-2.0 library_name: transformers pipeline_tag: image-text-to-text base_model:

• Qwen/Qwen3.5-4B
• rodrigomt/Qwen3.5-4B-Uncensored-Aggressive tags:
• qwen
• qwen3.5
• multimodal
• model-merge
• uncensored
• safetensors
• bfloat16

Qwen3.5-4B Base40 Uncensored60

Multimodal BF16 linear merge of:

• 40%: Qwen/Qwen3.5-4B
• 60%: rodrigomt/Qwen3.5-4B-Uncensored-Aggressive

Merge formula

merged = 0.40 × Qwen/Qwen3.5-4B + 0.60 × rodrigomt/Qwen3.5-4B-Uncensored-Aggressive

The interpolation was calculated in FP32 and saved as BF16 Safetensors. Tokenizer, chat-template, image-processor, and video-processor files come from the official Qwen checkpoint to preserve native multimodal compatibility.

This is an experimental merge and should be evaluated before production use.