martossien/qwen_2.5_vl_7b_uncensored_comfy_ready

Qwen2.5-VL-7B-Instruct - Heretic Uncensored (BF16)

This is an uncensored version of Qwen/Qwen2.5-VL-7B-Instruct.

The censorship (refusal mechanisms) has been removed using Heretic, targeting specific layers in the LLM component while preserving the Vision Encoder capabilities.

Details

• Method: Abliteration via Heretic (Optimized on 200 trials)
• Refusal Rate: ~4% (vs ~100% original) on harmful benchmarks.
• Format: BF16 (Bfloat16) - Native high precision.
• Architecture: Vision Language Model (VLM).

Files provided

1. Standard Transformers: All files in the root (config.json, model-xxxxx.safetensors) for use with transformers library.

2. ComfyUI Ready: qwen_2.5_vl_7b_uncensored_comfy_ready_bf16.safetensors

How to use in ComfyUI

To use as a text encoder for image generation or VLM chat:

1. Download qwen_2.5_vl_7b_uncensored_comfy_ready_bf16.safetensors.
2. Place it in ComfyUI/models/text_encoders/
3. It works with standard Qwen-VL workflows.

Credits

• Original model by Qwen Team (Alibaba Cloud).
• Uncensoring tool: Heretic.

---

license: apache-2.0 pipeline_tag: image-text-to-image tags: - image-text-to-text - vision - uncensored - heretic - comfyui base_model: - Qwen/Qwen2.5-VL-7B-Instruct