| license: apache-2.0 | |
| language: | |
| - zh | |
| - en | |
| base_model: | |
| - huihui-ai/Qwen2.5-VL-7B-Instruct-abliterated | |
| pipeline_tag: image-text-to-text | |
| tags: | |
| - qwen2_5_vl | |
| - multimodal | |
| - abliterated | |
| - uncensored | |
| - text-generation-inference | |
| Quantized gguf file from https://huggingface.co/huihui-ai/Qwen2.5-VL-7B-Instruct-abliterated | |
| Using "--leave-output-tensor" in quantizing to keep output layer precision at FP16. | |
| LM Studio is recommended to deploy it. |