library_name: transformers pipeline_tag: image-text-to-text tags:
- merlina
- grimoire
- image-text-to-text
- vision-language-model
- post_hoc_upload base_model:
- huihui-ai/Huihui-Qwen3.6-27B-abliterated
Huihui-Qwen3.6-27B-abliterated-Athanorlite-ORPO
Training Configuration
| Parameter | Value |
|---|---|
| Training Mode | POST_HOC_UPLOAD |
| Base Model | huihui-ai/Huihui-Qwen3.6-27B-abliterated |
| LoRA Rank (r) | 64 |
| LoRA Alpha | 64 |
| LoRA Dropout | 0.05 |
| Target Modules | k_proj, q_proj, v_proj, down_proj, o_proj, up_proj, gate_proj |
| GPU | NVIDIA GB10 |
Trained with Merlina