| --- |
| license: apache-2.0 |
| base_model: jarrelscy/GLM-5.2-NVFP4-AQLM-hybrid |
| tags: |
| - glm |
| - glm-5.2 |
| - abliterated |
| - vision |
| - nvfp4 |
| - aqlm |
| - dgx-spark |
| pipeline_tag: image-text-to-text |
| --- |
| |
| # GLM-5.2 NVFP4+AQLM Abliterated Vision |
|
|
| Drop-in **abliterated + vision** weights for the |
| [MiaAI-Lab 3× DGX Spark recipe](https://github.com/MiaAI-Lab/GLM-5.2-NVFP4-AQLM-Triple-DGX-Sparks). |
|
|
| ## Construction |
|
|
| | Piece | Source | |
| |---|---| |
| | Text + vision hybrid base | `jarrelscy/GLM-5.2-NVFP4-AQLM-hybrid` @ `53e0082eedebd806b63e19779c47905937d768ca` | |
| | Abliteration donor | `jacklarmer/GLM-5.2-Abliterated-MXFP8-NVFP4-NF3-Hybrid` | |
| | Method | **Tensor transplant** of BF16 `self_attn.o_proj.weight` for layers **13–77** (65 tensors; 62 differed from base) | |
| | Vision tower + projector | **Byte-identical** to the jarrelscy / Baseten vision hybrid (untouched) | |
|
|
| No re-quantization: `o_proj` is BF16 `[6144, 16384]` on both base and donor. |
|
|
| ## Intended serve stack |
|
|
| - Hardware: **3× NVIDIA DGX Spark** (GB10 / sm_121 / aarch64) |
| - Image: `ghcr.io/miaai-lab/glm-5.2-nvfp4-triple-dgx-sparks:k12l1-vision` |
| - Launcher: MiaAI-Lab `./start.sh` with `MM_ENCODER_TP_MODE=data`, TP=3 |
| - Playbook: https://github.com/FlyCockpit/GLM-5.2-Abliterated-Vision-3x-DGX-Sparks |
|
|
| ## Warning |
|
|
| This model has **reduced refusal behavior** relative to the stock hybrid. |
| You are responsible for lawful use and your own evaluation. |
|
|
| ## License |
|
|
| Packaging Apache-2.0. Base hybrid, vision components, and upstream GLM-5.2 |
| weights retain their original licenses/terms (see jarrelscy / DeepSeek-adjacent |
| upstream cards). Apache-2.0 is used for this packaging where compatible with |
| those terms. |
|
|
| ## Credits |
|
|
| - MiaAI-Lab triple-Spark recipe |
| - jarrelscy NVFP4+AQLM hybrid + vision graft |
| - jacklarmer abliterated donor |
| - Baseten / community MoonViT vision path |
|
|
