Upload README.md

README.md

@@ -0,0 +1,50 @@
+---
+library_name: mlx
+base_model: Jiunsong/supergemma4-26b-abliterated-multimodal
+license: gemma
+pipeline_tag: text-generation
+tags:
+- mlx
+- mlx-lm
+- quantized
+- 4-bit
+- base_model:Jiunsong/supergemma4-26b-abliterated-multimodal
+---
+
+# supergemma4-26b-abliterated-multimodal MLX 4-bit
+
+This repository contains an MLX-LM conversion of [Jiunsong/supergemma4-26b-abliterated-multimodal](https://huggingface.co/Jiunsong/supergemma4-26b-abliterated-multimodal).
+
+## Conversion Details
+
+- Original model: `Jiunsong/supergemma4-26b-abliterated-multimodal`
+- Model family: SuperGemma4
+- Source model type: `gemma4`
+- Model size: 25,805,936,206 parameters
+- Quantization: MLX-LM affine quantization
+- Bits: 4-bit
+- Group size: 64
+- Local MLX folder size at upload time: 13.26 GiB
+- Local safetensors weight size at upload time: 13.22 GiB
+
+This Gemma conversion follows the MLX-LM Gemma 4 shared-KV topology and uses non-strict checkpoint loading so extra HF tensors outside that topology are discarded during conversion.
+
+For mlx-swift compatibility, `per_layer_model_projection` was left unquantized while the rest of the eligible linear layers were quantized.
+
+For oMLX / mlx-swift chat-template compatibility, the published MLX package uses a simplified Gemma 4 chat template based on the `<|turn>role\n...<turn|>` format. The original upstream `chat_template.jinja` is preserved as `chat_template.original.jinja`.
+
+Abliteration credit: the abliterated source model was published by [Jiunsong](https://huggingface.co/Jiunsong). This repository only provides the MLX conversion and quantization.
+
+## Usage
+
+```bash
+mlx_lm.generate --model DreamFoundries/supergemma4-26b-abliterated-multimodal-4bit --prompt "Hello" --max-tokens 64
+```
+
+## Benchmarks
+
+No comparative benchmarks have been run yet. The repository does not currently provide quality, speed, memory, or benchmark comparisons against the original weights or other quantizations.
+
+## License
+
+This is a converted/quantized derivative of the original model. Please refer to the original model repository for the upstream license and usage terms: https://huggingface.co/Jiunsong/supergemma4-26b-abliterated-multimodal