Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,51 @@
+---
+base_model: google/gemma-4-12B
+license: gemma
+library_name: mlx
+pipeline_tag: image-text-to-text
+tags:
+  - mlx
+  - quantized
+  - gemma
+  - gemma4
+  - image-text-to-text
+  - apple-silicon
+  - turboquant
+---
+
+# gemma-4-12B — TurboQuant MLX MXFP4
+
+[`google/gemma-4-12B`](https://huggingface.co/google/gemma-4-12B) @ `023679ed352de9bb66cc873c9009ce3482585c08` quantized pack, published as `majentik/gemma-4-12B-TurboQuant-MLX-MXFP4`.
+
+## Method
+
+MLX quantization via mlx-vlm 0.6.3 (MXFP4, group_size 32); vision + audio towers retained in BF16 (not quantized).
+
+## Release line
+
+Released under the **TurboQuant** line. RotorQuant and TurboQuant are this project's release labels for this pack, not distinct quantization algorithms — both brand repos for a given tier carry byte-identical weights, produced once and published under two names. No brand-specific speedup is claimed or measured for either label.
+
+## Modality
+
+This pack is `image-text-to-text` capable: the vision and audio towers ship in BF16 alongside the quantized text tower, so image (and audio) inputs are supported end to end via `mlx-vlm`.
+
+**Base-model note:** this is the raw completion model (not instruction-tuned). It is not instruction-aligned for multimodal Q&A — expect free-form continuation behavior rather than chat-style image description, even though the vision/audio towers are present.
+
+**mlx-vlm suppress-tokens note:** the base model's `generation_config.json` carries `suppress_tokens` for six multimodal placeholder token ids so that `transformers` generation is clean. `mlx-vlm` does not honor `suppress_tokens` automatically, so text-only generation with `mlx-vlm` can leak placeholder tokens (observed as a degenerate `A<image|>A<image|>...` loop in smoke testing) unless you suppress them yourself:
+
+```python
+from mlx_vlm import load, generate
+
+model, processor = load("majentik/gemma-4-12B-TurboQuant-MLX-MXFP4")
+suppress = {255999: -1e9, 256000: -1e9, 258880: -1e9, 258881: -1e9, 258882: -1e9, 258883: -1e9}
+output = generate(
+    model, processor, prompt,
+    max_tokens=256,
+    logit_bias=suppress,
+)
+```
+
+## License
+
+Governed by the [Gemma Terms of Use](https://ai.google.dev/gemma/terms). See the upstream repo for the full license text.
+

config.json

@@ -0,0 +1,197 @@
+{
+    "architectures": [
+        "Gemma4UnifiedForConditionalGeneration"
+    ],
+    "audio_config": {
+        "_name_or_path": "",
+        "architectures": null,
+        "audio_embed_dim": 640,
+        "audio_samples_per_token": 640,
+        "chunk_size_feed_forward": 0,
+        "dtype": null,
+        "hidden_size": 640,
+        "id2label": {
+            "0": "LABEL_0",
+            "1": "LABEL_1"
+        },
+        "initializer_range": 0.02,
+        "is_encoder_decoder": false,
+        "label2id": {
+            "LABEL_0": 0,
+            "LABEL_1": 1
+        },
+        "model_type": "gemma4_unified_audio",
+        "output_attentions": false,
+        "output_hidden_states": false,
+        "output_proj_dims": 640,
+        "problem_type": null,
+        "return_dict": true,
+        "rms_norm_eps": 1e-06
+    },
+    "audio_token_id": 258881,
+    "boa_token_id": 256000,
+    "boi_token_id": 255999,
+    "do_sample": true,
+    "dtype": "bfloat16",
+    "eoa_token_index": 258883,
+    "eoi_token_id": 258882,
+    "eos_token_id": 1,
+    "generation_config": {
+        "bos_token_id": 2,
+        "do_sample": true,
+        "eos_token_id": 1,
+        "pad_token_id": 0,
+        "suppress_tokens": [
+            258883,
+            258882
+        ],
+        "temperature": 1.0,
+        "top_k": 64,
+        "top_p": 0.95,
+        "transformers_version": "5.10.0.dev0"
+    },
+    "image_token_id": 258880,
+    "initializer_range": 0.02,
+    "model_type": "gemma4_unified",
+    "quantization": {
+        "group_size": 32,
+        "bits": 4,
+        "mode": "mxfp4"
+    },
+    "quantization_config": {
+        "group_size": 32,
+        "bits": 4,
+        "mode": "mxfp4"
+    },
+    "temperature": 1.0,
+    "text_config": {
+        "attention_bias": false,
+        "attention_dropout": 0.0,
+        "attention_k_eq_v": true,
+        "bos_token_id": 2,
+        "enable_moe_block": false,
+        "eos_token_id": 1,
+        "final_logit_softcapping": 30.0,
+        "global_head_dim": 512,
+        "head_dim": 256,
+        "hidden_activation": "gelu_pytorch_tanh",
+        "hidden_size": 3840,
+        "hidden_size_per_layer_input": 0,
+        "initializer_range": 0.02,
+        "intermediate_size": 15360,
+        "layer_types": [
+            "sliding_attention",
+            "sliding_attention",
+            "sliding_attention",
+            "sliding_attention",
+            "sliding_attention",
+            "full_attention",
+            "sliding_attention",
+            "sliding_attention",
+            "sliding_attention",
+            "sliding_attention",
+            "sliding_attention",
+            "full_attention",
+            "sliding_attention",
+            "sliding_attention",
+            "sliding_attention",
+            "sliding_attention",
+            "sliding_attention",
+            "full_attention",
+            "sliding_attention",
+            "sliding_attention",
+            "sliding_attention",
+            "sliding_attention",
+            "sliding_attention",
+            "full_attention",
+            "sliding_attention",
+            "sliding_attention",
+            "sliding_attention",
+            "sliding_attention",
+            "sliding_attention",
+            "full_attention",
+            "sliding_attention",
+            "sliding_attention",
+            "sliding_attention",
+            "sliding_attention",
+            "sliding_attention",
+            "full_attention",
+            "sliding_attention",
+            "sliding_attention",
+            "sliding_attention",
+            "sliding_attention",
+            "sliding_attention",
+            "full_attention",
+            "sliding_attention",
+            "sliding_attention",
+            "sliding_attention",
+            "sliding_attention",
+            "sliding_attention",
+            "full_attention"
+        ],
+        "max_position_embeddings": 262144,
+        "model_type": "gemma4_unified_text",
+        "moe_intermediate_size": null,
+        "num_attention_heads": 16,
+        "num_experts": null,
+        "num_global_key_value_heads": 1,
+        "num_hidden_layers": 48,
+        "num_key_value_heads": 8,
+        "num_kv_shared_layers": 0,
+        "pad_token_id": 0,
+        "rms_norm_eps": 1e-06,
+        "rope_parameters": {
+            "full_attention": {
+                "partial_rotary_factor": 0.25,
+                "rope_theta": 1000000.0,
+                "rope_type": "proportional"
+            },
+            "sliding_attention": {
+                "rope_theta": 10000.0,
+                "rope_type": "default"
+            }
+        },
+        "sliding_window": 1024,
+        "tie_word_embeddings": true,
+        "top_k_experts": null,
+        "use_bidirectional_attention": "vision",
+        "use_cache": true,
+        "use_double_wide_mlp": false,
+        "vocab_size": 262144,
+        "vocab_size_per_layer_input": 262144
+    },
+    "tie_word_embeddings": true,
+    "top_k": 64,
+    "top_p": 0.95,
+    "transformers_version": "5.10.0.dev0",
+    "video_token_id": 258884,
+    "vision_config": {
+        "_name_or_path": "",
+        "architectures": null,
+        "chunk_size_feed_forward": 0,
+        "dtype": null,
+        "id2label": {
+            "0": "LABEL_0",
+            "1": "LABEL_1"
+        },
+        "initializer_range": 0.02,
+        "is_encoder_decoder": false,
+        "label2id": {
+            "LABEL_0": 0,
+            "LABEL_1": 1
+        },
+        "mm_embed_dim": 3840,
+        "mm_posemb_size": 1120,
+        "model_patch_size": 48,
+        "model_type": "gemma4_unified_vision",
+        "num_soft_tokens": 280,
+        "output_attentions": false,
+        "output_hidden_states": false,
+        "output_proj_dims": 3840,
+        "patch_size": 16,
+        "pooling_kernel_size": 3,
+        "problem_type": null,
+        "return_dict": true,
+        "rms_norm_eps": 1e-06
+    }
+}

generation_config.json

@@ -0,0 +1,18 @@
+{
+  "bos_token_id": 2,
+  "do_sample": true,
+  "eos_token_id": 1,
+  "pad_token_id": 0,
+  "suppress_tokens": [
+    255999,
+    256000,
+    258880,
+    258881,
+    258882,
+    258883
+  ],
+  "temperature": 1.0,
+  "top_k": 64,
+  "top_p": 0.95,
+  "transformers_version": "5.10.0.dev0"
+}

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f767a133827d478e5bd72c3c9368d27093f6cae7f9f6ba300e46f24c584cf68b
+size 5367921355

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e6aff45aef8a31e39e22b22cbf78f3b747750094c45311e582e20443b6e0a3f
+size 999627210

processor_config.json

@@ -0,0 +1,40 @@
+{
+  "image_processor": {
+    "do_convert_rgb": true,
+    "do_normalize": false,
+    "do_rescale": true,
+    "do_resize": true,
+    "image_mean": [
+      0.0,
+      0.0,
+      0.0
+    ],
+    "image_processor_type": "Gemma4UnifiedImageProcessor",
+    "image_std": [
+      1.0,
+      1.0,
+      1.0
+    ],
+    "max_soft_tokens": 280,
+    "model_patch_size": 48,
+    "patch_size": 16,
+    "pooling_kernel_size": 3,
+    "resample": 3,
+    "rescale_factor": 0.00392156862745098,
+    "size": {
+      "height": 224,
+      "width": 224
+    }
+  },
+  "processor_class": "Gemma4UnifiedProcessor",
+  "feature_extractor": {
+    "feature_extractor_type": "Gemma4UnifiedAudioFeatureExtractor",
+    "sampling_rate": 16000,
+    "num_mel_filters": 128,
+    "fft_length": 512,
+    "hop_length": 160,
+    "chunk_duration": 8.0,
+    "overlap_duration": 1.0
+  },
+  "audio_ms_per_token": 40
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12bac982b793c44b03d52a250a9f0d0b666813da566b910c24a6da0695fd11e6
+size 32170070

tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "audio_token": "<|audio|>",
+  "backend": "tokenizers",
+  "boa_token": "<|audio>",
+  "boi_token": "<|image>",
+  "bos_token": "<bos>",
+  "eoa_token": "<audio|>",
+  "eoc_token": "<channel|>",
+  "eoi_token": "<image|>",
+  "eos_token": "<eos>",
+  "eot_token": "<turn|>",
+  "escape_token": "<|\"|>",
+  "etc_token": "<tool_call|>",
+  "etd_token": "<tool|>",
+  "etr_token": "<tool_response|>",
+  "extra_special_tokens": [
+    "<|video|>"
+  ],
+  "image_token": "<|image|>",
+  "is_local": true,
+  "local_files_only": true,
+  "mask_token": "<mask>",
+  "model_max_length": 1000000000000000019884624838656,
+  "model_specific_special_tokens": {
+    "audio_token": "<|audio|>",
+    "boa_token": "<|audio>",
+    "boi_token": "<|image>",
+    "eoa_token": "<audio|>",
+    "eoc_token": "<channel|>",
+    "eoi_token": "<image|>",
+    "eot_token": "<turn|>",
+    "escape_token": "<|\"|>",
+    "etc_token": "<tool_call|>",
+    "etd_token": "<tool|>",
+    "etr_token": "<tool_response|>",
+    "image_token": "<|image|>",
+    "soc_token": "<|channel>",
+    "sot_token": "<|turn>",
+    "stc_token": "<|tool_call>",
+    "std_token": "<|tool>",
+    "str_token": "<|tool_response>",
+    "think_token": "<|think|>"
+  },
+  "pad_token": "<pad>",
+  "padding_side": "left",
+  "processor_class": "Gemma4UnifiedProcessor",
+  "soc_token": "<|channel>",
+  "sot_token": "<|turn>",
+  "stc_token": "<|tool_call>",
+  "std_token": "<|tool>",
+  "str_token": "<|tool_response>",
+  "think_token": "<|think|>",
+  "tokenizer_class": "GemmaTokenizer",
+  "unk_token": "<unk>"
+}