Upload gemma-4-26B-A4B-it-assistant-oQ8-fp16 via oMLX

.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 +1,18 @@
+---
+library_name: mlx
+tags:
+- mlx
+- oq
+- quantized
+---
+
+# gemma-4-26B-A4B-it-assistant-oQ8-fp16
+
+This model was quantized using [oQ](https://github.com/jundot/omlx) (oMLX v0.3.9.dev1) mixed-precision quantization.
+
+## Quantization details
+
+- **Model type**: gemma4_assistant
+- **Bits**: 8
+- **Group size**: 64
+- **Format**: MLX safetensors

config.json

@@ -0,0 +1,103 @@
+{
+  "architectures": [
+    "Gemma4AssistantForCausalLM"
+  ],
+  "audio_token_id": 258881,
+  "backbone_hidden_size": 2816,
+  "boa_token_id": 256000,
+  "boi_token_id": 255999,
+  "centroid_intermediate_top_k": 32,
+  "dtype": "bfloat16",
+  "eoa_token_id": 258883,
+  "eoi_token_id": 258882,
+  "image_token_id": 258880,
+  "model_type": "gemma4_assistant",
+  "num_centroids": 2048,
+  "text_config": {
+    "_name_or_path": "",
+    "architectures": null,
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "attention_k_eq_v": true,
+    "bos_token_id": 2,
+    "chunk_size_feed_forward": 0,
+    "dtype": "bfloat16",
+    "enable_moe_block": false,
+    "eos_token_id": 1,
+    "final_logit_softcapping": null,
+    "global_head_dim": 512,
+    "head_dim": 256,
+    "hidden_activation": "gelu_pytorch_tanh",
+    "hidden_size": 1024,
+    "hidden_size_per_layer_input": 0,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "initializer_range": 0.02,
+    "intermediate_size": 8192,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "layer_types": [
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention"
+    ],
+    "max_position_embeddings": 262144,
+    "model_type": "gemma4_text",
+    "moe_intermediate_size": null,
+    "num_attention_heads": 16,
+    "num_experts": null,
+    "num_global_key_value_heads": 2,
+    "num_hidden_layers": 4,
+    "num_key_value_heads": 8,
+    "num_kv_shared_layers": 4,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "pad_token_id": 0,
+    "problem_type": null,
+    "return_dict": true,
+    "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": null,
+    "use_cache": true,
+    "use_double_wide_mlp": false,
+    "vocab_size": 262144,
+    "vocab_size_per_layer_input": 0
+  },
+  "tie_word_embeddings": true,
+  "transformers_version": "5.7.0.dev0",
+  "use_ordered_embeddings": false,
+  "eos_token_id": [
+    1,
+    106,
+    50
+  ],
+  "quantization": {
+    "group_size": 64,
+    "bits": 8,
+    "mode": "affine"
+  },
+  "quantization_config": {
+    "group_size": 64,
+    "bits": 8,
+    "mode": "affine"
+  }
+}

generation_config.json

@@ -0,0 +1,17 @@
+{
+  "bos_token_id": 2,
+  "do_sample": true,
+  "eos_token_id": [
+    1,
+    106,
+    50
+  ],
+  "is_assistant": true,
+  "num_assistant_tokens": 6,
+  "num_assistant_tokens_schedule": "constant",
+  "pad_token_id": 0,
+  "temperature": 1.0,
+  "top_k": 64,
+  "top_p": 0.95,
+  "transformers_version": "5.7.0.dev0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ca3c449828c6b6acfee7f939f2c1796b6c990484a96b534d01f0635fb6080fd
+size 445970893

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:75a6583c1a418e2bbd79c60d95d28e0f5bf549ad3f2990b5bdb5238c6c2bf70c
+size 32169440

tokenizer_config.json

@@ -0,0 +1,30 @@
+{
+  "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": [],
+  "image_token": "<|image|>",
+  "mask_token": "<mask>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "padding_side": "left",
+  "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>"
+}