Re-upload google/gemma-4-26B-A4B-it MLX bf16

Converted from google/gemma-4-26B-A4B-it at revision 20da991ab4afab98e8f910c4a2e8f4fbefc404ad with the current mlx-vlm checkout.

README.md

@@ -5,21 +5,22 @@ license_link: https://ai.google.dev/gemma/docs/gemma_4_license
 pipeline_tag: image-text-to-text
 tags:
 - mlx
-base_model: google/gemma-4-26b-a4b-it
+- safetensors
+- gemma4
+- image-text-to-text
+- conversational
+- bf16
+base_model: google/gemma-4-26B-A4B-it
 ---
-
 # mlx-community/gemma-4-26b-a4b-it-bf16
 
-This model was converted to MLX format from [`google/gemma-4-26b-a4b-it`](https://huggingface.co/google/gemma-4-26b-a4b-it)
-using mlx-vlm version **0.4.3**.
-Refer to the [original model card](https://huggingface.co/google/gemma-4-26b-a4b-it) for more details on the model.
+This model was converted to MLX format from [google/gemma-4-26B-A4B-it](https://huggingface.co/google/gemma-4-26B-A4B-it) at revision `20da991ab4afab98e8f910c4a2e8f4fbefc404ad`.
 
-## Use with mlx
+It was generated from the current `mlx-vlm` source checkout.
 
-```bash
-pip install -U mlx-vlm
-```
+## Use with mlx-vlm
 
 ```bash
-python -m mlx_vlm.generate --model mlx-community/gemma-4-26b-a4b-it-bf16 --max-tokens 100 --temperature 0.0 --prompt "Describe this image." --image <path_to_image>
+pip install -U mlx-vlm
+mlx_vlm.generate --model mlx-community/gemma-4-26b-a4b-it-bf16 --max-tokens 100 --temperature 0.0 --prompt "Describe this image." --image <path_to_image>
 ```

config.json

@@ -6,6 +6,7 @@
     "audio_token_id": 258881,
     "boa_token_id": 256000,
     "boi_token_id": 255999,
+    "do_sample": true,
     "dtype": "bfloat16",
     "eoa_token_id": 258883,
     "eoa_token_index": 258883,
@@ -15,9 +16,24 @@
         106,
         50
     ],
+    "generation_config": {
+        "bos_token_id": 2,
+        "do_sample": true,
+        "eos_token_id": [
+            1,
+            106,
+            50
+        ],
+        "pad_token_id": 0,
+        "temperature": 1.0,
+        "top_k": 64,
+        "top_p": 0.95,
+        "transformers_version": "5.5.0.dev0"
+    },
     "image_token_id": 258880,
     "initializer_range": 0.02,
     "model_type": "gemma4",
+    "temperature": 1.0,
     "text_config": {
         "attention_bias": false,
         "attention_dropout": 0.0,
@@ -98,6 +114,8 @@
         "vocab_size_per_layer_input": 262144
     },
     "tie_word_embeddings": true,
+    "top_k": 64,
+    "top_p": 0.95,
     "transformers_version": "5.5.0.dev0",
     "video_token_id": 258884,
     "vision_config": {

model-00001-of-00011.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d45efa2acca485d4b0c5ab94aa9567618a16091921fee1cdf356475ae63a46d
-size 5345934797
+oid sha256:3d3abd759970cd5a07a718e7a94412ee190aa324dcb5863571c7fa04cb49552d
+size 5345934811

model-00002-of-00011.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6af2b5a0eaaa7ab03e0479d62d7b6fe88c3f778dd33be0e74dba5e81bfc0ad52
-size 4913415705
+oid sha256:e5555b937f147b35ccbc282c3234a6c947877ab3b2214768c75aa20d818cc273
+size 4913415699

model-00003-of-00011.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f6bba82c9697c77283f3eb2dd35e21e435ba84240e4e29515e88f2f0edb43fd7
-size 4884578957
+oid sha256:addadb54f41ef12f5a853751e88fdcd87d9ebeb35ef269f999300abf3ffbb0b9
+size 4884578893

model-00004-of-00011.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c8e044bcc0561fcf3767bcc4fa376c16c9ff8c179f4b2f7f5ee376a38240e88
-size 4913415704
+oid sha256:a704d896d6f698abbe526e6ece4a49b7bb9fb26feed6e57444e776fbe2ca6db6
+size 4913415700

model-00005-of-00011.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4a12f307fda6cce6609fcf348c7cf3349a77941bfa16dbb8e7a691e0e530483e
-size 4884579052
+oid sha256:f5ecbc6e6b7d7fa53fdb8bd1314d2cb9ede8e9ffc371bbc43b6efff01224ad7f
+size 4884578998

model-00006-of-00011.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cff7bf2d752626dc96c1c4b9d0c926a7c4bb26c7b0576eab1c00e5a7cff29f7d
-size 4913415787
+oid sha256:e1aa7283837a88857f24bc3cd2a38f0651c79adaae182f0743310375d0d97f8d
+size 4913415679

model-00007-of-00011.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:52a3396e00d73983eb232cad4144b82213a80d9ee5314db5c869b8c4ead0580b
-size 4884579052
+oid sha256:8fe948aded6caaae5f7870758b9087e0585c3f2f0984a9a53e9e80c89f251399
+size 4884579000

model-00008-of-00011.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e556d520889b47cc825c4be0b68d0e13976a00fa8f171c4d48121b6e541485fa
-size 4913415775
+oid sha256:3fdb53b1df10180b387fb78babb32b0cb5a4c2db7abcd81869e6c800db9f869d
+size 4913415731

model-00009-of-00011.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef5ad458f72a60c6e41b0b69ef1b463ff7a01b14e87f1572371d288bb2d3a02d
-size 4884578952
+oid sha256:5bd647b7d70969a358dd416beb1a50a1971cd3e73d0428c87c78651053389233
+size 4884579038

model-00010-of-00011.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:193b8a6b6cb356d6b99906fc982f6a1081d1220750216c4ec2e237629550f827
-size 4913415769
+oid sha256:7306fc374c6a2229a32e528828b10f06ffe1bfe216d66740ebb8ce66a66d2274
+size 4913415721

model-00011-of-00011.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb11c16f78bcb6eccd4d40748bfa82ae21e2687a30c2ea247f935c67abe74679
-size 2160681433
+oid sha256:9e1e4bcb5721025e6d7101d96904ac579ce1cb01e9cfdee72bb6c17798371662
+size 2160681171

processor_config.json

@@ -28,5 +28,36 @@
     }
   },
   "image_seq_length": 280,
-  "processor_class": "Gemma4Processor"
-}
+  "processor_class": "Gemma4Processor",
+  "video_processor": {
+    "default_fps": 2.0,
+    "do_normalize": true,
+    "do_rescale": true,
+    "image_mean": [
+      0.0,
+      0.0,
+      0.0
+    ],
+    "image_std": [
+      1.0,
+      1.0,
+      1.0
+    ],
+    "max_soft_tokens": 70,
+    "num_frames": 32,
+    "patch_size": 16,
+    "pooling_kernel_size": 3,
+    "rescale_factor": 0.00392156862745098,
+    "video_processor_type": "Gemma4VideoProcessor"
+  },
+  "feature_extractor": {
+    "feature_extractor_type": "Gemma4AudioFeatureExtractor",
+    "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_config.json

@@ -17,50 +17,72 @@
     "<|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": "Gemma4Processor",
   "response_schema": {
-    "type": "object",
     "properties": {
+      "content": {
+        "type": "string"
+      },
       "role": {
         "const": "assistant"
       },
       "thinking": {
         "type": "string"
       },
-      "content": {
-        "type": "string"
-      },
       "tool_calls": {
-        "x-regex-iterator": "<\\|tool_call>(.*?)<tool_call\\|>",
-        "type": "array",
         "items": {
-          "type": "object",
           "properties": {
-            "type": {
-              "const": "function"
-            },
             "function": {
-              "type": "object",
-              "x-regex": "call\\:(?P<name>\\w+)(?P<arguments>\\{.*\\})",
               "properties": {
-                "name": {
-                  "type": "string"
-                },
                 "arguments": {
+                  "additionalProperties": {},
                   "type": "object",
-                  "x-parser": "gemma4-tool-call",
-                  "additionalProperties": {}
+                  "x-parser": "gemma4-tool-call"
+                },
+                "name": {
+                  "type": "string"
                 }
-              }
+              },
+              "type": "object",
+              "x-regex": "call\\:(?P<name>\\w+)(?P<arguments>\\{.*\\})"
+            },
+            "type": {
+              "const": "function"
             }
-          }
-        }
+          },
+          "type": "object"
+        },
+        "type": "array",
+        "x-regex-iterator": "<\\|tool_call>(.*?)<tool_call\\|>"
       }
     },
+    "type": "object",
     "x-regex": "(\\<\\|channel\\>thought\\n(?P<thinking>.*?)\\<channel\\|\\>)?(?P<tool_calls>\\<\\|tool_call\\>.*\\<tool_call\\|\\>)?(?P<content>(?:(?!\\<turn\\|\\>)(?!\\<\\|tool_response\\>).)+)?(?:\\<turn\\|\\>|\\<\\|tool_response\\>)?"
   },
   "soc_token": "<|channel>",