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

@@ -1,4 +1,6 @@
 ---
+license: gemma
+pipeline_tag: image-text-to-text
 base_model:
 - zelk12/MT-Gen4_gemma-3-12B_flatten
 - zelk12/26_05_2025_Test_LazyMergekit_gemma-3-12B
@@ -15,6 +17,67 @@ tags:
 # MT-Gen4_gemma-3-12B
 
 
+___
+# EN
+
+This association is designed to change the results of the aligned model in order to see the vector of changes in the result in the table.
+
+Okay, I checked on the last model, I could add a description.
+Now I'll add to it a little bit.
+___
+# GGUF
+
+If I don't delete or forget to post it, then the GGUF probably Q6 of this model can be found here.:
+https://huggingface.co/{{ username }}/{{ model_name }}-Q6_K-GGUF
+
+It is also not uncommon to find GGUF and imatrix GGUF here:
+[mradermacher](https://huggingface.co/mradermacher )
+Most of the time, I use their quanta myself if possible.
+
+Well, sometimes he posts my models too.:
+[Otakadelic](https://huggingface.co/Otakadelic)
+But besides that, he is also engaged in combining models himself.
+
+___
+# Information
+
+Well, about the model itself, well, basically, it's just a combination of Gemma 3-12B, in general, nothing remarkable.
+
+The hypothetical model itself can work with a 128k context.
+Images are normalized to a resolution of 896 x 896 and encoded as 256 tokens.
+8192 tokens can be withdrawn at once.
+
+___
+# RU
+
+Эта объединение, с целью изменить результаты выровненой модели, для того, чтобы увидить вектор изменений результато в таблице.
+
+Ладно на прошлой модели проверил, описание добавить смог.
+Теперь немного его дополню.
+___
+# GGUF
+
+Если я не удалю и не забуду выложить, тогда GGUF вероятно Q6 этой модели можно будете найти здесь:
+https://huggingface.co/{{ username }}/{{ model_name }}-Q6_K-GGUF
+
+Также нередко GGUF и imatrix GGUF можно найти зесь:
+[mradermacher](https://huggingface.co/mradermacher)
+Чаще всего я сам использую их кванты если это возможно.
+
+Ну и иногда он тоже выкладывает мои модели:
+[Otakadelic](https://huggingface.co/Otakadelic)
+Но кроме того, он ещё и сам занимается объединением моделей.
+
+___
+# Информация
+
+Ну про саму модель, ну в основном, это просто объединение Gemma 3-12B, в целом ничего примечательного.
+
+Сама модель гипотетический может работать с контекстом 128к.
+Изображения нормализует в разрешение 896 x 896 и кодирует как 256 токенов.
+Вывести разом может 8192 токена.
+
+
 
 MT-Gen4_gemma-3-12B is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
 * [zelk12/MT-Gen4_gemma-3-12B_flatten](https://huggingface.co/zelk12/MT-Gen4_gemma-3-12B_flatten)

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<image_soft_token>": 262144
+}

config.json

@@ -0,0 +1,112 @@
+{
+  "architectures": [
+    "Gemma3ForConditionalGeneration"
+  ],
+  "boi_token_index": 255999,
+  "dtype": "bfloat16",
+  "eoi_token_index": 256000,
+  "eos_token_id": [
+    1,
+    106
+  ],
+  "image_token_index": 262144,
+  "initializer_range": 0.02,
+  "mm_tokens_per_image": 256,
+  "model_type": "gemma3",
+  "text_config": {
+    "_sliding_window_pattern": 6,
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "attn_logit_softcapping": null,
+    "cache_implementation": "hybrid",
+    "final_logit_softcapping": null,
+    "head_dim": 256,
+    "hidden_activation": "gelu_pytorch_tanh",
+    "hidden_size": 3840,
+    "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": 131072,
+    "model_type": "gemma3_text",
+    "num_attention_heads": 16,
+    "num_hidden_layers": 48,
+    "num_key_value_heads": 8,
+    "query_pre_attn_scalar": 256,
+    "rms_norm_eps": 1e-06,
+    "rope_local_base_freq": 10000.0,
+    "rope_scaling": {
+      "factor": 8.0,
+      "rope_type": "linear"
+    },
+    "rope_theta": 1000000.0,
+    "sliding_window": 1024,
+    "sliding_window_pattern": 6,
+    "use_bidirectional_attention": false,
+    "use_cache": true,
+    "vocab_size": 262208
+  },
+  "transformers_version": "4.57.3",
+  "vision_config": {
+    "attention_dropout": 0.0,
+    "hidden_act": "gelu_pytorch_tanh",
+    "hidden_size": 1152,
+    "image_size": 896,
+    "intermediate_size": 4304,
+    "layer_norm_eps": 1e-06,
+    "model_type": "siglip_vision_model",
+    "num_attention_heads": 16,
+    "num_channels": 3,
+    "num_hidden_layers": 27,
+    "patch_size": 14,
+    "vision_use_head": false
+  }
+}

mergekit_config.yml

@@ -0,0 +1,24 @@
+
+models:
+  - model: zelk12/MT-Gen4_gemma-3-12B_flatten
+    #no parameters necessary for base model
+  - model: zelk12/MT-Gen4_gemma-3-12B_flatten
+    parameters:
+      density: 0.266
+      weight: 0.833
+
+  - model: zelk12/26_05_2025_Test_LazyMergekit_gemma-3-12B
+    parameters:
+      density: 0.533
+      weight: 0.666
+
+  - model: zelk12/MT4-gemma-3-12B
+    parameters:
+      density: 0.8
+      weight: 0.5
+
+merge_method: multislerp
+base_model: zelk12/MT-Gen4_gemma-3-12B_flatten
+parameters:
+  normalize: true
+dtype: bfloat16

model-00001-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb8cf52837ae1e035cbe2d8eeba8208d991158a1e7c87a14810c24a027a8eebf
+size 4939493432

model-00002-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e956d117f27e719035be7391c8a2fdff587a50b218e1bd258bddb1c287351a95
+size 4931296656

model-00003-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:876e555d5b7282d21bfff90a89c254dca84e1c480780a7089666969a81a8bed4
+size 4931296656

model-00004-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dde5b6223aa6cc5203f6621ae4d733c63f65309a53bf4d380f8da4323ec02476
+size 4931296656

model-00005-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7c159cda765c2ef61a84a3cf268ce69c366f0722db8c722f2aed3c254717b68
+size 4641409680

preprocessor_config.json

@@ -0,0 +1,29 @@
+{
+  "do_convert_rgb": null,
+  "do_normalize": true,
+  "do_pan_and_scan": null,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_processor_type": "Gemma3ImageProcessor",
+  "image_seq_length": 256,
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "pan_and_scan_max_num_crops": null,
+  "pan_and_scan_min_crop_size": null,
+  "pan_and_scan_min_ratio_to_activate": null,
+  "processor_class": "Gemma3Processor",
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "height": 896,
+    "width": 896
+  }
+}

processor_config.json

@@ -0,0 +1,4 @@
+{
+  "image_seq_length": 256,
+  "processor_class": "Gemma3Processor"
+}

special_tokens_map.json

@@ -0,0 +1,33 @@
+{
+  "boi_token": "<start_of_image>",
+  "bos_token": {
+    "content": "<bos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eoi_token": "<end_of_image>",
+  "eos_token": {
+    "content": "<end_of_turn>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "image_token": "<image_soft_token>",
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4667f2089529e8e7657cfb6d1c19910ae71ff5f28aa7ab2ff2763330affad795
+size 33384568

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1299c11d7cf632ef3b4e11937501358ada021bbdf7c47638d13c0ee982f2e79c
+size 4689074