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 +1,89 @@
+---
+base_model:
+- zelk12/MT-Gen1-gemma-3-12B
+- soob3123/amoral-gemma3-12B-v2
+- zelk12/MT1-gemma-3-12B
+- IlyaGusev/saiga_gemma3_12b
+- TheDrummer/Fallen-Gemma3-12B-v1
+tags:
+- merge
+- mergekit
+- lazymergekit
+- zelk12/MT-Gen1-gemma-3-12B
+- soob3123/amoral-gemma3-12B-v2
+- zelk12/MT1-gemma-3-12B
+- IlyaGusev/saiga_gemma3_12b
+- TheDrummer/Fallen-Gemma3-12B-v1
+---
+
+# MT6-Gen2_gemma-3-12B
+
+MT6-Gen2_gemma-3-12B is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
+* [zelk12/MT-Gen1-gemma-3-12B](https://huggingface.co/zelk12/MT-Gen1-gemma-3-12B)
+* [soob3123/amoral-gemma3-12B-v2](https://huggingface.co/soob3123/amoral-gemma3-12B-v2)
+* [zelk12/MT1-gemma-3-12B](https://huggingface.co/zelk12/MT1-gemma-3-12B)
+* [IlyaGusev/saiga_gemma3_12b](https://huggingface.co/IlyaGusev/saiga_gemma3_12b)
+* [TheDrummer/Fallen-Gemma3-12B-v1](https://huggingface.co/TheDrummer/Fallen-Gemma3-12B-v1)
+
+## 🧩 Configuration
+
+```yaml
+models:
+  - model: zelk12/MT-gemma-3-12B
+    #no parameters necessary for base model
+  - model: zelk12/MT-Gen1-gemma-3-12B
+    parameters:
+      density: 0.5
+      weight: 0.8
+
+  - model: soob3123/amoral-gemma3-12B-v2
+    parameters:
+      density: 0.639
+      weight: 0.66
+
+  - model: zelk12/MT1-gemma-3-12B
+    parameters:
+      density: 0.729
+      weight: 0.57
+
+  - model: IlyaGusev/saiga_gemma3_12b
+    parameters:
+      density: 0.736
+      weight: 0.56
+
+  - model: TheDrummer/Fallen-Gemma3-12B-v1
+    parameters:
+      density: 0.8
+      weight: 0.5
+
+merge_method: dare_ties
+base_model: zelk12/MT-gemma-3-12B
+parameters:
+  normalize: true
+dtype: bfloat16
+```
+
+## 💻 Usage
+
+```python
+!pip install -qU transformers accelerate
+
+from transformers import AutoTokenizer
+import transformers
+import torch
+
+model = "zelk12/MT6-Gen2_gemma-3-12B"
+messages = [{"role": "user", "content": "What is a large language model?"}]
+
+tokenizer = AutoTokenizer.from_pretrained(model)
+prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
+pipeline = transformers.pipeline(
+    "text-generation",
+    model=model,
+    torch_dtype=torch.float16,
+    device_map="auto",
+)
+
+outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
+print(outputs[0]["generated_text"])
+```

added_tokens.json

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

config.json

@@ -0,0 +1,110 @@
+{
+  "architectures": [
+    "Gemma3ForConditionalGeneration"
+  ],
+  "boi_token_index": 255999,
+  "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,
+    "use_cache": true,
+    "vocab_size": 262208
+  },
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.53.2",
+  "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 +1,34 @@
+
+models:
+  - model: zelk12/MT-gemma-3-12B
+    #no parameters necessary for base model
+  - model: zelk12/MT-Gen1-gemma-3-12B
+    parameters:
+      density: 0.5
+      weight: 0.8
+
+  - model: soob3123/amoral-gemma3-12B-v2
+    parameters:
+      density: 0.639
+      weight: 0.66
+
+  - model: zelk12/MT1-gemma-3-12B
+    parameters:
+      density: 0.729
+      weight: 0.57
+
+  - model: IlyaGusev/saiga_gemma3_12b
+    parameters:
+      density: 0.736
+      weight: 0.56
+
+  - model: TheDrummer/Fallen-Gemma3-12B-v1
+    parameters:
+      density: 0.8
+      weight: 0.5
+
+merge_method: dare_ties
+base_model: zelk12/MT-gemma-3-12B
+parameters:
+  normalize: true
+dtype: bfloat16

model-00001-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c7a05cf24f7216b5b1a9ce5c63a035dc5c99af4b6e679baf76641aab42a5210c
+size 4939493432

model-00002-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ecae86ef2ef088290ac3387c6fd2e76c8918d9a612338c6c6503931c603834ce
+size 4931296656

model-00003-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81f38ca8e14f64addd7d89f53339e6192600e9959f457d77d7a15d81f7863c69
+size 4931296656

model-00004-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ab386d7c94bb149d73bf4f92592f329db560b9d4ad056e88f073d1576935808
+size 4931296656

model-00005-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d873b783dedbd2dbf2e1a205f6c9e2818d907c8bcf5aa38438ee6954c180bdd
+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