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 +1,92 @@
+---
+base_model:
+- google/gemma-3-12b-it
+- google/translategemma-12b-it
+library_name: transformers
+tags:
+- mergekit
+- merge
+- translation
+- multimodal
+- gemma-3
+license: gemma
+---
+
+# GemmaTranslate-v3-12B
+
+GemmaTranslate-v3-12B is a high-performance, multimodal hybrid model designed for advanced translation and general-purpose assistance. It is a [SLERP](https://en.wikipedia.org/wiki/Slerp) merge of two state-of-the-art models: [Gemma-3-12B-IT](https://huggingface.co/google/gemma-3-12b-it) and [TranslateGemma-12B-IT](https://huggingface.co/google/translategemma-12b-it).
+
+By combining the general reasoning and multimodal capabilities of Gemma-3 with the specialized translation expertise of TranslateGemma, this model offers superior performance in multilingual contexts while maintaining the ability to process visual information.
+
+## Model Details
+
+- **Architecture:** Gemma-3 (Multimodal, 128K context length)
+- **Merge Method:** SLERP (Spherical Linear Interpolation)
+- **Base Models:**
+  - [google/gemma-3-12b-it](https://huggingface.co/google/gemma-3-12b-it)
+  - [google/translategemma-12b-it](https://huggingface.co/google/translategemma-12b-it)
+- **Language(s):** Multilingual (Supports 30+ languages)
+- **License:** [Gemma Terms of Use](https://ai.google.dev/gemma/terms)
+
+## Key Features
+
+- **Multimodal Capabilities:** Inherits the vision tower and multimodal projector from Gemma-3-12B-IT, enabling image understanding and visual reasoning.
+- **Enhanced Translation:** Optimized for translation tasks by merging with TranslateGemma-12B-IT.
+- **Large Context Window:** Supports up to 128K tokens.
+- **Hybrid Reasoning:** Combines instruction-following capabilities with high-fidelity translation.
+
+## Merge Configuration
+
+The following YAML configuration was used to produce this model:
+
+```yaml
+base_model: google/gemma-3-12b-it
+dtype: bfloat16
+merge_method: slerp
+parameters:
+  t:
+    - filter: vision_tower
+      value: 0
+    - filter: multi_modal_projector
+      value: 0
+    - value: 0.5
+models:
+  - model: google/gemma-3-12b-it
+  - model: google/translategemma-12b-it
+```
+
+*Note: The `vision_tower` and `multi_modal_projector` weights are taken 100% from Gemma-3-12B-IT (`t=0`) to ensure visual stability, while the language model weights are a 50/50 SLERP merge (`t=0.5`).*
+
+## Usage
+
+You can use this model with the Hugging Face `transformers` library.
+
+```python
+from transformers import Gemma3ForConditionalGeneration, AutoProcessor
+import torch
+
+model_id = "SpongeBOB9684/GemmaTranslate-v3-12B"
+
+model = Gemma3ForConditionalGeneration.from_pretrained(
+    model_id,
+    device_map="auto",
+    torch_dtype=torch.bfloat16
+)
+processor = AutoProcessor.from_pretrained(model_id)
+
+# Example: Multimodal Translation
+# (Add your image and prompt here)
+prompt = "Translate the text in this image to French and explain its context."
+# inputs = processor(text=prompt, images=image, return_tensors="pt").to(model.device)
+
+# Example: Text-only Translation
+prompt = "Translate the following English text to Japanese: 'The future of AI is multimodal.'"
+inputs = processor(text=prompt, return_tensors="pt").to(model.device)
+
+output = model.generate(**inputs, max_new_tokens=256)
+print(processor.decode(output[0], skip_special_tokens=True))
+```
+
+## License
+
+This model is subject to the [Gemma Terms of Use](https://ai.google.dev/gemma/terms). By using this model, you agree to the terms and conditions specified by Google.

added_tokens.json

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

config.json

@@ -0,0 +1,120 @@
+{
+  "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,
+    "bos_token_id": 2,
+    "eos_token_id": 1,
+    "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,
+    "pad_token_id": 0,
+    "query_pre_attn_scalar": 256,
+    "rms_norm_eps": 1e-06,
+    "rope_parameters": {
+      "full_attention": {
+        "factor": 8.0,
+        "rope_theta": 1000000.0,
+        "rope_type": "linear"
+      },
+      "sliding_attention": {
+        "rope_theta": 10000.0,
+        "rope_type": "default"
+      }
+    },
+    "sliding_window": 1024,
+    "tie_word_embeddings": true,
+    "use_bidirectional_attention": false,
+    "use_cache": true,
+    "vocab_size": 262208
+  },
+  "tie_word_embeddings": true,
+  "transformers_version": "5.3.0",
+  "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 +1,13 @@
+base_model: google/gemma-3-12b-it
+dtype: bfloat16
+merge_method: slerp
+parameters:
+  t:
+    - filter: vision_tower
+      value: 0
+    - filter: multi_modal_projector
+      value: 0
+    - value: 0.5
+models:
+  - model: google/gemma-3-12b-it
+  - model: google/translategemma-12b-it

model-00001-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f3e18123fa0b54a16ae974b93b03081bbdd13fa7822fa69cd363e2387568147
+size 4939493432

model-00002-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:806c02c2f374018fe2bc88d44910c4d8ac9b4710836ae7aa479c595d4c27e195
+size 4931296656

model-00003-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f225dbe2eb3fe72da6295e2f23c213ba2ef7ebe5b3ff36722e76bdc24facb3f
+size 4931296656

model-00004-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e7e97639bac28d3dbddea3781d595c42996869fc4110c930cd0e515857a72a07
+size 4931296656

model-00005-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9009d97341ee98d41cbb63e04a654fe5ea2f634daf39a0a4cb9725143dfac7c4
+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": "<eos>",
+    "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