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 +1,37 @@
+---
+base_model: google/t5gemma-2-270m-270m
+license: gemma
+tags:
+  - gemma2
+  - encoder-only
+  - text-encoder
+  - embeddings
+  - bidirectional
+---
+
+# T5Gemma-2-270m — Text Encoder Only (Bidirectional)
+
+Text encoder extracted from [google/t5gemma-2-270m-270m](https://huggingface.co/google/t5gemma-2-270m-270m), 
+saved as standard `Gemma2Model` with **bidirectional attention** (`is_decoder=False`).
+
+> Gemma is provided under and subject to the Gemma Terms of Use found at https://ai.google.dev/gemma/terms
+
+## Architecture
+- 18 layers, hidden_size=640, heads=4
+- Sliding window attention (512) + full attention every 6 layers
+- Bidirectional (no causal mask)
+- Parameters: 268M
+
+## Usage
+```python
+from transformers import AutoModel, AutoTokenizer
+
+model     = AutoModel.from_pretrained("knowledgator/t5gemma-2-text-encoder-270m")
+tokenizer = AutoTokenizer.from_pretrained("knowledgator/t5gemma-2-text-encoder-270m")
+
+inputs  = tokenizer("Your text here", return_tensors="pt", padding=True, truncation=True)
+outputs = model(**inputs)
+
+token_embeddings = outputs.last_hidden_state          # (batch, seq_len, 640)
+pooled           = outputs.last_hidden_state.mean(1)  # mean pooling -> (batch, 640)
+```

config.json

@@ -0,0 +1,56 @@
+{
+  "architectures": [
+    "Gemma2Model"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "attn_logit_softcapping": null,
+  "bos_token_id": 2,
+  "dtype": "float32",
+  "eos_token_id": 1,
+  "final_logit_softcapping": null,
+  "head_dim": 256,
+  "hidden_activation": "gelu_pytorch_tanh",
+  "hidden_size": 640,
+  "initializer_range": 0.02,
+  "intermediate_size": 2048,
+  "is_decoder": false,
+  "layer_types": [
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 32768,
+  "model_type": "gemma2",
+  "num_attention_heads": 4,
+  "num_hidden_layers": 18,
+  "num_key_value_heads": 1,
+  "pad_token_id": 0,
+  "query_pre_attn_scalar": 256,
+  "rms_norm_eps": 1e-06,
+  "rope_parameters": {
+    "rope_theta": 10000,
+    "rope_type": "default"
+  },
+  "sliding_window": 512,
+  "tie_word_embeddings": true,
+  "transformers_version": "5.3.0.dev0",
+  "use_bidirectional_attention": null,
+  "use_cache": true,
+  "vocab_size": 262144
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36e3f29bb9c10785f51d6ba285c58ebd8aba6434e1741ca96d37cbe45b70b7d9
+size 1072377272

text_encoder_weights.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb5f372cb57300ba2f3b0f19291b36e3f54b6eaa5d8236418e3f5ce29d56edd8
+size 536291708

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5b325224482ec441ec5fbe2a5ac08c3758e0f9605f6e54368e31f736fcfb01d
+size 33384387

tokenizer_config.json

@@ -0,0 +1,26 @@
+{
+  "backend": "tokenizers",
+  "boi_token": "<start_of_image>",
+  "bos_token": "<bos>",
+  "clean_up_tokenization_spaces": false,
+  "eoi_token": "<end_of_image>",
+  "eos_token": "<eos>",
+  "extra_special_tokens": [],
+  "image_token": "<image_soft_token>",
+  "is_local": false,
+  "mask_token": "<mask>",
+  "model_max_length": 1000000000000000019884624838656,
+  "model_specific_special_tokens": {
+    "boi_token": "<start_of_image>",
+    "eoi_token": "<end_of_image>",
+    "image_token": "<image_soft_token>"
+  },
+  "pad_token": "<pad>",
+  "padding_side": "right",
+  "processor_class": "Gemma3Processor",
+  "sp_model_kwargs": null,
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "GemmaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}