Upload model

README.md

@@ -1,5 +1,6 @@
 ---
 tags:
+- unsloth
 - sentence-transformers
 - sentence-similarity
 - feature-extraction
@@ -7,7 +8,6 @@ tags:
 - generated_from_trainer
 - dataset_size:10000
 - loss:MultipleNegativesRankingLoss
-- unsloth
 base_model: unsloth/embeddinggemma-300m
 widget:
 - source_sentence: 'What is the most successful treatment for lung SFTs?
@@ -920,7 +920,12 @@ model-index:
       name: Cosine Map@100
 ---
 
-# SentenceTransformer based on unsloth/embeddinggemma-300m
+# SentenceTransformer
+
+This model was finetuned with [Unsloth](https://github.com/unslothai/unsloth).
+
+[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
+ based on unsloth/embeddinggemma-300m
 
 This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [unsloth/embeddinggemma-300m](https://huggingface.co/unsloth/embeddinggemma-300m) on the generator dataset. It maps sentences & paragraphs to a 768-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.
 

config.json

@@ -0,0 +1,61 @@
+{
+    "_sliding_window_pattern": 6,
+    "architectures": [
+        "Gemma3TextModel"
+    ],
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "attn_logit_softcapping": null,
+    "bos_token_id": 2,
+    "torch_dtype": "float16",
+    "eos_token_id": 1,
+    "final_logit_softcapping": null,
+    "head_dim": 256,
+    "hidden_activation": "gelu_pytorch_tanh",
+    "hidden_size": 768,
+    "initializer_range": 0.02,
+    "intermediate_size": 1152,
+    "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"
+    ],
+    "max_position_embeddings": 2048,
+    "model_type": "gemma3_text",
+    "num_attention_heads": 3,
+    "num_hidden_layers": 24,
+    "num_key_value_heads": 1,
+    "pad_token_id": 0,
+    "query_pre_attn_scalar": 256,
+    "rms_norm_eps": 1e-06,
+    "rope_local_base_freq": 10000.0,
+    "rope_scaling": null,
+    "rope_theta": 1000000.0,
+    "sliding_window": 512,
+    "tokenizer_class": "GemmaTokenizerFast",
+    "unsloth_version": "2026.2.1",
+    "use_bidirectional_attention": true,
+    "use_cache": true,
+    "vocab_size": 262144
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd1c4ad9cf050c98d5cd0390aa0cb76b270d2e3eed3ae673f013c579c0bfb3cf
+size 1211486072

tokenizer_config.json

@@ -51342,4 +51342,4 @@
   "tokenizer_class": "GemmaTokenizer",
   "unk_token": "<unk>",
   "use_default_system_prompt": false
-}
+}