Sentence Similarity
sentence-transformers
Safetensors
Transformers
PyTorch
English
gemma3_text
feature-extraction
mteb
Eval Results (legacy)
text-embeddings-inference
Instructions to use Surpem/Supertron-embedding-300M with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use Surpem/Supertron-embedding-300M with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("Surpem/Supertron-embedding-300M") sentences = [ "That is a happy person", "That is a happy dog", "That is a very happy person", "Today is a sunny day" ] embeddings = model.encode(sentences) similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [4, 4] - Transformers
How to use Surpem/Supertron-embedding-300M with Transformers:
# Load model directly from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("Surpem/Supertron-embedding-300M") model = AutoModel.from_pretrained("Surpem/Supertron-embedding-300M") - Notebooks
- Google Colab
- Kaggle
Add files using upload-large-folder tool
Browse files- .gitattributes +1 -0
- 1_Pooling/config.json +5 -0
- 2_Dense/config.json +8 -0
- 2_Dense/model.safetensors +3 -0
- 3_Dense/config.json +8 -0
- 3_Dense/model.safetensors +3 -0
- config.json +68 -0
- config_sentence_transformers.json +26 -0
- model.safetensors +3 -0
- modules.json +32 -0
- sentence_bert_config.json +10 -0
- tokenizer.json +3 -0
- tokenizer_config.json +25 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
1_Pooling/config.json
ADDED
|
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"embedding_dimension": 768,
|
| 3 |
+
"pooling_mode": "mean",
|
| 4 |
+
"include_prompt": true
|
| 5 |
+
}
|
2_Dense/config.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"in_features": 768,
|
| 3 |
+
"out_features": 3072,
|
| 4 |
+
"bias": false,
|
| 5 |
+
"activation_function": "torch.nn.modules.linear.Identity",
|
| 6 |
+
"module_input_name": "sentence_embedding",
|
| 7 |
+
"module_output_name": "sentence_embedding"
|
| 8 |
+
}
|
2_Dense/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:44c45c2de56409b2c916fbf4475c57d99fc7d30bdfbb8cce9358ac1f4e5bbc2a
|
| 3 |
+
size 4718680
|
3_Dense/config.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"in_features": 3072,
|
| 3 |
+
"out_features": 768,
|
| 4 |
+
"bias": false,
|
| 5 |
+
"activation_function": "torch.nn.modules.linear.Identity",
|
| 6 |
+
"module_input_name": "sentence_embedding",
|
| 7 |
+
"module_output_name": "sentence_embedding"
|
| 8 |
+
}
|
3_Dense/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a9ee64d3fb0213e7496ab779de668d71714b55d7751629b722f6461ae94e1d9b
|
| 3 |
+
size 4718680
|
config.json
ADDED
|
@@ -0,0 +1,68 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_sliding_window_pattern": 6,
|
| 3 |
+
"architectures": [
|
| 4 |
+
"Gemma3TextModel"
|
| 5 |
+
],
|
| 6 |
+
"attention_bias": false,
|
| 7 |
+
"attention_dropout": 0.0,
|
| 8 |
+
"attn_logit_softcapping": null,
|
| 9 |
+
"bos_token_id": 2,
|
| 10 |
+
"dtype": "bfloat16",
|
| 11 |
+
"eos_token_id": 1,
|
| 12 |
+
"final_logit_softcapping": null,
|
| 13 |
+
"head_dim": 256,
|
| 14 |
+
"hidden_activation": "gelu_pytorch_tanh",
|
| 15 |
+
"hidden_size": 768,
|
| 16 |
+
"initializer_range": 0.02,
|
| 17 |
+
"intermediate_size": 1152,
|
| 18 |
+
"layer_types": [
|
| 19 |
+
"sliding_attention",
|
| 20 |
+
"sliding_attention",
|
| 21 |
+
"sliding_attention",
|
| 22 |
+
"sliding_attention",
|
| 23 |
+
"sliding_attention",
|
| 24 |
+
"full_attention",
|
| 25 |
+
"sliding_attention",
|
| 26 |
+
"sliding_attention",
|
| 27 |
+
"sliding_attention",
|
| 28 |
+
"sliding_attention",
|
| 29 |
+
"sliding_attention",
|
| 30 |
+
"full_attention",
|
| 31 |
+
"sliding_attention",
|
| 32 |
+
"sliding_attention",
|
| 33 |
+
"sliding_attention",
|
| 34 |
+
"sliding_attention",
|
| 35 |
+
"sliding_attention",
|
| 36 |
+
"full_attention",
|
| 37 |
+
"sliding_attention",
|
| 38 |
+
"sliding_attention",
|
| 39 |
+
"sliding_attention",
|
| 40 |
+
"sliding_attention",
|
| 41 |
+
"sliding_attention",
|
| 42 |
+
"full_attention"
|
| 43 |
+
],
|
| 44 |
+
"max_position_embeddings": 2048,
|
| 45 |
+
"model_type": "gemma3_text",
|
| 46 |
+
"num_attention_heads": 3,
|
| 47 |
+
"num_hidden_layers": 24,
|
| 48 |
+
"num_key_value_heads": 1,
|
| 49 |
+
"pad_token_id": 0,
|
| 50 |
+
"query_pre_attn_scalar": 256,
|
| 51 |
+
"rms_norm_eps": 1e-06,
|
| 52 |
+
"rope_parameters": {
|
| 53 |
+
"full_attention": {
|
| 54 |
+
"rope_theta": 1000000.0,
|
| 55 |
+
"rope_type": "default"
|
| 56 |
+
},
|
| 57 |
+
"sliding_attention": {
|
| 58 |
+
"rope_theta": 10000.0,
|
| 59 |
+
"rope_type": "default"
|
| 60 |
+
}
|
| 61 |
+
},
|
| 62 |
+
"sliding_window": 257,
|
| 63 |
+
"tie_word_embeddings": true,
|
| 64 |
+
"transformers_version": "5.6.2",
|
| 65 |
+
"use_bidirectional_attention": true,
|
| 66 |
+
"use_cache": true,
|
| 67 |
+
"vocab_size": 262144
|
| 68 |
+
}
|
config_sentence_transformers.json
ADDED
|
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"__version__": {
|
| 3 |
+
"pytorch": "2.6.0+cu124",
|
| 4 |
+
"sentence_transformers": "5.4.1",
|
| 5 |
+
"transformers": "5.6.2"
|
| 6 |
+
},
|
| 7 |
+
"default_prompt_name": null,
|
| 8 |
+
"model_type": "SentenceTransformer",
|
| 9 |
+
"prompts": {
|
| 10 |
+
"BitextMining": "task: search result | query: ",
|
| 11 |
+
"Classification": "task: classification | query: ",
|
| 12 |
+
"Clustering": "task: clustering | query: ",
|
| 13 |
+
"InstructionRetrieval": "task: code retrieval | query: ",
|
| 14 |
+
"MultilabelClassification": "task: classification | query: ",
|
| 15 |
+
"PairClassification": "task: sentence similarity | query: ",
|
| 16 |
+
"Reranking": "task: search result | query: ",
|
| 17 |
+
"Retrieval": "task: search result | query: ",
|
| 18 |
+
"Retrieval-document": "title: none | text: ",
|
| 19 |
+
"Retrieval-query": "task: search result | query: ",
|
| 20 |
+
"STS": "task: sentence similarity | query: ",
|
| 21 |
+
"Summarization": "task: summarization | query: ",
|
| 22 |
+
"document": "title: none | text: ",
|
| 23 |
+
"query": "task: search result | query: "
|
| 24 |
+
},
|
| 25 |
+
"similarity_fn_name": "cosine"
|
| 26 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8b9bf2a97362dcbc5013a35adb17e2d5dbe861c6ae22f69ac2856bab7c6dc630
|
| 3 |
+
size 605759848
|
modules.json
ADDED
|
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
[
|
| 2 |
+
{
|
| 3 |
+
"idx": 0,
|
| 4 |
+
"name": "0",
|
| 5 |
+
"path": "",
|
| 6 |
+
"type": "sentence_transformers.base.modules.transformer.Transformer"
|
| 7 |
+
},
|
| 8 |
+
{
|
| 9 |
+
"idx": 1,
|
| 10 |
+
"name": "1",
|
| 11 |
+
"path": "1_Pooling",
|
| 12 |
+
"type": "sentence_transformers.sentence_transformer.modules.pooling.Pooling"
|
| 13 |
+
},
|
| 14 |
+
{
|
| 15 |
+
"idx": 2,
|
| 16 |
+
"name": "2",
|
| 17 |
+
"path": "2_Dense",
|
| 18 |
+
"type": "sentence_transformers.base.modules.dense.Dense"
|
| 19 |
+
},
|
| 20 |
+
{
|
| 21 |
+
"idx": 3,
|
| 22 |
+
"name": "3",
|
| 23 |
+
"path": "3_Dense",
|
| 24 |
+
"type": "sentence_transformers.base.modules.dense.Dense"
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"idx": 4,
|
| 28 |
+
"name": "4",
|
| 29 |
+
"path": "4_Normalize",
|
| 30 |
+
"type": "sentence_transformers.sentence_transformer.modules.normalize.Normalize"
|
| 31 |
+
}
|
| 32 |
+
]
|
sentence_bert_config.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"transformer_task": "feature-extraction",
|
| 3 |
+
"modality_config": {
|
| 4 |
+
"text": {
|
| 5 |
+
"method": "forward",
|
| 6 |
+
"method_output_name": "last_hidden_state"
|
| 7 |
+
}
|
| 8 |
+
},
|
| 9 |
+
"module_output_name": "token_embeddings"
|
| 10 |
+
}
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:574b6e5f174a8b4b060b4ab002cfc78dd2620ea384940b7150d7e49571c25865
|
| 3 |
+
size 33385260
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"backend": "tokenizers",
|
| 3 |
+
"boi_token": "<start_of_image>",
|
| 4 |
+
"bos_token": "<bos>",
|
| 5 |
+
"clean_up_tokenization_spaces": false,
|
| 6 |
+
"eoi_token": "<end_of_image>",
|
| 7 |
+
"eos_token": "<eos>",
|
| 8 |
+
"image_token": "<image_soft_token>",
|
| 9 |
+
"is_local": false,
|
| 10 |
+
"local_files_only": false,
|
| 11 |
+
"mask_token": "<mask>",
|
| 12 |
+
"model_max_length": 256,
|
| 13 |
+
"model_specific_special_tokens": {
|
| 14 |
+
"boi_token": "<start_of_image>",
|
| 15 |
+
"eoi_token": "<end_of_image>",
|
| 16 |
+
"image_token": "<image_soft_token>"
|
| 17 |
+
},
|
| 18 |
+
"pad_token": "<pad>",
|
| 19 |
+
"padding_side": "right",
|
| 20 |
+
"sp_model_kwargs": null,
|
| 21 |
+
"spaces_between_special_tokens": false,
|
| 22 |
+
"tokenizer_class": "GemmaTokenizer",
|
| 23 |
+
"unk_token": "<unk>",
|
| 24 |
+
"use_default_system_prompt": false
|
| 25 |
+
}
|