Add new SentenceTransformer model
Browse files- .gitattributes +1 -0
- 1_Pooling/config.json +10 -0
- 2_Dense/config.json +6 -0
- 2_Dense/model.safetensors +3 -0
- 3_Dense/config.json +6 -0
- 3_Dense/model.safetensors +3 -0
- README.md +0 -0
- added_tokens.json +3 -0
- config.json +60 -0
- config_sentence_transformers.json +25 -0
- model.safetensors +3 -0
- modules.json +32 -0
- sentence_bert_config.json +4 -0
- special_tokens_map.json +33 -0
- tokenizer.json +3 -0
- tokenizer.model +3 -0
- tokenizer_config.json +0 -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 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"word_embedding_dimension": 768,
|
3 |
+
"pooling_mode_cls_token": false,
|
4 |
+
"pooling_mode_mean_tokens": true,
|
5 |
+
"pooling_mode_max_tokens": false,
|
6 |
+
"pooling_mode_mean_sqrt_len_tokens": false,
|
7 |
+
"pooling_mode_weightedmean_tokens": false,
|
8 |
+
"pooling_mode_lasttoken": false,
|
9 |
+
"include_prompt": true
|
10 |
+
}
|
2_Dense/config.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"in_features": 768,
|
3 |
+
"out_features": 3072,
|
4 |
+
"bias": false,
|
5 |
+
"activation_function": "torch.nn.modules.linear.Identity"
|
6 |
+
}
|
2_Dense/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4695c79aa42cdd30011bbd5af5685d589ebb53aebf1714c769d473345f9db281
|
3 |
+
size 9437272
|
3_Dense/config.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"in_features": 3072,
|
3 |
+
"out_features": 768,
|
4 |
+
"bias": false,
|
5 |
+
"activation_function": "torch.nn.modules.linear.Identity"
|
6 |
+
}
|
3_Dense/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cc83ae813f46b8207b995701de9fd39f1828df3bc1d2b4829413cc205d112f03
|
3 |
+
size 9437272
|
README.md
ADDED
The diff for this file is too large to render.
See raw diff
|
|
added_tokens.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<image_soft_token>": 262144
|
3 |
+
}
|
config.json
ADDED
@@ -0,0 +1,60 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"eos_token_id": 1,
|
11 |
+
"final_logit_softcapping": null,
|
12 |
+
"head_dim": 256,
|
13 |
+
"hidden_activation": "gelu_pytorch_tanh",
|
14 |
+
"hidden_size": 768,
|
15 |
+
"initializer_range": 0.02,
|
16 |
+
"intermediate_size": 1152,
|
17 |
+
"layer_types": [
|
18 |
+
"sliding_attention",
|
19 |
+
"sliding_attention",
|
20 |
+
"sliding_attention",
|
21 |
+
"sliding_attention",
|
22 |
+
"sliding_attention",
|
23 |
+
"full_attention",
|
24 |
+
"sliding_attention",
|
25 |
+
"sliding_attention",
|
26 |
+
"sliding_attention",
|
27 |
+
"sliding_attention",
|
28 |
+
"sliding_attention",
|
29 |
+
"full_attention",
|
30 |
+
"sliding_attention",
|
31 |
+
"sliding_attention",
|
32 |
+
"sliding_attention",
|
33 |
+
"sliding_attention",
|
34 |
+
"sliding_attention",
|
35 |
+
"full_attention",
|
36 |
+
"sliding_attention",
|
37 |
+
"sliding_attention",
|
38 |
+
"sliding_attention",
|
39 |
+
"sliding_attention",
|
40 |
+
"sliding_attention",
|
41 |
+
"full_attention"
|
42 |
+
],
|
43 |
+
"max_position_embeddings": 1024,
|
44 |
+
"model_type": "gemma3_text",
|
45 |
+
"num_attention_heads": 3,
|
46 |
+
"num_hidden_layers": 24,
|
47 |
+
"num_key_value_heads": 1,
|
48 |
+
"pad_token_id": 0,
|
49 |
+
"query_pre_attn_scalar": 256,
|
50 |
+
"rms_norm_eps": 1e-06,
|
51 |
+
"rope_local_base_freq": 10000.0,
|
52 |
+
"rope_scaling": null,
|
53 |
+
"rope_theta": 1000000.0,
|
54 |
+
"sliding_window": 512,
|
55 |
+
"torch_dtype": "float32",
|
56 |
+
"transformers_version": "4.56.0.dev0",
|
57 |
+
"use_bidirectional_attention": true,
|
58 |
+
"use_cache": true,
|
59 |
+
"vocab_size": 262144
|
60 |
+
}
|
config_sentence_transformers.json
ADDED
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"model_type": "SentenceTransformer",
|
3 |
+
"__version__": {
|
4 |
+
"sentence_transformers": "5.2.0.dev0",
|
5 |
+
"transformers": "4.56.0.dev0",
|
6 |
+
"pytorch": "2.7.1+cu126"
|
7 |
+
},
|
8 |
+
"prompts": {
|
9 |
+
"query": "task: search result | query: ",
|
10 |
+
"document": "title: none | text: ",
|
11 |
+
"BitextMining": "task: search result | query: ",
|
12 |
+
"Clustering": "task: clustering | query: ",
|
13 |
+
"Classification": "task: classification | query: ",
|
14 |
+
"InstructionRetrieval": "task: code retrieval | query: ",
|
15 |
+
"MultilabelClassification": "task: classification | query: ",
|
16 |
+
"PairClassification": "task: sentence similarity | query: ",
|
17 |
+
"Reranking": "task: search result | query: ",
|
18 |
+
"Retrieval-query": "task: search result | query: ",
|
19 |
+
"Retrieval-document": "title: none | text: ",
|
20 |
+
"STS": "task: sentence similarity | query: ",
|
21 |
+
"Summarization": "task: summarization | query: "
|
22 |
+
},
|
23 |
+
"default_prompt_name": null,
|
24 |
+
"similarity_fn_name": "cosine"
|
25 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:266c19826ad0019e3565b880299a9228eac351869e1e4055b017eebbe989323c
|
3 |
+
size 1211486072
|
modules.json
ADDED
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
[
|
2 |
+
{
|
3 |
+
"idx": 0,
|
4 |
+
"name": "0",
|
5 |
+
"path": "",
|
6 |
+
"type": "sentence_transformers.models.Transformer"
|
7 |
+
},
|
8 |
+
{
|
9 |
+
"idx": 1,
|
10 |
+
"name": "1",
|
11 |
+
"path": "1_Pooling",
|
12 |
+
"type": "sentence_transformers.models.Pooling"
|
13 |
+
},
|
14 |
+
{
|
15 |
+
"idx": 2,
|
16 |
+
"name": "2",
|
17 |
+
"path": "2_Dense",
|
18 |
+
"type": "sentence_transformers.models.Dense"
|
19 |
+
},
|
20 |
+
{
|
21 |
+
"idx": 3,
|
22 |
+
"name": "3",
|
23 |
+
"path": "3_Dense",
|
24 |
+
"type": "sentence_transformers.models.Dense"
|
25 |
+
},
|
26 |
+
{
|
27 |
+
"idx": 4,
|
28 |
+
"name": "4",
|
29 |
+
"path": "4_Normalize",
|
30 |
+
"type": "sentence_transformers.models.Normalize"
|
31 |
+
}
|
32 |
+
]
|
sentence_bert_config.json
ADDED
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"max_seq_length": 1024,
|
3 |
+
"do_lower_case": false
|
4 |
+
}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"boi_token": "<start_of_image>",
|
3 |
+
"bos_token": {
|
4 |
+
"content": "<bos>",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false
|
9 |
+
},
|
10 |
+
"eoi_token": "<end_of_image>",
|
11 |
+
"eos_token": {
|
12 |
+
"content": "<eos>",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false
|
17 |
+
},
|
18 |
+
"image_token": "<image_soft_token>",
|
19 |
+
"pad_token": {
|
20 |
+
"content": "<pad>",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false
|
25 |
+
},
|
26 |
+
"unk_token": {
|
27 |
+
"content": "<unk>",
|
28 |
+
"lstrip": false,
|
29 |
+
"normalized": false,
|
30 |
+
"rstrip": false,
|
31 |
+
"single_word": false
|
32 |
+
}
|
33 |
+
}
|
tokenizer.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:adc2f14b5333aff345c0727fa2f47d949d8dbf85da000169d59c24bea6de7b61
|
3 |
+
size 33385262
|
tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1299c11d7cf632ef3b4e11937501358ada021bbdf7c47638d13c0ee982f2e79c
|
3 |
+
size 4689074
|
tokenizer_config.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|