Syed Junaid Iqbal
commited on
Commit
•
2793341
1
Parent(s):
1bd5cae
added embeddings
Browse files- embeddings/fast-bge-small-en-v1.5/config.json +31 -0
- embeddings/fast-bge-small-en-v1.5/model.onnx +3 -0
- embeddings/fast-bge-small-en-v1.5/ort_config.json +38 -0
- embeddings/fast-bge-small-en-v1.5/special_tokens_map.json +7 -0
- embeddings/fast-bge-small-en-v1.5/tokenizer.json +0 -0
- embeddings/fast-bge-small-en-v1.5/tokenizer_config.json +15 -0
- embeddings/fast-bge-small-en-v1.5/vocab.txt +0 -0
embeddings/fast-bge-small-en-v1.5/config.json
ADDED
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "BAAI/bge-small-en-v1.5",
|
3 |
+
"architectures": [
|
4 |
+
"BertModel"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"hidden_act": "gelu",
|
9 |
+
"hidden_dropout_prob": 0.1,
|
10 |
+
"hidden_size": 384,
|
11 |
+
"id2label": {
|
12 |
+
"0": "LABEL_0"
|
13 |
+
},
|
14 |
+
"initializer_range": 0.02,
|
15 |
+
"intermediate_size": 1536,
|
16 |
+
"label2id": {
|
17 |
+
"LABEL_0": 0
|
18 |
+
},
|
19 |
+
"layer_norm_eps": 1e-12,
|
20 |
+
"max_position_embeddings": 512,
|
21 |
+
"model_type": "bert",
|
22 |
+
"num_attention_heads": 12,
|
23 |
+
"num_hidden_layers": 12,
|
24 |
+
"pad_token_id": 0,
|
25 |
+
"position_embedding_type": "absolute",
|
26 |
+
"torch_dtype": "float32",
|
27 |
+
"transformers_version": "4.33.2",
|
28 |
+
"type_vocab_size": 2,
|
29 |
+
"use_cache": true,
|
30 |
+
"vocab_size": 30522
|
31 |
+
}
|
embeddings/fast-bge-small-en-v1.5/model.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:20e3bd678b8e67a722f151f3ee1e3827fc3f230839c0d57c025a3753cefa6b2e
|
3 |
+
size 132883455
|
embeddings/fast-bge-small-en-v1.5/ort_config.json
ADDED
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"one_external_file": true,
|
3 |
+
"opset": null,
|
4 |
+
"optimization": {
|
5 |
+
"disable_attention": null,
|
6 |
+
"disable_attention_fusion": false,
|
7 |
+
"disable_bias_gelu": null,
|
8 |
+
"disable_bias_gelu_fusion": false,
|
9 |
+
"disable_bias_skip_layer_norm": null,
|
10 |
+
"disable_bias_skip_layer_norm_fusion": false,
|
11 |
+
"disable_embed_layer_norm": true,
|
12 |
+
"disable_embed_layer_norm_fusion": true,
|
13 |
+
"disable_gelu": null,
|
14 |
+
"disable_gelu_fusion": false,
|
15 |
+
"disable_group_norm_fusion": true,
|
16 |
+
"disable_layer_norm": null,
|
17 |
+
"disable_layer_norm_fusion": false,
|
18 |
+
"disable_packed_kv": true,
|
19 |
+
"disable_shape_inference": false,
|
20 |
+
"disable_skip_layer_norm": null,
|
21 |
+
"disable_skip_layer_norm_fusion": false,
|
22 |
+
"enable_gelu_approximation": true,
|
23 |
+
"enable_gemm_fast_gelu_fusion": false,
|
24 |
+
"enable_transformers_specific_optimizations": true,
|
25 |
+
"fp16": false,
|
26 |
+
"no_attention_mask": false,
|
27 |
+
"optimization_level": 2,
|
28 |
+
"optimize_for_gpu": false,
|
29 |
+
"optimize_with_onnxruntime_only": null,
|
30 |
+
"use_mask_index": false,
|
31 |
+
"use_multi_head_attention": false,
|
32 |
+
"use_raw_attention_mask": false
|
33 |
+
},
|
34 |
+
"optimum_version": "1.13.2",
|
35 |
+
"quantization": {},
|
36 |
+
"transformers_version": "4.33.2",
|
37 |
+
"use_external_data_format": false
|
38 |
+
}
|
embeddings/fast-bge-small-en-v1.5/special_tokens_map.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": "[CLS]",
|
3 |
+
"mask_token": "[MASK]",
|
4 |
+
"pad_token": "[PAD]",
|
5 |
+
"sep_token": "[SEP]",
|
6 |
+
"unk_token": "[UNK]"
|
7 |
+
}
|
embeddings/fast-bge-small-en-v1.5/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
embeddings/fast-bge-small-en-v1.5/tokenizer_config.json
ADDED
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"clean_up_tokenization_spaces": true,
|
3 |
+
"cls_token": "[CLS]",
|
4 |
+
"do_basic_tokenize": true,
|
5 |
+
"do_lower_case": true,
|
6 |
+
"mask_token": "[MASK]",
|
7 |
+
"model_max_length": 1000000000000000019884624838656,
|
8 |
+
"never_split": null,
|
9 |
+
"pad_token": "[PAD]",
|
10 |
+
"sep_token": "[SEP]",
|
11 |
+
"strip_accents": null,
|
12 |
+
"tokenize_chinese_chars": true,
|
13 |
+
"tokenizer_class": "BertTokenizer",
|
14 |
+
"unk_token": "[UNK]"
|
15 |
+
}
|
embeddings/fast-bge-small-en-v1.5/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|