florianhoenicke commited on
Commit
2bc8028
1 Parent(s): 7e9924f

feat: push custom model

Browse files
1_Pooling/config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "word_embedding_dimension": 512,
3
+ "pooling_mode_cls_token": true,
4
+ "pooling_mode_mean_tokens": false,
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
+ }
README.md ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ # e-commerce-1000-64-16-jinaai_jina-embeddings-v2-small-en-1000_9062874564
2
+
3
+ ## Model Description
4
+
5
+ e-commerce-1000-64-16-jinaai_jina-embeddings-v2-small-en-1000_9062874564 is a fine-tuned version of jinaai/jina-embeddings-v2-small-en designed for a specific domain.
6
+
7
+ ## Use Case
8
+ This model is designed to support various applications in natural language processing and understanding.
9
+
10
+ ## Associated Dataset
11
+
12
+ This the dataset for this model can be found [**here**](https://huggingface.co/datasets/florianhoenicke/e-commerce-1000-64-16-jinaai_jina-embeddings-v2-small-en-1000_9062874564).
13
+
14
+ ## How to Use
15
+
16
+ This model can be easily integrated into your NLP pipeline for tasks such as text classification, sentiment analysis, entity recognition, and more. Here's a simple example to get you started:
17
+
18
+ ```python
19
+ from transformers import AutoModel, AutoTokenizer
20
+
21
+ llm_name = "e-commerce-1000-64-16-jinaai_jina-embeddings-v2-small-en-1000_9062874564"
22
+ tokenizer = AutoTokenizer.from_pretrained(llm_name)
23
+ model = AutoModel.from_pretrained(llm_name)
24
+
25
+ tokens = tokenizer("Your text here", return_tensors="pt")
26
+ embedding = model(**tokens)
27
+ ```
config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "mytmp/finetuned_model",
3
+ "architectures": [
4
+ "BertModel"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.0,
7
+ "auto_map": {
8
+ "AutoConfig": "jinaai/jina-bert-implementation--configuration_bert.JinaBertConfig",
9
+ "AutoModel": "jinaai/jina-bert-implementation--modeling_bert.JinaBertModel",
10
+ "AutoModelForMaskedLM": "jinaai/jina-bert-implementation--modeling_bert.JinaBertForMaskedLM",
11
+ "AutoModelForSequenceClassification": "jinaai/jina-bert-implementation--modeling_bert.JinaBertForSequenceClassification"
12
+ },
13
+ "classifier_dropout": null,
14
+ "emb_pooler": "mean",
15
+ "feed_forward_type": "geglu",
16
+ "gradient_checkpointing": false,
17
+ "hidden_act": "gelu",
18
+ "hidden_dropout_prob": 0.1,
19
+ "hidden_size": 512,
20
+ "initializer_range": 0.02,
21
+ "intermediate_size": 2048,
22
+ "layer_norm_eps": 1e-12,
23
+ "max_position_embeddings": 8192,
24
+ "model_max_length": 8192,
25
+ "model_type": "bert",
26
+ "num_attention_heads": 8,
27
+ "num_hidden_layers": 4,
28
+ "pad_token_id": 0,
29
+ "position_embedding_type": "alibi",
30
+ "torch_dtype": "float32",
31
+ "transformers_version": "4.39.3",
32
+ "type_vocab_size": 2,
33
+ "use_cache": true,
34
+ "vocab_size": 30528
35
+ }
config_sentence_transformers.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "__version__": {
3
+ "sentence_transformers": "2.6.1",
4
+ "transformers": "4.39.3",
5
+ "pytorch": "1.11.0+cpu"
6
+ },
7
+ "prompts": {},
8
+ "default_prompt_name": null
9
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:99eb87513830f0986e9b5d534a285bcb59d42cd8b14f8c1b1b65bd26c5a4db7e
3
+ size 130803392
modules.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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_Normalize",
18
+ "type": "sentence_transformers.models.Normalize"
19
+ }
20
+ ]
sentence_bert_config.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "max_seq_length": 8192,
3
+ "do_lower_case": false
4
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": {
3
+ "content": "[CLS]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "mask_token": {
10
+ "content": "[MASK]",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "[PAD]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "sep_token": {
24
+ "content": "[SEP]",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "unk_token": {
31
+ "content": "[UNK]",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ }
37
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "100": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "101": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "102": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "103": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "clean_up_tokenization_spaces": true,
45
+ "cls_token": "[CLS]",
46
+ "do_basic_tokenize": true,
47
+ "do_lower_case": true,
48
+ "mask_token": "[MASK]",
49
+ "model_max_length": 2147483648,
50
+ "never_split": null,
51
+ "pad_token": "[PAD]",
52
+ "sep_token": "[SEP]",
53
+ "strip_accents": null,
54
+ "tokenize_chinese_chars": true,
55
+ "tokenizer_class": "BertTokenizer",
56
+ "unk_token": "[UNK]"
57
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ca8851404309b24e494567b08c6191c502cbab6e91a825d02cba5a2adcf2be6
3
+ size 4655
vocab.txt ADDED
The diff for this file is too large to render. See raw diff