Hugging Face's logo

alphaedge-ai
/
multilingual-e5-small-nld-32768

Sentence Similarity
sentence-transformers
Safetensors
Dutch
bert
trimmed
text-embeddings-inference
Model card Files
xet
 Community
lbourdois commited on
Commit
d6d0d19
·
verified ·
1 Parent(s): 6ae15d6

Upload pruned model

Browse files
Files changed (4) hide show
  1. README.md +48 -39
  2. config.json +25 -25
  3. special_tokens_map.json +51 -51
  4. tokenizer_config.json +56 -56
README.md CHANGED
@@ -1,39 +1,48 @@
1
- ---
2
- pipeline_tag: sentence-similarity
3
- language: nld
4
- license: mit
5
- tags:
6
- - trimmed
7
- library_name: sentence-transformers
8
- base_model: intfloat/multilingual-e5-small
9
- base_model_relation: quantized
10
- datasets:
11
- - Lumberjackk/fineweb-2-trimming
12
- ---
13
-
14
- # multilingual-e5-small-nld-32768
15
-
16
- This model is a 70.9% smaller version of [intfloat/multilingual-e5-small](https://huggingface.co/intfloat/multilingual-e5-small)
17
- optimized for Dutch language via vocabulary pruning.
18
-
19
- **Total vocabulary size**: 32768 tokens (reduced from 250002)
20
- **Tokenizer type**: Unigram
21
- **Training samples per language**: 200000 texts
22
- **Dataset**: [Lumberjackk/fineweb-2-trimming](https://huggingface.co/datasets/Lumberjackk/fineweb-2-trimming)
23
-
24
- ## Language Distribution
25
-
26
- - **nld**: 32768 tokens
27
-
28
- This pruned model should perform similarly to the original model for Dutch with a much smaller
29
- memory footprint. However, it may not perform well for other languages as tokens not commonly used in the selected
30
- languages were removed from the vocabulary.
31
-
32
- ## Usage
33
-
34
-
35
- You can use this model with the SentenceTransformer library:
36
- ```python
37
- from sentence_transformers import SentenceTransformer
38
- model = SentenceTransformer("Lumberjackk/multilingual-e5-small-nld-32768")
39
- ```
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ pipeline_tag: sentence-similarity
3
+ language: nld
4
+ license: mit
5
+ tags:
6
+ - trimmed
7
+ library_name: sentence-transformers
8
+ base_model: intfloat/multilingual-e5-small
9
+ base_model_relation: quantized
10
+ datasets:
11
+ - Lumberjackk/fineweb-2-trimming
12
+ ---
13
+
14
+ # multilingual-e5-small-nld-32768
15
+
16
+ This model is a 70.9% smaller version of [intfloat/multilingual-e5-small](https://huggingface.co/intfloat/multilingual-e5-small)
17
+ optimized for 32768 language via vocabulary pruning.
18
+
19
+ **Total vocabulary size**: 32768 tokens (reduced from 250002)
20
+ **Tokenizer type**: Unigram
21
+ **Training samples per language**: 200000 texts
22
+ **Dataset**: [Lumberjackk/fineweb-2-trimming](https://huggingface.co/datasets/Lumberjackk/fineweb-2-trimming)
23
+
24
+ ## Language Distribution
25
+
26
+ - **nld**: 32768 tokens
27
+
28
+ This pruned model should perform similarly to the original model for 32768 with a much smaller
29
+ memory footprint. However, it may not perform well for other languages as tokens not commonly used in the selected
30
+ languages were removed from the vocabulary.
31
+
32
+ ## Usage
33
+
34
+ You can use this model with the Transformers library:
35
+ ```python
36
+ from transformers import AutoModel, AutoTokenizer
37
+
38
+ model_name = "Lumberjackk/multilingual-e5-small-nld-32768"
39
+ model = AutoModel.from_pretrained(model_name)
40
+ tokenizer = AutoTokenizer.from_pretrained(model_name)
41
+ ```
42
+
43
+ ## Model Statistics
44
+
45
+ - **Original model size**: 117.7M parameters
46
+ - **Pruned model size**: 34.2M parameters
47
+ - **Size reduction**: 70.9%
48
+ - **Vocabulary reduction**: 86.9%
config.json CHANGED
@@ -1,25 +1,25 @@
1
- {
2
- "architectures": [
3
- "BertModel"
4
- ],
5
- "attention_probs_dropout_prob": 0.1,
6
- "classifier_dropout": null,
7
- "dtype": "float32",
8
- "hidden_act": "gelu",
9
- "hidden_dropout_prob": 0.1,
10
- "hidden_size": 384,
11
- "initializer_range": 0.02,
12
- "intermediate_size": 1536,
13
- "layer_norm_eps": 1e-12,
14
- "max_position_embeddings": 512,
15
- "model_type": "bert",
16
- "num_attention_heads": 12,
17
- "num_hidden_layers": 12,
18
- "pad_token_id": 0,
19
- "position_embedding_type": "absolute",
20
- "tokenizer_class": "XLMRobertaTokenizer",
21
- "transformers_version": "4.57.1",
22
- "type_vocab_size": 2,
23
- "use_cache": true,
24
- "vocab_size": 32768
25
- }
 
1
+ {
2
+ "architectures": [
3
+ "BertModel"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "classifier_dropout": null,
7
+ "dtype": "float32",
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 384,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 1536,
13
+ "layer_norm_eps": 1e-12,
14
+ "max_position_embeddings": 512,
15
+ "model_type": "bert",
16
+ "num_attention_heads": 12,
17
+ "num_hidden_layers": 12,
18
+ "pad_token_id": 0,
19
+ "position_embedding_type": "absolute",
20
+ "tokenizer_class": "XLMRobertaTokenizer",
21
+ "transformers_version": "4.57.1",
22
+ "type_vocab_size": 2,
23
+ "use_cache": true,
24
+ "vocab_size": 32768
25
+ }
special_tokens_map.json CHANGED
@@ -1,51 +1,51 @@
1
- {
2
- "bos_token": {
3
- "content": "<s>",
4
- "lstrip": false,
5
- "normalized": false,
6
- "rstrip": false,
7
- "single_word": false
8
- },
9
- "cls_token": {
10
- "content": "<s>",
11
- "lstrip": false,
12
- "normalized": false,
13
- "rstrip": false,
14
- "single_word": false
15
- },
16
- "eos_token": {
17
- "content": "</s>",
18
- "lstrip": false,
19
- "normalized": false,
20
- "rstrip": false,
21
- "single_word": false
22
- },
23
- "mask_token": {
24
- "content": "<mask>",
25
- "lstrip": false,
26
- "normalized": false,
27
- "rstrip": false,
28
- "single_word": false
29
- },
30
- "pad_token": {
31
- "content": "<pad>",
32
- "lstrip": false,
33
- "normalized": false,
34
- "rstrip": false,
35
- "single_word": false
36
- },
37
- "sep_token": {
38
- "content": "</s>",
39
- "lstrip": false,
40
- "normalized": false,
41
- "rstrip": false,
42
- "single_word": false
43
- },
44
- "unk_token": {
45
- "content": "<unk>",
46
- "lstrip": false,
47
- "normalized": false,
48
- "rstrip": false,
49
- "single_word": false
50
- }
51
- }
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "<s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "</s>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "mask_token": {
24
+ "content": "<mask>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "pad_token": {
31
+ "content": "<pad>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "sep_token": {
38
+ "content": "</s>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ },
44
+ "unk_token": {
45
+ "content": "<unk>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false
50
+ }
51
+ }
tokenizer_config.json CHANGED
@@ -1,56 +1,56 @@
1
- {
2
- "added_tokens_decoder": {
3
- "0": {
4
- "content": "<s>",
5
- "lstrip": false,
6
- "normalized": false,
7
- "rstrip": false,
8
- "single_word": false,
9
- "special": true
10
- },
11
- "1": {
12
- "content": "<pad>",
13
- "lstrip": false,
14
- "normalized": false,
15
- "rstrip": false,
16
- "single_word": false,
17
- "special": true
18
- },
19
- "2": {
20
- "content": "</s>",
21
- "lstrip": false,
22
- "normalized": false,
23
- "rstrip": false,
24
- "single_word": false,
25
- "special": true
26
- },
27
- "3": {
28
- "content": "<unk>",
29
- "lstrip": false,
30
- "normalized": false,
31
- "rstrip": false,
32
- "single_word": false,
33
- "special": true
34
- },
35
- "32767": {
36
- "content": "<mask>",
37
- "lstrip": false,
38
- "normalized": false,
39
- "rstrip": false,
40
- "single_word": false,
41
- "special": true
42
- }
43
- },
44
- "bos_token": "<s>",
45
- "clean_up_tokenization_spaces": true,
46
- "cls_token": "<s>",
47
- "eos_token": "</s>",
48
- "extra_special_tokens": {},
49
- "mask_token": "<mask>",
50
- "model_max_length": 512,
51
- "pad_token": "<pad>",
52
- "sep_token": "</s>",
53
- "sp_model_kwargs": {},
54
- "tokenizer_class": "PreTrainedTokenizerFast",
55
- "unk_token": "<unk>"
56
- }
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<s>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<pad>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "<unk>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "32767": {
36
+ "content": "<mask>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "bos_token": "<s>",
45
+ "clean_up_tokenization_spaces": true,
46
+ "cls_token": "<s>",
47
+ "eos_token": "</s>",
48
+ "extra_special_tokens": {},
49
+ "mask_token": "<mask>",
50
+ "model_max_length": 512,
51
+ "pad_token": "<pad>",
52
+ "sep_token": "</s>",
53
+ "sp_model_kwargs": {},
54
+ "tokenizer_class": "PreTrainedTokenizerFast",
55
+ "unk_token": "<unk>"
56
+ }