SouhilOuchene commited on
Commit
2a786bf
1 Parent(s): 118d2c9

Add SetFit model

Browse files
1_Pooling/config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "word_embedding_dimension": 384,
3
  "pooling_mode_cls_token": false,
4
  "pooling_mode_mean_tokens": true,
5
  "pooling_mode_max_tokens": false,
 
1
  {
2
+ "word_embedding_dimension": 1024,
3
  "pooling_mode_cls_token": false,
4
  "pooling_mode_mean_tokens": true,
5
  "pooling_mode_max_tokens": false,
config.json CHANGED
@@ -1,26 +1,29 @@
1
  {
2
- "_name_or_path": "/root/.cache/torch/sentence_transformers/sentence-transformers_paraphrase-multilingual-MiniLM-L12-v2/",
3
  "architectures": [
4
- "BertModel"
5
  ],
6
  "attention_probs_dropout_prob": 0.1,
 
7
  "classifier_dropout": null,
 
8
  "gradient_checkpointing": false,
9
  "hidden_act": "gelu",
10
  "hidden_dropout_prob": 0.1,
11
- "hidden_size": 384,
12
  "initializer_range": 0.02,
13
- "intermediate_size": 1536,
14
- "layer_norm_eps": 1e-12,
15
- "max_position_embeddings": 512,
16
- "model_type": "bert",
17
- "num_attention_heads": 12,
18
- "num_hidden_layers": 12,
19
- "pad_token_id": 0,
 
20
  "position_embedding_type": "absolute",
21
  "torch_dtype": "float32",
22
  "transformers_version": "4.28.1",
23
- "type_vocab_size": 2,
24
  "use_cache": true,
25
- "vocab_size": 250037
26
  }
 
1
  {
2
+ "_name_or_path": "/root/.cache/torch/sentence_transformers/dangvantuan_sentence-camembert-large",
3
  "architectures": [
4
+ "CamembertModel"
5
  ],
6
  "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
  "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
  "gradient_checkpointing": false,
11
  "hidden_act": "gelu",
12
  "hidden_dropout_prob": 0.1,
13
+ "hidden_size": 1024,
14
  "initializer_range": 0.02,
15
+ "intermediate_size": 4096,
16
+ "layer_norm_eps": 1e-05,
17
+ "max_position_embeddings": 514,
18
+ "model_type": "camembert",
19
+ "num_attention_heads": 16,
20
+ "num_hidden_layers": 24,
21
+ "output_past": true,
22
+ "pad_token_id": 1,
23
  "position_embedding_type": "absolute",
24
  "torch_dtype": "float32",
25
  "transformers_version": "4.28.1",
26
+ "type_vocab_size": 1,
27
  "use_cache": true,
28
+ "vocab_size": 32005
29
  }
config_sentence_transformers.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
  "__version__": {
3
- "sentence_transformers": "2.0.0",
4
- "transformers": "4.7.0",
5
- "pytorch": "1.9.0+cu102"
6
  }
7
  }
 
1
  {
2
  "__version__": {
3
+ "sentence_transformers": "2.2.2",
4
+ "transformers": "4.28.1",
5
+ "pytorch": "2.0.0+cu118"
6
  }
7
  }
model_head.pkl CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dcfff30f5180369d54cd8f4c8a8df47eeb15f36b8828aab526a9f39ebda2dda8
3
- size 13175
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1701c157edd9142887618177c4eadff39a8130f8b8557a27bafeb2c8818de119
3
+ size 33655
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8fbc82b78933613e3ebcec889190807f528973c19b23e78daefaba85083642bc
3
- size 470686253
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de9abdc1c6a7b4c9b0d938557abfdd52bebd4e5b49d660ea41b6c120c71846ec
3
+ size 1346782317
sentence_bert_config.json CHANGED
@@ -1,4 +1,4 @@
1
  {
2
- "max_seq_length": 128,
3
  "do_lower_case": false
4
  }
 
1
  {
2
+ "max_seq_length": 514,
3
  "do_lower_case": false
4
  }
sentencepiece.bpe.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f98f266fdc548c94216aaadc13ffaaafacf0c8793303e2195322d954549ea261
3
+ size 808767
special_tokens_map.json CHANGED
@@ -1,11 +1,15 @@
1
  {
 
 
 
 
2
  "bos_token": "<s>",
3
  "cls_token": "<s>",
4
  "eos_token": "</s>",
5
  "mask_token": {
6
  "content": "<mask>",
7
  "lstrip": true,
8
- "normalized": false,
9
  "rstrip": false,
10
  "single_word": false
11
  },
 
1
  {
2
+ "additional_special_tokens": [
3
+ "<s>NOTUSED",
4
+ "</s>NOTUSED"
5
+ ],
6
  "bos_token": "<s>",
7
  "cls_token": "<s>",
8
  "eos_token": "</s>",
9
  "mask_token": {
10
  "content": "<mask>",
11
  "lstrip": true,
12
+ "normalized": true,
13
  "rstrip": false,
14
  "single_word": false
15
  },
tokenizer.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b60b6b43406a48bf3638526314f3d232d97058bc93472ff2de930d43686fa441
3
- size 17082913
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da4a19b41f008689418c2e004192b6eeca0292138a0ef0c775d7dfaf70584a0c
3
+ size 2418775
tokenizer_config.json CHANGED
@@ -1,8 +1,11 @@
1
  {
 
 
 
 
2
  "bos_token": "<s>",
3
  "clean_up_tokenization_spaces": true,
4
  "cls_token": "<s>",
5
- "do_lower_case": true,
6
  "eos_token": "</s>",
7
  "mask_token": {
8
  "__type": "AddedToken",
@@ -12,11 +15,10 @@
12
  "rstrip": false,
13
  "single_word": false
14
  },
15
- "model_max_length": 512,
16
  "pad_token": "<pad>",
17
  "sep_token": "</s>",
18
- "strip_accents": null,
19
- "tokenize_chinese_chars": true,
20
- "tokenizer_class": "BertTokenizer",
21
  "unk_token": "<unk>"
22
  }
 
1
  {
2
+ "additional_special_tokens": [
3
+ "<s>NOTUSED",
4
+ "</s>NOTUSED"
5
+ ],
6
  "bos_token": "<s>",
7
  "clean_up_tokenization_spaces": true,
8
  "cls_token": "<s>",
 
9
  "eos_token": "</s>",
10
  "mask_token": {
11
  "__type": "AddedToken",
 
15
  "rstrip": false,
16
  "single_word": false
17
  },
18
+ "model_max_length": 1000000000000000019884624838656,
19
  "pad_token": "<pad>",
20
  "sep_token": "</s>",
21
+ "sp_model_kwargs": {},
22
+ "tokenizer_class": "CamembertTokenizer",
 
23
  "unk_token": "<unk>"
24
  }