Hugging Face's logo

Turbo-AI
/
jina-reranker-v0-base-multilingual__trimm_vocab

Text Classification
Transformers
Safetensors
cross-encoder
custom_code
Inference Endpoints
Model card Files Community
jina-reranker-v0-base-multilingual__trimm_vocab
File size: 2,083 Bytes 
b9f7351
 
 
 
 
 
 
456cd6e
b9f7351
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
 
{
  "_name_or_path": "outputs/test2024-11-28_17-03-44",
  "architectures": [
    "XLMRobertaForSequenceClassification"
  ],
  "attention_probs_dropout_prob": 0.1,
  "auto_map": {
    "AutoConfig": "jinaai/jina-reranker-v2-base-multilingual--configuration_xlm_roberta.XLMRobertaFlashConfig",
    "AutoModel": "jinaai/jina-reranker-v2-base-multilingual--modeling_xlm_roberta.XLMRobertaModel",
    "AutoModelForSequenceClassification": "jinaai/jina-reranker-v2-base-multilingual--modeling_xlm_roberta.XLMRobertaForSequenceClassification"
  },
  "bos_token_id": 0,
  "classifier_dropout": null,
  "emb_pooler": null,
  "eos_token_id": 2,
  "hidden_act": "gelu",
  "hidden_dropout_prob": 0.1,
  "hidden_size": 768,
  "id2label": {
    "0": "LABEL_0"
  },
  "initializer_range": 0.02,
  "intermediate_size": 3072,
  "label2id": {
    "LABEL_0": 0
  },
  "layer_norm_eps": 1e-05,
  "load_trained_adapters": false,
  "lora_adaptations": null,
  "lora_alpha": 1,
  "lora_dropout_p": 0.0,
  "lora_main_params_trainable": false,
  "lora_rank": 4,
  "matryoshka_dimensions": null,
  "max_position_embeddings": 1026,
  "num_attention_heads": 12,
  "num_hidden_layers": 12,
  "output_past": true,
  "pad_token_id": 1,
  "position_embedding_type": "absolute",
  "torch_dtype": "bfloat16",
  "transformers_version": "4.45.2",
  "truncate_dim": null,
  "type_vocab_size": 1,
  "use_cache": false,
  "use_flash_attn": true,
  "vocab_size": 16456,
  "vocabtrimmer": {
    "mining_config": {
      "dataset": "Turbo-AI/data-corpus",
      "dataset_column": "text",
      "dataset_name": null,
      "dataset_split": "train",
      "language": "vi",
      "min_frequency": 2,
      "target_vocab_size": null
    },
    "stats": {
      "compression_rate_embedding": 6.58234734122127,
      "compression_rate_full": 35.58222497890578,
      "parameter_size_embedding/raw": 192001536,
      "parameter_size_embedding/trimmed": 12638208,
      "parameter_size_full/raw": 278437633,
      "parameter_size_full/trimmed": 99074305,
      "vocab_size/raw": 250002,
      "vocab_size/trimmed": 16456
    }
  }
}