v22.0: InfoNCE contrastive loss, temperature annealing, 99.87% recall
Browse files- README.md +111 -0
- added_tokens.json +3 -0
- config.json +45 -0
- model.safetensors +3 -0
- special_tokens_map.json +51 -0
- tokenizer.json +0 -0
- tokenizer_config.json +322 -0
- vocab.txt +0 -0
README.md
ADDED
|
@@ -0,0 +1,111 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
language:
|
| 3 |
+
- ko
|
| 4 |
+
license: apache-2.0
|
| 5 |
+
library_name: transformers
|
| 6 |
+
tags:
|
| 7 |
+
- sparse-retrieval
|
| 8 |
+
- splade
|
| 9 |
+
- opensearch
|
| 10 |
+
- korean
|
| 11 |
+
- neural-sparse
|
| 12 |
+
- infonce
|
| 13 |
+
pipeline_tag: feature-extraction
|
| 14 |
+
---
|
| 15 |
+
|
| 16 |
+
# Korean Neural Sparse Encoder v22.0
|
| 17 |
+
|
| 18 |
+
한국어 신경망 희소 인코더 - OpenSearch Neural Sparse 검색을 위한 SPLADE 기반 모델
|
| 19 |
+
|
| 20 |
+
## Model Description
|
| 21 |
+
|
| 22 |
+
This model is a SPLADE-based sparse encoder fine-tuned for Korean text, specifically optimized for:
|
| 23 |
+
- Legal domain terminology
|
| 24 |
+
- Medical domain terminology
|
| 25 |
+
- General Korean synonym expansion
|
| 26 |
+
|
| 27 |
+
### v22.0 Improvements (over v21.4)
|
| 28 |
+
|
| 29 |
+
- **InfoNCE Contrastive Loss**: In-batch negatives for better discriminative representations
|
| 30 |
+
- **Temperature Annealing**: 0.07 → 0.05 → 0.03 for progressively sharper discrimination
|
| 31 |
+
- **Expanded Training Data**: 840,859 total triplets across 3 phases
|
| 32 |
+
- **Curriculum Learning**: 3-phase training with dynamic InfoNCE weight increase
|
| 33 |
+
|
| 34 |
+
### Training Results
|
| 35 |
+
|
| 36 |
+
| Metric | v21.4 | v22.0 |
|
| 37 |
+
|--------|-------|-------|
|
| 38 |
+
| Training Recall@1 | - | **99.87%** |
|
| 39 |
+
| Training MRR | - | **0.9994** |
|
| 40 |
+
| General Terms Recall | 78.7% | **81.5%** |
|
| 41 |
+
| Garbage Outputs | 0/5 | 0/5 |
|
| 42 |
+
|
| 43 |
+
### Training Phases
|
| 44 |
+
|
| 45 |
+
| Phase | Epochs | Data Size | Temperature | InfoNCE Weight |
|
| 46 |
+
|-------|--------|-----------|-------------|----------------|
|
| 47 |
+
| Phase 1 (Single-term) | 1-10 | 66,685 | 0.07 | 1.0 |
|
| 48 |
+
| Phase 2 (Balanced) | 11-20 | 224,177 | 0.05 | 1.5 |
|
| 49 |
+
| Phase 3 (Full) | 21-30 | 549,997 | 0.03 | 2.0 |
|
| 50 |
+
|
| 51 |
+
## Usage
|
| 52 |
+
|
| 53 |
+
```python
|
| 54 |
+
from transformers import AutoTokenizer, AutoModelForMaskedLM
|
| 55 |
+
import torch
|
| 56 |
+
import torch.nn as nn
|
| 57 |
+
|
| 58 |
+
# Load model
|
| 59 |
+
tokenizer = AutoTokenizer.from_pretrained("sewoong/korean-neural-sparse-encoder-v21.4")
|
| 60 |
+
model = AutoModelForMaskedLM.from_pretrained("sewoong/korean-neural-sparse-encoder-v21.4")
|
| 61 |
+
|
| 62 |
+
# Encode text
|
| 63 |
+
def encode(text):
|
| 64 |
+
inputs = tokenizer(text, return_tensors="pt", padding=True, truncation=True, max_length=64)
|
| 65 |
+
with torch.no_grad():
|
| 66 |
+
outputs = model(**inputs)
|
| 67 |
+
logits = outputs.logits
|
| 68 |
+
relu = nn.ReLU()
|
| 69 |
+
token_scores = torch.log1p(relu(logits))
|
| 70 |
+
mask = inputs["attention_mask"].unsqueeze(-1).float()
|
| 71 |
+
sparse_repr = (token_scores * mask).max(dim=1).values[0]
|
| 72 |
+
return sparse_repr
|
| 73 |
+
|
| 74 |
+
# Example
|
| 75 |
+
sparse = encode("당뇨병 치료 방법")
|
| 76 |
+
top_values, top_indices = sparse.topk(10)
|
| 77 |
+
for idx, val in zip(top_indices, top_values):
|
| 78 |
+
print(f"{tokenizer.decode([idx])}: {val:.4f}")
|
| 79 |
+
```
|
| 80 |
+
|
| 81 |
+
### Example Expansions
|
| 82 |
+
|
| 83 |
+
| Query | Top Expansions |
|
| 84 |
+
|-------|----------------|
|
| 85 |
+
| 손해배상 | 손해, 피해, 배상, 손실, 보상, 소송, 위자료 |
|
| 86 |
+
| 인공지능 | AI, 지능, 컴퓨터, IT, 로봇, 알고리즘 |
|
| 87 |
+
| 당뇨병 | 당뇨, 혈당, 인슐린, 비만, 콜레스테롤 |
|
| 88 |
+
| 계약서 | 계약, 약정, 협약, 합의, 계약금, 약관 |
|
| 89 |
+
|
| 90 |
+
## OpenSearch Integration
|
| 91 |
+
|
| 92 |
+
This model is designed to work with OpenSearch Neural Sparse Search. See the [OpenSearch documentation](https://opensearch.org/docs/latest/search-plugins/neural-sparse-search/) for integration details.
|
| 93 |
+
|
| 94 |
+
## Base Model
|
| 95 |
+
|
| 96 |
+
- **Base**: skt/A.X-Encoder-base
|
| 97 |
+
- **Parameters**: 149,372,240
|
| 98 |
+
- **Vocabulary**: 50,000 tokens
|
| 99 |
+
- **Max Length**: 64 tokens
|
| 100 |
+
|
| 101 |
+
## Citation
|
| 102 |
+
|
| 103 |
+
```bibtex
|
| 104 |
+
@misc{korean-neural-sparse-v22.0,
|
| 105 |
+
author = {Sewoong Lee},
|
| 106 |
+
title = {Korean Neural Sparse Encoder v22.0},
|
| 107 |
+
year = {2025},
|
| 108 |
+
publisher = {HuggingFace},
|
| 109 |
+
url = {https://huggingface.co/sewoong/korean-neural-sparse-encoder-v21.4}
|
| 110 |
+
}
|
| 111 |
+
```
|
added_tokens.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"<pad>": 49999
|
| 3 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,45 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"ModernBertForMaskedLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_bias": false,
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 0,
|
| 8 |
+
"classifier_activation": "gelu",
|
| 9 |
+
"classifier_bias": false,
|
| 10 |
+
"classifier_dropout": 0.0,
|
| 11 |
+
"classifier_pooling": "mean",
|
| 12 |
+
"cls_token_id": 0,
|
| 13 |
+
"decoder_bias": true,
|
| 14 |
+
"deterministic_flash_attn": false,
|
| 15 |
+
"dtype": "float32",
|
| 16 |
+
"embedding_dropout": 0.0,
|
| 17 |
+
"eos_token_id": 1,
|
| 18 |
+
"global_attn_every_n_layers": 3,
|
| 19 |
+
"global_rope_theta": 160000,
|
| 20 |
+
"gradient_checkpointing": false,
|
| 21 |
+
"hidden_activation": "gelu",
|
| 22 |
+
"hidden_size": 768,
|
| 23 |
+
"initializer_cutoff_factor": 2.0,
|
| 24 |
+
"initializer_range": 0.02,
|
| 25 |
+
"intermediate_size": 1152,
|
| 26 |
+
"layer_norm_eps": 1e-05,
|
| 27 |
+
"local_attention": 128,
|
| 28 |
+
"local_rope_theta": 10000.0,
|
| 29 |
+
"max_position_embeddings": 16384,
|
| 30 |
+
"mlp_bias": false,
|
| 31 |
+
"mlp_dropout": 0.0,
|
| 32 |
+
"model_type": "modernbert",
|
| 33 |
+
"norm_bias": false,
|
| 34 |
+
"norm_eps": 1e-05,
|
| 35 |
+
"num_attention_heads": 12,
|
| 36 |
+
"num_hidden_layers": 22,
|
| 37 |
+
"pad_token_id": 49999,
|
| 38 |
+
"position_embedding_type": "absolute",
|
| 39 |
+
"repad_logits_with_grad": false,
|
| 40 |
+
"sep_token_id": 1,
|
| 41 |
+
"sparse_pred_ignore_index": -100,
|
| 42 |
+
"sparse_prediction": false,
|
| 43 |
+
"transformers_version": "4.57.1",
|
| 44 |
+
"vocab_size": 50000
|
| 45 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:46a1ef6bab97ccff884781c54d261156acbeee5750180dfe1264acc600fa6834
|
| 3 |
+
size 597503064
|
special_tokens_map.json
ADDED
|
@@ -0,0 +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": "<cls>",
|
| 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": "<sep>",
|
| 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.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,322 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": "<\\s>",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "<unk>",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"3": {
|
| 28 |
+
"content": "<sep>",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"4": {
|
| 36 |
+
"content": "<mask>",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
},
|
| 43 |
+
"5": {
|
| 44 |
+
"content": "<cls>",
|
| 45 |
+
"lstrip": false,
|
| 46 |
+
"normalized": false,
|
| 47 |
+
"rstrip": false,
|
| 48 |
+
"single_word": false,
|
| 49 |
+
"special": true
|
| 50 |
+
},
|
| 51 |
+
"6": {
|
| 52 |
+
"content": "<unused0>",
|
| 53 |
+
"lstrip": false,
|
| 54 |
+
"normalized": false,
|
| 55 |
+
"rstrip": false,
|
| 56 |
+
"single_word": false,
|
| 57 |
+
"special": true
|
| 58 |
+
},
|
| 59 |
+
"7": {
|
| 60 |
+
"content": "<unused1>",
|
| 61 |
+
"lstrip": false,
|
| 62 |
+
"normalized": false,
|
| 63 |
+
"rstrip": false,
|
| 64 |
+
"single_word": false,
|
| 65 |
+
"special": true
|
| 66 |
+
},
|
| 67 |
+
"8": {
|
| 68 |
+
"content": "<unused2>",
|
| 69 |
+
"lstrip": false,
|
| 70 |
+
"normalized": false,
|
| 71 |
+
"rstrip": false,
|
| 72 |
+
"single_word": false,
|
| 73 |
+
"special": true
|
| 74 |
+
},
|
| 75 |
+
"9": {
|
| 76 |
+
"content": "<unused3>",
|
| 77 |
+
"lstrip": false,
|
| 78 |
+
"normalized": false,
|
| 79 |
+
"rstrip": false,
|
| 80 |
+
"single_word": false,
|
| 81 |
+
"special": true
|
| 82 |
+
},
|
| 83 |
+
"10": {
|
| 84 |
+
"content": "<unused4>",
|
| 85 |
+
"lstrip": false,
|
| 86 |
+
"normalized": false,
|
| 87 |
+
"rstrip": false,
|
| 88 |
+
"single_word": false,
|
| 89 |
+
"special": true
|
| 90 |
+
},
|
| 91 |
+
"11": {
|
| 92 |
+
"content": "<unused5>",
|
| 93 |
+
"lstrip": false,
|
| 94 |
+
"normalized": false,
|
| 95 |
+
"rstrip": false,
|
| 96 |
+
"single_word": false,
|
| 97 |
+
"special": true
|
| 98 |
+
},
|
| 99 |
+
"12": {
|
| 100 |
+
"content": "<unused6>",
|
| 101 |
+
"lstrip": false,
|
| 102 |
+
"normalized": false,
|
| 103 |
+
"rstrip": false,
|
| 104 |
+
"single_word": false,
|
| 105 |
+
"special": true
|
| 106 |
+
},
|
| 107 |
+
"13": {
|
| 108 |
+
"content": "<unused7>",
|
| 109 |
+
"lstrip": false,
|
| 110 |
+
"normalized": false,
|
| 111 |
+
"rstrip": false,
|
| 112 |
+
"single_word": false,
|
| 113 |
+
"special": true
|
| 114 |
+
},
|
| 115 |
+
"14": {
|
| 116 |
+
"content": "<unused8>",
|
| 117 |
+
"lstrip": false,
|
| 118 |
+
"normalized": false,
|
| 119 |
+
"rstrip": false,
|
| 120 |
+
"single_word": false,
|
| 121 |
+
"special": true
|
| 122 |
+
},
|
| 123 |
+
"15": {
|
| 124 |
+
"content": "<unused9>",
|
| 125 |
+
"lstrip": false,
|
| 126 |
+
"normalized": false,
|
| 127 |
+
"rstrip": false,
|
| 128 |
+
"single_word": false,
|
| 129 |
+
"special": true
|
| 130 |
+
},
|
| 131 |
+
"16": {
|
| 132 |
+
"content": "<unused10>",
|
| 133 |
+
"lstrip": false,
|
| 134 |
+
"normalized": false,
|
| 135 |
+
"rstrip": false,
|
| 136 |
+
"single_word": false,
|
| 137 |
+
"special": true
|
| 138 |
+
},
|
| 139 |
+
"17": {
|
| 140 |
+
"content": "<unused11>",
|
| 141 |
+
"lstrip": false,
|
| 142 |
+
"normalized": false,
|
| 143 |
+
"rstrip": false,
|
| 144 |
+
"single_word": false,
|
| 145 |
+
"special": true
|
| 146 |
+
},
|
| 147 |
+
"18": {
|
| 148 |
+
"content": "<unused12>",
|
| 149 |
+
"lstrip": false,
|
| 150 |
+
"normalized": false,
|
| 151 |
+
"rstrip": false,
|
| 152 |
+
"single_word": false,
|
| 153 |
+
"special": true
|
| 154 |
+
},
|
| 155 |
+
"19": {
|
| 156 |
+
"content": "<unused13>",
|
| 157 |
+
"lstrip": false,
|
| 158 |
+
"normalized": false,
|
| 159 |
+
"rstrip": false,
|
| 160 |
+
"single_word": false,
|
| 161 |
+
"special": true
|
| 162 |
+
},
|
| 163 |
+
"20": {
|
| 164 |
+
"content": "<unused14>",
|
| 165 |
+
"lstrip": false,
|
| 166 |
+
"normalized": false,
|
| 167 |
+
"rstrip": false,
|
| 168 |
+
"single_word": false,
|
| 169 |
+
"special": true
|
| 170 |
+
},
|
| 171 |
+
"21": {
|
| 172 |
+
"content": "<unused15>",
|
| 173 |
+
"lstrip": false,
|
| 174 |
+
"normalized": false,
|
| 175 |
+
"rstrip": false,
|
| 176 |
+
"single_word": false,
|
| 177 |
+
"special": true
|
| 178 |
+
},
|
| 179 |
+
"22": {
|
| 180 |
+
"content": "<unused16>",
|
| 181 |
+
"lstrip": false,
|
| 182 |
+
"normalized": false,
|
| 183 |
+
"rstrip": false,
|
| 184 |
+
"single_word": false,
|
| 185 |
+
"special": true
|
| 186 |
+
},
|
| 187 |
+
"23": {
|
| 188 |
+
"content": "<unused17>",
|
| 189 |
+
"lstrip": false,
|
| 190 |
+
"normalized": false,
|
| 191 |
+
"rstrip": false,
|
| 192 |
+
"single_word": false,
|
| 193 |
+
"special": true
|
| 194 |
+
},
|
| 195 |
+
"24": {
|
| 196 |
+
"content": "<unused18>",
|
| 197 |
+
"lstrip": false,
|
| 198 |
+
"normalized": false,
|
| 199 |
+
"rstrip": false,
|
| 200 |
+
"single_word": false,
|
| 201 |
+
"special": true
|
| 202 |
+
},
|
| 203 |
+
"25": {
|
| 204 |
+
"content": "<unused19>",
|
| 205 |
+
"lstrip": false,
|
| 206 |
+
"normalized": false,
|
| 207 |
+
"rstrip": false,
|
| 208 |
+
"single_word": false,
|
| 209 |
+
"special": true
|
| 210 |
+
},
|
| 211 |
+
"26": {
|
| 212 |
+
"content": "<unused20>",
|
| 213 |
+
"lstrip": false,
|
| 214 |
+
"normalized": false,
|
| 215 |
+
"rstrip": false,
|
| 216 |
+
"single_word": false,
|
| 217 |
+
"special": true
|
| 218 |
+
},
|
| 219 |
+
"27": {
|
| 220 |
+
"content": "<unused21>",
|
| 221 |
+
"lstrip": false,
|
| 222 |
+
"normalized": false,
|
| 223 |
+
"rstrip": false,
|
| 224 |
+
"single_word": false,
|
| 225 |
+
"special": true
|
| 226 |
+
},
|
| 227 |
+
"28": {
|
| 228 |
+
"content": "<unused22>",
|
| 229 |
+
"lstrip": false,
|
| 230 |
+
"normalized": false,
|
| 231 |
+
"rstrip": false,
|
| 232 |
+
"single_word": false,
|
| 233 |
+
"special": true
|
| 234 |
+
},
|
| 235 |
+
"29": {
|
| 236 |
+
"content": "<unused23>",
|
| 237 |
+
"lstrip": false,
|
| 238 |
+
"normalized": false,
|
| 239 |
+
"rstrip": false,
|
| 240 |
+
"single_word": false,
|
| 241 |
+
"special": true
|
| 242 |
+
},
|
| 243 |
+
"30": {
|
| 244 |
+
"content": "<unused24>",
|
| 245 |
+
"lstrip": false,
|
| 246 |
+
"normalized": false,
|
| 247 |
+
"rstrip": false,
|
| 248 |
+
"single_word": false,
|
| 249 |
+
"special": true
|
| 250 |
+
},
|
| 251 |
+
"31": {
|
| 252 |
+
"content": "<unused25>",
|
| 253 |
+
"lstrip": false,
|
| 254 |
+
"normalized": false,
|
| 255 |
+
"rstrip": false,
|
| 256 |
+
"single_word": false,
|
| 257 |
+
"special": true
|
| 258 |
+
},
|
| 259 |
+
"32": {
|
| 260 |
+
"content": "<unused26>",
|
| 261 |
+
"lstrip": false,
|
| 262 |
+
"normalized": false,
|
| 263 |
+
"rstrip": false,
|
| 264 |
+
"single_word": false,
|
| 265 |
+
"special": true
|
| 266 |
+
},
|
| 267 |
+
"33": {
|
| 268 |
+
"content": "<unused27>",
|
| 269 |
+
"lstrip": false,
|
| 270 |
+
"normalized": false,
|
| 271 |
+
"rstrip": false,
|
| 272 |
+
"single_word": false,
|
| 273 |
+
"special": true
|
| 274 |
+
},
|
| 275 |
+
"34": {
|
| 276 |
+
"content": "<unused28>",
|
| 277 |
+
"lstrip": false,
|
| 278 |
+
"normalized": false,
|
| 279 |
+
"rstrip": false,
|
| 280 |
+
"single_word": false,
|
| 281 |
+
"special": true
|
| 282 |
+
},
|
| 283 |
+
"35": {
|
| 284 |
+
"content": "<unused29>",
|
| 285 |
+
"lstrip": false,
|
| 286 |
+
"normalized": false,
|
| 287 |
+
"rstrip": false,
|
| 288 |
+
"single_word": false,
|
| 289 |
+
"special": true
|
| 290 |
+
},
|
| 291 |
+
"36": {
|
| 292 |
+
"content": "<unused30>",
|
| 293 |
+
"lstrip": false,
|
| 294 |
+
"normalized": false,
|
| 295 |
+
"rstrip": false,
|
| 296 |
+
"single_word": false,
|
| 297 |
+
"special": true
|
| 298 |
+
},
|
| 299 |
+
"49999": {
|
| 300 |
+
"content": "<pad>",
|
| 301 |
+
"lstrip": false,
|
| 302 |
+
"normalized": false,
|
| 303 |
+
"rstrip": false,
|
| 304 |
+
"single_word": false,
|
| 305 |
+
"special": true
|
| 306 |
+
}
|
| 307 |
+
},
|
| 308 |
+
"bos_token": "<s>",
|
| 309 |
+
"clean_up_tokenization_spaces": true,
|
| 310 |
+
"cls_token": "<cls>",
|
| 311 |
+
"do_lower_case": false,
|
| 312 |
+
"eos_token": "<\\s>",
|
| 313 |
+
"extra_special_tokens": {},
|
| 314 |
+
"mask_token": "<mask>",
|
| 315 |
+
"model_max_length": 1024,
|
| 316 |
+
"pad_token": "<pad>",
|
| 317 |
+
"sep_token": "<sep>",
|
| 318 |
+
"strip_accents": null,
|
| 319 |
+
"tokenize_chinese_chars": true,
|
| 320 |
+
"tokenizer_class": "BertTokenizer",
|
| 321 |
+
"unk_token": "<unk>"
|
| 322 |
+
}
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|