Upload folder using huggingface_hub
Browse files- added_tokens.json +3 -0
- config.json +45 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +9 -0
- spm.model +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +23 -0
added_tokens.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"[MASK]": 128000
|
| 3 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,45 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "models/token_searcher/deberta_small/checkpoint-10000",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"DebertaV2ForTokenClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"hidden_act": "gelu",
|
| 8 |
+
"hidden_dropout_prob": 0.1,
|
| 9 |
+
"hidden_size": 768,
|
| 10 |
+
"id2label": {
|
| 11 |
+
"0": "O",
|
| 12 |
+
"1": "B-ENT",
|
| 13 |
+
"2": "I-ENT"
|
| 14 |
+
},
|
| 15 |
+
"initializer_range": 0.02,
|
| 16 |
+
"intermediate_size": 3072,
|
| 17 |
+
"label2id": {
|
| 18 |
+
"B-ENT": 1,
|
| 19 |
+
"I-ENT": 2,
|
| 20 |
+
"O": 0
|
| 21 |
+
},
|
| 22 |
+
"layer_norm_eps": 1e-07,
|
| 23 |
+
"max_position_embeddings": 512,
|
| 24 |
+
"max_relative_positions": -1,
|
| 25 |
+
"model_type": "deberta-v2",
|
| 26 |
+
"norm_rel_ebd": "layer_norm",
|
| 27 |
+
"num_attention_heads": 12,
|
| 28 |
+
"num_hidden_layers": 6,
|
| 29 |
+
"pad_token_id": 0,
|
| 30 |
+
"pooler_dropout": 0,
|
| 31 |
+
"pooler_hidden_act": "gelu",
|
| 32 |
+
"pooler_hidden_size": 768,
|
| 33 |
+
"pos_att_type": [
|
| 34 |
+
"p2c",
|
| 35 |
+
"c2p"
|
| 36 |
+
],
|
| 37 |
+
"position_biased_input": false,
|
| 38 |
+
"position_buckets": 256,
|
| 39 |
+
"relative_attention": true,
|
| 40 |
+
"share_att_key": true,
|
| 41 |
+
"torch_dtype": "float32",
|
| 42 |
+
"transformers_version": "4.33.0.dev0",
|
| 43 |
+
"type_vocab_size": 0,
|
| 44 |
+
"vocab_size": 128100
|
| 45 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:14e783f4dd4b5e73ffa8bf419f2f3acdbdc55fbeafb631547edf051d9e79c671
|
| 3 |
+
size 565262061
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "[CLS]",
|
| 3 |
+
"cls_token": "[CLS]",
|
| 4 |
+
"eos_token": "[SEP]",
|
| 5 |
+
"mask_token": "[MASK]",
|
| 6 |
+
"pad_token": "[PAD]",
|
| 7 |
+
"sep_token": "[SEP]",
|
| 8 |
+
"unk_token": "[UNK]"
|
| 9 |
+
}
|
spm.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
|
| 3 |
+
size 2464616
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "[CLS]",
|
| 3 |
+
"clean_up_tokenization_spaces": true,
|
| 4 |
+
"cls_token": "[CLS]",
|
| 5 |
+
"do_lower_case": false,
|
| 6 |
+
"eos_token": "[SEP]",
|
| 7 |
+
"mask_token": "[MASK]",
|
| 8 |
+
"max_length": 1024,
|
| 9 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 10 |
+
"pad_to_multiple_of": null,
|
| 11 |
+
"pad_token": "[PAD]",
|
| 12 |
+
"pad_token_type_id": 0,
|
| 13 |
+
"padding_side": "right",
|
| 14 |
+
"sep_token": "[SEP]",
|
| 15 |
+
"sp_model_kwargs": {},
|
| 16 |
+
"split_by_punct": false,
|
| 17 |
+
"stride": 0,
|
| 18 |
+
"tokenizer_class": "DebertaV2Tokenizer",
|
| 19 |
+
"truncation_side": "right",
|
| 20 |
+
"truncation_strategy": "longest_first",
|
| 21 |
+
"unk_token": "[UNK]",
|
| 22 |
+
"vocab_type": "spm"
|
| 23 |
+
}
|