add model
Browse files- added_tokens.json +1 -0
- config.json +44 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +1 -0
- spm.model +3 -0
- tokenizer_config.json +1 -0
- training_args.bin +3 -0
added_tokens.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"[MASK]": 128000}
|
config.json
ADDED
|
@@ -0,0 +1,44 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "microsoft/deberta-v2-xxlarge",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"DebertaV2ForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_head_size": 64,
|
| 7 |
+
"attention_probs_dropout_prob": 0.1,
|
| 8 |
+
"conv_act": "gelu",
|
| 9 |
+
"conv_kernel_size": 3,
|
| 10 |
+
"hidden_act": "gelu",
|
| 11 |
+
"hidden_dropout_prob": 0.1,
|
| 12 |
+
"hidden_size": 1536,
|
| 13 |
+
"id2label": {
|
| 14 |
+
"0": "LABEL_0"
|
| 15 |
+
},
|
| 16 |
+
"initializer_range": 0.02,
|
| 17 |
+
"intermediate_size": 6144,
|
| 18 |
+
"label2id": {
|
| 19 |
+
"LABEL_0": 0
|
| 20 |
+
},
|
| 21 |
+
"layer_norm_eps": 1e-07,
|
| 22 |
+
"max_position_embeddings": 512,
|
| 23 |
+
"max_relative_positions": -1,
|
| 24 |
+
"model_type": "deberta-v2",
|
| 25 |
+
"norm_rel_ebd": "layer_norm",
|
| 26 |
+
"num_attention_heads": 24,
|
| 27 |
+
"num_hidden_layers": 48,
|
| 28 |
+
"pad_token_id": 0,
|
| 29 |
+
"pooler_dropout": 0,
|
| 30 |
+
"pooler_hidden_act": "gelu",
|
| 31 |
+
"pooler_hidden_size": 1536,
|
| 32 |
+
"pos_att_type": [
|
| 33 |
+
"p2c",
|
| 34 |
+
"c2p"
|
| 35 |
+
],
|
| 36 |
+
"position_biased_input": false,
|
| 37 |
+
"position_buckets": 256,
|
| 38 |
+
"relative_attention": true,
|
| 39 |
+
"share_att_key": true,
|
| 40 |
+
"torch_dtype": "bfloat16",
|
| 41 |
+
"transformers_version": "4.17.0",
|
| 42 |
+
"type_vocab_size": 0,
|
| 43 |
+
"vocab_size": 128100
|
| 44 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4e21f6dcfa5b5da94681e0810127347400c3c90cd1ca83cc848d952c099738db
|
| 3 |
+
size 3134003815
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"bos_token": "[CLS]", "eos_token": "[SEP]", "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
|
spm.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5598d5e96f339a8d980c15f9afd405a2e5e1be7db41de3ed13b0f03fac1e8c17
|
| 3 |
+
size 2447305
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"do_lower_case": false, "bos_token": "[CLS]", "eos_token": "[SEP]", "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "split_by_punct": false, "sp_model_kwargs": {}, "vocab_type": "spm", "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "microsoft/deberta-v2-xxlarge", "tokenizer_class": "DebertaV2Tokenizer"}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:beb5500461a0dbac8865b1973d38ceecddbb2233fa67ca4ea2e2b88c4e2c4385
|
| 3 |
+
size 4399
|