Upload classifier_v1 backbone, tokenizer, and head weights
Browse files
classifier_v1/backbone/config.json
ADDED
|
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"DebertaModel"
|
| 4 |
+
],
|
| 5 |
+
"attention_probs_dropout_prob": 0.1,
|
| 6 |
+
"bos_token_id": null,
|
| 7 |
+
"dtype": "float32",
|
| 8 |
+
"eos_token_id": null,
|
| 9 |
+
"hidden_act": "gelu",
|
| 10 |
+
"hidden_dropout_prob": 0.1,
|
| 11 |
+
"hidden_size": 768,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 3072,
|
| 14 |
+
"layer_norm_eps": 1e-07,
|
| 15 |
+
"legacy": true,
|
| 16 |
+
"max_position_embeddings": 512,
|
| 17 |
+
"max_relative_positions": -1,
|
| 18 |
+
"model_type": "deberta",
|
| 19 |
+
"num_attention_heads": 12,
|
| 20 |
+
"num_hidden_layers": 12,
|
| 21 |
+
"pad_token_id": 0,
|
| 22 |
+
"pooler_dropout": 0.0,
|
| 23 |
+
"pooler_hidden_act": "gelu",
|
| 24 |
+
"pooler_hidden_size": 768,
|
| 25 |
+
"pos_att_type": [
|
| 26 |
+
"c2p",
|
| 27 |
+
"p2c"
|
| 28 |
+
],
|
| 29 |
+
"position_biased_input": false,
|
| 30 |
+
"relative_attention": true,
|
| 31 |
+
"tie_word_embeddings": true,
|
| 32 |
+
"transformers_version": "5.19.0",
|
| 33 |
+
"type_vocab_size": 0,
|
| 34 |
+
"vocab_size": 50265
|
| 35 |
+
}
|
classifier_v1/backbone/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:44e80dcec5a89aa40704cbc6e50530fa83f6a2ce76dca1bd866e23c0074966da
|
| 3 |
+
size 554429144
|
classifier_v1/backbone/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
classifier_v1/backbone/tokenizer_config.json
ADDED
|
@@ -0,0 +1,18 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"backend": "tokenizers",
|
| 4 |
+
"bos_token": "[CLS]",
|
| 5 |
+
"cls_token": "[CLS]",
|
| 6 |
+
"do_lower_case": false,
|
| 7 |
+
"eos_token": "[SEP]",
|
| 8 |
+
"errors": "replace",
|
| 9 |
+
"is_local": false,
|
| 10 |
+
"local_files_only": false,
|
| 11 |
+
"mask_token": "[MASK]",
|
| 12 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 13 |
+
"pad_token": "[PAD]",
|
| 14 |
+
"sep_token": "[SEP]",
|
| 15 |
+
"tokenizer_class": "DebertaTokenizer",
|
| 16 |
+
"unk_token": "[UNK]",
|
| 17 |
+
"vocab_type": "gpt2"
|
| 18 |
+
}
|
classifier_v1/config.json
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"model_name": "microsoft/deberta-base",
|
| 3 |
+
"hidden_size": 768,
|
| 4 |
+
"num_labels": 2,
|
| 5 |
+
"head_hidden_dims": [
|
| 6 |
+
256,
|
| 7 |
+
64
|
| 8 |
+
],
|
| 9 |
+
"dropout": 0.1,
|
| 10 |
+
"max_length": 256,
|
| 11 |
+
"learning_rate": 2e-05,
|
| 12 |
+
"batch_size": 16,
|
| 13 |
+
"epochs": 3,
|
| 14 |
+
"weight_decay": 0.01,
|
| 15 |
+
"warmup_ratio": 0.1
|
| 16 |
+
}
|
classifier_v1/head.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:21854e1ef262d9022950fd8e5c1451addabde3eb79712abdee0d039e3b88e9e2
|
| 3 |
+
size 856625
|