Upload BertForSequenceClassification
Browse files- config.json +16 -36
- model.safetensors +2 -2
config.json
CHANGED
|
@@ -1,24 +1,12 @@
|
|
| 1 |
{
|
| 2 |
"architectures": [
|
| 3 |
-
"
|
| 4 |
],
|
| 5 |
-
"
|
| 6 |
-
"
|
| 7 |
-
"bos_token_id": 50281,
|
| 8 |
-
"classifier_activation": "gelu",
|
| 9 |
-
"classifier_bias": false,
|
| 10 |
-
"classifier_dropout": 0.0,
|
| 11 |
-
"classifier_pooling": "mean",
|
| 12 |
-
"cls_token_id": 50281,
|
| 13 |
-
"decoder_bias": true,
|
| 14 |
-
"deterministic_flash_attn": false,
|
| 15 |
-
"dtype": "float32",
|
| 16 |
-
"embedding_dropout": 0.0,
|
| 17 |
-
"eos_token_id": 50282,
|
| 18 |
-
"global_attn_every_n_layers": 3,
|
| 19 |
-
"global_rope_theta": 160000.0,
|
| 20 |
"gradient_checkpointing": false,
|
| 21 |
-
"
|
|
|
|
| 22 |
"hidden_size": 1024,
|
| 23 |
"id2label": {
|
| 24 |
"0": "LABEL_0",
|
|
@@ -36,9 +24,8 @@
|
|
| 36 |
"12": "LABEL_12",
|
| 37 |
"13": "LABEL_13"
|
| 38 |
},
|
| 39 |
-
"initializer_cutoff_factor": 2.0,
|
| 40 |
"initializer_range": 0.02,
|
| 41 |
-
"intermediate_size":
|
| 42 |
"label2id": {
|
| 43 |
"LABEL_0": 0,
|
| 44 |
"LABEL_1": 1,
|
|
@@ -55,23 +42,16 @@
|
|
| 55 |
"LABEL_8": 8,
|
| 56 |
"LABEL_9": 9
|
| 57 |
},
|
| 58 |
-
"layer_norm_eps": 1e-
|
| 59 |
-
"
|
| 60 |
-
"
|
| 61 |
-
"max_position_embeddings": 8192,
|
| 62 |
-
"mlp_bias": false,
|
| 63 |
-
"mlp_dropout": 0.0,
|
| 64 |
-
"model_type": "modernbert",
|
| 65 |
-
"norm_bias": false,
|
| 66 |
-
"norm_eps": 1e-05,
|
| 67 |
"num_attention_heads": 16,
|
| 68 |
-
"num_hidden_layers":
|
| 69 |
-
"pad_token_id":
|
| 70 |
"position_embedding_type": "absolute",
|
| 71 |
-
"
|
| 72 |
-
"
|
| 73 |
-
"
|
| 74 |
-
"
|
| 75 |
-
"
|
| 76 |
-
"vocab_size": 50368
|
| 77 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"architectures": [
|
| 3 |
+
"BertForSequenceClassification"
|
| 4 |
],
|
| 5 |
+
"attention_probs_dropout_prob": 0.1,
|
| 6 |
+
"classifier_dropout": null,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 7 |
"gradient_checkpointing": false,
|
| 8 |
+
"hidden_act": "gelu",
|
| 9 |
+
"hidden_dropout_prob": 0.1,
|
| 10 |
"hidden_size": 1024,
|
| 11 |
"id2label": {
|
| 12 |
"0": "LABEL_0",
|
|
|
|
| 24 |
"12": "LABEL_12",
|
| 25 |
"13": "LABEL_13"
|
| 26 |
},
|
|
|
|
| 27 |
"initializer_range": 0.02,
|
| 28 |
+
"intermediate_size": 4096,
|
| 29 |
"label2id": {
|
| 30 |
"LABEL_0": 0,
|
| 31 |
"LABEL_1": 1,
|
|
|
|
| 42 |
"LABEL_8": 8,
|
| 43 |
"LABEL_9": 9
|
| 44 |
},
|
| 45 |
+
"layer_norm_eps": 1e-12,
|
| 46 |
+
"max_position_embeddings": 512,
|
| 47 |
+
"model_type": "bert",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 48 |
"num_attention_heads": 16,
|
| 49 |
+
"num_hidden_layers": 24,
|
| 50 |
+
"pad_token_id": 0,
|
| 51 |
"position_embedding_type": "absolute",
|
| 52 |
+
"torch_dtype": "float32",
|
| 53 |
+
"transformers_version": "4.52.4",
|
| 54 |
+
"type_vocab_size": 2,
|
| 55 |
+
"use_cache": true,
|
| 56 |
+
"vocab_size": 30522
|
|
|
|
| 57 |
}
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:69affcfcb7b122429081c36bb06f54e8bce874a9479b66a441701b6dfe79ae99
|
| 3 |
+
size 1340671968
|