Upload DebertaV2ForSequenceClassification
Browse files- config.json +71 -0
- model.safetensors +3 -0
config.json
ADDED
|
@@ -0,0 +1,71 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "classification-testing",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"DebertaV2ForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"finetuning_task": "text-classification",
|
| 8 |
+
"hidden_act": "gelu",
|
| 9 |
+
"hidden_dropout_prob": 0.1,
|
| 10 |
+
"hidden_size": 1024,
|
| 11 |
+
"id2label": {
|
| 12 |
+
"0": "analysis or decision explanation",
|
| 13 |
+
"1": "assisting or creative writing",
|
| 14 |
+
"2": "classification",
|
| 15 |
+
"3": "coding",
|
| 16 |
+
"4": "editing or rewriting",
|
| 17 |
+
"5": "factual information (general or professional), history or common practices",
|
| 18 |
+
"6": "information extraction or summarization",
|
| 19 |
+
"7": "linguistics",
|
| 20 |
+
"8": "logical reasoning",
|
| 21 |
+
"9": "mathematical reasoning or calculation",
|
| 22 |
+
"10": "multilinguality or translation",
|
| 23 |
+
"11": "other",
|
| 24 |
+
"12": "recommendation",
|
| 25 |
+
"13": "roleplay",
|
| 26 |
+
"14": "tips, opinions or advice"
|
| 27 |
+
},
|
| 28 |
+
"initializer_range": 0.02,
|
| 29 |
+
"intermediate_size": 4096,
|
| 30 |
+
"label2id": {
|
| 31 |
+
"analysis or decision explanation": 0,
|
| 32 |
+
"assisting or creative writing": 1,
|
| 33 |
+
"classification": 2,
|
| 34 |
+
"coding": 3,
|
| 35 |
+
"editing or rewriting": 4,
|
| 36 |
+
"factual information (general or professional), history or common practices": 5,
|
| 37 |
+
"information extraction or summarization": 6,
|
| 38 |
+
"linguistics": 7,
|
| 39 |
+
"logical reasoning": 8,
|
| 40 |
+
"mathematical reasoning or calculation": 9,
|
| 41 |
+
"multilinguality or translation": 10,
|
| 42 |
+
"other": 11,
|
| 43 |
+
"recommendation": 12,
|
| 44 |
+
"roleplay": 13,
|
| 45 |
+
"tips, opinions or advice": 14
|
| 46 |
+
},
|
| 47 |
+
"layer_norm_eps": 1e-07,
|
| 48 |
+
"max_position_embeddings": 512,
|
| 49 |
+
"max_relative_positions": -1,
|
| 50 |
+
"model_type": "deberta-v2",
|
| 51 |
+
"norm_rel_ebd": "layer_norm",
|
| 52 |
+
"num_attention_heads": 16,
|
| 53 |
+
"num_hidden_layers": 24,
|
| 54 |
+
"pad_token_id": 0,
|
| 55 |
+
"pooler_dropout": 0,
|
| 56 |
+
"pooler_hidden_act": "gelu",
|
| 57 |
+
"pooler_hidden_size": 1024,
|
| 58 |
+
"pos_att_type": [
|
| 59 |
+
"p2c",
|
| 60 |
+
"c2p"
|
| 61 |
+
],
|
| 62 |
+
"position_biased_input": false,
|
| 63 |
+
"position_buckets": 256,
|
| 64 |
+
"problem_type": "single_label_classification",
|
| 65 |
+
"relative_attention": true,
|
| 66 |
+
"share_att_key": true,
|
| 67 |
+
"torch_dtype": "float32",
|
| 68 |
+
"transformers_version": "4.39.0.dev0",
|
| 69 |
+
"type_vocab_size": 0,
|
| 70 |
+
"vocab_size": 128100
|
| 71 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:add34ffe23d99efe60e3e6b3a2770f050e647e5c3c6644f7d48a39d2aa03e9e8
|
| 3 |
+
size 1740357748
|