moe_guard_gate_iter2 / config.json
SparshSyde's picture
Upload XLMRobertaForSequenceClassification
1d7943b verified
{
"_name_or_path": "markussagen/xlm-roberta-longformer-base-4096",
"architectures": [
"XLMRobertaForSequenceClassification"
],
"attention_probs_dropout_prob": 0.1,
"attention_window": [
512,
512,
512,
512,
512,
512,
512,
512,
512,
512,
512,
512
],
"bos_token_id": 0,
"classifier_dropout": null,
"eos_token_id": 2,
"gradient_checkpointing": false,
"hidden_act": "gelu",
"hidden_dropout_prob": 0.1,
"hidden_size": 768,
"id2label": {
"0": "Base32",
"1": "Base64",
"2": "Direct",
"3": "Emoji",
"4": "First_Last_Same",
"5": "Ignore_Instructions",
"6": "Languages",
"7": "Leetspeak",
"8": "Masking",
"9": "Payload_Splitting",
"10": "Reverse",
"11": "Roleplay",
"12": "ROT13",
"13": "VES",
"14": "Leading_Statements",
"15": "Word_Order",
"16": "DAN",
"17": "sudo_dev",
"18": "System_prompt"
},
"initializer_range": 0.02,
"intermediate_size": 3072,
"label2id": {
"Base32": 0,
"Base64": 1,
"DAN": 16,
"Direct": 2,
"Emoji": 3,
"First_Last_Same": 4,
"Ignore_Instructions": 5,
"Languages": 6,
"Leading_Statements": 14,
"Leetspeak": 7,
"Masking": 8,
"Payload_Splitting": 9,
"ROT13": 12,
"Reverse": 10,
"Roleplay": 11,
"System_prompt": 18,
"VES": 13,
"Word_Order": 15,
"sudo_dev": 17
},
"layer_norm_eps": 1e-05,
"max_position_embeddings": 4098,
"model_type": "xlm-roberta",
"num_attention_heads": 12,
"num_hidden_layers": 12,
"output_past": true,
"pad_token_id": 1,
"position_embedding_type": "absolute",
"problem_type": "multi_label_classification",
"torch_dtype": "float32",
"transformers_version": "4.38.2",
"type_vocab_size": 1,
"use_cache": true,
"vocab_size": 250002
}