enta-st-st / config.json
kangXn's picture
Upload XmodForSequenceClassification
44bea1c verified
{
"_name_or_path": "kangXn/enta-st",
"adapter_layer_norm": false,
"adapter_reduction_factor": 2,
"adapter_reuse_layer_norm": true,
"architectures": [
"XmodForSequenceClassification"
],
"attention_probs_dropout_prob": 0.1,
"bos_token_id": 0,
"classifier_dropout": null,
"default_language": "ta_IN",
"eos_token_id": 2,
"hidden_act": "gelu",
"hidden_dropout_prob": 0.1,
"hidden_size": 768,
"id2label": {
"0": "LABEL_0"
},
"initializer_range": 0.02,
"intermediate_size": 3072,
"label2id": {
"LABEL_0": 0
},
"languages": [
"en_XX",
"id_ID",
"vi_VN",
"ru_RU",
"fa_IR",
"sv_SE",
"ja_XX",
"fr_XX",
"de_DE",
"ro_RO",
"ko_KR",
"hu_HU",
"es_XX",
"fi_FI",
"uk_UA",
"da_DK",
"pt_XX",
"no_XX",
"th_TH",
"pl_PL",
"bg_BG",
"nl_XX",
"zh_CN",
"he_IL",
"el_GR",
"it_IT",
"sk_SK",
"hr_HR",
"tr_TR",
"ar_AR",
"cs_CZ",
"lt_LT",
"hi_IN",
"zh_TW",
"ca_ES",
"ms_MY",
"sl_SI",
"lv_LV",
"ta_IN",
"bn_IN",
"et_EE",
"az_AZ",
"sq_AL",
"sr_RS",
"kk_KZ",
"ka_GE",
"tl_XX",
"ur_PK",
"is_IS",
"hy_AM",
"ml_IN",
"mk_MK",
"be_BY",
"la_VA",
"te_IN",
"eu_ES",
"gl_ES",
"mn_MN",
"kn_IN",
"ne_NP",
"sw_KE",
"si_LK",
"mr_IN",
"af_ZA",
"gu_IN",
"cy_GB",
"eo_EO",
"km_KH",
"ky_KG",
"uz_UZ",
"ps_AF",
"pa_IN",
"ga_IE",
"ha_NG",
"am_ET",
"lo_LA",
"ku_TR",
"so_SO",
"my_MM",
"or_IN",
"sa_IN"
],
"layer_norm_eps": 1e-05,
"ln_before_adapter": true,
"max_position_embeddings": 514,
"model_type": "xmod",
"num_attention_heads": 12,
"num_hidden_layers": 12,
"pad_token_id": 1,
"position_embedding_type": "absolute",
"pre_norm": false,
"problem_type": "regression",
"torch_dtype": "float32",
"transformers_version": "4.38.2",
"type_vocab_size": 1,
"use_cache": true,
"vocab_size": 250002
}