| { | |
| "num_classes": 3, | |
| "dropout": 0.0, | |
| "init_args": [ | |
| { | |
| "is_encoder": true, | |
| "causal": false, | |
| "n_langs": 15, | |
| "use_lang_embeddings": true, | |
| "vocab_size": 95000, | |
| "eos_token_id": 1, | |
| "pad_token_id": 2, | |
| "hidden_size": 1024, | |
| "num_attention_heads": 8, | |
| "num_hidden_layers": 12, | |
| "hidden_dropout_prob": 0.1, | |
| "attention_probs_dropout_prob": 0.1, | |
| "max_position_embeddings": 512, | |
| "use_sinusoidal_embeddings": false, | |
| "layer_norm_eps": 1e-12, | |
| "hidden_act": "gelu", | |
| "embed_init_std": 0.02209708691207961, | |
| "init_std": 0.02, | |
| "use_asm": false, | |
| "asm_cutoffs": 1, | |
| "asm_div_value": 1, | |
| "mask_token_id": 0, | |
| "lang_id": 4, | |
| "lang2id": { | |
| "ar": 0, | |
| "bg": 1, | |
| "de": 2, | |
| "el": 3, | |
| "en": 4, | |
| "es": 5, | |
| "fr": 6, | |
| "hi": 7, | |
| "ru": 8, | |
| "sw": 9, | |
| "th": 10, | |
| "tr": 11, | |
| "ur": 12, | |
| "vi": 13, | |
| "zh": 14 | |
| }, | |
| "init_class": "XLMModel" | |
| } | |
| ], | |
| "init_class": "XLMForSequenceClassification" | |
| } |