| { | |
| "architectures": [ | |
| "XLMWithLMHeadModel" | |
| ], | |
| "asm": false, | |
| "attention_dropout": 0.1, | |
| "bos_index": 0, | |
| "bos_token_id": 0, | |
| "causal": false, | |
| "dropout": 0.1, | |
| "emb_dim": 1024, | |
| "embed_init_std": 0.02209708691207961, | |
| "end_n_top": 5, | |
| "eos_index": 1, | |
| "gelu_activation": true, | |
| "id2lang": { | |
| "0": "ar", | |
| "1": "bg", | |
| "10": "th", | |
| "11": "tr", | |
| "12": "ur", | |
| "13": "vi", | |
| "14": "zh", | |
| "2": "de", | |
| "3": "el", | |
| "4": "en", | |
| "5": "es", | |
| "6": "fr", | |
| "7": "hi", | |
| "8": "ru", | |
| "9": "sw" | |
| }, | |
| "init_std": 0.02, | |
| "is_encoder": true, | |
| "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 | |
| }, | |
| "lang_id": 0, | |
| "layer_norm_eps": 1e-12, | |
| "mask_index": 5, | |
| "mask_token_id": 0, | |
| "max_position_embeddings": 512, | |
| "max_vocab": 95000, | |
| "min_count": 0, | |
| "model_type": "xlm", | |
| "n_heads": 8, | |
| "n_langs": 15, | |
| "n_layers": 12, | |
| "pad_index": 2, | |
| "pad_token_id": 2, | |
| "same_enc_dec": true, | |
| "share_inout_emb": true, | |
| "sinusoidal_embeddings": false, | |
| "start_n_top": 5, | |
| "summary_activation": null, | |
| "summary_first_dropout": 0.1, | |
| "summary_proj_to_labels": true, | |
| "summary_type": "first", | |
| "summary_use_proj": true, | |
| "unk_index": 3, | |
| "use_lang_emb": true, | |
| "vocab_size": 95000 | |
| } | |