{ "_name_or_path": "hf-internal-testing/tiny-random-XLMModel", "architectures": [ "XLMModel" ], "asm": false, "attention_dropout": 0.1, "bos_index": 0, "bos_token_id": 0, "causal": false, "dropout": 0.1, "emb_dim": 32, "embed_init_std": 0.02209708691207961, "end_n_top": 5, "eos_index": 1, "gelu_activation": true, "init_std": 0.02, "initializer_range": 0.02, "is_encoder": true, "lang_id": 0, "layer_norm_eps": 1e-12, "mask_index": 5, "mask_token_id": 5, "max_position_embeddings": 512, "model_type": "xlm", "n_heads": 4, "n_langs": 2, "n_layers": 5, "n_special": 0, "neuron": { "auto_cast": null, "auto_cast_type": null, "compiler_type": "neuronx-cc", "compiler_version": "2.15.128.0+56dc5a86", "disable_fallback": false, "disable_fast_relayout": false, "dynamic_batch_size": false, "inline_weights_to_neff": true, "input_names": [ "input_ids", "attention_mask", "token_type_ids" ], "model_type": "xlm", "optlevel": "2", "output_attentions": false, "output_hidden_states": false, "output_names": [ "logits" ], "static_batch_size": 1, "static_sequence_length": 32 }, "pad_index": 2, "pad_token_id": 2, "sinusoidal_embeddings": false, "start_n_top": 5, "summary_activation": null, "summary_first_dropout": 0.1, "summary_proj_to_labels": true, "summary_type": "last", "summary_use_proj": true, "task": "token-classification", "torchscript": true, "transformers_version": "4.43.2", "unk_index": 3, "use_lang_emb": true, "use_proj": true, "vocab_size": 30145 }