| { | |
| "activation_dropout": 0.0, | |
| "architectures": [ | |
| "AfroLid" | |
| ], | |
| "attention_dropout": 0.1, | |
| "bias": false, | |
| "checkpoint_activations": false, | |
| "decoder_vocab_size": 528, | |
| "dropout": 0.1, | |
| "embed_dim": 768, | |
| "encoder_vocab_size": 64001, | |
| "ffn_dim": 3072, | |
| "layerdrop": 0.0, | |
| "layernorm_embedding": false, | |
| "learned_pos": false, | |
| "max_seq_len": 512, | |
| "max_source_positions": 1024, | |
| "max_target_positions": 1024, | |
| "model_type": "xlm-r", | |
| "no_token_positional_embeddings": false, | |
| "normalize_before": false, | |
| "num_heads": 12, | |
| "num_layers": 12, | |
| "offload_activations": false, | |
| "share_all_embeddings": false, | |
| "share_decoder_input_output_embed": true, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.47.1" | |
| } | |