| { | |
| "_attn_impl": "flash_attention_2", | |
| "_name_or_path": "junnyu/roformer_chinese_base", | |
| "architectures": [ | |
| "RoFormerForMaskedLM" | |
| ], | |
| "attention_probs_dropout_prob": 0.1, | |
| "embedding_size": 768, | |
| "hidden_act": "gelu", | |
| "hidden_dropout_prob": 0.1, | |
| "hidden_size": 768, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 3072, | |
| "layer_norm_eps": 1e-12, | |
| "max_position_embeddings": 1536, | |
| "model_type": "roformer", | |
| "num_attention_heads": 12, | |
| "num_hidden_layers": 12, | |
| "pad_token_id": 0, | |
| "rope_scaling": { | |
| "factor": 1.0, | |
| "type": "default" | |
| }, | |
| "rope_theta": 10000, | |
| "rotary_value": false, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.39.1", | |
| "type_vocab_size": 2, | |
| "use_cache": true, | |
| "vocab_size": 50000 | |
| } | |