| { | |
| "architectures": [ | |
| "KinoeForCausalLM" | |
| ], | |
| "auto_map": { | |
| "AutoConfig": "configuration_kinoe.KinoeConfig", | |
| "AutoModelForCausalLM": "modeling_kinoe.KinoeForCausalLM", | |
| "AutoModelForSequenceClassification": "modeling_kinoe.KinoeForSequenceClassification", | |
| "AutoModelForTokenClassification": "modeling_kinoe.KinoeForTokenClassification" | |
| }, | |
| "attention_dropout": 0.0, | |
| "pad_token_id": 0, | |
| "bos_token_id": 1, | |
| "eos_token_id": 2, | |
| "hidden_act": "silu", | |
| "hidden_size": 5120, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 14336, | |
| "max_position_embeddings": 32768, | |
| "max_sequence_length": 2048, | |
| "model_type": "kinoe", | |
| "num_attention_heads": 40, | |
| "num_hidden_layers": 24, | |
| "num_key_value_heads": 10, | |
| "rms_norm_eps": 1e-06, | |
| "rope_theta": 10000.0, | |
| "sliding_window": 1024, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.40.1", | |
| "use_cache": true, | |
| "vocab_size": 55424 | |
| } | |