| { | |
| "FFN_type": "softmoe_v3", | |
| "_name_or_path": "./steel_modify_from_qwen_1_5", | |
| "architectures": [ | |
| "SteelForCausalLM" | |
| ], | |
| "attention_dropout": 0.0, | |
| "auto_map": { | |
| "AutoConfig": "configuration_steel.SteelConfig", | |
| "AutoModelForCausalLM": "modeling_steel.SteelForCausalLM" | |
| }, | |
| "bos_token_id": 151643, | |
| "eos_token_id": 151645, | |
| "hidden_act": "silu", | |
| "hidden_size": 1792, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 1792, | |
| "max_position_embeddings": 32768, | |
| "max_window_layers": 21, | |
| "mlp_div_ratio": 4, | |
| "mlp_type": "senet", | |
| "model_type": "qwen2", | |
| "n_experts": 6, | |
| "num_attention_heads": 32, | |
| "num_hidden_layers": 18, | |
| "num_key_value_heads": 32, | |
| "rms_norm_eps": 1e-06, | |
| "rope_theta": 1000000.0, | |
| "sliding_window": 32768, | |
| "slots_per_expert": 1, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.41.1", | |
| "use_cache": true, | |
| "use_sliding_window": false, | |
| "vocab_size": 151936 | |
| } | |