| { | |
| "architectures": [ | |
| "DogeForCausalLM" | |
| ], | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "hidden_act": "silu", | |
| "hidden_dropout": 0.0, | |
| "hidden_size": 256, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 512, | |
| "is_moe": false, | |
| "keep_window_size": 1024, | |
| "max_position_embeddings": 2048, | |
| "mlp_bias": false, | |
| "model_type": "doge", | |
| "norm_topk_prob": false, | |
| "num_attention_heads": 2, | |
| "num_experts": 16384, | |
| "num_experts_per_tok": 64, | |
| "num_hidden_layers": 8, | |
| "num_key_value_heads": 1, | |
| "output_router_logits": false, | |
| "rms_norm_eps": 1e-06, | |
| "rope_scaling": null, | |
| "rope_theta": 10000.0, | |
| "router_aux_loss_coef": 0.001, | |
| "sliding_window": null, | |
| "tie_word_embeddings": true, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.54.0.dev0", | |
| "use_cache": true, | |
| "vocab_size": 128256 | |
| } | |