| { | |
| "architectures": [ | |
| "OpenMoeForCausalLM" | |
| ], | |
| "bos_token_id": 1, | |
| "capacity_factor_eval": 2.0, | |
| "capacity_factor_train": 1.25, | |
| "drop_tks": true, | |
| "dropout_rate": 0.0, | |
| "eos_token_id": 2, | |
| "expert_parallel": null, | |
| "gated": true, | |
| "head_dim": 128, | |
| "hidden_act": "swiglu", | |
| "hidden_size": 2048, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 8192, | |
| "layer_norm_epsilon": 1e-06, | |
| "max_position_embeddings": 2048, | |
| "min_capacity": 4, | |
| "model_type": "llama", | |
| "moe_layer_interval": 6, | |
| "noisy_policy": null, | |
| "num_attention_heads": 24, | |
| "num_experts": 32, | |
| "num_hidden_layers": 24, | |
| "num_key_value_heads": 24, | |
| "pretraining_tp": 1, | |
| "rms_norm_eps": 1e-06, | |
| "rope_scaling": null, | |
| "rope_theta": 10000.0, | |
| "tie_word_embeddings": false, | |
| "topk": 2, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.33.1", | |
| "use_cache": true, | |
| "vocab_size": 256384 | |
| } | |