| { |
| "all2all_overlap": true, |
| "architectures": [ |
| "BailingMoeForCausalLM" |
| ], |
| "atorch_backend": "MegaBlocks", |
| "attention_dropout": 0.0, |
| "auto_map": { |
| "AutoConfig": "configuration_bailing_moe.BailingMoeConfig", |
| "AutoModel": "modeling_bailing_moe.BailingMoeModel", |
| "AutoModelForCausalLM": "modeling_bailing_moe.BailingMoeForCausalLM" |
| }, |
| "bos_token_id": 126080, |
| "dispatcher_type": "AllToAll", |
| "embedding_dropout": 0.0, |
| "eos_token_id": 126081, |
| "expert_model_parallelism": false, |
| "first_k_dense_replace": 0, |
| "head_dim": 128, |
| "hidden_act": "silu", |
| "hidden_size": 2048, |
| "initializer_range": 0.006, |
| "intermediate_size": 1408, |
| "is_scale_gradient": true, |
| "last_logits_l2_alpha": -1.0, |
| "max_position_embeddings": 32768, |
| "max_window_layers": 28, |
| "merge_w1_v1": false, |
| "model_type": "bailing_moe", |
| "moe_impl": "raw", |
| "moe_intermediate_size": 1408, |
| "moe_mlp_prefix": false, |
| "norm_head": false, |
| "norm_softmax": false, |
| "norm_topk_prob": true, |
| "num_attention_heads": 16, |
| "num_experts": 64, |
| "num_experts_per_tok": 6, |
| "num_hidden_layers": 28, |
| "num_key_value_heads": 4, |
| "num_shared_experts": 2, |
| "output_dropout": 0.0, |
| "output_router_logits": false, |
| "pad_token_id": 126081, |
| "pretraining_tp": 1, |
| "rms_norm_eps": 1e-06, |
| "rope_scaling": null, |
| "rope_theta": 600000, |
| "router_balance_loss_alpha": 0, |
| "router_group_balance_loss_alpha": 0.0, |
| "router_z_loss_alpha": 0, |
| "sliding_window": 4096, |
| "tie_word_embeddings": false, |
| "torch_dtype": "bfloat16", |
| "transformers_version": "4.51.1", |
| "transpose_w1": true, |
| "use_bias": false, |
| "use_cache": true, |
| "use_qkv_bias": false, |
| "use_sliding_window": false, |
| "use_swiglu": false, |
| "vocab_size": 126464 |
| } |
|
|