| { |
| "architectures": [ |
| "BailingMoeV2_5ForCausalLM" |
| ], |
| "attention_dropout": 0.0, |
| "auto_map": { |
| "AutoConfig": "configuration_bailing_moe_v2_5.BailingMoeV2_5Config", |
| "AutoModel": "modeling_bailing_moe_v2_5.BailingMoeV2_5Model", |
| "AutoModelForCausalLM": "modeling_bailing_moe_v2_5.BailingMoeV2_5ForCausalLM" |
| }, |
| "first_k_dense_replace": 1, |
| "group_norm_size": 4, |
| "head_dim": 128, |
| "hidden_act": "silu", |
| "hidden_size": 4096, |
| "intermediate_size": 9216, |
| "kv_lora_rank": 512, |
| "layer_group_size": 8, |
| "linear_silu": false, |
| "max_position_embeddings": 262144, |
| "model_type": "bailing_hybrid", |
| "moe_intermediate_size": 1024, |
| "moe_layer_freq": 1, |
| "moe_router_enable_expert_bias": true, |
| "moe_shared_expert_intermediate_size": 1024, |
| "n_group": 8, |
| "n_routed_experts": 256, |
| "norm_topk_prob": true, |
| "num_attention_heads": 32, |
| "num_experts": 256, |
| "num_experts_per_tok": 8, |
| "num_hidden_layers": 32, |
| "num_key_value_heads": 32, |
| "num_kv_heads_for_linear_attn": 32, |
| "num_nextn_predict_layers": 1, |
| "num_shared_experts": 1, |
| "q_lora_rank": 1536, |
| "qk_nope_head_dim": 128, |
| "qk_rope_head_dim": 64, |
| "rms_norm_eps": 1e-06, |
| "rope_theta": 6000000, |
| "rotary_dim": 64, |
| "routed_scaling_factor": 2.5, |
| "score_function": "sigmoid", |
| "scoring_func": "sigmoid", |
| "seq_aux": true, |
| "tie_word_embeddings": false, |
| "topk_group": 4, |
| "topk_method": "noaux_tc", |
| "torch_dtype": "bfloat16", |
| "transformers_version": "4.33.1", |
| "use_bias": false, |
| "use_cache": true, |
| "use_qk_norm": true, |
| "v_head_dim": 128, |
| "vocab_size": 157184, |
| "quantization_config": { |
| "activation_scheme": "dynamic", |
| "fmt": "e4m3", |
| "quant_method": "fp8", |
| "weight_block_size": [ |
| 128, |
| 128 |
| ] |
| } |
| } |
|
|
