dus-merge / config.json
semran1's picture
Upload folder using huggingface_hub
ffb88bc verified
{
"_moe_implementation": "fused",
"architectures": [
"BailingMoeV2ForCausalLM"
],
"attention_dropout": 0.0,
"auto_map": {
"AutoConfig": "configuration_bailing_moe_v2.BailingMoeV2Config",
"AutoModel": "modeling_bailing_moe_v2.BailingMoeV2Model",
"AutoModelForCausalLM": "modeling_bailing_moe_v2.BailingMoeV2ForCausalLM"
},
"model_type": "ling",
"bos_token_id": 151643,
"dtype": "bfloat16",
"embedding_dropout": 0.0,
"eos_token_id": 151645,
"first_k_dense_replace": 1,
"head_dim": 128,
"hidden_act": "silu",
"hidden_size": 2048,
"initializer_range": 0.02,
"intermediate_size": 5120,
"max_position_embeddings": 32768,
"max_window_layers": 30,
"moe_intermediate_size": 512,
"moe_router_enable_expert_bias": true,
"moe_shared_expert_intermediate_size": 512,
"mtp_loss_scaling_factor": 0,
"n_group": 8,
"norm_topk_prob": true,
"num_attention_heads": 16,
"num_experts": 224,
"num_experts_per_tok": 8,
"num_hidden_layers": 30,
"num_key_value_heads": 4,
"num_nextn_predict_layers": 0,
"num_shared_experts": null,
"output_dropout": 0.0,
"output_router_logits": true,
"pad_token_id": null,
"partial_rotary_factor": 0.5,
"pruning_info": {
"original_experts": 256,
"original_model_path": "5kling-fuse_heal",
"pruned_experts": 224,
"pruning_date": "2026-01-16T05:26:11.661656",
"pruning_method": "MoP"
},
"quantize": false,
"rms_norm_eps": 1e-06,
"rope_scaling": null,
"rope_theta": 600000,
"routed_scaling_factor": 2.5,
"router_dtype": "fp32",
"score_function": "sigmoid",
"tie_word_embeddings": false,
"topk_group": 4,
"transformers_version": "4.57.3",
"use_bias": false,
"use_cache": true,
"use_qk_norm": true,
"use_qkv_bias": false,
"use_rmsnorm": true,
"vocab_size": 151936,
"layer_types": [
"sliding_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"full_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"full_attention",
"sliding_attention",
"sliding_attention",
"full_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"full_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention"
]
}