File size: 1,406 Bytes
2510df9 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 |
{
"architectures": [
"BailingMoeLinearForCausalLM"
],
"attention_dropout": 0.0,
"auto_map": {
"AutoConfig": "configuration_bailing_moe_linear.BailingMoeLinearConfig",
"AutoModel": "modeling_bailing_moe_linear.BailingMoeLinearModel",
"AutoModelForCausalLM": "modeling_bailing_moe_linear.BailingMoeLinearForCausalLM"
},
"eos_token_id": 126081,
"pad_token_id": 126081,
"first_k_dense_replace": 0,
"hidden_act": "silu",
"hidden_size": 2048,
"initializer_range": 0.006,
"intermediate_size": 5632,
"max_position_embeddings": 16384,
"model_type": "bailing_moe_linear",
"moe_intermediate_size": 1408,
"num_experts": 64,
"num_shared_experts": 2,
"norm_topk_prob": true,
"num_attention_heads": 16,
"num_experts_per_tok": 6,
"num_hidden_layers": 28,
"num_key_value_heads": 4,
"pretraining_tp": 1,
"rms_norm_eps": 1e-05,
"rope_scaling": null,
"rope_theta": 600000,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.36.0",
"use_cache": true,
"use_bias": false,
"use_qkv_bias": false,
"vocab_size": 126464,
"embedding_dropout": 0.0,
"norm_head": true,
"norm_softmax": false,
"output_dropout": 0.0,
"output_router_logits": false,
"layer_group_size": 7,
"use_linear_silu": false,
"linear_rope": true,
"use_linear_gpa": false,
"use_low_rank": false,
"linear_mode": "chunk"
}
|