openPangu-2.0-Flash / config.json
liyh00's picture
Upload config.json with huggingface_hub
1ed1a82 verified
Raw
History Blame Contribute Delete
1.85 kB
{
"architectures": ["OpenPanguV2ForCausalLM"],
"attention_dropout": 0.0,
"auto_map": {
"AutoConfig": "configuration_openpangu_v2.OpenPanguV2Config"
},
"_attn_implementation":"eager",
"block_post_layernorm_idx": [0, 4, 9, 14, 19, 24, 29, 34, 39],
"bos_token_id": 148899,
"dsa_layers": [0, 3, 6, 9, 12, 15, 18, 21, 24, 27, 30, 33, 36, 39, 42, 45],
"dtype": "bfloat16",
"eos_token_id": 148902,
"first_k_dense_replace": 2,
"hidden_act": "silu",
"hidden_size": 2560,
"index_head_dim": 128,
"index_n_heads": 24,
"index_topk": 2048,
"intermediate_size": 9216,
"kv_lora_rank": 512,
"max_position_embeddings": 524288,
"mhc_num_stream": 4,
"mhc_recur_norm": 20,
"mhc_use_gamma": true,
"model_type": "openpangu_v2",
"moe_intermediate_size": 1024,
"n_routed_experts": 256,
"n_shared_experts": 1,
"norm_topk_prob": true,
"num_attention_heads": 48,
"num_experts_per_tok": 8,
"num_hidden_layers": 46,
"num_nextn_predict_layers": 3,
"pad_token_id": 148902,
"param_sink_number": 128,
"q_lora_rank": 1024,
"qk_nope_head_dim": 128,
"qk_rope_head_dim": 64,
"rms_norm_eps": 1e-05,
"rope_theta": 6400000,
"rope_interleave": false,
"router_enable_expert_bias": true,
"routed_scaling_factor": 2.5,
"router_sliding_window": 3,
"sandwich_norm": true,
"sliding_window": 512,
"sliding_window_list": [512, 512, 512, 512, 512, 512, 512, 512, 512, 512, 512, 512, 512, 512, 512, 512, 512, 512, 512, 512, 512, 512, 512, 512, 512, 512, 512, 512, 512, 512, 2048, 2048, 2048],
"swa_layers": [1, 2, 4, 5, 7, 8, 10, 11, 13, 14, 16, 17, 19, 20, 22, 23, 25, 26, 28, 29, 31, 32, 34, 35, 37, 38, 40, 41, 43, 44, 46, 47, 48],
"tie_word_embeddings": false,
"transformers_version": "5.0.0",
"use_cache": true,
"use_mhc": true,
"use_mome": true,
"v_head_dim": 128,
"vocab_size": 151552
}