41 lines
1000 B
JSON
41 lines
1000 B
JSON
|
|
{
|
||
|
|
"architectures": [
|
||
|
|
"Qwen3MoeForCausalLM"
|
||
|
|
],
|
||
|
|
"attention_bias": false,
|
||
|
|
"attention_dropout": 0.0,
|
||
|
|
"bos_token_id": 151643,
|
||
|
|
"decoder_sparse_step": 1,
|
||
|
|
"dtype": "float32",
|
||
|
|
"eos_token_id": 151643,
|
||
|
|
"head_dim": 128,
|
||
|
|
"hidden_act": "silu",
|
||
|
|
"hidden_size": 1024,
|
||
|
|
"initializer_range": 0.02,
|
||
|
|
"intermediate_size": 3072,
|
||
|
|
"max_position_embeddings": 32768,
|
||
|
|
"max_window_layers": 28,
|
||
|
|
"mlp_only_layers": [],
|
||
|
|
"model_type": "qwen3_moe",
|
||
|
|
"moe_intermediate_size": 768,
|
||
|
|
"norm_topk_prob": true,
|
||
|
|
"num_attention_heads": 16,
|
||
|
|
"num_experts": 256,
|
||
|
|
"num_experts_per_tok": 8,
|
||
|
|
"num_hidden_layers": 28,
|
||
|
|
"num_key_value_heads": 8,
|
||
|
|
"output_router_logits": false,
|
||
|
|
"qkv_bias": false,
|
||
|
|
"rms_norm_eps": 1e-06,
|
||
|
|
"rope_scaling": null,
|
||
|
|
"rope_theta": 1000000.0,
|
||
|
|
"router_aux_loss_coef": 0.001,
|
||
|
|
"sliding_window": null,
|
||
|
|
"tie_word_embeddings": true,
|
||
|
|
"transformers_version": "4.57.1",
|
||
|
|
"use_cache": true,
|
||
|
|
"use_qk_norm": true,
|
||
|
|
"use_sliding_window": false,
|
||
|
|
"vocab_size": 151936
|
||
|
|
}
|