Add config.json
Browse files- config.json +43 -0
config.json
ADDED
|
@@ -0,0 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Qwen3NextForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_dropout": 0.0,
|
| 6 |
+
"bos_token_id": 151643,
|
| 7 |
+
"decoder_sparse_step": 1,
|
| 8 |
+
"eos_token_id": 151645,
|
| 9 |
+
"full_attention_interval": 4,
|
| 10 |
+
"head_dim": 256,
|
| 11 |
+
"hidden_act": "silu",
|
| 12 |
+
"hidden_size": 2048,
|
| 13 |
+
"initializer_range": 0.02,
|
| 14 |
+
"intermediate_size": 5120,
|
| 15 |
+
"linear_conv_kernel_dim": 4,
|
| 16 |
+
"linear_key_head_dim": 128,
|
| 17 |
+
"linear_num_key_heads": 16,
|
| 18 |
+
"linear_num_value_heads": 32,
|
| 19 |
+
"linear_value_head_dim": 128,
|
| 20 |
+
"max_position_embeddings": 262144,
|
| 21 |
+
"mlp_only_layers": [],
|
| 22 |
+
"model_type": "qwen3_next",
|
| 23 |
+
"moe_intermediate_size": 512,
|
| 24 |
+
"norm_topk_prob": true,
|
| 25 |
+
"num_attention_heads": 16,
|
| 26 |
+
"num_experts": 512,
|
| 27 |
+
"num_experts_per_tok": 10,
|
| 28 |
+
"num_hidden_layers": 48,
|
| 29 |
+
"num_key_value_heads": 2,
|
| 30 |
+
"output_router_logits": false,
|
| 31 |
+
"partial_rotary_factor": 0.25,
|
| 32 |
+
"rms_norm_eps": 1e-06,
|
| 33 |
+
"rope_scaling": null,
|
| 34 |
+
"rope_theta": 10000000,
|
| 35 |
+
"router_aux_loss_coef": 0.001,
|
| 36 |
+
"shared_expert_intermediate_size": 512,
|
| 37 |
+
"tie_word_embeddings": false,
|
| 38 |
+
"torch_dtype": "bfloat16",
|
| 39 |
+
"transformers_version": "4.57.0.dev0",
|
| 40 |
+
"use_cache": true,
|
| 41 |
+
"use_sliding_window": false,
|
| 42 |
+
"vocab_size": 151936
|
| 43 |
+
}
|