rQwen25Sep
#27
by
bigfundu
- opened
- config.json +6 -5
config.json
CHANGED
|
@@ -2,18 +2,16 @@
|
|
| 2 |
"architectures": [
|
| 3 |
"Qwen3MoeForCausalLM"
|
| 4 |
],
|
| 5 |
-
"attention_bias": false,
|
| 6 |
"attention_dropout": 0.0,
|
| 7 |
-
"bos_token_id": 151643,
|
| 8 |
"decoder_sparse_step": 1,
|
| 9 |
"eos_token_id": 151645,
|
| 10 |
"head_dim": 128,
|
| 11 |
"hidden_act": "silu",
|
| 12 |
"hidden_size": 2048,
|
| 13 |
"initializer_range": 0.02,
|
| 14 |
-
"intermediate_size":
|
| 15 |
"max_position_embeddings": 262144,
|
| 16 |
-
"max_window_layers":
|
| 17 |
"mlp_only_layers": [],
|
| 18 |
"model_type": "qwen3_moe",
|
| 19 |
"moe_intermediate_size": 768,
|
|
@@ -24,15 +22,18 @@
|
|
| 24 |
"num_hidden_layers": 48,
|
| 25 |
"num_key_value_heads": 4,
|
| 26 |
"output_router_logits": false,
|
|
|
|
| 27 |
"rms_norm_eps": 1e-06,
|
| 28 |
"rope_scaling": null,
|
| 29 |
"rope_theta": 10000000,
|
| 30 |
-
"router_aux_loss_coef": 0.
|
|
|
|
| 31 |
"sliding_window": null,
|
| 32 |
"tie_word_embeddings": false,
|
| 33 |
"torch_dtype": "bfloat16",
|
| 34 |
"transformers_version": "4.52.3",
|
| 35 |
"use_cache": true,
|
|
|
|
| 36 |
"use_sliding_window": false,
|
| 37 |
"vocab_size": 151936
|
| 38 |
}
|
|
|
|
| 2 |
"architectures": [
|
| 3 |
"Qwen3MoeForCausalLM"
|
| 4 |
],
|
|
|
|
| 5 |
"attention_dropout": 0.0,
|
|
|
|
| 6 |
"decoder_sparse_step": 1,
|
| 7 |
"eos_token_id": 151645,
|
| 8 |
"head_dim": 128,
|
| 9 |
"hidden_act": "silu",
|
| 10 |
"hidden_size": 2048,
|
| 11 |
"initializer_range": 0.02,
|
| 12 |
+
"intermediate_size": 5472,
|
| 13 |
"max_position_embeddings": 262144,
|
| 14 |
+
"max_window_layers": 28,
|
| 15 |
"mlp_only_layers": [],
|
| 16 |
"model_type": "qwen3_moe",
|
| 17 |
"moe_intermediate_size": 768,
|
|
|
|
| 22 |
"num_hidden_layers": 48,
|
| 23 |
"num_key_value_heads": 4,
|
| 24 |
"output_router_logits": false,
|
| 25 |
+
"qkv_bias": false,
|
| 26 |
"rms_norm_eps": 1e-06,
|
| 27 |
"rope_scaling": null,
|
| 28 |
"rope_theta": 10000000,
|
| 29 |
+
"router_aux_loss_coef": 0.0,
|
| 30 |
+
"shared_expert_intermediate_size": 0,
|
| 31 |
"sliding_window": null,
|
| 32 |
"tie_word_embeddings": false,
|
| 33 |
"torch_dtype": "bfloat16",
|
| 34 |
"transformers_version": "4.52.3",
|
| 35 |
"use_cache": true,
|
| 36 |
+
"use_qk_norm": true,
|
| 37 |
"use_sliding_window": false,
|
| 38 |
"vocab_size": 151936
|
| 39 |
}
|