Update config.json
Browse files- config.json +17 -19
config.json
CHANGED
@@ -11,9 +11,9 @@
|
|
11 |
"hidden_act": "silu",
|
12 |
"hidden_size": 4096,
|
13 |
"initializer_range": 0.02,
|
14 |
-
"intermediate_size":
|
15 |
-
"max_position_embeddings":
|
16 |
-
"max_window_layers":
|
17 |
"mlp_only_layers": [],
|
18 |
"model_type": "qwen3_moe",
|
19 |
"moe_intermediate_size": 1536,
|
@@ -24,7 +24,17 @@
|
|
24 |
"num_hidden_layers": 94,
|
25 |
"num_key_value_heads": 4,
|
26 |
"output_router_logits": false,
|
27 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
28 |
"quantization_config": {
|
29 |
"activation_scheme": "dynamic",
|
30 |
"modules_to_not_convert": [
|
@@ -312,23 +322,11 @@
|
|
312 |
"model.layers.93.mlp.gate",
|
313 |
"model.layers.93.post_attention_layernorm"
|
314 |
],
|
|
|
315 |
"quant_method": "fp8",
|
316 |
"weight_block_size": [
|
317 |
128,
|
318 |
128
|
319 |
]
|
320 |
-
}
|
321 |
-
|
322 |
-
"rope_scaling": null,
|
323 |
-
"rope_theta": 5000000,
|
324 |
-
"router_aux_loss_coef": 0.0,
|
325 |
-
"shared_expert_intermediate_size": 0,
|
326 |
-
"sliding_window": null,
|
327 |
-
"tie_word_embeddings": false,
|
328 |
-
"torch_dtype": "bfloat16",
|
329 |
-
"transformers_version": "4.51.3",
|
330 |
-
"use_cache": true,
|
331 |
-
"use_qk_norm": true,
|
332 |
-
"use_sliding_window": false,
|
333 |
-
"vocab_size": 151936
|
334 |
-
}
|
|
|
11 |
"hidden_act": "silu",
|
12 |
"hidden_size": 4096,
|
13 |
"initializer_range": 0.02,
|
14 |
+
"intermediate_size": 12288,
|
15 |
+
"max_position_embeddings": 262144,
|
16 |
+
"max_window_layers": 94,
|
17 |
"mlp_only_layers": [],
|
18 |
"model_type": "qwen3_moe",
|
19 |
"moe_intermediate_size": 1536,
|
|
|
24 |
"num_hidden_layers": 94,
|
25 |
"num_key_value_heads": 4,
|
26 |
"output_router_logits": false,
|
27 |
+
"rms_norm_eps": 1e-06,
|
28 |
+
"rope_scaling": null,
|
29 |
+
"rope_theta": 5000000,
|
30 |
+
"router_aux_loss_coef": 0.001,
|
31 |
+
"sliding_window": null,
|
32 |
+
"tie_word_embeddings": false,
|
33 |
+
"torch_dtype": "bfloat16",
|
34 |
+
"transformers_version": "4.51.0",
|
35 |
+
"use_cache": true,
|
36 |
+
"use_sliding_window": false,
|
37 |
+
"vocab_size": 151936,
|
38 |
"quantization_config": {
|
39 |
"activation_scheme": "dynamic",
|
40 |
"modules_to_not_convert": [
|
|
|
322 |
"model.layers.93.mlp.gate",
|
323 |
"model.layers.93.post_attention_layernorm"
|
324 |
],
|
325 |
+
"fmt": "e4m3",
|
326 |
"quant_method": "fp8",
|
327 |
"weight_block_size": [
|
328 |
128,
|
329 |
128
|
330 |
]
|
331 |
+
}
|
332 |
+
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|