Update config.json
Browse files- config.json +33 -2
config.json
CHANGED
|
@@ -9,6 +9,36 @@
|
|
| 9 |
"hidden_size": 3584,
|
| 10 |
"initializer_range": 0.02,
|
| 11 |
"intermediate_size": 18944,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 12 |
"max_position_embeddings": 131072,
|
| 13 |
"max_window_layers": 28,
|
| 14 |
"model_type": "qwen2",
|
|
@@ -16,11 +46,12 @@
|
|
| 16 |
"num_hidden_layers": 28,
|
| 17 |
"num_key_value_heads": 4,
|
| 18 |
"rms_norm_eps": 1e-06,
|
|
|
|
| 19 |
"rope_theta": 10000,
|
| 20 |
-
"sliding_window":
|
| 21 |
"tie_word_embeddings": false,
|
| 22 |
"torch_dtype": "bfloat16",
|
| 23 |
-
"transformers_version": "4.
|
| 24 |
"use_cache": true,
|
| 25 |
"use_mrope": false,
|
| 26 |
"use_sliding_window": false,
|
|
|
|
| 9 |
"hidden_size": 3584,
|
| 10 |
"initializer_range": 0.02,
|
| 11 |
"intermediate_size": 18944,
|
| 12 |
+
"layer_types": [
|
| 13 |
+
"full_attention",
|
| 14 |
+
"full_attention",
|
| 15 |
+
"full_attention",
|
| 16 |
+
"full_attention",
|
| 17 |
+
"full_attention",
|
| 18 |
+
"full_attention",
|
| 19 |
+
"full_attention",
|
| 20 |
+
"full_attention",
|
| 21 |
+
"full_attention",
|
| 22 |
+
"full_attention",
|
| 23 |
+
"full_attention",
|
| 24 |
+
"full_attention",
|
| 25 |
+
"full_attention",
|
| 26 |
+
"full_attention",
|
| 27 |
+
"full_attention",
|
| 28 |
+
"full_attention",
|
| 29 |
+
"full_attention",
|
| 30 |
+
"full_attention",
|
| 31 |
+
"full_attention",
|
| 32 |
+
"full_attention",
|
| 33 |
+
"full_attention",
|
| 34 |
+
"full_attention",
|
| 35 |
+
"full_attention",
|
| 36 |
+
"full_attention",
|
| 37 |
+
"full_attention",
|
| 38 |
+
"full_attention",
|
| 39 |
+
"full_attention",
|
| 40 |
+
"full_attention"
|
| 41 |
+
],
|
| 42 |
"max_position_embeddings": 131072,
|
| 43 |
"max_window_layers": 28,
|
| 44 |
"model_type": "qwen2",
|
|
|
|
| 46 |
"num_hidden_layers": 28,
|
| 47 |
"num_key_value_heads": 4,
|
| 48 |
"rms_norm_eps": 1e-06,
|
| 49 |
+
"rope_scaling": null,
|
| 50 |
"rope_theta": 10000,
|
| 51 |
+
"sliding_window": null,
|
| 52 |
"tie_word_embeddings": false,
|
| 53 |
"torch_dtype": "bfloat16",
|
| 54 |
+
"transformers_version": "4.55.0",
|
| 55 |
"use_cache": true,
|
| 56 |
"use_mrope": false,
|
| 57 |
"use_sliding_window": false,
|