Fix config.json for vLLM compatibility (remove layer_types, fix rope_parameters)
Browse files- config.json +4 -36
config.json
CHANGED
|
@@ -10,36 +10,6 @@
|
|
| 10 |
"hidden_size": 3584,
|
| 11 |
"initializer_range": 0.02,
|
| 12 |
"intermediate_size": 18944,
|
| 13 |
-
"layer_types": [
|
| 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 |
-
"full_attention"
|
| 42 |
-
],
|
| 43 |
"max_position_embeddings": 32768,
|
| 44 |
"max_window_layers": 28,
|
| 45 |
"model_type": "qwen2",
|
|
@@ -48,14 +18,12 @@
|
|
| 48 |
"num_key_value_heads": 4,
|
| 49 |
"pad_token_id": null,
|
| 50 |
"rms_norm_eps": 1e-06,
|
| 51 |
-
"rope_parameters": {
|
| 52 |
-
"rope_theta": 1000000.0,
|
| 53 |
-
"rope_type": "default"
|
| 54 |
-
},
|
| 55 |
"sliding_window": null,
|
| 56 |
"tie_word_embeddings": false,
|
| 57 |
"transformers_version": "5.0.0",
|
| 58 |
"use_cache": true,
|
| 59 |
"use_sliding_window": false,
|
| 60 |
-
"vocab_size": 152064
|
| 61 |
-
|
|
|
|
|
|
|
|
|
| 10 |
"hidden_size": 3584,
|
| 11 |
"initializer_range": 0.02,
|
| 12 |
"intermediate_size": 18944,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 13 |
"max_position_embeddings": 32768,
|
| 14 |
"max_window_layers": 28,
|
| 15 |
"model_type": "qwen2",
|
|
|
|
| 18 |
"num_key_value_heads": 4,
|
| 19 |
"pad_token_id": null,
|
| 20 |
"rms_norm_eps": 1e-06,
|
|
|
|
|
|
|
|
|
|
|
|
|
| 21 |
"sliding_window": null,
|
| 22 |
"tie_word_embeddings": false,
|
| 23 |
"transformers_version": "5.0.0",
|
| 24 |
"use_cache": true,
|
| 25 |
"use_sliding_window": false,
|
| 26 |
+
"vocab_size": 152064,
|
| 27 |
+
"rope_theta": 1000000.0,
|
| 28 |
+
"rope_scaling": null
|
| 29 |
+
}
|