Update config.json
Browse files- config.json +15 -118
config.json
CHANGED
|
@@ -1,138 +1,35 @@
|
|
| 1 |
{
|
| 2 |
-
"_name_or_path": "microsoft/Phi-3-mini-
|
| 3 |
"architectures": [
|
| 4 |
-
"
|
| 5 |
],
|
| 6 |
"attention_dropout": 0.0,
|
| 7 |
-
"
|
| 8 |
-
"AutoConfig": "
|
| 9 |
-
"AutoModelForCausalLM": "
|
| 10 |
},
|
| 11 |
"bos_token_id": 1,
|
| 12 |
-
"
|
|
|
|
| 13 |
"hidden_act": "silu",
|
| 14 |
"hidden_size": 3072,
|
| 15 |
"initializer_range": 0.02,
|
| 16 |
"intermediate_size": 8192,
|
| 17 |
-
"max_position_embeddings":
|
| 18 |
"model_type": "phi3",
|
| 19 |
-
"xmodel_type": "phi_longrope",
|
| 20 |
"num_attention_heads": 32,
|
| 21 |
"num_hidden_layers": 32,
|
| 22 |
"num_key_value_heads": 32,
|
| 23 |
"original_max_position_embeddings": 4096,
|
|
|
|
|
|
|
| 24 |
"rms_norm_eps": 1e-05,
|
| 25 |
-
"rope_scaling":
|
| 26 |
-
"long_factor": [
|
| 27 |
-
1.0,
|
| 28 |
-
1.0,
|
| 29 |
-
1.0,
|
| 30 |
-
1.0,
|
| 31 |
-
1.0,
|
| 32 |
-
1.0,
|
| 33 |
-
1.0,
|
| 34 |
-
1.0,
|
| 35 |
-
1.0,
|
| 36 |
-
3.7391297817230225,
|
| 37 |
-
3.7699999999999756,
|
| 38 |
-
6.679999999999908,
|
| 39 |
-
11.956522941589355,
|
| 40 |
-
14.695652961730957,
|
| 41 |
-
16.649999999999697,
|
| 42 |
-
20.83000000000035,
|
| 43 |
-
22.91304588317871,
|
| 44 |
-
25.652175903320312,
|
| 45 |
-
28.391305923461914,
|
| 46 |
-
31.130435943603516,
|
| 47 |
-
33.869564056396484,
|
| 48 |
-
36.60869598388672,
|
| 49 |
-
39.34782409667969,
|
| 50 |
-
42.08695983886719,
|
| 51 |
-
44.826087951660156,
|
| 52 |
-
47.565216064453125,
|
| 53 |
-
50.30434799194336,
|
| 54 |
-
53.04347610473633,
|
| 55 |
-
55.78260803222656,
|
| 56 |
-
58.5217399597168,
|
| 57 |
-
61.26087188720703,
|
| 58 |
-
64.0,
|
| 59 |
-
64.0,
|
| 60 |
-
64.0,
|
| 61 |
-
64.0,
|
| 62 |
-
64.0,
|
| 63 |
-
64.0,
|
| 64 |
-
64.0,
|
| 65 |
-
64.0,
|
| 66 |
-
64.0,
|
| 67 |
-
64.0,
|
| 68 |
-
64.0,
|
| 69 |
-
64.0,
|
| 70 |
-
64.0,
|
| 71 |
-
64.0,
|
| 72 |
-
64.0,
|
| 73 |
-
64.0,
|
| 74 |
-
64.0
|
| 75 |
-
],
|
| 76 |
-
"short_factor": [
|
| 77 |
-
1.0,
|
| 78 |
-
1.0,
|
| 79 |
-
1.0,
|
| 80 |
-
1.0,
|
| 81 |
-
1.05,
|
| 82 |
-
1.05,
|
| 83 |
-
1.1500000000000001,
|
| 84 |
-
1.2000000000000002,
|
| 85 |
-
1.2500000000000002,
|
| 86 |
-
1.5000000000000004,
|
| 87 |
-
1.8000000000000007,
|
| 88 |
-
2.25,
|
| 89 |
-
2.3000000000000007,
|
| 90 |
-
2.3500000000000014,
|
| 91 |
-
2.5,
|
| 92 |
-
2.5,
|
| 93 |
-
2.55,
|
| 94 |
-
2.5999999999999988,
|
| 95 |
-
2.6999999999999993,
|
| 96 |
-
2.6999999999999993,
|
| 97 |
-
2.8499999999999988,
|
| 98 |
-
2.8999999999999986,
|
| 99 |
-
2.9999999999999982,
|
| 100 |
-
2.9999999999999982,
|
| 101 |
-
2.9999999999999982,
|
| 102 |
-
3.099999999999998,
|
| 103 |
-
3.299999999999997,
|
| 104 |
-
3.399999999999997,
|
| 105 |
-
3.599999999999996,
|
| 106 |
-
3.649999999999996,
|
| 107 |
-
3.7999999999999954,
|
| 108 |
-
3.899999999999995,
|
| 109 |
-
3.899999999999995,
|
| 110 |
-
3.899999999999995,
|
| 111 |
-
4.099999999999994,
|
| 112 |
-
4.099999999999994,
|
| 113 |
-
4.099999999999994,
|
| 114 |
-
4.099999999999994,
|
| 115 |
-
4.099999999999994,
|
| 116 |
-
4.149999999999994,
|
| 117 |
-
4.149999999999994,
|
| 118 |
-
4.149999999999994,
|
| 119 |
-
4.149999999999994,
|
| 120 |
-
4.149999999999994,
|
| 121 |
-
4.199999999999994,
|
| 122 |
-
4.249999999999994,
|
| 123 |
-
4.299999999999994,
|
| 124 |
-
4.399999999999993
|
| 125 |
-
],
|
| 126 |
-
"type": "longrope"
|
| 127 |
-
},
|
| 128 |
"rope_theta": 10000.0,
|
| 129 |
-
"sliding_window":
|
| 130 |
"tie_word_embeddings": false,
|
| 131 |
"torch_dtype": "bfloat16",
|
| 132 |
-
"transformers_version": "4.
|
| 133 |
-
"transformers.js_config": {
|
| 134 |
-
"kv_cache_dtype": "float16"
|
| 135 |
-
},
|
| 136 |
"use_cache": true,
|
| 137 |
-
"vocab_size":
|
| 138 |
-
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"_name_or_path": "microsoft/Phi-3-mini-4k-instruct-onnx",
|
| 3 |
"architectures": [
|
| 4 |
+
"Phi3ForCausalLM"
|
| 5 |
],
|
| 6 |
"attention_dropout": 0.0,
|
| 7 |
+
"auto_map": {
|
| 8 |
+
"AutoConfig": "configuration_phi3.Phi3Config",
|
| 9 |
+
"AutoModelForCausalLM": "modeling_phi3.Phi3ForCausalLM"
|
| 10 |
},
|
| 11 |
"bos_token_id": 1,
|
| 12 |
+
"embd_pdrop": 0.0,
|
| 13 |
+
"eos_token_id": 32000,
|
| 14 |
"hidden_act": "silu",
|
| 15 |
"hidden_size": 3072,
|
| 16 |
"initializer_range": 0.02,
|
| 17 |
"intermediate_size": 8192,
|
| 18 |
+
"max_position_embeddings": 4096,
|
| 19 |
"model_type": "phi3",
|
|
|
|
| 20 |
"num_attention_heads": 32,
|
| 21 |
"num_hidden_layers": 32,
|
| 22 |
"num_key_value_heads": 32,
|
| 23 |
"original_max_position_embeddings": 4096,
|
| 24 |
+
"pad_token_id": 32000,
|
| 25 |
+
"resid_pdrop": 0.0,
|
| 26 |
"rms_norm_eps": 1e-05,
|
| 27 |
+
"rope_scaling": null,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 28 |
"rope_theta": 10000.0,
|
| 29 |
+
"sliding_window": 2047,
|
| 30 |
"tie_word_embeddings": false,
|
| 31 |
"torch_dtype": "bfloat16",
|
| 32 |
+
"transformers_version": "4.39.3",
|
|
|
|
|
|
|
|
|
|
| 33 |
"use_cache": true,
|
| 34 |
+
"vocab_size": 32064
|
| 35 |
+
}
|