Create config.json
Browse files- config.json +137 -0
config.json
ADDED
@@ -0,0 +1,137 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "Phi-3-mini-128k-instruct",
|
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": 131072,
|
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": {
|
28 |
+
"long_factor": [
|
29 |
+
1.0299999713897705,
|
30 |
+
1.0499999523162842,
|
31 |
+
1.0499999523162842,
|
32 |
+
1.0799999237060547,
|
33 |
+
1.2299998998641968,
|
34 |
+
1.2299998998641968,
|
35 |
+
1.2999999523162842,
|
36 |
+
1.4499999284744263,
|
37 |
+
1.5999999046325684,
|
38 |
+
1.6499998569488525,
|
39 |
+
1.8999998569488525,
|
40 |
+
2.859999895095825,
|
41 |
+
3.68999981880188,
|
42 |
+
5.419999599456787,
|
43 |
+
5.489999771118164,
|
44 |
+
5.489999771118164,
|
45 |
+
9.09000015258789,
|
46 |
+
11.579999923706055,
|
47 |
+
15.65999984741211,
|
48 |
+
15.769999504089355,
|
49 |
+
15.789999961853027,
|
50 |
+
18.360000610351562,
|
51 |
+
21.989999771118164,
|
52 |
+
23.079999923706055,
|
53 |
+
30.009998321533203,
|
54 |
+
32.35000228881836,
|
55 |
+
32.590003967285156,
|
56 |
+
35.56000518798828,
|
57 |
+
39.95000457763672,
|
58 |
+
53.840003967285156,
|
59 |
+
56.20000457763672,
|
60 |
+
57.95000457763672,
|
61 |
+
59.29000473022461,
|
62 |
+
59.77000427246094,
|
63 |
+
59.920005798339844,
|
64 |
+
61.190006256103516,
|
65 |
+
61.96000671386719,
|
66 |
+
62.50000762939453,
|
67 |
+
63.3700065612793,
|
68 |
+
63.48000717163086,
|
69 |
+
63.48000717163086,
|
70 |
+
63.66000747680664,
|
71 |
+
63.850006103515625,
|
72 |
+
64.08000946044922,
|
73 |
+
64.760009765625,
|
74 |
+
64.80001068115234,
|
75 |
+
64.81001281738281,
|
76 |
+
64.81001281738281
|
77 |
+
],
|
78 |
+
"short_factor": [
|
79 |
+
1.05,
|
80 |
+
1.05,
|
81 |
+
1.05,
|
82 |
+
1.1,
|
83 |
+
1.1,
|
84 |
+
1.1500000000000001,
|
85 |
+
1.2000000000000002,
|
86 |
+
1.2500000000000002,
|
87 |
+
1.3000000000000003,
|
88 |
+
1.3500000000000003,
|
89 |
+
1.5000000000000004,
|
90 |
+
2.000000000000001,
|
91 |
+
2.000000000000001,
|
92 |
+
2.000000000000001,
|
93 |
+
2.000000000000001,
|
94 |
+
2.000000000000001,
|
95 |
+
2.000000000000001,
|
96 |
+
2.000000000000001,
|
97 |
+
2.000000000000001,
|
98 |
+
2.000000000000001,
|
99 |
+
2.000000000000001,
|
100 |
+
2.000000000000001,
|
101 |
+
2.000000000000001,
|
102 |
+
2.000000000000001,
|
103 |
+
2.000000000000001,
|
104 |
+
2.000000000000001,
|
105 |
+
2.000000000000001,
|
106 |
+
2.000000000000001,
|
107 |
+
2.000000000000001,
|
108 |
+
2.000000000000001,
|
109 |
+
2.000000000000001,
|
110 |
+
2.000000000000001,
|
111 |
+
2.0500000000000007,
|
112 |
+
2.0500000000000007,
|
113 |
+
2.0500000000000007,
|
114 |
+
2.1000000000000005,
|
115 |
+
2.1000000000000005,
|
116 |
+
2.1000000000000005,
|
117 |
+
2.1500000000000004,
|
118 |
+
2.1500000000000004,
|
119 |
+
2.3499999999999996,
|
120 |
+
2.549999999999999,
|
121 |
+
2.5999999999999988,
|
122 |
+
2.5999999999999988,
|
123 |
+
2.7499999999999982,
|
124 |
+
2.849999999999998,
|
125 |
+
2.849999999999998,
|
126 |
+
2.9499999999999975
|
127 |
+
],
|
128 |
+
"type": "su"
|
129 |
+
},
|
130 |
+
"rope_theta": 10000.0,
|
131 |
+
"sliding_window": 262144,
|
132 |
+
"tie_word_embeddings": false,
|
133 |
+
"torch_dtype": "bfloat16",
|
134 |
+
"transformers_version": "4.39.3",
|
135 |
+
"use_cache": true,
|
136 |
+
"vocab_size": 32064
|
137 |
+
}
|