Hugging Face's logo

DongfuJiang
/
PairRM-V2-phi3-3-mini-checkpoint-2000

Text Generation
Transformers
Safetensors
phi3
conversational
custom_code
text-generation-inference
Inference Endpoints
Model card Files Community
DongfuJiang commited on
Commit
07427c9
•
1 Parent(s): dd43c35

Upload config.json with huggingface_hub

Browse files
Files changed (1) hide show
  1. config.json +139 -1
config.json CHANGED
@@ -1 +1,139 @@
1
- {"_name_or_path": "microsoft/Phi-3-mini-128k-instruct", "architectures": ["Phi3ForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "auto_map": {"AutoConfig": "configuration_phi3.Phi3Config", "AutoModel": "modeling_phi3.Phi3ForCausalLM", "AutoModelForCausalLM": "modeling_phi3.Phi3ForCausalLM"}, "bos_token_id": 1, "embd_pdrop": 0.0, "eos_token_id": 32000, "hidden_act": "silu", "hidden_size": 3072, "initializer_range": 0.02, "intermediate_size": 8192, "max_position_embeddings": 131072, "model_type": "phi3", "num_attention_heads": 32, "num_hidden_layers": 32, "num_key_value_heads": 32, "original_max_position_embeddings": 4096, "pad_token_id": 32000, "resid_pdrop": 0.0, "rms_norm_eps": 1e-05, "rope_scaling": {"long_factor": [1.0700000524520874, 1.1200000047683716, 1.149999976158142, 1.4199999570846558, 1.5699999332427979, 1.7999999523162842, 2.129999876022339, 2.129999876022339, 3.009999990463257, 5.910000324249268, 6.950000286102295, 9.070000648498535, 9.930000305175781, 10.710000038146973, 11.130000114440918, 14.609999656677246, 15.409998893737793, 19.809999465942383, 37.279998779296875, 38.279998779296875, 38.599998474121094, 40.12000274658203, 46.20000457763672, 50.940006256103516, 53.66000747680664, 54.9373893737793, 56.89738845825195, 57.28738784790039, 59.98738479614258, 60.86738586425781, 60.887386322021484, 61.71739196777344, 62.91739273071289, 62.957393646240234, 63.41739273071289, 63.8173942565918, 63.83739471435547, 63.897396087646484, 63.93739700317383, 64.06739807128906, 64.11434936523438, 64.12435150146484, 64.15435028076172, 64.19435119628906, 64.24435424804688, 64.57435607910156, 64.69000244140625, 64.76000213623047], "short_factor": [1.1, 1.1, 1.1, 1.3000000000000003, 1.3500000000000003, 1.3500000000000003, 1.4000000000000004, 1.5500000000000005, 2.000000000000001, 2.000000000000001, 2.000000000000001, 2.000000000000001, 2.000000000000001, 2.000000000000001, 2.000000000000001, 2.000000000000001, 2.000000000000001, 2.000000000000001, 2.000000000000001, 2.000000000000001, 2.000000000000001, 2.000000000000001, 2.000000000000001, 2.000000000000001, 2.000000000000001, 2.0500000000000007, 2.0500000000000007, 2.0500000000000007, 2.0500000000000007, 2.0500000000000007, 2.0500000000000007, 2.1000000000000005, 2.1000000000000005, 2.1500000000000004, 2.25, 2.25, 2.25, 2.25, 2.25, 2.3999999999999995, 2.4499999999999993, 2.499999999999999, 2.6999999999999984, 2.6999999999999984, 2.7499999999999982, 2.799999999999998, 2.8999999999999977, 3.049999999999997], "type": "longrope"}, "rope_theta": 10000.0, "sliding_window": 262144, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "transformers_version": "4.43.1", "use_cache": false, "vocab_size": 32064}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "microsoft/Phi-3-mini-128k-instruct",
3
+ "architectures": [
4
+ "Phi3ForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "auto_map": {
9
+ "AutoConfig": "configuration_phi3.Phi3Config",
10
+ "AutoModel": "modeling_phi3.Phi3ForCausalLM",
11
+ "AutoModelForCausalLM": "modeling_phi3.Phi3ForCausalLM"
12
+ },
13
+ "bos_token_id": 1,
14
+ "embd_pdrop": 0.0,
15
+ "eos_token_id": 32000,
16
+ "hidden_act": "silu",
17
+ "hidden_size": 3072,
18
+ "initializer_range": 0.02,
19
+ "intermediate_size": 8192,
20
+ "max_position_embeddings": 131072,
21
+ "model_type": "phi3",
22
+ "num_attention_heads": 32,
23
+ "num_hidden_layers": 32,
24
+ "num_key_value_heads": 32,
25
+ "original_max_position_embeddings": 4096,
26
+ "pad_token_id": 32000,
27
+ "resid_pdrop": 0.0,
28
+ "rms_norm_eps": 1e-05,
29
+ "rope_scaling": {
30
+ "long_factor": [
31
+ 1.0700000524520874,
32
+ 1.1200000047683716,
33
+ 1.149999976158142,
34
+ 1.4199999570846558,
35
+ 1.5699999332427979,
36
+ 1.7999999523162842,
37
+ 2.129999876022339,
38
+ 2.129999876022339,
39
+ 3.009999990463257,
40
+ 5.910000324249268,
41
+ 6.950000286102295,
42
+ 9.070000648498535,
43
+ 9.930000305175781,
44
+ 10.710000038146973,
45
+ 11.130000114440918,
46
+ 14.609999656677246,
47
+ 15.409998893737793,
48
+ 19.809999465942383,
49
+ 37.279998779296875,
50
+ 38.279998779296875,
51
+ 38.599998474121094,
52
+ 40.12000274658203,
53
+ 46.20000457763672,
54
+ 50.940006256103516,
55
+ 53.66000747680664,
56
+ 54.9373893737793,
57
+ 56.89738845825195,
58
+ 57.28738784790039,
59
+ 59.98738479614258,
60
+ 60.86738586425781,
61
+ 60.887386322021484,
62
+ 61.71739196777344,
63
+ 62.91739273071289,
64
+ 62.957393646240234,
65
+ 63.41739273071289,
66
+ 63.8173942565918,
67
+ 63.83739471435547,
68
+ 63.897396087646484,
69
+ 63.93739700317383,
70
+ 64.06739807128906,
71
+ 64.11434936523438,
72
+ 64.12435150146484,
73
+ 64.15435028076172,
74
+ 64.19435119628906,
75
+ 64.24435424804688,
76
+ 64.57435607910156,
77
+ 64.69000244140625,
78
+ 64.76000213623047
79
+ ],
80
+ "short_factor": [
81
+ 1.1,
82
+ 1.1,
83
+ 1.1,
84
+ 1.3000000000000003,
85
+ 1.3500000000000003,
86
+ 1.3500000000000003,
87
+ 1.4000000000000004,
88
+ 1.5500000000000005,
89
+ 2.000000000000001,
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
+ 2.0500000000000007,
107
+ 2.0500000000000007,
108
+ 2.0500000000000007,
109
+ 2.0500000000000007,
110
+ 2.0500000000000007,
111
+ 2.0500000000000007,
112
+ 2.1000000000000005,
113
+ 2.1000000000000005,
114
+ 2.1500000000000004,
115
+ 2.25,
116
+ 2.25,
117
+ 2.25,
118
+ 2.25,
119
+ 2.25,
120
+ 2.3999999999999995,
121
+ 2.4499999999999993,
122
+ 2.499999999999999,
123
+ 2.6999999999999984,
124
+ 2.6999999999999984,
125
+ 2.7499999999999982,
126
+ 2.799999999999998,
127
+ 2.8999999999999977,
128
+ 3.049999999999997
129
+ ],
130
+ "type": "longrope"
131
+ },
132
+ "rope_theta": 10000.0,
133
+ "sliding_window": 262144,
134
+ "tie_word_embeddings": false,
135
+ "torch_dtype": "bfloat16",
136
+ "transformers_version": "4.43.1",
137
+ "use_cache": false,
138
+ "vocab_size": 32064
139
+ }