AdnanRiaz107 commited on
Commit
b9b345f
1 Parent(s): 2f00608

Upload config

Browse files
Files changed (2) hide show
  1. README.md +1 -1
  2. config.json +133 -24
README.md CHANGED
@@ -1,9 +1,9 @@
1
  ---
2
- base_model: microsoft/codebert-base-mlm
3
  tags:
4
  - trl
5
  - sft
6
  - generated_from_trainer
 
7
  datasets:
8
  - apps
9
  model-index:
 
1
  ---
 
2
  tags:
3
  - trl
4
  - sft
5
  - generated_from_trainer
6
+ base_model: microsoft/codebert-base-mlm
7
  datasets:
8
  - apps
9
  model-index:
config.json CHANGED
@@ -1,29 +1,138 @@
1
  {
2
- "_name_or_path": "microsoft/codebert-base-mlm",
3
  "architectures": [
4
- "RobertaForCausalLM"
5
  ],
6
- "attention_probs_dropout_prob": 0.1,
7
- "bos_token_id": 0,
8
- "classifier_dropout": null,
9
- "eos_token_id": 2,
10
- "hidden_act": "gelu",
11
- "hidden_dropout_prob": 0.1,
12
- "hidden_size": 768,
 
 
 
 
13
  "initializer_range": 0.02,
14
- "intermediate_size": 3072,
15
- "is_decoder": true,
16
- "layer_norm_eps": 1e-05,
17
- "max_position_embeddings": 514,
18
- "model_type": "roberta",
19
- "num_attention_heads": 12,
20
- "num_hidden_layers": 12,
21
- "output_past": true,
22
- "pad_token_id": 1,
23
- "position_embedding_type": "absolute",
24
- "torch_dtype": "float32",
25
- "transformers_version": "4.38.2",
26
- "type_vocab_size": 1,
27
- "use_cache": false,
28
- "vocab_size": 50265
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
29
  }
 
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": "microsoft/Phi-3-mini-128k-instruct--configuration_phi3.Phi3Config",
10
+ "AutoModelForCausalLM": "microsoft/Phi-3-mini-128k-instruct--modeling_phi3.Phi3ForCausalLM"
11
+ },
12
+ "bos_token_id": 1,
13
+ "embd_pdrop": 0.0,
14
+ "eos_token_id": 32000,
15
+ "hidden_act": "silu",
16
+ "hidden_size": 3072,
17
  "initializer_range": 0.02,
18
+ "intermediate_size": 8192,
19
+ "max_position_embeddings": 131072,
20
+ "model_type": "phi3",
21
+ "num_attention_heads": 32,
22
+ "num_hidden_layers": 32,
23
+ "num_key_value_heads": 32,
24
+ "original_max_position_embeddings": 4096,
25
+ "pad_token_id": 32000,
26
+ "resid_pdrop": 0.0,
27
+ "rms_norm_eps": 1e-05,
28
+ "rope_scaling": {
29
+ "long_factor": [
30
+ 1.0700000524520874,
31
+ 1.1200000047683716,
32
+ 1.149999976158142,
33
+ 1.4199999570846558,
34
+ 1.5699999332427979,
35
+ 1.7999999523162842,
36
+ 2.129999876022339,
37
+ 2.129999876022339,
38
+ 3.009999990463257,
39
+ 5.910000324249268,
40
+ 6.950000286102295,
41
+ 9.070000648498535,
42
+ 9.930000305175781,
43
+ 10.710000038146973,
44
+ 11.130000114440918,
45
+ 14.609999656677246,
46
+ 15.409998893737793,
47
+ 19.809999465942383,
48
+ 37.279998779296875,
49
+ 38.279998779296875,
50
+ 38.599998474121094,
51
+ 40.12000274658203,
52
+ 46.20000457763672,
53
+ 50.940006256103516,
54
+ 53.66000747680664,
55
+ 54.9373893737793,
56
+ 56.89738845825195,
57
+ 57.28738784790039,
58
+ 59.98738479614258,
59
+ 60.86738586425781,
60
+ 60.887386322021484,
61
+ 61.71739196777344,
62
+ 62.91739273071289,
63
+ 62.957393646240234,
64
+ 63.41739273071289,
65
+ 63.8173942565918,
66
+ 63.83739471435547,
67
+ 63.897396087646484,
68
+ 63.93739700317383,
69
+ 64.06739807128906,
70
+ 64.11434936523438,
71
+ 64.12435150146484,
72
+ 64.15435028076172,
73
+ 64.19435119628906,
74
+ 64.24435424804688,
75
+ 64.57435607910156,
76
+ 64.69000244140625,
77
+ 64.76000213623047
78
+ ],
79
+ "short_factor": [
80
+ 1.1,
81
+ 1.1,
82
+ 1.1,
83
+ 1.3000000000000003,
84
+ 1.3500000000000003,
85
+ 1.3500000000000003,
86
+ 1.4000000000000004,
87
+ 1.5500000000000005,
88
+ 2.000000000000001,
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
+ 2.0500000000000007,
106
+ 2.0500000000000007,
107
+ 2.0500000000000007,
108
+ 2.0500000000000007,
109
+ 2.0500000000000007,
110
+ 2.0500000000000007,
111
+ 2.1000000000000005,
112
+ 2.1000000000000005,
113
+ 2.1500000000000004,
114
+ 2.25,
115
+ 2.25,
116
+ 2.25,
117
+ 2.25,
118
+ 2.25,
119
+ 2.3999999999999995,
120
+ 2.4499999999999993,
121
+ 2.499999999999999,
122
+ 2.6999999999999984,
123
+ 2.6999999999999984,
124
+ 2.7499999999999982,
125
+ 2.799999999999998,
126
+ 2.8999999999999977,
127
+ 3.049999999999997
128
+ ],
129
+ "type": "longrope"
130
+ },
131
+ "rope_theta": 10000.0,
132
+ "sliding_window": 262144,
133
+ "tie_word_embeddings": false,
134
+ "torch_dtype": "bfloat16",
135
+ "transformers_version": "4.40.2",
136
+ "use_cache": true,
137
+ "vocab_size": 32064
138
  }