Hugging Face's logo

junaedifahmi
/
phi3-indonesian

PEFT
Safetensors
phi3
trl
sft
Generated from Trainer
custom_code
4-bit precision
bitsandbytes
Model card Files Community
junaedifahmi commited on
Commit
0323cc2
•
1 Parent(s): 48de4d1

Upload Phi3ForCausalLM

Browse files
Files changed (3) hide show
  1. config.json +153 -0
  2. generation_config.json +7 -0
  3. model.safetensors +3 -0
config.json ADDED
@@ -0,0 +1,153 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 32011,
13
+ "embd_pdrop": 0.0,
14
+ "eos_token_id": 32012,
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": 32012,
26
+ "quantization_config": {
27
+ "_load_in_4bit": true,
28
+ "_load_in_8bit": false,
29
+ "bnb_4bit_compute_dtype": "bfloat16",
30
+ "bnb_4bit_quant_storage": "uint8",
31
+ "bnb_4bit_quant_type": "nf4",
32
+ "bnb_4bit_use_double_quant": true,
33
+ "llm_int8_enable_fp32_cpu_offload": false,
34
+ "llm_int8_has_fp16_weight": false,
35
+ "llm_int8_skip_modules": null,
36
+ "llm_int8_threshold": 6.0,
37
+ "load_in_4bit": true,
38
+ "load_in_8bit": false,
39
+ "quant_method": "bitsandbytes"
40
+ },
41
+ "resid_pdrop": 0.0,
42
+ "rms_norm_eps": 1e-05,
43
+ "rope_scaling": {
44
+ "long_factor": [
45
+ 1.0700000524520874,
46
+ 1.1200000047683716,
47
+ 1.149999976158142,
48
+ 1.4199999570846558,
49
+ 1.5699999332427979,
50
+ 1.7999999523162842,
51
+ 2.129999876022339,
52
+ 2.129999876022339,
53
+ 3.009999990463257,
54
+ 5.910000324249268,
55
+ 6.950000286102295,
56
+ 9.070000648498535,
57
+ 9.930000305175781,
58
+ 10.710000038146973,
59
+ 11.130000114440918,
60
+ 14.609999656677246,
61
+ 15.409998893737793,
62
+ 19.809999465942383,
63
+ 37.279998779296875,
64
+ 38.279998779296875,
65
+ 38.599998474121094,
66
+ 40.12000274658203,
67
+ 46.20000457763672,
68
+ 50.940006256103516,
69
+ 53.66000747680664,
70
+ 54.9373893737793,
71
+ 56.89738845825195,
72
+ 57.28738784790039,
73
+ 59.98738479614258,
74
+ 60.86738586425781,
75
+ 60.887386322021484,
76
+ 61.71739196777344,
77
+ 62.91739273071289,
78
+ 62.957393646240234,
79
+ 63.41739273071289,
80
+ 63.8173942565918,
81
+ 63.83739471435547,
82
+ 63.897396087646484,
83
+ 63.93739700317383,
84
+ 64.06739807128906,
85
+ 64.11434936523438,
86
+ 64.12435150146484,
87
+ 64.15435028076172,
88
+ 64.19435119628906,
89
+ 64.24435424804688,
90
+ 64.57435607910156,
91
+ 64.69000244140625,
92
+ 64.76000213623047
93
+ ],
94
+ "short_factor": [
95
+ 1.1,
96
+ 1.1,
97
+ 1.1,
98
+ 1.3000000000000003,
99
+ 1.3500000000000003,
100
+ 1.3500000000000003,
101
+ 1.4000000000000004,
102
+ 1.5500000000000005,
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
+ 2.000000000000001,
112
+ 2.000000000000001,
113
+ 2.000000000000001,
114
+ 2.000000000000001,
115
+ 2.000000000000001,
116
+ 2.000000000000001,
117
+ 2.000000000000001,
118
+ 2.000000000000001,
119
+ 2.000000000000001,
120
+ 2.0500000000000007,
121
+ 2.0500000000000007,
122
+ 2.0500000000000007,
123
+ 2.0500000000000007,
124
+ 2.0500000000000007,
125
+ 2.0500000000000007,
126
+ 2.1000000000000005,
127
+ 2.1000000000000005,
128
+ 2.1500000000000004,
129
+ 2.25,
130
+ 2.25,
131
+ 2.25,
132
+ 2.25,
133
+ 2.25,
134
+ 2.3999999999999995,
135
+ 2.4499999999999993,
136
+ 2.499999999999999,
137
+ 2.6999999999999984,
138
+ 2.6999999999999984,
139
+ 2.7499999999999982,
140
+ 2.799999999999998,
141
+ 2.8999999999999977,
142
+ 3.049999999999997
143
+ ],
144
+ "type": "longrope"
145
+ },
146
+ "rope_theta": 10000.0,
147
+ "sliding_window": 262144,
148
+ "tie_word_embeddings": false,
149
+ "torch_dtype": "float32",
150
+ "transformers_version": "4.44.2",
151
+ "use_cache": true,
152
+ "vocab_size": 32013
153
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 32011,
4
+ "eos_token_id": 32012,
5
+ "pad_token_id": 32012,
6
+ "transformers_version": "4.44.2"
7
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f91e6182fdfdb241fcf637dc02647bb4777aee060a544834204a0b5f5b276e3f
3
+ size 2657260886