dbaek111 commited on
Commit
1a26141
1 Parent(s): 25578dc

Upload Phi3ForCausalLM

Browse files
Files changed (4) hide show
  1. README.md +3 -1
  2. config.json +153 -0
  3. generation_config.json +11 -0
  4. model.safetensors +3 -0
README.md CHANGED
@@ -1,6 +1,8 @@
1
  ---
2
  library_name: transformers
3
- tags: []
 
 
4
  ---
5
 
6
  # Model Card for Model ID
 
1
  ---
2
  library_name: transformers
3
+ tags:
4
+ - trl
5
+ - sft
6
  ---
7
 
8
  # Model Card for Model ID
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_dropout": 0.0,
7
+ "auto_map": {
8
+ "AutoConfig": "microsoft/Phi-3-mini-128k-instruct--configuration_phi3.Phi3Config",
9
+ "AutoModelForCausalLM": "microsoft/Phi-3-mini-128k-instruct--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
+ "pretraining_tp": 1,
26
+ "quantization_config": {
27
+ "_load_in_4bit": true,
28
+ "_load_in_8bit": false,
29
+ "bnb_4bit_compute_dtype": "float16",
30
+ "bnb_4bit_quant_storage": "uint8",
31
+ "bnb_4bit_quant_type": "nf4",
32
+ "bnb_4bit_use_double_quant": false,
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
+ 1.0299999713897705,
46
+ 1.0499999523162842,
47
+ 1.0499999523162842,
48
+ 1.0799999237060547,
49
+ 1.2299998998641968,
50
+ 1.2299998998641968,
51
+ 1.2999999523162842,
52
+ 1.4499999284744263,
53
+ 1.5999999046325684,
54
+ 1.6499998569488525,
55
+ 1.8999998569488525,
56
+ 2.859999895095825,
57
+ 3.68999981880188,
58
+ 5.419999599456787,
59
+ 5.489999771118164,
60
+ 5.489999771118164,
61
+ 9.09000015258789,
62
+ 11.579999923706055,
63
+ 15.65999984741211,
64
+ 15.769999504089355,
65
+ 15.789999961853027,
66
+ 18.360000610351562,
67
+ 21.989999771118164,
68
+ 23.079999923706055,
69
+ 30.009998321533203,
70
+ 32.35000228881836,
71
+ 32.590003967285156,
72
+ 35.56000518798828,
73
+ 39.95000457763672,
74
+ 53.840003967285156,
75
+ 56.20000457763672,
76
+ 57.95000457763672,
77
+ 59.29000473022461,
78
+ 59.77000427246094,
79
+ 59.920005798339844,
80
+ 61.190006256103516,
81
+ 61.96000671386719,
82
+ 62.50000762939453,
83
+ 63.3700065612793,
84
+ 63.48000717163086,
85
+ 63.48000717163086,
86
+ 63.66000747680664,
87
+ 63.850006103515625,
88
+ 64.08000946044922,
89
+ 64.760009765625,
90
+ 64.80001068115234,
91
+ 64.81001281738281,
92
+ 64.81001281738281
93
+ ],
94
+ "short_factor": [
95
+ 1.05,
96
+ 1.05,
97
+ 1.05,
98
+ 1.1,
99
+ 1.1,
100
+ 1.1500000000000001,
101
+ 1.2000000000000002,
102
+ 1.2500000000000002,
103
+ 1.3000000000000003,
104
+ 1.3500000000000003,
105
+ 1.5000000000000004,
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
+ 2.000000000000001,
121
+ 2.000000000000001,
122
+ 2.000000000000001,
123
+ 2.000000000000001,
124
+ 2.000000000000001,
125
+ 2.000000000000001,
126
+ 2.000000000000001,
127
+ 2.0500000000000007,
128
+ 2.0500000000000007,
129
+ 2.0500000000000007,
130
+ 2.1000000000000005,
131
+ 2.1000000000000005,
132
+ 2.1000000000000005,
133
+ 2.1500000000000004,
134
+ 2.1500000000000004,
135
+ 2.3499999999999996,
136
+ 2.549999999999999,
137
+ 2.5999999999999988,
138
+ 2.5999999999999988,
139
+ 2.7499999999999982,
140
+ 2.849999999999998,
141
+ 2.849999999999998,
142
+ 2.9499999999999975
143
+ ],
144
+ "type": "su"
145
+ },
146
+ "rope_theta": 10000.0,
147
+ "sliding_window": 262144,
148
+ "tie_word_embeddings": false,
149
+ "torch_dtype": "float32",
150
+ "transformers_version": "4.40.1",
151
+ "use_cache": true,
152
+ "vocab_size": 32064
153
+ }
generation_config.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": [
5
+ 32000,
6
+ 32001,
7
+ 32007
8
+ ],
9
+ "pad_token_id": 32000,
10
+ "transformers_version": "4.40.1"
11
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eee7417c7cd87d03a7c361a695041f07c6345aabcf22ab2eef0a59f4e8cf9487
3
+ size 2827324312