TitleOS commited on
Commit
5dd17a9
·
verified ·
1 Parent(s): 85c0939

Upload 6 files

Browse files
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
chat_template.jinja ADDED
@@ -0,0 +1 @@
 
 
1
+ {{ '<|system|>Your name is Phi, an AI math expert developed by Microsoft.' }}{% for message in messages %}{% if message['role'] == 'system' %} {{ message['content'] }}{% if 'tools' in message and message['tools'] is not none %}{{ '<|tool|>' + message['tools'] + '<|/tool|>' }}{% endif %}{% endif %}{% endfor %}{{ '<|end|>' }}{% for message in messages %}{% if message['role'] != 'system' %}{{ '<|' + message['role'] + '|>' + message['content'] + '<|end|>' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>' }}{% else %}{{ eos_token }}{% endif %}
config.json ADDED
@@ -0,0 +1,141 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Phi3ForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 199999,
8
+ "dtype": "float16",
9
+ "embd_pdrop": 0.0,
10
+ "eos_token_id": 199999,
11
+ "full_attn_mod": 1,
12
+ "hidden_act": "silu",
13
+ "hidden_size": 3072,
14
+ "initializer_range": 0.02,
15
+ "intermediate_size": 8192,
16
+ "interpolate_factor": 1,
17
+ "lm_head_bias": false,
18
+ "max_position_embeddings": 131072,
19
+ "mlp_bias": false,
20
+ "model_type": "phi3",
21
+ "num_attention_heads": 24,
22
+ "num_hidden_layers": 32,
23
+ "num_key_value_heads": 8,
24
+ "original_max_position_embeddings": 4096,
25
+ "pad_token_id": 199999,
26
+ "partial_rotary_factor": 0.75,
27
+ "resid_pdrop": 0.0,
28
+ "rms_norm_eps": 1e-05,
29
+ "rope_parameters": {
30
+ "long_factor": [
31
+ 1,
32
+ 1.118320672,
33
+ 1.250641126,
34
+ 1.398617824,
35
+ 1.564103225,
36
+ 1.74916897,
37
+ 1.956131817,
38
+ 2.187582649,
39
+ 2.446418898,
40
+ 2.735880826,
41
+ 3.059592084,
42
+ 3.421605075,
43
+ 3.826451687,
44
+ 4.279200023,
45
+ 4.785517845,
46
+ 5.351743533,
47
+ 5.984965424,
48
+ 6.693110555,
49
+ 7.485043894,
50
+ 8.370679318,
51
+ 9.36110372,
52
+ 10.4687158,
53
+ 11.70738129,
54
+ 13.09260651,
55
+ 14.64173252,
56
+ 16.37415215,
57
+ 18.31155283,
58
+ 20.47818807,
59
+ 22.90118105,
60
+ 25.61086418,
61
+ 28.64115884,
62
+ 32.03,
63
+ 32.1,
64
+ 32.13,
65
+ 32.23,
66
+ 32.6,
67
+ 32.61,
68
+ 32.64,
69
+ 32.66,
70
+ 32.7,
71
+ 32.71,
72
+ 32.93,
73
+ 32.97,
74
+ 33.28,
75
+ 33.49,
76
+ 33.5,
77
+ 44.16,
78
+ 47.77
79
+ ],
80
+ "original_max_position_embeddings": 4096,
81
+ "partial_rotary_factor": 0.75,
82
+ "rope_theta": 10000.0,
83
+ "rope_type": "longrope",
84
+ "short_factor": [
85
+ 1,
86
+ 1.118320672,
87
+ 1.250641126,
88
+ 1.398617824,
89
+ 1.564103225,
90
+ 1.74916897,
91
+ 1.956131817,
92
+ 2.187582649,
93
+ 2.446418898,
94
+ 2.735880826,
95
+ 3.059592084,
96
+ 3.421605075,
97
+ 3.826451687,
98
+ 4.279200023,
99
+ 4.785517845,
100
+ 5.351743533,
101
+ 5.984965424,
102
+ 6.693110555,
103
+ 7.485043894,
104
+ 8.370679318,
105
+ 9.36110372,
106
+ 10.4687158,
107
+ 11.70738129,
108
+ 13.09260651,
109
+ 14.64173252,
110
+ 16.37415215,
111
+ 18.31155283,
112
+ 20.47818807,
113
+ 22.90118105,
114
+ 25.61086418,
115
+ 28.64115884,
116
+ 32.03,
117
+ 32.1,
118
+ 32.13,
119
+ 32.23,
120
+ 32.6,
121
+ 32.61,
122
+ 32.64,
123
+ 32.66,
124
+ 32.7,
125
+ 32.71,
126
+ 32.93,
127
+ 32.97,
128
+ 33.28,
129
+ 33.49,
130
+ 33.5,
131
+ 44.16,
132
+ 47.77
133
+ ],
134
+ "type": "longrope"
135
+ },
136
+ "sliding_window": 262144,
137
+ "tie_word_embeddings": true,
138
+ "transformers_version": "5.5.0",
139
+ "use_cache": true,
140
+ "vocab_size": 200064
141
+ }
generation_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 199999,
4
+ "eos_token_id": [
5
+ 200020,
6
+ 199999
7
+ ],
8
+ "pad_token_id": 199999,
9
+ "transformers_version": "5.5.0"
10
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:025b2e97687e09254f50396e8a6c055639ccb3989793b44f37a1e47acd8bc150
3
+ size 7672066056
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ea8bdf68c3e7549a3fb4342523288ce628f6ab56a618f9a4dfb234a0b4d46a8
3
+ size 15524476
tokenizer_config.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "backend": "tokenizers",
4
+ "bos_token": "<|endoftext|>",
5
+ "clean_up_tokenization_spaces": false,
6
+ "eos_token": "<|endoftext|>",
7
+ "is_local": false,
8
+ "max_length": 1024,
9
+ "model_max_length": 131072,
10
+ "pad_token": "<|endoftext|>",
11
+ "stride": 0,
12
+ "tokenizer_class": "TokenizersBackend",
13
+ "truncation_side": "right",
14
+ "truncation_strategy": "longest_first",
15
+ "unk_token": "<|endoftext|>"
16
+ }