Hugging Face's logo

simaai
/
Phi-3.5-mini-instruct-a16w4

Text Generation
llima
llm
generative_ai
embedded
sima
Model card Files
xet
Community
amychensima commited on
Commit
93aa0d8
·
verified ·
1 Parent(s): 754230b

Upload folder using huggingface_hub

Browse files
Files changed (3) hide show
  1. devkit/models--microsoft--Phi-3.5-mini-instruct_language_embeddings.npy +3 -0
  2. devkit/tokenizer.model +3 -0
  3. devkit/vlm_config.json +184 -0
devkit/models--microsoft--Phi-3.5-mini-instruct_language_embeddings.npy ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb4b0d60837dae95859e0ae3576f1591142bfc6e963084e2b4139e8279d58316
3
+ size 394002560
devkit/tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
devkit/vlm_config.json ADDED
@@ -0,0 +1,184 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "model_name": "models--microsoft--Phi-3.5-mini-instruct",
3
+ "model_type": "llm-phi3.5",
4
+ "vm_cfg": null,
5
+ "mm_cfg": null,
6
+ "lm_cfg": {
7
+ "model_type": "phi3",
8
+ "data_type": "bfloat16",
9
+ "arch": "phi",
10
+ "gen": "3.5",
11
+ "size": "mini",
12
+ "token_cfg": {
13
+ "tokenizer_type": "spiece",
14
+ "tokenizer_path": "/project/mlasw/users/amy.chen/debug/models--microsoft--Phi-3.5-mini-instruct/blobs/9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347",
15
+ "vocab_size": 32064,
16
+ "special_tokens": {
17
+ "bos_token_id": 1,
18
+ "eos_token_id": [
19
+ 32000,
20
+ 32001,
21
+ 32007
22
+ ],
23
+ "pad_token_id": 32000
24
+ }
25
+ },
26
+ "rope_cfg": {
27
+ "rope_theta": 10000,
28
+ "rope_local_base_freq": 10000,
29
+ "rope_scaling": {
30
+ "factor": 1.0,
31
+ "low_freq_factor": 0,
32
+ "high_freq_factor": 0,
33
+ "original_max_position_embeddings": 4096,
34
+ "long_factor": [
35
+ 1.0800000429153442,
36
+ 1.1100000143051147,
37
+ 1.1399999856948853,
38
+ 1.340000033378601,
39
+ 1.5899999141693115,
40
+ 1.600000023841858,
41
+ 1.6200000047683716,
42
+ 2.620000123977661,
43
+ 3.2300000190734863,
44
+ 3.2300000190734863,
45
+ 4.789999961853027,
46
+ 7.400000095367432,
47
+ 7.700000286102295,
48
+ 9.09000015258789,
49
+ 12.199999809265137,
50
+ 17.670000076293945,
51
+ 24.46000099182129,
52
+ 28.57000160217285,
53
+ 30.420001983642578,
54
+ 30.840002059936523,
55
+ 32.590003967285156,
56
+ 32.93000411987305,
57
+ 42.320003509521484,
58
+ 44.96000289916992,
59
+ 50.340003967285156,
60
+ 50.45000457763672,
61
+ 57.55000305175781,
62
+ 57.93000411987305,
63
+ 58.21000289916992,
64
+ 60.1400032043457,
65
+ 62.61000442504883,
66
+ 62.62000274658203,
67
+ 62.71000289916992,
68
+ 63.1400032043457,
69
+ 63.1400032043457,
70
+ 63.77000427246094,
71
+ 63.93000411987305,
72
+ 63.96000289916992,
73
+ 63.970001220703125,
74
+ 64.02999877929688,
75
+ 64.06999969482422,
76
+ 64.08000183105469,
77
+ 64.12000274658203,
78
+ 64.41000366210938,
79
+ 64.4800033569336,
80
+ 64.51000213623047,
81
+ 64.52999877929688,
82
+ 64.83999633789062
83
+ ],
84
+ "short_factor": [
85
+ 1.0,
86
+ 1.0199999809265137,
87
+ 1.0299999713897705,
88
+ 1.0299999713897705,
89
+ 1.0499999523162842,
90
+ 1.0499999523162842,
91
+ 1.0499999523162842,
92
+ 1.0499999523162842,
93
+ 1.0499999523162842,
94
+ 1.0699999332427979,
95
+ 1.0999999046325684,
96
+ 1.1099998950958252,
97
+ 1.1599998474121094,
98
+ 1.1599998474121094,
99
+ 1.1699998378753662,
100
+ 1.2899998426437378,
101
+ 1.339999794960022,
102
+ 1.679999828338623,
103
+ 1.7899998426437378,
104
+ 1.8199998140335083,
105
+ 1.8499997854232788,
106
+ 1.8799997568130493,
107
+ 1.9099997282028198,
108
+ 1.9399996995925903,
109
+ 1.9899996519088745,
110
+ 2.0199997425079346,
111
+ 2.0199997425079346,
112
+ 2.0199997425079346,
113
+ 2.0199997425079346,
114
+ 2.0199997425079346,
115
+ 2.0199997425079346,
116
+ 2.0299997329711914,
117
+ 2.0299997329711914,
118
+ 2.0299997329711914,
119
+ 2.0299997329711914,
120
+ 2.0299997329711914,
121
+ 2.0299997329711914,
122
+ 2.0299997329711914,
123
+ 2.0299997329711914,
124
+ 2.0299997329711914,
125
+ 2.0799996852874756,
126
+ 2.0899996757507324,
127
+ 2.189999580383301,
128
+ 2.2199995517730713,
129
+ 2.5899994373321533,
130
+ 2.729999542236328,
131
+ 2.749999523162842,
132
+ 2.8399994373321533
133
+ ],
134
+ "rope_type": "longrope"
135
+ }
136
+ },
137
+ "attn_cfg": {
138
+ "num_attention_heads": 32,
139
+ "num_key_value_heads": 32,
140
+ "head_dim": 96,
141
+ "swa_enable": false,
142
+ "swa_ratio": 0,
143
+ "sliding_window": 262144,
144
+ "attention_bias": false,
145
+ "attention_dropout": 0.0,
146
+ "query_pre_attn_scalar": 0
147
+ },
148
+ "mlp_cfg": {
149
+ "intermediate_size": 8192,
150
+ "act": "silu",
151
+ "num_layers": 3,
152
+ "mlp_bias": false
153
+ },
154
+ "hidden_size": 3072,
155
+ "num_hidden_layers": 32,
156
+ "max_position_embeddings": 2048,
157
+ "rms_norm_eps": 1e-05,
158
+ "layer_norms": [
159
+ "pre_attn",
160
+ "post_attn"
161
+ ],
162
+ "attn_logit_softcapping": null,
163
+ "final_logit_softcapping": null,
164
+ "lm_head_num_splits": 1,
165
+ "lm_head_split_dim": 32064
166
+ },
167
+ "pipeline_cfg": {
168
+ "system_prompt": null,
169
+ "max_num_tokens": 1024,
170
+ "input_token_group_size": 128,
171
+ "input_token_group_offsets": [
172
+ 0,
173
+ 128,
174
+ 256,
175
+ 384,
176
+ 512,
177
+ 640,
178
+ 768,
179
+ 896
180
+ ],
181
+ "future_token_mask_size": 128
182
+ },
183
+ "language_model_name": "models--microsoft--Phi-3.5-mini-instruct_language"
184
+ }