Hugging Face's logo

PruningVSQuantization
/
Phi-3.5-mini-instruct-awq-bits4-seed0

Text Generation
Transformers
Safetensors
phi3
conversational
custom_code
text-generation-inference
4-bit precision
awq
Model card Files
xet
 Community
S1mKu commited on
Commit
341b671
·
verified ·
1 Parent(s): b4def39

Upload Phi3ForCausalLM

Browse files
Files changed (3) hide show
  1. config.json +151 -0
  2. generation_config.json +12 -0
  3. model.safetensors +3 -0
config.json ADDED
@@ -0,0 +1,151 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Phi3ForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "auto_map": {
8
+ "AutoConfig": "configuration_phi3.Phi3Config",
9
+ "AutoModelForCausalLM": "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
+ "partial_rotary_factor": 1.0,
26
+ "quantization_config": {
27
+ "backend": "autoawq",
28
+ "bits": 4,
29
+ "do_fuse": false,
30
+ "exllama_config": null,
31
+ "fuse_max_seq_len": null,
32
+ "group_size": 128,
33
+ "modules_to_fuse": null,
34
+ "modules_to_not_convert": null,
35
+ "quant_method": "awq",
36
+ "version": "gemm",
37
+ "zero_point": true
38
+ },
39
+ "resid_pdrop": 0.0,
40
+ "rms_norm_eps": 1e-05,
41
+ "rope_scaling": {
42
+ "long_factor": [
43
+ 1.0800000429153442,
44
+ 1.1100000143051147,
45
+ 1.1399999856948853,
46
+ 1.340000033378601,
47
+ 1.5899999141693115,
48
+ 1.600000023841858,
49
+ 1.6200000047683716,
50
+ 2.620000123977661,
51
+ 3.2300000190734863,
52
+ 3.2300000190734863,
53
+ 4.789999961853027,
54
+ 7.400000095367432,
55
+ 7.700000286102295,
56
+ 9.09000015258789,
57
+ 12.199999809265137,
58
+ 17.670000076293945,
59
+ 24.46000099182129,
60
+ 28.57000160217285,
61
+ 30.420001983642578,
62
+ 30.840002059936523,
63
+ 32.590003967285156,
64
+ 32.93000411987305,
65
+ 42.320003509521484,
66
+ 44.96000289916992,
67
+ 50.340003967285156,
68
+ 50.45000457763672,
69
+ 57.55000305175781,
70
+ 57.93000411987305,
71
+ 58.21000289916992,
72
+ 60.1400032043457,
73
+ 62.61000442504883,
74
+ 62.62000274658203,
75
+ 62.71000289916992,
76
+ 63.1400032043457,
77
+ 63.1400032043457,
78
+ 63.77000427246094,
79
+ 63.93000411987305,
80
+ 63.96000289916992,
81
+ 63.970001220703125,
82
+ 64.02999877929688,
83
+ 64.06999969482422,
84
+ 64.08000183105469,
85
+ 64.12000274658203,
86
+ 64.41000366210938,
87
+ 64.4800033569336,
88
+ 64.51000213623047,
89
+ 64.52999877929688,
90
+ 64.83999633789062
91
+ ],
92
+ "short_factor": [
93
+ 1.0,
94
+ 1.0199999809265137,
95
+ 1.0299999713897705,
96
+ 1.0299999713897705,
97
+ 1.0499999523162842,
98
+ 1.0499999523162842,
99
+ 1.0499999523162842,
100
+ 1.0499999523162842,
101
+ 1.0499999523162842,
102
+ 1.0699999332427979,
103
+ 1.0999999046325684,
104
+ 1.1099998950958252,
105
+ 1.1599998474121094,
106
+ 1.1599998474121094,
107
+ 1.1699998378753662,
108
+ 1.2899998426437378,
109
+ 1.339999794960022,
110
+ 1.679999828338623,
111
+ 1.7899998426437378,
112
+ 1.8199998140335083,
113
+ 1.8499997854232788,
114
+ 1.8799997568130493,
115
+ 1.9099997282028198,
116
+ 1.9399996995925903,
117
+ 1.9899996519088745,
118
+ 2.0199997425079346,
119
+ 2.0199997425079346,
120
+ 2.0199997425079346,
121
+ 2.0199997425079346,
122
+ 2.0199997425079346,
123
+ 2.0199997425079346,
124
+ 2.0299997329711914,
125
+ 2.0299997329711914,
126
+ 2.0299997329711914,
127
+ 2.0299997329711914,
128
+ 2.0299997329711914,
129
+ 2.0299997329711914,
130
+ 2.0299997329711914,
131
+ 2.0299997329711914,
132
+ 2.0299997329711914,
133
+ 2.0799996852874756,
134
+ 2.0899996757507324,
135
+ 2.189999580383301,
136
+ 2.2199995517730713,
137
+ 2.5899994373321533,
138
+ 2.729999542236328,
139
+ 2.749999523162842,
140
+ 2.8399994373321533
141
+ ],
142
+ "type": "longrope"
143
+ },
144
+ "rope_theta": 10000.0,
145
+ "sliding_window": 262144,
146
+ "tie_word_embeddings": false,
147
+ "torch_dtype": "float16",
148
+ "transformers_version": "4.51.3",
149
+ "use_cache": false,
150
+ "vocab_size": 32064
151
+ }
generation_config.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "do_sample": true,
5
+ "eos_token_id": [
6
+ 32007,
7
+ 32001,
8
+ 32000
9
+ ],
10
+ "pad_token_id": 32000,
11
+ "transformers_version": "4.51.3"
12
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5eec5bb6dfba2e4ff4ad2cb1be42c017961d5cf5dd5bf34117f77d00b6212114
3
+ size 2277171624