Hugging Face's logo

pytorch
/
Phi-4-mini-instruct-INT8-INT4

Text Generation
Transformers
PyTorch
multilingual
phi3
torchao
phi
phi4
nlp
code
math
chat
conversational
custom_code
text-generation-inference
Model card Files
xet
Community
5
metascroy commited on
Commit
9d60992
·
verified ·
1 Parent(s): 35cb97b

Delete 26b5ee14345ab0d7547c3877f138b8703256022a

Browse files
Files changed (1) hide show
  1. 26b5ee14345ab0d7547c3877f138b8703256022a +0 -226
26b5ee14345ab0d7547c3877f138b8703256022a DELETED
@@ -1,226 +0,0 @@
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
- "AutoTokenizer": "Xenova/gpt-4o"
11
- },
12
- "bos_token_id": 199999,
13
- "dtype": "bfloat16",
14
- "embd_pdrop": 0.0,
15
- "eos_token_id": 199999,
16
- "full_attn_mod": 1,
17
- "hidden_act": "silu",
18
- "hidden_size": 3072,
19
- "initializer_range": 0.02,
20
- "intermediate_size": 8192,
21
- "interpolate_factor": 1,
22
- "lm_head_bias": false,
23
- "max_position_embeddings": 131072,
24
- "mlp_bias": false,
25
- "model_type": "phi3",
26
- "num_attention_heads": 24,
27
- "num_hidden_layers": 32,
28
- "num_key_value_heads": 8,
29
- "original_max_position_embeddings": 4096,
30
- "pad_token_id": 199999,
31
- "partial_rotary_factor": 0.75,
32
- "quantization_config": {
33
- "include_input_output_embeddings": true,
34
- "modules_to_not_convert": [],
35
- "quant_method": "torchao",
36
- "quant_type": {
37
- "default": {
38
- "_data": {
39
- "module_fqn_to_config": {
40
- "_default": {
41
- "_data": {
42
- "act_mapping_type": {
43
- "_data": "ASYMMETRIC",
44
- "_type": "MappingType"
45
- },
46
- "intx_packing_format": {
47
- "_data": "UNPACKED_TO_INT8",
48
- "_type": "IntxPackingFormat"
49
- },
50
- "layout": {
51
- "_data": {},
52
- "_type": "QDQLayout",
53
- "_version": 1
54
- },
55
- "weight_dtype": {
56
- "_data": "int4",
57
- "_type": "torch.dtype"
58
- },
59
- "weight_granularity": {
60
- "_data": {
61
- "group_size": 32
62
- },
63
- "_type": "PerGroup",
64
- "_version": 1
65
- },
66
- "weight_mapping_type": {
67
- "_data": "SYMMETRIC",
68
- "_type": "MappingType"
69
- },
70
- "weight_scale_dtype": null
71
- },
72
- "_type": "Int8DynamicActivationIntxWeightConfig",
73
- "_version": 2
74
- },
75
- "model.embed_tokens": {
76
- "_data": {
77
- "granularity": {
78
- "_data": {
79
- "axis": 0
80
- },
81
- "_type": "PerAxis",
82
- "_version": 1
83
- },
84
- "intx_packing_format": {
85
- "_data": "UNPACKED_TO_INT8",
86
- "_type": "IntxPackingFormat"
87
- },
88
- "layout": {
89
- "_data": {},
90
- "_type": "QDQLayout",
91
- "_version": 1
92
- },
93
- "mapping_type": {
94
- "_data": "SYMMETRIC",
95
- "_type": "MappingType"
96
- },
97
- "scale_dtype": null,
98
- "weight_dtype": {
99
- "_data": "int8",
100
- "_type": "torch.dtype"
101
- }
102
- },
103
- "_type": "IntxWeightOnlyConfig",
104
- "_version": 2
105
- }
106
- }
107
- },
108
- "_type": "ModuleFqnToConfig",
109
- "_version": 1
110
- }
111
- },
112
- "quant_type_kwargs": {},
113
- "untie_embedding_weights": false
114
- },
115
- "resid_pdrop": 0.0,
116
- "rms_norm_eps": 1e-05,
117
- "rope_scaling": {
118
- "long_factor": [
119
- 1,
120
- 1.118320672,
121
- 1.250641126,
122
- 1.398617824,
123
- 1.564103225,
124
- 1.74916897,
125
- 1.956131817,
126
- 2.187582649,
127
- 2.446418898,
128
- 2.735880826,
129
- 3.059592084,
130
- 3.421605075,
131
- 3.826451687,
132
- 4.279200023,
133
- 4.785517845,
134
- 5.351743533,
135
- 5.984965424,
136
- 6.693110555,
137
- 7.485043894,
138
- 8.370679318,
139
- 9.36110372,
140
- 10.4687158,
141
- 11.70738129,
142
- 13.09260651,
143
- 14.64173252,
144
- 16.37415215,
145
- 18.31155283,
146
- 20.47818807,
147
- 22.90118105,
148
- 25.61086418,
149
- 28.64115884,
150
- 32.03,
151
- 32.1,
152
- 32.13,
153
- 32.23,
154
- 32.6,
155
- 32.61,
156
- 32.64,
157
- 32.66,
158
- 32.7,
159
- 32.71,
160
- 32.93,
161
- 32.97,
162
- 33.28,
163
- 33.49,
164
- 33.5,
165
- 44.16,
166
- 47.77
167
- ],
168
- "short_factor": [
169
- 1.0,
170
- 1.0,
171
- 1.0,
172
- 1.0,
173
- 1.0,
174
- 1.0,
175
- 1.0,
176
- 1.0,
177
- 1.0,
178
- 1.0,
179
- 1.0,
180
- 1.0,
181
- 1.0,
182
- 1.0,
183
- 1.0,
184
- 1.0,
185
- 1.0,
186
- 1.0,
187
- 1.0,
188
- 1.0,
189
- 1.0,
190
- 1.0,
191
- 1.0,
192
- 1.0,
193
- 1.0,
194
- 1.0,
195
- 1.0,
196
- 1.0,
197
- 1.0,
198
- 1.0,
199
- 1.0,
200
- 1.0,
201
- 1.0,
202
- 1.0,
203
- 1.0,
204
- 1.0,
205
- 1.0,
206
- 1.0,
207
- 1.0,
208
- 1.0,
209
- 1.0,
210
- 1.0,
211
- 1.0,
212
- 1.0,
213
- 1.0,
214
- 1.0,
215
- 1.0,
216
- 1.0
217
- ],
218
- "type": "longrope"
219
- },
220
- "rope_theta": 10000.0,
221
- "sliding_window": 262144,
222
- "tie_word_embeddings": false,
223
- "transformers_version": "4.57.0.dev0",
224
- "use_cache": true,
225
- "vocab_size": 200064
226
- }