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
32fb0bf
·
verified ·
1 Parent(s): 45cf0b8

Delete pytorch_model.bin.index.json

Browse files
Files changed (1) hide show
  1. pytorch_model.bin.index.json +0 -202
pytorch_model.bin.index.json DELETED
@@ -1,202 +0,0 @@
1
- {
2
- "metadata": {
3
- "total_size": 6654615552
4
- },
5
- "weight_map": {
6
- "lm_head.weight": "pytorch_model-00002-of-00002.bin",
7
- "model.embed_tokens.weight": "pytorch_model-00001-of-00002.bin",
8
- "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
9
- "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
10
- "model.layers.0.mlp.gate_up_proj.weight": "pytorch_model-00001-of-00002.bin",
11
- "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
12
- "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
13
- "model.layers.0.self_attn.qkv_proj.weight": "pytorch_model-00001-of-00002.bin",
14
- "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
15
- "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
16
- "model.layers.1.mlp.gate_up_proj.weight": "pytorch_model-00001-of-00002.bin",
17
- "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
18
- "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
19
- "model.layers.1.self_attn.qkv_proj.weight": "pytorch_model-00001-of-00002.bin",
20
- "model.layers.10.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
21
- "model.layers.10.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
22
- "model.layers.10.mlp.gate_up_proj.weight": "pytorch_model-00001-of-00002.bin",
23
- "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
24
- "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
25
- "model.layers.10.self_attn.qkv_proj.weight": "pytorch_model-00001-of-00002.bin",
26
- "model.layers.11.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
27
- "model.layers.11.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
28
- "model.layers.11.mlp.gate_up_proj.weight": "pytorch_model-00001-of-00002.bin",
29
- "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
30
- "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
31
- "model.layers.11.self_attn.qkv_proj.weight": "pytorch_model-00001-of-00002.bin",
32
- "model.layers.12.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
33
- "model.layers.12.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
34
- "model.layers.12.mlp.gate_up_proj.weight": "pytorch_model-00001-of-00002.bin",
35
- "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
36
- "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
37
- "model.layers.12.self_attn.qkv_proj.weight": "pytorch_model-00001-of-00002.bin",
38
- "model.layers.13.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
39
- "model.layers.13.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
40
- "model.layers.13.mlp.gate_up_proj.weight": "pytorch_model-00001-of-00002.bin",
41
- "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
42
- "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
43
- "model.layers.13.self_attn.qkv_proj.weight": "pytorch_model-00001-of-00002.bin",
44
- "model.layers.14.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
45
- "model.layers.14.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
46
- "model.layers.14.mlp.gate_up_proj.weight": "pytorch_model-00001-of-00002.bin",
47
- "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
48
- "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
49
- "model.layers.14.self_attn.qkv_proj.weight": "pytorch_model-00001-of-00002.bin",
50
- "model.layers.15.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
51
- "model.layers.15.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
52
- "model.layers.15.mlp.gate_up_proj.weight": "pytorch_model-00001-of-00002.bin",
53
- "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
54
- "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
55
- "model.layers.15.self_attn.qkv_proj.weight": "pytorch_model-00001-of-00002.bin",
56
- "model.layers.16.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
57
- "model.layers.16.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
58
- "model.layers.16.mlp.gate_up_proj.weight": "pytorch_model-00001-of-00002.bin",
59
- "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
60
- "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
61
- "model.layers.16.self_attn.qkv_proj.weight": "pytorch_model-00001-of-00002.bin",
62
- "model.layers.17.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
63
- "model.layers.17.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
64
- "model.layers.17.mlp.gate_up_proj.weight": "pytorch_model-00001-of-00002.bin",
65
- "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
66
- "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
67
- "model.layers.17.self_attn.qkv_proj.weight": "pytorch_model-00001-of-00002.bin",
68
- "model.layers.18.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
69
- "model.layers.18.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
70
- "model.layers.18.mlp.gate_up_proj.weight": "pytorch_model-00001-of-00002.bin",
71
- "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
72
- "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
73
- "model.layers.18.self_attn.qkv_proj.weight": "pytorch_model-00001-of-00002.bin",
74
- "model.layers.19.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
75
- "model.layers.19.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
76
- "model.layers.19.mlp.gate_up_proj.weight": "pytorch_model-00001-of-00002.bin",
77
- "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
78
- "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
79
- "model.layers.19.self_attn.qkv_proj.weight": "pytorch_model-00001-of-00002.bin",
80
- "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
81
- "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
82
- "model.layers.2.mlp.gate_up_proj.weight": "pytorch_model-00001-of-00002.bin",
83
- "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
84
- "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
85
- "model.layers.2.self_attn.qkv_proj.weight": "pytorch_model-00001-of-00002.bin",
86
- "model.layers.20.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
87
- "model.layers.20.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
88
- "model.layers.20.mlp.gate_up_proj.weight": "pytorch_model-00001-of-00002.bin",
89
- "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
90
- "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
91
- "model.layers.20.self_attn.qkv_proj.weight": "pytorch_model-00001-of-00002.bin",
92
- "model.layers.21.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
93
- "model.layers.21.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
94
- "model.layers.21.mlp.gate_up_proj.weight": "pytorch_model-00001-of-00002.bin",
95
- "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
96
- "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
97
- "model.layers.21.self_attn.qkv_proj.weight": "pytorch_model-00001-of-00002.bin",
98
- "model.layers.22.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
99
- "model.layers.22.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
100
- "model.layers.22.mlp.gate_up_proj.weight": "pytorch_model-00001-of-00002.bin",
101
- "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
102
- "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
103
- "model.layers.22.self_attn.qkv_proj.weight": "pytorch_model-00001-of-00002.bin",
104
- "model.layers.23.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
105
- "model.layers.23.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
106
- "model.layers.23.mlp.gate_up_proj.weight": "pytorch_model-00002-of-00002.bin",
107
- "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
108
- "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
109
- "model.layers.23.self_attn.qkv_proj.weight": "pytorch_model-00002-of-00002.bin",
110
- "model.layers.24.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
111
- "model.layers.24.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
112
- "model.layers.24.mlp.gate_up_proj.weight": "pytorch_model-00002-of-00002.bin",
113
- "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
114
- "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
115
- "model.layers.24.self_attn.qkv_proj.weight": "pytorch_model-00002-of-00002.bin",
116
- "model.layers.25.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
117
- "model.layers.25.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
118
- "model.layers.25.mlp.gate_up_proj.weight": "pytorch_model-00002-of-00002.bin",
119
- "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
120
- "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
121
- "model.layers.25.self_attn.qkv_proj.weight": "pytorch_model-00002-of-00002.bin",
122
- "model.layers.26.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
123
- "model.layers.26.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
124
- "model.layers.26.mlp.gate_up_proj.weight": "pytorch_model-00002-of-00002.bin",
125
- "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
126
- "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
127
- "model.layers.26.self_attn.qkv_proj.weight": "pytorch_model-00002-of-00002.bin",
128
- "model.layers.27.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
129
- "model.layers.27.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
130
- "model.layers.27.mlp.gate_up_proj.weight": "pytorch_model-00002-of-00002.bin",
131
- "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
132
- "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
133
- "model.layers.27.self_attn.qkv_proj.weight": "pytorch_model-00002-of-00002.bin",
134
- "model.layers.28.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
135
- "model.layers.28.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
136
- "model.layers.28.mlp.gate_up_proj.weight": "pytorch_model-00002-of-00002.bin",
137
- "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
138
- "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
139
- "model.layers.28.self_attn.qkv_proj.weight": "pytorch_model-00002-of-00002.bin",
140
- "model.layers.29.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
141
- "model.layers.29.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
142
- "model.layers.29.mlp.gate_up_proj.weight": "pytorch_model-00002-of-00002.bin",
143
- "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
144
- "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
145
- "model.layers.29.self_attn.qkv_proj.weight": "pytorch_model-00002-of-00002.bin",
146
- "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
147
- "model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
148
- "model.layers.3.mlp.gate_up_proj.weight": "pytorch_model-00001-of-00002.bin",
149
- "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
150
- "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
151
- "model.layers.3.self_attn.qkv_proj.weight": "pytorch_model-00001-of-00002.bin",
152
- "model.layers.30.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
153
- "model.layers.30.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
154
- "model.layers.30.mlp.gate_up_proj.weight": "pytorch_model-00002-of-00002.bin",
155
- "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
156
- "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
157
- "model.layers.30.self_attn.qkv_proj.weight": "pytorch_model-00002-of-00002.bin",
158
- "model.layers.31.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
159
- "model.layers.31.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
160
- "model.layers.31.mlp.gate_up_proj.weight": "pytorch_model-00002-of-00002.bin",
161
- "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
162
- "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
163
- "model.layers.31.self_attn.qkv_proj.weight": "pytorch_model-00002-of-00002.bin",
164
- "model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
165
- "model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
166
- "model.layers.4.mlp.gate_up_proj.weight": "pytorch_model-00001-of-00002.bin",
167
- "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
168
- "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
169
- "model.layers.4.self_attn.qkv_proj.weight": "pytorch_model-00001-of-00002.bin",
170
- "model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
171
- "model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
172
- "model.layers.5.mlp.gate_up_proj.weight": "pytorch_model-00001-of-00002.bin",
173
- "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
174
- "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
175
- "model.layers.5.self_attn.qkv_proj.weight": "pytorch_model-00001-of-00002.bin",
176
- "model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
177
- "model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
178
- "model.layers.6.mlp.gate_up_proj.weight": "pytorch_model-00001-of-00002.bin",
179
- "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
180
- "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
181
- "model.layers.6.self_attn.qkv_proj.weight": "pytorch_model-00001-of-00002.bin",
182
- "model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
183
- "model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
184
- "model.layers.7.mlp.gate_up_proj.weight": "pytorch_model-00001-of-00002.bin",
185
- "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
186
- "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
187
- "model.layers.7.self_attn.qkv_proj.weight": "pytorch_model-00001-of-00002.bin",
188
- "model.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
189
- "model.layers.8.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
190
- "model.layers.8.mlp.gate_up_proj.weight": "pytorch_model-00001-of-00002.bin",
191
- "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
192
- "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
193
- "model.layers.8.self_attn.qkv_proj.weight": "pytorch_model-00001-of-00002.bin",
194
- "model.layers.9.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
195
- "model.layers.9.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
196
- "model.layers.9.mlp.gate_up_proj.weight": "pytorch_model-00001-of-00002.bin",
197
- "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
198
- "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
199
- "model.layers.9.self_attn.qkv_proj.weight": "pytorch_model-00001-of-00002.bin",
200
- "model.norm.weight": "pytorch_model-00002-of-00002.bin"
201
- }
202
- }