Hugging Face's logo

smarquie
/
falcon-7b-qlora-fincrisis

Text Generation
Transformers
PyTorch
falcon
custom_code
text-generation-inference
Inference Endpoints
Model card Files Community
smarquie commited on
Commit
f5900a3
•
1 Parent(s): 8d65f80

Delete pytorch_model.bin.index.json

Browse files
Files changed (1) hide show
  1. pytorch_model.bin.index.json +0 -203
pytorch_model.bin.index.json DELETED
@@ -1,203 +0,0 @@
1
- {
2
- "metadata": {
3
- "total_size": 28868759040
4
- },
5
- "weight_map": {
6
- "lm_head.weight": "pytorch_model-00003-of-00003.bin",
7
- "transformer.h.0.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
8
- "transformer.h.0.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
9
- "transformer.h.0.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00003.bin",
10
- "transformer.h.0.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
11
- "transformer.h.0.self_attention.dense.weight": "pytorch_model-00001-of-00003.bin",
12
- "transformer.h.0.self_attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
13
- "transformer.h.1.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
14
- "transformer.h.1.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
15
- "transformer.h.1.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00003.bin",
16
- "transformer.h.1.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
17
- "transformer.h.1.self_attention.dense.weight": "pytorch_model-00001-of-00003.bin",
18
- "transformer.h.1.self_attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
19
- "transformer.h.10.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
20
- "transformer.h.10.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
21
- "transformer.h.10.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
22
- "transformer.h.10.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
23
- "transformer.h.10.self_attention.dense.weight": "pytorch_model-00001-of-00003.bin",
24
- "transformer.h.10.self_attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
25
- "transformer.h.11.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
26
- "transformer.h.11.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
27
- "transformer.h.11.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
28
- "transformer.h.11.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
29
- "transformer.h.11.self_attention.dense.weight": "pytorch_model-00002-of-00003.bin",
30
- "transformer.h.11.self_attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
31
- "transformer.h.12.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
32
- "transformer.h.12.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
33
- "transformer.h.12.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
34
- "transformer.h.12.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
35
- "transformer.h.12.self_attention.dense.weight": "pytorch_model-00002-of-00003.bin",
36
- "transformer.h.12.self_attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
37
- "transformer.h.13.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
38
- "transformer.h.13.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
39
- "transformer.h.13.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
40
- "transformer.h.13.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
41
- "transformer.h.13.self_attention.dense.weight": "pytorch_model-00002-of-00003.bin",
42
- "transformer.h.13.self_attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
43
- "transformer.h.14.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
44
- "transformer.h.14.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
45
- "transformer.h.14.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
46
- "transformer.h.14.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
47
- "transformer.h.14.self_attention.dense.weight": "pytorch_model-00002-of-00003.bin",
48
- "transformer.h.14.self_attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
49
- "transformer.h.15.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
50
- "transformer.h.15.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
51
- "transformer.h.15.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
52
- "transformer.h.15.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
53
- "transformer.h.15.self_attention.dense.weight": "pytorch_model-00002-of-00003.bin",
54
- "transformer.h.15.self_attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
55
- "transformer.h.16.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
56
- "transformer.h.16.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
57
- "transformer.h.16.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
58
- "transformer.h.16.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
59
- "transformer.h.16.self_attention.dense.weight": "pytorch_model-00002-of-00003.bin",
60
- "transformer.h.16.self_attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
61
- "transformer.h.17.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
62
- "transformer.h.17.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
63
- "transformer.h.17.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
64
- "transformer.h.17.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
65
- "transformer.h.17.self_attention.dense.weight": "pytorch_model-00002-of-00003.bin",
66
- "transformer.h.17.self_attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
67
- "transformer.h.18.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
68
- "transformer.h.18.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
69
- "transformer.h.18.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
70
- "transformer.h.18.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
71
- "transformer.h.18.self_attention.dense.weight": "pytorch_model-00002-of-00003.bin",
72
- "transformer.h.18.self_attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
73
- "transformer.h.19.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
74
- "transformer.h.19.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
75
- "transformer.h.19.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
76
- "transformer.h.19.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
77
- "transformer.h.19.self_attention.dense.weight": "pytorch_model-00002-of-00003.bin",
78
- "transformer.h.19.self_attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
79
- "transformer.h.2.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
80
- "transformer.h.2.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
81
- "transformer.h.2.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00003.bin",
82
- "transformer.h.2.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
83
- "transformer.h.2.self_attention.dense.weight": "pytorch_model-00001-of-00003.bin",
84
- "transformer.h.2.self_attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
85
- "transformer.h.20.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
86
- "transformer.h.20.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
87
- "transformer.h.20.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
88
- "transformer.h.20.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
89
- "transformer.h.20.self_attention.dense.weight": "pytorch_model-00002-of-00003.bin",
90
- "transformer.h.20.self_attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
91
- "transformer.h.21.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
92
- "transformer.h.21.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
93
- "transformer.h.21.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
94
- "transformer.h.21.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
95
- "transformer.h.21.self_attention.dense.weight": "pytorch_model-00002-of-00003.bin",
96
- "transformer.h.21.self_attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
97
- "transformer.h.22.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
98
- "transformer.h.22.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
99
- "transformer.h.22.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00003.bin",
100
- "transformer.h.22.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
101
- "transformer.h.22.self_attention.dense.weight": "pytorch_model-00002-of-00003.bin",
102
- "transformer.h.22.self_attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
103
- "transformer.h.23.input_layernorm.bias": "pytorch_model-00003-of-00003.bin",
104
- "transformer.h.23.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
105
- "transformer.h.23.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00003.bin",
106
- "transformer.h.23.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00003.bin",
107
- "transformer.h.23.self_attention.dense.weight": "pytorch_model-00003-of-00003.bin",
108
- "transformer.h.23.self_attention.query_key_value.weight": "pytorch_model-00003-of-00003.bin",
109
- "transformer.h.24.input_layernorm.bias": "pytorch_model-00003-of-00003.bin",
110
- "transformer.h.24.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
111
- "transformer.h.24.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00003.bin",
112
- "transformer.h.24.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00003.bin",
113
- "transformer.h.24.self_attention.dense.weight": "pytorch_model-00003-of-00003.bin",
114
- "transformer.h.24.self_attention.query_key_value.weight": "pytorch_model-00003-of-00003.bin",
115
- "transformer.h.25.input_layernorm.bias": "pytorch_model-00003-of-00003.bin",
116
- "transformer.h.25.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
117
- "transformer.h.25.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00003.bin",
118
- "transformer.h.25.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00003.bin",
119
- "transformer.h.25.self_attention.dense.weight": "pytorch_model-00003-of-00003.bin",
120
- "transformer.h.25.self_attention.query_key_value.weight": "pytorch_model-00003-of-00003.bin",
121
- "transformer.h.26.input_layernorm.bias": "pytorch_model-00003-of-00003.bin",
122
- "transformer.h.26.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
123
- "transformer.h.26.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00003.bin",
124
- "transformer.h.26.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00003.bin",
125
- "transformer.h.26.self_attention.dense.weight": "pytorch_model-00003-of-00003.bin",
126
- "transformer.h.26.self_attention.query_key_value.weight": "pytorch_model-00003-of-00003.bin",
127
- "transformer.h.27.input_layernorm.bias": "pytorch_model-00003-of-00003.bin",
128
- "transformer.h.27.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
129
- "transformer.h.27.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00003.bin",
130
- "transformer.h.27.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00003.bin",
131
- "transformer.h.27.self_attention.dense.weight": "pytorch_model-00003-of-00003.bin",
132
- "transformer.h.27.self_attention.query_key_value.weight": "pytorch_model-00003-of-00003.bin",
133
- "transformer.h.28.input_layernorm.bias": "pytorch_model-00003-of-00003.bin",
134
- "transformer.h.28.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
135
- "transformer.h.28.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00003.bin",
136
- "transformer.h.28.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00003.bin",
137
- "transformer.h.28.self_attention.dense.weight": "pytorch_model-00003-of-00003.bin",
138
- "transformer.h.28.self_attention.query_key_value.weight": "pytorch_model-00003-of-00003.bin",
139
- "transformer.h.29.input_layernorm.bias": "pytorch_model-00003-of-00003.bin",
140
- "transformer.h.29.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
141
- "transformer.h.29.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00003.bin",
142
- "transformer.h.29.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00003.bin",
143
- "transformer.h.29.self_attention.dense.weight": "pytorch_model-00003-of-00003.bin",
144
- "transformer.h.29.self_attention.query_key_value.weight": "pytorch_model-00003-of-00003.bin",
145
- "transformer.h.3.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
146
- "transformer.h.3.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
147
- "transformer.h.3.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00003.bin",
148
- "transformer.h.3.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
149
- "transformer.h.3.self_attention.dense.weight": "pytorch_model-00001-of-00003.bin",
150
- "transformer.h.3.self_attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
151
- "transformer.h.30.input_layernorm.bias": "pytorch_model-00003-of-00003.bin",
152
- "transformer.h.30.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
153
- "transformer.h.30.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00003.bin",
154
- "transformer.h.30.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00003.bin",
155
- "transformer.h.30.self_attention.dense.weight": "pytorch_model-00003-of-00003.bin",
156
- "transformer.h.30.self_attention.query_key_value.weight": "pytorch_model-00003-of-00003.bin",
157
- "transformer.h.31.input_layernorm.bias": "pytorch_model-00003-of-00003.bin",
158
- "transformer.h.31.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
159
- "transformer.h.31.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00003.bin",
160
- "transformer.h.31.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00003.bin",
161
- "transformer.h.31.self_attention.dense.weight": "pytorch_model-00003-of-00003.bin",
162
- "transformer.h.31.self_attention.query_key_value.weight": "pytorch_model-00003-of-00003.bin",
163
- "transformer.h.4.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
164
- "transformer.h.4.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
165
- "transformer.h.4.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00003.bin",
166
- "transformer.h.4.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
167
- "transformer.h.4.self_attention.dense.weight": "pytorch_model-00001-of-00003.bin",
168
- "transformer.h.4.self_attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
169
- "transformer.h.5.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
170
- "transformer.h.5.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
171
- "transformer.h.5.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00003.bin",
172
- "transformer.h.5.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
173
- "transformer.h.5.self_attention.dense.weight": "pytorch_model-00001-of-00003.bin",
174
- "transformer.h.5.self_attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
175
- "transformer.h.6.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
176
- "transformer.h.6.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
177
- "transformer.h.6.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00003.bin",
178
- "transformer.h.6.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
179
- "transformer.h.6.self_attention.dense.weight": "pytorch_model-00001-of-00003.bin",
180
- "transformer.h.6.self_attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
181
- "transformer.h.7.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
182
- "transformer.h.7.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
183
- "transformer.h.7.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00003.bin",
184
- "transformer.h.7.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
185
- "transformer.h.7.self_attention.dense.weight": "pytorch_model-00001-of-00003.bin",
186
- "transformer.h.7.self_attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
187
- "transformer.h.8.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
188
- "transformer.h.8.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
189
- "transformer.h.8.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00003.bin",
190
- "transformer.h.8.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
191
- "transformer.h.8.self_attention.dense.weight": "pytorch_model-00001-of-00003.bin",
192
- "transformer.h.8.self_attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
193
- "transformer.h.9.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
194
- "transformer.h.9.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
195
- "transformer.h.9.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00003.bin",
196
- "transformer.h.9.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
197
- "transformer.h.9.self_attention.dense.weight": "pytorch_model-00001-of-00003.bin",
198
- "transformer.h.9.self_attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
199
- "transformer.ln_f.bias": "pytorch_model-00003-of-00003.bin",
200
- "transformer.ln_f.weight": "pytorch_model-00003-of-00003.bin",
201
- "transformer.word_embeddings.weight": "pytorch_model-00001-of-00003.bin"
202
- }
203
- }