Hugging Face's logo

sumangpt
/
merged

Text Generation
Transformers
Safetensors
falcon
custom_code
text-generation-inference
Inference Endpoints
8-bit precision
Model card Files Community
sumangpt commited on
Commit
cabae59
•
1 Parent(s): 06b8fc1

Upload FalconForCausalLM

Browse files
Files changed (5) hide show
  1. config.json +4 -1
  2. model-00001-of-00003.safetensors +3 -0
  3. model-00002-of-00003.safetensors +3 -0
  4. model-00003-of-00003.safetensors +3 -0
  5. model.safetensors.index.json +196 -196
config.json CHANGED
@@ -21,6 +21,7 @@
21
  "hidden_size": 4544,
22
  "initializer_range": 0.02,
23
  "layer_norm_epsilon": 1e-05,
 
24
  "model_type": "falcon",
25
  "multi_query": true,
26
  "new_decoder_architecture": false,
@@ -28,7 +29,9 @@
28
  "num_hidden_layers": 32,
29
  "num_kv_heads": 71,
30
  "parallel_attn": true,
31
- "torch_dtype": "float32",
 
 
32
  "transformers_version": "4.37.0.dev0",
33
  "use_cache": true,
34
  "vocab_size": 65024
 
21
  "hidden_size": 4544,
22
  "initializer_range": 0.02,
23
  "layer_norm_epsilon": 1e-05,
24
+ "max_position_embeddings": 2048,
25
  "model_type": "falcon",
26
  "multi_query": true,
27
  "new_decoder_architecture": false,
 
29
  "num_hidden_layers": 32,
30
  "num_kv_heads": 71,
31
  "parallel_attn": true,
32
+ "rope_scaling": null,
33
+ "rope_theta": 10000.0,
34
+ "torch_dtype": "bfloat16",
35
  "transformers_version": "4.37.0.dev0",
36
  "use_cache": true,
37
  "vocab_size": 65024
model-00001-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:87e09a850ab69ea0ea2e5a667c2556df1f885898270f8e2573e5f1eff6c580f9
3
+ size 4981285848
model-00002-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ad9cc16090e1198da520aade587b70cf8d78b2bc3aa18c58f1eec79cb29bd97
3
+ size 4969690568
model-00003-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3378c07fc1220421947908246403af87d9563073811d4eaf30c1f4536e900337
3
+ size 3892488296
model.safetensors.index.json CHANGED
@@ -1,202 +1,202 @@
1
  {
2
  "metadata": {
3
- "total_size": 27686882816
4
  },
5
  "weight_map": {
6
- "transformer.h.0.input_layernorm.bias": "model-00001-of-00006.safetensors",
7
- "transformer.h.0.input_layernorm.weight": "model-00001-of-00006.safetensors",
8
- "transformer.h.0.mlp.dense_4h_to_h.weight": "model-00001-of-00006.safetensors",
9
- "transformer.h.0.mlp.dense_h_to_4h.weight": "model-00001-of-00006.safetensors",
10
- "transformer.h.0.self_attention.dense.weight": "model-00001-of-00006.safetensors",
11
- "transformer.h.0.self_attention.query_key_value.weight": "model-00001-of-00006.safetensors",
12
- "transformer.h.1.input_layernorm.bias": "model-00001-of-00006.safetensors",
13
- "transformer.h.1.input_layernorm.weight": "model-00001-of-00006.safetensors",
14
- "transformer.h.1.mlp.dense_4h_to_h.weight": "model-00001-of-00006.safetensors",
15
- "transformer.h.1.mlp.dense_h_to_4h.weight": "model-00001-of-00006.safetensors",
16
- "transformer.h.1.self_attention.dense.weight": "model-00001-of-00006.safetensors",
17
- "transformer.h.1.self_attention.query_key_value.weight": "model-00001-of-00006.safetensors",
18
- "transformer.h.10.input_layernorm.bias": "model-00003-of-00006.safetensors",
19
- "transformer.h.10.input_layernorm.weight": "model-00003-of-00006.safetensors",
20
- "transformer.h.10.mlp.dense_4h_to_h.weight": "model-00003-of-00006.safetensors",
21
- "transformer.h.10.mlp.dense_h_to_4h.weight": "model-00002-of-00006.safetensors",
22
- "transformer.h.10.self_attention.dense.weight": "model-00002-of-00006.safetensors",
23
- "transformer.h.10.self_attention.query_key_value.weight": "model-00002-of-00006.safetensors",
24
- "transformer.h.11.input_layernorm.bias": "model-00003-of-00006.safetensors",
25
- "transformer.h.11.input_layernorm.weight": "model-00003-of-00006.safetensors",
26
- "transformer.h.11.mlp.dense_4h_to_h.weight": "model-00003-of-00006.safetensors",
27
- "transformer.h.11.mlp.dense_h_to_4h.weight": "model-00003-of-00006.safetensors",
28
- "transformer.h.11.self_attention.dense.weight": "model-00003-of-00006.safetensors",
29
- "transformer.h.11.self_attention.query_key_value.weight": "model-00003-of-00006.safetensors",
30
- "transformer.h.12.input_layernorm.bias": "model-00003-of-00006.safetensors",
31
- "transformer.h.12.input_layernorm.weight": "model-00003-of-00006.safetensors",
32
- "transformer.h.12.mlp.dense_4h_to_h.weight": "model-00003-of-00006.safetensors",
33
- "transformer.h.12.mlp.dense_h_to_4h.weight": "model-00003-of-00006.safetensors",
34
- "transformer.h.12.self_attention.dense.weight": "model-00003-of-00006.safetensors",
35
- "transformer.h.12.self_attention.query_key_value.weight": "model-00003-of-00006.safetensors",
36
- "transformer.h.13.input_layernorm.bias": "model-00003-of-00006.safetensors",
37
- "transformer.h.13.input_layernorm.weight": "model-00003-of-00006.safetensors",
38
- "transformer.h.13.mlp.dense_4h_to_h.weight": "model-00003-of-00006.safetensors",
39
- "transformer.h.13.mlp.dense_h_to_4h.weight": "model-00003-of-00006.safetensors",
40
- "transformer.h.13.self_attention.dense.weight": "model-00003-of-00006.safetensors",
41
- "transformer.h.13.self_attention.query_key_value.weight": "model-00003-of-00006.safetensors",
42
- "transformer.h.14.input_layernorm.bias": "model-00003-of-00006.safetensors",
43
- "transformer.h.14.input_layernorm.weight": "model-00003-of-00006.safetensors",
44
- "transformer.h.14.mlp.dense_4h_to_h.weight": "model-00003-of-00006.safetensors",
45
- "transformer.h.14.mlp.dense_h_to_4h.weight": "model-00003-of-00006.safetensors",
46
- "transformer.h.14.self_attention.dense.weight": "model-00003-of-00006.safetensors",
47
- "transformer.h.14.self_attention.query_key_value.weight": "model-00003-of-00006.safetensors",
48
- "transformer.h.15.input_layernorm.bias": "model-00003-of-00006.safetensors",
49
- "transformer.h.15.input_layernorm.weight": "model-00003-of-00006.safetensors",
50
- "transformer.h.15.mlp.dense_4h_to_h.weight": "model-00003-of-00006.safetensors",
51
- "transformer.h.15.mlp.dense_h_to_4h.weight": "model-00003-of-00006.safetensors",
52
- "transformer.h.15.self_attention.dense.weight": "model-00003-of-00006.safetensors",
53
- "transformer.h.15.self_attention.query_key_value.weight": "model-00003-of-00006.safetensors",
54
- "transformer.h.16.input_layernorm.bias": "model-00004-of-00006.safetensors",
55
- "transformer.h.16.input_layernorm.weight": "model-00004-of-00006.safetensors",
56
- "transformer.h.16.mlp.dense_4h_to_h.weight": "model-00004-of-00006.safetensors",
57
- "transformer.h.16.mlp.dense_h_to_4h.weight": "model-00003-of-00006.safetensors",
58
- "transformer.h.16.self_attention.dense.weight": "model-00003-of-00006.safetensors",
59
- "transformer.h.16.self_attention.query_key_value.weight": "model-00003-of-00006.safetensors",
60
- "transformer.h.17.input_layernorm.bias": "model-00004-of-00006.safetensors",
61
- "transformer.h.17.input_layernorm.weight": "model-00004-of-00006.safetensors",
62
- "transformer.h.17.mlp.dense_4h_to_h.weight": "model-00004-of-00006.safetensors",
63
- "transformer.h.17.mlp.dense_h_to_4h.weight": "model-00004-of-00006.safetensors",
64
- "transformer.h.17.self_attention.dense.weight": "model-00004-of-00006.safetensors",
65
- "transformer.h.17.self_attention.query_key_value.weight": "model-00004-of-00006.safetensors",
66
- "transformer.h.18.input_layernorm.bias": "model-00004-of-00006.safetensors",
67
- "transformer.h.18.input_layernorm.weight": "model-00004-of-00006.safetensors",
68
- "transformer.h.18.mlp.dense_4h_to_h.weight": "model-00004-of-00006.safetensors",
69
- "transformer.h.18.mlp.dense_h_to_4h.weight": "model-00004-of-00006.safetensors",
70
- "transformer.h.18.self_attention.dense.weight": "model-00004-of-00006.safetensors",
71
- "transformer.h.18.self_attention.query_key_value.weight": "model-00004-of-00006.safetensors",
72
- "transformer.h.19.input_layernorm.bias": "model-00004-of-00006.safetensors",
73
- "transformer.h.19.input_layernorm.weight": "model-00004-of-00006.safetensors",
74
- "transformer.h.19.mlp.dense_4h_to_h.weight": "model-00004-of-00006.safetensors",
75
- "transformer.h.19.mlp.dense_h_to_4h.weight": "model-00004-of-00006.safetensors",
76
- "transformer.h.19.self_attention.dense.weight": "model-00004-of-00006.safetensors",
77
- "transformer.h.19.self_attention.query_key_value.weight": "model-00004-of-00006.safetensors",
78
- "transformer.h.2.input_layernorm.bias": "model-00001-of-00006.safetensors",
79
- "transformer.h.2.input_layernorm.weight": "model-00001-of-00006.safetensors",
80
- "transformer.h.2.mlp.dense_4h_to_h.weight": "model-00001-of-00006.safetensors",
81
- "transformer.h.2.mlp.dense_h_to_4h.weight": "model-00001-of-00006.safetensors",
82
- "transformer.h.2.self_attention.dense.weight": "model-00001-of-00006.safetensors",
83
- "transformer.h.2.self_attention.query_key_value.weight": "model-00001-of-00006.safetensors",
84
- "transformer.h.20.input_layernorm.bias": "model-00004-of-00006.safetensors",
85
- "transformer.h.20.input_layernorm.weight": "model-00004-of-00006.safetensors",
86
- "transformer.h.20.mlp.dense_4h_to_h.weight": "model-00004-of-00006.safetensors",
87
- "transformer.h.20.mlp.dense_h_to_4h.weight": "model-00004-of-00006.safetensors",
88
- "transformer.h.20.self_attention.dense.weight": "model-00004-of-00006.safetensors",
89
- "transformer.h.20.self_attention.query_key_value.weight": "model-00004-of-00006.safetensors",
90
- "transformer.h.21.input_layernorm.bias": "model-00004-of-00006.safetensors",
91
- "transformer.h.21.input_layernorm.weight": "model-00004-of-00006.safetensors",
92
- "transformer.h.21.mlp.dense_4h_to_h.weight": "model-00004-of-00006.safetensors",
93
- "transformer.h.21.mlp.dense_h_to_4h.weight": "model-00004-of-00006.safetensors",
94
- "transformer.h.21.self_attention.dense.weight": "model-00004-of-00006.safetensors",
95
- "transformer.h.21.self_attention.query_key_value.weight": "model-00004-of-00006.safetensors",
96
- "transformer.h.22.input_layernorm.bias": "model-00005-of-00006.safetensors",
97
- "transformer.h.22.input_layernorm.weight": "model-00005-of-00006.safetensors",
98
- "transformer.h.22.mlp.dense_4h_to_h.weight": "model-00005-of-00006.safetensors",
99
- "transformer.h.22.mlp.dense_h_to_4h.weight": "model-00004-of-00006.safetensors",
100
- "transformer.h.22.self_attention.dense.weight": "model-00004-of-00006.safetensors",
101
- "transformer.h.22.self_attention.query_key_value.weight": "model-00004-of-00006.safetensors",
102
- "transformer.h.23.input_layernorm.bias": "model-00005-of-00006.safetensors",
103
- "transformer.h.23.input_layernorm.weight": "model-00005-of-00006.safetensors",
104
- "transformer.h.23.mlp.dense_4h_to_h.weight": "model-00005-of-00006.safetensors",
105
- "transformer.h.23.mlp.dense_h_to_4h.weight": "model-00005-of-00006.safetensors",
106
- "transformer.h.23.self_attention.dense.weight": "model-00005-of-00006.safetensors",
107
- "transformer.h.23.self_attention.query_key_value.weight": "model-00005-of-00006.safetensors",
108
- "transformer.h.24.input_layernorm.bias": "model-00005-of-00006.safetensors",
109
- "transformer.h.24.input_layernorm.weight": "model-00005-of-00006.safetensors",
110
- "transformer.h.24.mlp.dense_4h_to_h.weight": "model-00005-of-00006.safetensors",
111
- "transformer.h.24.mlp.dense_h_to_4h.weight": "model-00005-of-00006.safetensors",
112
- "transformer.h.24.self_attention.dense.weight": "model-00005-of-00006.safetensors",
113
- "transformer.h.24.self_attention.query_key_value.weight": "model-00005-of-00006.safetensors",
114
- "transformer.h.25.input_layernorm.bias": "model-00005-of-00006.safetensors",
115
- "transformer.h.25.input_layernorm.weight": "model-00005-of-00006.safetensors",
116
- "transformer.h.25.mlp.dense_4h_to_h.weight": "model-00005-of-00006.safetensors",
117
- "transformer.h.25.mlp.dense_h_to_4h.weight": "model-00005-of-00006.safetensors",
118
- "transformer.h.25.self_attention.dense.weight": "model-00005-of-00006.safetensors",
119
- "transformer.h.25.self_attention.query_key_value.weight": "model-00005-of-00006.safetensors",
120
- "transformer.h.26.input_layernorm.bias": "model-00005-of-00006.safetensors",
121
- "transformer.h.26.input_layernorm.weight": "model-00005-of-00006.safetensors",
122
- "transformer.h.26.mlp.dense_4h_to_h.weight": "model-00005-of-00006.safetensors",
123
- "transformer.h.26.mlp.dense_h_to_4h.weight": "model-00005-of-00006.safetensors",
124
- "transformer.h.26.self_attention.dense.weight": "model-00005-of-00006.safetensors",
125
- "transformer.h.26.self_attention.query_key_value.weight": "model-00005-of-00006.safetensors",
126
- "transformer.h.27.input_layernorm.bias": "model-00005-of-00006.safetensors",
127
- "transformer.h.27.input_layernorm.weight": "model-00005-of-00006.safetensors",
128
- "transformer.h.27.mlp.dense_4h_to_h.weight": "model-00005-of-00006.safetensors",
129
- "transformer.h.27.mlp.dense_h_to_4h.weight": "model-00005-of-00006.safetensors",
130
- "transformer.h.27.self_attention.dense.weight": "model-00005-of-00006.safetensors",
131
- "transformer.h.27.self_attention.query_key_value.weight": "model-00005-of-00006.safetensors",
132
- "transformer.h.28.input_layernorm.bias": "model-00006-of-00006.safetensors",
133
- "transformer.h.28.input_layernorm.weight": "model-00006-of-00006.safetensors",
134
- "transformer.h.28.mlp.dense_4h_to_h.weight": "model-00006-of-00006.safetensors",
135
- "transformer.h.28.mlp.dense_h_to_4h.weight": "model-00005-of-00006.safetensors",
136
- "transformer.h.28.self_attention.dense.weight": "model-00005-of-00006.safetensors",
137
- "transformer.h.28.self_attention.query_key_value.weight": "model-00005-of-00006.safetensors",
138
- "transformer.h.29.input_layernorm.bias": "model-00006-of-00006.safetensors",
139
- "transformer.h.29.input_layernorm.weight": "model-00006-of-00006.safetensors",
140
- "transformer.h.29.mlp.dense_4h_to_h.weight": "model-00006-of-00006.safetensors",
141
- "transformer.h.29.mlp.dense_h_to_4h.weight": "model-00006-of-00006.safetensors",
142
- "transformer.h.29.self_attention.dense.weight": "model-00006-of-00006.safetensors",
143
- "transformer.h.29.self_attention.query_key_value.weight": "model-00006-of-00006.safetensors",
144
- "transformer.h.3.input_layernorm.bias": "model-00001-of-00006.safetensors",
145
- "transformer.h.3.input_layernorm.weight": "model-00001-of-00006.safetensors",
146
- "transformer.h.3.mlp.dense_4h_to_h.weight": "model-00001-of-00006.safetensors",
147
- "transformer.h.3.mlp.dense_h_to_4h.weight": "model-00001-of-00006.safetensors",
148
- "transformer.h.3.self_attention.dense.weight": "model-00001-of-00006.safetensors",
149
- "transformer.h.3.self_attention.query_key_value.weight": "model-00001-of-00006.safetensors",
150
- "transformer.h.30.input_layernorm.bias": "model-00006-of-00006.safetensors",
151
- "transformer.h.30.input_layernorm.weight": "model-00006-of-00006.safetensors",
152
- "transformer.h.30.mlp.dense_4h_to_h.weight": "model-00006-of-00006.safetensors",
153
- "transformer.h.30.mlp.dense_h_to_4h.weight": "model-00006-of-00006.safetensors",
154
- "transformer.h.30.self_attention.dense.weight": "model-00006-of-00006.safetensors",
155
- "transformer.h.30.self_attention.query_key_value.weight": "model-00006-of-00006.safetensors",
156
- "transformer.h.31.input_layernorm.bias": "model-00006-of-00006.safetensors",
157
- "transformer.h.31.input_layernorm.weight": "model-00006-of-00006.safetensors",
158
- "transformer.h.31.mlp.dense_4h_to_h.weight": "model-00006-of-00006.safetensors",
159
- "transformer.h.31.mlp.dense_h_to_4h.weight": "model-00006-of-00006.safetensors",
160
- "transformer.h.31.self_attention.dense.weight": "model-00006-of-00006.safetensors",
161
- "transformer.h.31.self_attention.query_key_value.weight": "model-00006-of-00006.safetensors",
162
- "transformer.h.4.input_layernorm.bias": "model-00002-of-00006.safetensors",
163
- "transformer.h.4.input_layernorm.weight": "model-00002-of-00006.safetensors",
164
- "transformer.h.4.mlp.dense_4h_to_h.weight": "model-00002-of-00006.safetensors",
165
- "transformer.h.4.mlp.dense_h_to_4h.weight": "model-00001-of-00006.safetensors",
166
- "transformer.h.4.self_attention.dense.weight": "model-00001-of-00006.safetensors",
167
- "transformer.h.4.self_attention.query_key_value.weight": "model-00001-of-00006.safetensors",
168
- "transformer.h.5.input_layernorm.bias": "model-00002-of-00006.safetensors",
169
- "transformer.h.5.input_layernorm.weight": "model-00002-of-00006.safetensors",
170
- "transformer.h.5.mlp.dense_4h_to_h.weight": "model-00002-of-00006.safetensors",
171
- "transformer.h.5.mlp.dense_h_to_4h.weight": "model-00002-of-00006.safetensors",
172
- "transformer.h.5.self_attention.dense.weight": "model-00002-of-00006.safetensors",
173
- "transformer.h.5.self_attention.query_key_value.weight": "model-00002-of-00006.safetensors",
174
- "transformer.h.6.input_layernorm.bias": "model-00002-of-00006.safetensors",
175
- "transformer.h.6.input_layernorm.weight": "model-00002-of-00006.safetensors",
176
- "transformer.h.6.mlp.dense_4h_to_h.weight": "model-00002-of-00006.safetensors",
177
- "transformer.h.6.mlp.dense_h_to_4h.weight": "model-00002-of-00006.safetensors",
178
- "transformer.h.6.self_attention.dense.weight": "model-00002-of-00006.safetensors",
179
- "transformer.h.6.self_attention.query_key_value.weight": "model-00002-of-00006.safetensors",
180
- "transformer.h.7.input_layernorm.bias": "model-00002-of-00006.safetensors",
181
- "transformer.h.7.input_layernorm.weight": "model-00002-of-00006.safetensors",
182
- "transformer.h.7.mlp.dense_4h_to_h.weight": "model-00002-of-00006.safetensors",
183
- "transformer.h.7.mlp.dense_h_to_4h.weight": "model-00002-of-00006.safetensors",
184
- "transformer.h.7.self_attention.dense.weight": "model-00002-of-00006.safetensors",
185
- "transformer.h.7.self_attention.query_key_value.weight": "model-00002-of-00006.safetensors",
186
- "transformer.h.8.input_layernorm.bias": "model-00002-of-00006.safetensors",
187
- "transformer.h.8.input_layernorm.weight": "model-00002-of-00006.safetensors",
188
- "transformer.h.8.mlp.dense_4h_to_h.weight": "model-00002-of-00006.safetensors",
189
- "transformer.h.8.mlp.dense_h_to_4h.weight": "model-00002-of-00006.safetensors",
190
- "transformer.h.8.self_attention.dense.weight": "model-00002-of-00006.safetensors",
191
- "transformer.h.8.self_attention.query_key_value.weight": "model-00002-of-00006.safetensors",
192
- "transformer.h.9.input_layernorm.bias": "model-00002-of-00006.safetensors",
193
- "transformer.h.9.input_layernorm.weight": "model-00002-of-00006.safetensors",
194
- "transformer.h.9.mlp.dense_4h_to_h.weight": "model-00002-of-00006.safetensors",
195
- "transformer.h.9.mlp.dense_h_to_4h.weight": "model-00002-of-00006.safetensors",
196
- "transformer.h.9.self_attention.dense.weight": "model-00002-of-00006.safetensors",
197
- "transformer.h.9.self_attention.query_key_value.weight": "model-00002-of-00006.safetensors",
198
- "transformer.ln_f.bias": "model-00006-of-00006.safetensors",
199
- "transformer.ln_f.weight": "model-00006-of-00006.safetensors",
200
- "transformer.word_embeddings.weight": "model-00001-of-00006.safetensors"
201
  }
202
  }
 
1
  {
2
  "metadata": {
3
+ "total_size": 13843441408
4
  },
5
  "weight_map": {
6
+ "transformer.h.0.input_layernorm.bias": "model-00001-of-00003.safetensors",
7
+ "transformer.h.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
8
+ "transformer.h.0.mlp.dense_4h_to_h.weight": "model-00001-of-00003.safetensors",
9
+ "transformer.h.0.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
10
+ "transformer.h.0.self_attention.dense.weight": "model-00001-of-00003.safetensors",
11
+ "transformer.h.0.self_attention.query_key_value.weight": "model-00001-of-00003.safetensors",
12
+ "transformer.h.1.input_layernorm.bias": "model-00001-of-00003.safetensors",
13
+ "transformer.h.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
14
+ "transformer.h.1.mlp.dense_4h_to_h.weight": "model-00001-of-00003.safetensors",
15
+ "transformer.h.1.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
16
+ "transformer.h.1.self_attention.dense.weight": "model-00001-of-00003.safetensors",
17
+ "transformer.h.1.self_attention.query_key_value.weight": "model-00001-of-00003.safetensors",
18
+ "transformer.h.10.input_layernorm.bias": "model-00002-of-00003.safetensors",
19
+ "transformer.h.10.input_layernorm.weight": "model-00002-of-00003.safetensors",
20
+ "transformer.h.10.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
21
+ "transformer.h.10.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
22
+ "transformer.h.10.self_attention.dense.weight": "model-00001-of-00003.safetensors",
23
+ "transformer.h.10.self_attention.query_key_value.weight": "model-00001-of-00003.safetensors",
24
+ "transformer.h.11.input_layernorm.bias": "model-00002-of-00003.safetensors",
25
+ "transformer.h.11.input_layernorm.weight": "model-00002-of-00003.safetensors",
26
+ "transformer.h.11.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
27
+ "transformer.h.11.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
28
+ "transformer.h.11.self_attention.dense.weight": "model-00002-of-00003.safetensors",
29
+ "transformer.h.11.self_attention.query_key_value.weight": "model-00002-of-00003.safetensors",
30
+ "transformer.h.12.input_layernorm.bias": "model-00002-of-00003.safetensors",
31
+ "transformer.h.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
32
+ "transformer.h.12.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
33
+ "transformer.h.12.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
34
+ "transformer.h.12.self_attention.dense.weight": "model-00002-of-00003.safetensors",
35
+ "transformer.h.12.self_attention.query_key_value.weight": "model-00002-of-00003.safetensors",
36
+ "transformer.h.13.input_layernorm.bias": "model-00002-of-00003.safetensors",
37
+ "transformer.h.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
38
+ "transformer.h.13.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
39
+ "transformer.h.13.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
40
+ "transformer.h.13.self_attention.dense.weight": "model-00002-of-00003.safetensors",
41
+ "transformer.h.13.self_attention.query_key_value.weight": "model-00002-of-00003.safetensors",
42
+ "transformer.h.14.input_layernorm.bias": "model-00002-of-00003.safetensors",
43
+ "transformer.h.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
44
+ "transformer.h.14.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
45
+ "transformer.h.14.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
46
+ "transformer.h.14.self_attention.dense.weight": "model-00002-of-00003.safetensors",
47
+ "transformer.h.14.self_attention.query_key_value.weight": "model-00002-of-00003.safetensors",
48
+ "transformer.h.15.input_layernorm.bias": "model-00002-of-00003.safetensors",
49
+ "transformer.h.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
50
+ "transformer.h.15.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
51
+ "transformer.h.15.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
52
+ "transformer.h.15.self_attention.dense.weight": "model-00002-of-00003.safetensors",
53
+ "transformer.h.15.self_attention.query_key_value.weight": "model-00002-of-00003.safetensors",
54
+ "transformer.h.16.input_layernorm.bias": "model-00002-of-00003.safetensors",
55
+ "transformer.h.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
56
+ "transformer.h.16.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
57
+ "transformer.h.16.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
58
+ "transformer.h.16.self_attention.dense.weight": "model-00002-of-00003.safetensors",
59
+ "transformer.h.16.self_attention.query_key_value.weight": "model-00002-of-00003.safetensors",
60
+ "transformer.h.17.input_layernorm.bias": "model-00002-of-00003.safetensors",
61
+ "transformer.h.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
62
+ "transformer.h.17.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
63
+ "transformer.h.17.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
64
+ "transformer.h.17.self_attention.dense.weight": "model-00002-of-00003.safetensors",
65
+ "transformer.h.17.self_attention.query_key_value.weight": "model-00002-of-00003.safetensors",
66
+ "transformer.h.18.input_layernorm.bias": "model-00002-of-00003.safetensors",
67
+ "transformer.h.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
68
+ "transformer.h.18.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
69
+ "transformer.h.18.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
70
+ "transformer.h.18.self_attention.dense.weight": "model-00002-of-00003.safetensors",
71
+ "transformer.h.18.self_attention.query_key_value.weight": "model-00002-of-00003.safetensors",
72
+ "transformer.h.19.input_layernorm.bias": "model-00002-of-00003.safetensors",
73
+ "transformer.h.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
74
+ "transformer.h.19.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
75
+ "transformer.h.19.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
76
+ "transformer.h.19.self_attention.dense.weight": "model-00002-of-00003.safetensors",
77
+ "transformer.h.19.self_attention.query_key_value.weight": "model-00002-of-00003.safetensors",
78
+ "transformer.h.2.input_layernorm.bias": "model-00001-of-00003.safetensors",
79
+ "transformer.h.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
80
+ "transformer.h.2.mlp.dense_4h_to_h.weight": "model-00001-of-00003.safetensors",
81
+ "transformer.h.2.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
82
+ "transformer.h.2.self_attention.dense.weight": "model-00001-of-00003.safetensors",
83
+ "transformer.h.2.self_attention.query_key_value.weight": "model-00001-of-00003.safetensors",
84
+ "transformer.h.20.input_layernorm.bias": "model-00002-of-00003.safetensors",
85
+ "transformer.h.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
86
+ "transformer.h.20.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
87
+ "transformer.h.20.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
88
+ "transformer.h.20.self_attention.dense.weight": "model-00002-of-00003.safetensors",
89
+ "transformer.h.20.self_attention.query_key_value.weight": "model-00002-of-00003.safetensors",
90
+ "transformer.h.21.input_layernorm.bias": "model-00002-of-00003.safetensors",
91
+ "transformer.h.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
92
+ "transformer.h.21.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
93
+ "transformer.h.21.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
94
+ "transformer.h.21.self_attention.dense.weight": "model-00002-of-00003.safetensors",
95
+ "transformer.h.21.self_attention.query_key_value.weight": "model-00002-of-00003.safetensors",
96
+ "transformer.h.22.input_layernorm.bias": "model-00003-of-00003.safetensors",
97
+ "transformer.h.22.input_layernorm.weight": "model-00003-of-00003.safetensors",
98
+ "transformer.h.22.mlp.dense_4h_to_h.weight": "model-00003-of-00003.safetensors",
99
+ "transformer.h.22.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
100
+ "transformer.h.22.self_attention.dense.weight": "model-00002-of-00003.safetensors",
101
+ "transformer.h.22.self_attention.query_key_value.weight": "model-00002-of-00003.safetensors",
102
+ "transformer.h.23.input_layernorm.bias": "model-00003-of-00003.safetensors",
103
+ "transformer.h.23.input_layernorm.weight": "model-00003-of-00003.safetensors",
104
+ "transformer.h.23.mlp.dense_4h_to_h.weight": "model-00003-of-00003.safetensors",
105
+ "transformer.h.23.mlp.dense_h_to_4h.weight": "model-00003-of-00003.safetensors",
106
+ "transformer.h.23.self_attention.dense.weight": "model-00003-of-00003.safetensors",
107
+ "transformer.h.23.self_attention.query_key_value.weight": "model-00003-of-00003.safetensors",
108
+ "transformer.h.24.input_layernorm.bias": "model-00003-of-00003.safetensors",
109
+ "transformer.h.24.input_layernorm.weight": "model-00003-of-00003.safetensors",
110
+ "transformer.h.24.mlp.dense_4h_to_h.weight": "model-00003-of-00003.safetensors",
111
+ "transformer.h.24.mlp.dense_h_to_4h.weight": "model-00003-of-00003.safetensors",
112
+ "transformer.h.24.self_attention.dense.weight": "model-00003-of-00003.safetensors",
113
+ "transformer.h.24.self_attention.query_key_value.weight": "model-00003-of-00003.safetensors",
114
+ "transformer.h.25.input_layernorm.bias": "model-00003-of-00003.safetensors",
115
+ "transformer.h.25.input_layernorm.weight": "model-00003-of-00003.safetensors",
116
+ "transformer.h.25.mlp.dense_4h_to_h.weight": "model-00003-of-00003.safetensors",
117
+ "transformer.h.25.mlp.dense_h_to_4h.weight": "model-00003-of-00003.safetensors",
118
+ "transformer.h.25.self_attention.dense.weight": "model-00003-of-00003.safetensors",
119
+ "transformer.h.25.self_attention.query_key_value.weight": "model-00003-of-00003.safetensors",
120
+ "transformer.h.26.input_layernorm.bias": "model-00003-of-00003.safetensors",
121
+ "transformer.h.26.input_layernorm.weight": "model-00003-of-00003.safetensors",
122
+ "transformer.h.26.mlp.dense_4h_to_h.weight": "model-00003-of-00003.safetensors",
123
+ "transformer.h.26.mlp.dense_h_to_4h.weight": "model-00003-of-00003.safetensors",
124
+ "transformer.h.26.self_attention.dense.weight": "model-00003-of-00003.safetensors",
125
+ "transformer.h.26.self_attention.query_key_value.weight": "model-00003-of-00003.safetensors",
126
+ "transformer.h.27.input_layernorm.bias": "model-00003-of-00003.safetensors",
127
+ "transformer.h.27.input_layernorm.weight": "model-00003-of-00003.safetensors",
128
+ "transformer.h.27.mlp.dense_4h_to_h.weight": "model-00003-of-00003.safetensors",
129
+ "transformer.h.27.mlp.dense_h_to_4h.weight": "model-00003-of-00003.safetensors",
130
+ "transformer.h.27.self_attention.dense.weight": "model-00003-of-00003.safetensors",
131
+ "transformer.h.27.self_attention.query_key_value.weight": "model-00003-of-00003.safetensors",
132
+ "transformer.h.28.input_layernorm.bias": "model-00003-of-00003.safetensors",
133
+ "transformer.h.28.input_layernorm.weight": "model-00003-of-00003.safetensors",
134
+ "transformer.h.28.mlp.dense_4h_to_h.weight": "model-00003-of-00003.safetensors",
135
+ "transformer.h.28.mlp.dense_h_to_4h.weight": "model-00003-of-00003.safetensors",
136
+ "transformer.h.28.self_attention.dense.weight": "model-00003-of-00003.safetensors",
137
+ "transformer.h.28.self_attention.query_key_value.weight": "model-00003-of-00003.safetensors",
138
+ "transformer.h.29.input_layernorm.bias": "model-00003-of-00003.safetensors",
139
+ "transformer.h.29.input_layernorm.weight": "model-00003-of-00003.safetensors",
140
+ "transformer.h.29.mlp.dense_4h_to_h.weight": "model-00003-of-00003.safetensors",
141
+ "transformer.h.29.mlp.dense_h_to_4h.weight": "model-00003-of-00003.safetensors",
142
+ "transformer.h.29.self_attention.dense.weight": "model-00003-of-00003.safetensors",
143
+ "transformer.h.29.self_attention.query_key_value.weight": "model-00003-of-00003.safetensors",
144
+ "transformer.h.3.input_layernorm.bias": "model-00001-of-00003.safetensors",
145
+ "transformer.h.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
146
+ "transformer.h.3.mlp.dense_4h_to_h.weight": "model-00001-of-00003.safetensors",
147
+ "transformer.h.3.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
148
+ "transformer.h.3.self_attention.dense.weight": "model-00001-of-00003.safetensors",
149
+ "transformer.h.3.self_attention.query_key_value.weight": "model-00001-of-00003.safetensors",
150
+ "transformer.h.30.input_layernorm.bias": "model-00003-of-00003.safetensors",
151
+ "transformer.h.30.input_layernorm.weight": "model-00003-of-00003.safetensors",
152
+ "transformer.h.30.mlp.dense_4h_to_h.weight": "model-00003-of-00003.safetensors",
153
+ "transformer.h.30.mlp.dense_h_to_4h.weight": "model-00003-of-00003.safetensors",
154
+ "transformer.h.30.self_attention.dense.weight": "model-00003-of-00003.safetensors",
155
+ "transformer.h.30.self_attention.query_key_value.weight": "model-00003-of-00003.safetensors",
156
+ "transformer.h.31.input_layernorm.bias": "model-00003-of-00003.safetensors",
157
+ "transformer.h.31.input_layernorm.weight": "model-00003-of-00003.safetensors",
158
+ "transformer.h.31.mlp.dense_4h_to_h.weight": "model-00003-of-00003.safetensors",
159
+ "transformer.h.31.mlp.dense_h_to_4h.weight": "model-00003-of-00003.safetensors",
160
+ "transformer.h.31.self_attention.dense.weight": "model-00003-of-00003.safetensors",
161
+ "transformer.h.31.self_attention.query_key_value.weight": "model-00003-of-00003.safetensors",
162
+ "transformer.h.4.input_layernorm.bias": "model-00001-of-00003.safetensors",
163
+ "transformer.h.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
164
+ "transformer.h.4.mlp.dense_4h_to_h.weight": "model-00001-of-00003.safetensors",
165
+ "transformer.h.4.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
166
+ "transformer.h.4.self_attention.dense.weight": "model-00001-of-00003.safetensors",
167
+ "transformer.h.4.self_attention.query_key_value.weight": "model-00001-of-00003.safetensors",
168
+ "transformer.h.5.input_layernorm.bias": "model-00001-of-00003.safetensors",
169
+ "transformer.h.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
170
+ "transformer.h.5.mlp.dense_4h_to_h.weight": "model-00001-of-00003.safetensors",
171
+ "transformer.h.5.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
172
+ "transformer.h.5.self_attention.dense.weight": "model-00001-of-00003.safetensors",
173
+ "transformer.h.5.self_attention.query_key_value.weight": "model-00001-of-00003.safetensors",
174
+ "transformer.h.6.input_layernorm.bias": "model-00001-of-00003.safetensors",
175
+ "transformer.h.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
176
+ "transformer.h.6.mlp.dense_4h_to_h.weight": "model-00001-of-00003.safetensors",
177
+ "transformer.h.6.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
178
+ "transformer.h.6.self_attention.dense.weight": "model-00001-of-00003.safetensors",
179
+ "transformer.h.6.self_attention.query_key_value.weight": "model-00001-of-00003.safetensors",
180
+ "transformer.h.7.input_layernorm.bias": "model-00001-of-00003.safetensors",
181
+ "transformer.h.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
182
+ "transformer.h.7.mlp.dense_4h_to_h.weight": "model-00001-of-00003.safetensors",
183
+ "transformer.h.7.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
184
+ "transformer.h.7.self_attention.dense.weight": "model-00001-of-00003.safetensors",
185
+ "transformer.h.7.self_attention.query_key_value.weight": "model-00001-of-00003.safetensors",
186
+ "transformer.h.8.input_layernorm.bias": "model-00001-of-00003.safetensors",
187
+ "transformer.h.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
188
+ "transformer.h.8.mlp.dense_4h_to_h.weight": "model-00001-of-00003.safetensors",
189
+ "transformer.h.8.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
190
+ "transformer.h.8.self_attention.dense.weight": "model-00001-of-00003.safetensors",
191
+ "transformer.h.8.self_attention.query_key_value.weight": "model-00001-of-00003.safetensors",
192
+ "transformer.h.9.input_layernorm.bias": "model-00001-of-00003.safetensors",
193
+ "transformer.h.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
194
+ "transformer.h.9.mlp.dense_4h_to_h.weight": "model-00001-of-00003.safetensors",
195
+ "transformer.h.9.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
196
+ "transformer.h.9.self_attention.dense.weight": "model-00001-of-00003.safetensors",
197
+ "transformer.h.9.self_attention.query_key_value.weight": "model-00001-of-00003.safetensors",
198
+ "transformer.ln_f.bias": "model-00003-of-00003.safetensors",
199
+ "transformer.ln_f.weight": "model-00003-of-00003.safetensors",
200
+ "transformer.word_embeddings.weight": "model-00001-of-00003.safetensors"
201
  }
202
  }