Spaces:
Running
Running
Upload folder using huggingface_hub
Browse files
checkpoints/llamastack/config.json
CHANGED
@@ -1,25 +1,26 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
3 |
"architectures": [
|
4 |
-
"
|
5 |
],
|
6 |
-
"
|
7 |
-
"
|
|
|
8 |
"hidden_act": "gelu",
|
9 |
-
"
|
|
|
10 |
"initializer_range": 0.02,
|
11 |
-
"intermediate_size":
|
12 |
-
"layer_norm_eps": 1e-
|
13 |
-
"max_position_embeddings":
|
14 |
-
"model_type": "
|
15 |
-
"num_attention_heads":
|
16 |
-
"num_hidden_layers":
|
17 |
-
"
|
18 |
-
"
|
19 |
-
"tie_word_embeddings": false,
|
20 |
"torch_dtype": "float32",
|
21 |
-
"transformers_version": "4.
|
|
|
22 |
"use_cache": true,
|
23 |
-
"
|
24 |
-
"vocab_size": 50304
|
25 |
}
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "bert-base-cased",
|
3 |
"architectures": [
|
4 |
+
"BertModel"
|
5 |
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"gradient_checkpointing": false,
|
9 |
"hidden_act": "gelu",
|
10 |
+
"hidden_dropout_prob": 0.1,
|
11 |
+
"hidden_size": 768,
|
12 |
"initializer_range": 0.02,
|
13 |
+
"intermediate_size": 3072,
|
14 |
+
"layer_norm_eps": 1e-12,
|
15 |
+
"max_position_embeddings": 512,
|
16 |
+
"model_type": "bert",
|
17 |
+
"num_attention_heads": 12,
|
18 |
+
"num_hidden_layers": 12,
|
19 |
+
"pad_token_id": 0,
|
20 |
+
"position_embedding_type": "absolute",
|
|
|
21 |
"torch_dtype": "float32",
|
22 |
+
"transformers_version": "4.29.2",
|
23 |
+
"type_vocab_size": 2,
|
24 |
"use_cache": true,
|
25 |
+
"vocab_size": 28996
|
|
|
26 |
}
|
checkpoints/llamastack/pytorch_model-00001-of-00003.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:49a78274352d78140a0815f4d9223109be52486e9e634f0d7cf7773909580283
|
3 |
+
size 194646579
|
checkpoints/llamastack/pytorch_model-00002-of-00003.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c69b3f1cd4e70ddbeac3609e2c175c3c207df3f79b5d2436532a4ffd354c8f95
|
3 |
+
size 198498043
|
checkpoints/llamastack/pytorch_model-00003-of-00003.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:492c90340fe8439dcd723b70fc995d1998ebe83075117a66235b8cc846ff74f7
|
3 |
+
size 40167707
|
checkpoints/llamastack/pytorch_model.bin.index.json
ADDED
@@ -0,0 +1,207 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"metadata": {
|
3 |
+
"total_size": 433245184
|
4 |
+
},
|
5 |
+
"weight_map": {
|
6 |
+
"embeddings.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
|
7 |
+
"embeddings.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
|
8 |
+
"embeddings.position_embeddings.weight": "pytorch_model-00001-of-00003.bin",
|
9 |
+
"embeddings.position_ids": "pytorch_model-00001-of-00003.bin",
|
10 |
+
"embeddings.token_type_embeddings.weight": "pytorch_model-00001-of-00003.bin",
|
11 |
+
"embeddings.word_embeddings.weight": "pytorch_model-00001-of-00003.bin",
|
12 |
+
"encoder.layer.0.attention.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
|
13 |
+
"encoder.layer.0.attention.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
|
14 |
+
"encoder.layer.0.attention.output.dense.bias": "pytorch_model-00001-of-00003.bin",
|
15 |
+
"encoder.layer.0.attention.output.dense.weight": "pytorch_model-00001-of-00003.bin",
|
16 |
+
"encoder.layer.0.attention.self.key.bias": "pytorch_model-00001-of-00003.bin",
|
17 |
+
"encoder.layer.0.attention.self.key.weight": "pytorch_model-00001-of-00003.bin",
|
18 |
+
"encoder.layer.0.attention.self.query.bias": "pytorch_model-00001-of-00003.bin",
|
19 |
+
"encoder.layer.0.attention.self.query.weight": "pytorch_model-00001-of-00003.bin",
|
20 |
+
"encoder.layer.0.attention.self.value.bias": "pytorch_model-00001-of-00003.bin",
|
21 |
+
"encoder.layer.0.attention.self.value.weight": "pytorch_model-00001-of-00003.bin",
|
22 |
+
"encoder.layer.0.intermediate.dense.bias": "pytorch_model-00001-of-00003.bin",
|
23 |
+
"encoder.layer.0.intermediate.dense.weight": "pytorch_model-00001-of-00003.bin",
|
24 |
+
"encoder.layer.0.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
|
25 |
+
"encoder.layer.0.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
|
26 |
+
"encoder.layer.0.output.dense.bias": "pytorch_model-00001-of-00003.bin",
|
27 |
+
"encoder.layer.0.output.dense.weight": "pytorch_model-00001-of-00003.bin",
|
28 |
+
"encoder.layer.1.attention.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
|
29 |
+
"encoder.layer.1.attention.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
|
30 |
+
"encoder.layer.1.attention.output.dense.bias": "pytorch_model-00001-of-00003.bin",
|
31 |
+
"encoder.layer.1.attention.output.dense.weight": "pytorch_model-00001-of-00003.bin",
|
32 |
+
"encoder.layer.1.attention.self.key.bias": "pytorch_model-00001-of-00003.bin",
|
33 |
+
"encoder.layer.1.attention.self.key.weight": "pytorch_model-00001-of-00003.bin",
|
34 |
+
"encoder.layer.1.attention.self.query.bias": "pytorch_model-00001-of-00003.bin",
|
35 |
+
"encoder.layer.1.attention.self.query.weight": "pytorch_model-00001-of-00003.bin",
|
36 |
+
"encoder.layer.1.attention.self.value.bias": "pytorch_model-00001-of-00003.bin",
|
37 |
+
"encoder.layer.1.attention.self.value.weight": "pytorch_model-00001-of-00003.bin",
|
38 |
+
"encoder.layer.1.intermediate.dense.bias": "pytorch_model-00001-of-00003.bin",
|
39 |
+
"encoder.layer.1.intermediate.dense.weight": "pytorch_model-00001-of-00003.bin",
|
40 |
+
"encoder.layer.1.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
|
41 |
+
"encoder.layer.1.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
|
42 |
+
"encoder.layer.1.output.dense.bias": "pytorch_model-00001-of-00003.bin",
|
43 |
+
"encoder.layer.1.output.dense.weight": "pytorch_model-00001-of-00003.bin",
|
44 |
+
"encoder.layer.10.attention.output.LayerNorm.bias": "pytorch_model-00002-of-00003.bin",
|
45 |
+
"encoder.layer.10.attention.output.LayerNorm.weight": "pytorch_model-00002-of-00003.bin",
|
46 |
+
"encoder.layer.10.attention.output.dense.bias": "pytorch_model-00002-of-00003.bin",
|
47 |
+
"encoder.layer.10.attention.output.dense.weight": "pytorch_model-00002-of-00003.bin",
|
48 |
+
"encoder.layer.10.attention.self.key.bias": "pytorch_model-00002-of-00003.bin",
|
49 |
+
"encoder.layer.10.attention.self.key.weight": "pytorch_model-00002-of-00003.bin",
|
50 |
+
"encoder.layer.10.attention.self.query.bias": "pytorch_model-00002-of-00003.bin",
|
51 |
+
"encoder.layer.10.attention.self.query.weight": "pytorch_model-00002-of-00003.bin",
|
52 |
+
"encoder.layer.10.attention.self.value.bias": "pytorch_model-00002-of-00003.bin",
|
53 |
+
"encoder.layer.10.attention.self.value.weight": "pytorch_model-00002-of-00003.bin",
|
54 |
+
"encoder.layer.10.intermediate.dense.bias": "pytorch_model-00002-of-00003.bin",
|
55 |
+
"encoder.layer.10.intermediate.dense.weight": "pytorch_model-00002-of-00003.bin",
|
56 |
+
"encoder.layer.10.output.LayerNorm.bias": "pytorch_model-00003-of-00003.bin",
|
57 |
+
"encoder.layer.10.output.LayerNorm.weight": "pytorch_model-00003-of-00003.bin",
|
58 |
+
"encoder.layer.10.output.dense.bias": "pytorch_model-00003-of-00003.bin",
|
59 |
+
"encoder.layer.10.output.dense.weight": "pytorch_model-00003-of-00003.bin",
|
60 |
+
"encoder.layer.11.attention.output.LayerNorm.bias": "pytorch_model-00003-of-00003.bin",
|
61 |
+
"encoder.layer.11.attention.output.LayerNorm.weight": "pytorch_model-00003-of-00003.bin",
|
62 |
+
"encoder.layer.11.attention.output.dense.bias": "pytorch_model-00003-of-00003.bin",
|
63 |
+
"encoder.layer.11.attention.output.dense.weight": "pytorch_model-00003-of-00003.bin",
|
64 |
+
"encoder.layer.11.attention.self.key.bias": "pytorch_model-00003-of-00003.bin",
|
65 |
+
"encoder.layer.11.attention.self.key.weight": "pytorch_model-00003-of-00003.bin",
|
66 |
+
"encoder.layer.11.attention.self.query.bias": "pytorch_model-00003-of-00003.bin",
|
67 |
+
"encoder.layer.11.attention.self.query.weight": "pytorch_model-00003-of-00003.bin",
|
68 |
+
"encoder.layer.11.attention.self.value.bias": "pytorch_model-00003-of-00003.bin",
|
69 |
+
"encoder.layer.11.attention.self.value.weight": "pytorch_model-00003-of-00003.bin",
|
70 |
+
"encoder.layer.11.intermediate.dense.bias": "pytorch_model-00003-of-00003.bin",
|
71 |
+
"encoder.layer.11.intermediate.dense.weight": "pytorch_model-00003-of-00003.bin",
|
72 |
+
"encoder.layer.11.output.LayerNorm.bias": "pytorch_model-00003-of-00003.bin",
|
73 |
+
"encoder.layer.11.output.LayerNorm.weight": "pytorch_model-00003-of-00003.bin",
|
74 |
+
"encoder.layer.11.output.dense.bias": "pytorch_model-00003-of-00003.bin",
|
75 |
+
"encoder.layer.11.output.dense.weight": "pytorch_model-00003-of-00003.bin",
|
76 |
+
"encoder.layer.2.attention.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
|
77 |
+
"encoder.layer.2.attention.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
|
78 |
+
"encoder.layer.2.attention.output.dense.bias": "pytorch_model-00001-of-00003.bin",
|
79 |
+
"encoder.layer.2.attention.output.dense.weight": "pytorch_model-00001-of-00003.bin",
|
80 |
+
"encoder.layer.2.attention.self.key.bias": "pytorch_model-00001-of-00003.bin",
|
81 |
+
"encoder.layer.2.attention.self.key.weight": "pytorch_model-00001-of-00003.bin",
|
82 |
+
"encoder.layer.2.attention.self.query.bias": "pytorch_model-00001-of-00003.bin",
|
83 |
+
"encoder.layer.2.attention.self.query.weight": "pytorch_model-00001-of-00003.bin",
|
84 |
+
"encoder.layer.2.attention.self.value.bias": "pytorch_model-00001-of-00003.bin",
|
85 |
+
"encoder.layer.2.attention.self.value.weight": "pytorch_model-00001-of-00003.bin",
|
86 |
+
"encoder.layer.2.intermediate.dense.bias": "pytorch_model-00001-of-00003.bin",
|
87 |
+
"encoder.layer.2.intermediate.dense.weight": "pytorch_model-00001-of-00003.bin",
|
88 |
+
"encoder.layer.2.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
|
89 |
+
"encoder.layer.2.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
|
90 |
+
"encoder.layer.2.output.dense.bias": "pytorch_model-00001-of-00003.bin",
|
91 |
+
"encoder.layer.2.output.dense.weight": "pytorch_model-00001-of-00003.bin",
|
92 |
+
"encoder.layer.3.attention.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
|
93 |
+
"encoder.layer.3.attention.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
|
94 |
+
"encoder.layer.3.attention.output.dense.bias": "pytorch_model-00001-of-00003.bin",
|
95 |
+
"encoder.layer.3.attention.output.dense.weight": "pytorch_model-00001-of-00003.bin",
|
96 |
+
"encoder.layer.3.attention.self.key.bias": "pytorch_model-00001-of-00003.bin",
|
97 |
+
"encoder.layer.3.attention.self.key.weight": "pytorch_model-00001-of-00003.bin",
|
98 |
+
"encoder.layer.3.attention.self.query.bias": "pytorch_model-00001-of-00003.bin",
|
99 |
+
"encoder.layer.3.attention.self.query.weight": "pytorch_model-00001-of-00003.bin",
|
100 |
+
"encoder.layer.3.attention.self.value.bias": "pytorch_model-00001-of-00003.bin",
|
101 |
+
"encoder.layer.3.attention.self.value.weight": "pytorch_model-00001-of-00003.bin",
|
102 |
+
"encoder.layer.3.intermediate.dense.bias": "pytorch_model-00001-of-00003.bin",
|
103 |
+
"encoder.layer.3.intermediate.dense.weight": "pytorch_model-00001-of-00003.bin",
|
104 |
+
"encoder.layer.3.output.LayerNorm.bias": "pytorch_model-00002-of-00003.bin",
|
105 |
+
"encoder.layer.3.output.LayerNorm.weight": "pytorch_model-00002-of-00003.bin",
|
106 |
+
"encoder.layer.3.output.dense.bias": "pytorch_model-00002-of-00003.bin",
|
107 |
+
"encoder.layer.3.output.dense.weight": "pytorch_model-00002-of-00003.bin",
|
108 |
+
"encoder.layer.4.attention.output.LayerNorm.bias": "pytorch_model-00002-of-00003.bin",
|
109 |
+
"encoder.layer.4.attention.output.LayerNorm.weight": "pytorch_model-00002-of-00003.bin",
|
110 |
+
"encoder.layer.4.attention.output.dense.bias": "pytorch_model-00002-of-00003.bin",
|
111 |
+
"encoder.layer.4.attention.output.dense.weight": "pytorch_model-00002-of-00003.bin",
|
112 |
+
"encoder.layer.4.attention.self.key.bias": "pytorch_model-00002-of-00003.bin",
|
113 |
+
"encoder.layer.4.attention.self.key.weight": "pytorch_model-00002-of-00003.bin",
|
114 |
+
"encoder.layer.4.attention.self.query.bias": "pytorch_model-00002-of-00003.bin",
|
115 |
+
"encoder.layer.4.attention.self.query.weight": "pytorch_model-00002-of-00003.bin",
|
116 |
+
"encoder.layer.4.attention.self.value.bias": "pytorch_model-00002-of-00003.bin",
|
117 |
+
"encoder.layer.4.attention.self.value.weight": "pytorch_model-00002-of-00003.bin",
|
118 |
+
"encoder.layer.4.intermediate.dense.bias": "pytorch_model-00002-of-00003.bin",
|
119 |
+
"encoder.layer.4.intermediate.dense.weight": "pytorch_model-00002-of-00003.bin",
|
120 |
+
"encoder.layer.4.output.LayerNorm.bias": "pytorch_model-00002-of-00003.bin",
|
121 |
+
"encoder.layer.4.output.LayerNorm.weight": "pytorch_model-00002-of-00003.bin",
|
122 |
+
"encoder.layer.4.output.dense.bias": "pytorch_model-00002-of-00003.bin",
|
123 |
+
"encoder.layer.4.output.dense.weight": "pytorch_model-00002-of-00003.bin",
|
124 |
+
"encoder.layer.5.attention.output.LayerNorm.bias": "pytorch_model-00002-of-00003.bin",
|
125 |
+
"encoder.layer.5.attention.output.LayerNorm.weight": "pytorch_model-00002-of-00003.bin",
|
126 |
+
"encoder.layer.5.attention.output.dense.bias": "pytorch_model-00002-of-00003.bin",
|
127 |
+
"encoder.layer.5.attention.output.dense.weight": "pytorch_model-00002-of-00003.bin",
|
128 |
+
"encoder.layer.5.attention.self.key.bias": "pytorch_model-00002-of-00003.bin",
|
129 |
+
"encoder.layer.5.attention.self.key.weight": "pytorch_model-00002-of-00003.bin",
|
130 |
+
"encoder.layer.5.attention.self.query.bias": "pytorch_model-00002-of-00003.bin",
|
131 |
+
"encoder.layer.5.attention.self.query.weight": "pytorch_model-00002-of-00003.bin",
|
132 |
+
"encoder.layer.5.attention.self.value.bias": "pytorch_model-00002-of-00003.bin",
|
133 |
+
"encoder.layer.5.attention.self.value.weight": "pytorch_model-00002-of-00003.bin",
|
134 |
+
"encoder.layer.5.intermediate.dense.bias": "pytorch_model-00002-of-00003.bin",
|
135 |
+
"encoder.layer.5.intermediate.dense.weight": "pytorch_model-00002-of-00003.bin",
|
136 |
+
"encoder.layer.5.output.LayerNorm.bias": "pytorch_model-00002-of-00003.bin",
|
137 |
+
"encoder.layer.5.output.LayerNorm.weight": "pytorch_model-00002-of-00003.bin",
|
138 |
+
"encoder.layer.5.output.dense.bias": "pytorch_model-00002-of-00003.bin",
|
139 |
+
"encoder.layer.5.output.dense.weight": "pytorch_model-00002-of-00003.bin",
|
140 |
+
"encoder.layer.6.attention.output.LayerNorm.bias": "pytorch_model-00002-of-00003.bin",
|
141 |
+
"encoder.layer.6.attention.output.LayerNorm.weight": "pytorch_model-00002-of-00003.bin",
|
142 |
+
"encoder.layer.6.attention.output.dense.bias": "pytorch_model-00002-of-00003.bin",
|
143 |
+
"encoder.layer.6.attention.output.dense.weight": "pytorch_model-00002-of-00003.bin",
|
144 |
+
"encoder.layer.6.attention.self.key.bias": "pytorch_model-00002-of-00003.bin",
|
145 |
+
"encoder.layer.6.attention.self.key.weight": "pytorch_model-00002-of-00003.bin",
|
146 |
+
"encoder.layer.6.attention.self.query.bias": "pytorch_model-00002-of-00003.bin",
|
147 |
+
"encoder.layer.6.attention.self.query.weight": "pytorch_model-00002-of-00003.bin",
|
148 |
+
"encoder.layer.6.attention.self.value.bias": "pytorch_model-00002-of-00003.bin",
|
149 |
+
"encoder.layer.6.attention.self.value.weight": "pytorch_model-00002-of-00003.bin",
|
150 |
+
"encoder.layer.6.intermediate.dense.bias": "pytorch_model-00002-of-00003.bin",
|
151 |
+
"encoder.layer.6.intermediate.dense.weight": "pytorch_model-00002-of-00003.bin",
|
152 |
+
"encoder.layer.6.output.LayerNorm.bias": "pytorch_model-00002-of-00003.bin",
|
153 |
+
"encoder.layer.6.output.LayerNorm.weight": "pytorch_model-00002-of-00003.bin",
|
154 |
+
"encoder.layer.6.output.dense.bias": "pytorch_model-00002-of-00003.bin",
|
155 |
+
"encoder.layer.6.output.dense.weight": "pytorch_model-00002-of-00003.bin",
|
156 |
+
"encoder.layer.7.attention.output.LayerNorm.bias": "pytorch_model-00002-of-00003.bin",
|
157 |
+
"encoder.layer.7.attention.output.LayerNorm.weight": "pytorch_model-00002-of-00003.bin",
|
158 |
+
"encoder.layer.7.attention.output.dense.bias": "pytorch_model-00002-of-00003.bin",
|
159 |
+
"encoder.layer.7.attention.output.dense.weight": "pytorch_model-00002-of-00003.bin",
|
160 |
+
"encoder.layer.7.attention.self.key.bias": "pytorch_model-00002-of-00003.bin",
|
161 |
+
"encoder.layer.7.attention.self.key.weight": "pytorch_model-00002-of-00003.bin",
|
162 |
+
"encoder.layer.7.attention.self.query.bias": "pytorch_model-00002-of-00003.bin",
|
163 |
+
"encoder.layer.7.attention.self.query.weight": "pytorch_model-00002-of-00003.bin",
|
164 |
+
"encoder.layer.7.attention.self.value.bias": "pytorch_model-00002-of-00003.bin",
|
165 |
+
"encoder.layer.7.attention.self.value.weight": "pytorch_model-00002-of-00003.bin",
|
166 |
+
"encoder.layer.7.intermediate.dense.bias": "pytorch_model-00002-of-00003.bin",
|
167 |
+
"encoder.layer.7.intermediate.dense.weight": "pytorch_model-00002-of-00003.bin",
|
168 |
+
"encoder.layer.7.output.LayerNorm.bias": "pytorch_model-00002-of-00003.bin",
|
169 |
+
"encoder.layer.7.output.LayerNorm.weight": "pytorch_model-00002-of-00003.bin",
|
170 |
+
"encoder.layer.7.output.dense.bias": "pytorch_model-00002-of-00003.bin",
|
171 |
+
"encoder.layer.7.output.dense.weight": "pytorch_model-00002-of-00003.bin",
|
172 |
+
"encoder.layer.8.attention.output.LayerNorm.bias": "pytorch_model-00002-of-00003.bin",
|
173 |
+
"encoder.layer.8.attention.output.LayerNorm.weight": "pytorch_model-00002-of-00003.bin",
|
174 |
+
"encoder.layer.8.attention.output.dense.bias": "pytorch_model-00002-of-00003.bin",
|
175 |
+
"encoder.layer.8.attention.output.dense.weight": "pytorch_model-00002-of-00003.bin",
|
176 |
+
"encoder.layer.8.attention.self.key.bias": "pytorch_model-00002-of-00003.bin",
|
177 |
+
"encoder.layer.8.attention.self.key.weight": "pytorch_model-00002-of-00003.bin",
|
178 |
+
"encoder.layer.8.attention.self.query.bias": "pytorch_model-00002-of-00003.bin",
|
179 |
+
"encoder.layer.8.attention.self.query.weight": "pytorch_model-00002-of-00003.bin",
|
180 |
+
"encoder.layer.8.attention.self.value.bias": "pytorch_model-00002-of-00003.bin",
|
181 |
+
"encoder.layer.8.attention.self.value.weight": "pytorch_model-00002-of-00003.bin",
|
182 |
+
"encoder.layer.8.intermediate.dense.bias": "pytorch_model-00002-of-00003.bin",
|
183 |
+
"encoder.layer.8.intermediate.dense.weight": "pytorch_model-00002-of-00003.bin",
|
184 |
+
"encoder.layer.8.output.LayerNorm.bias": "pytorch_model-00002-of-00003.bin",
|
185 |
+
"encoder.layer.8.output.LayerNorm.weight": "pytorch_model-00002-of-00003.bin",
|
186 |
+
"encoder.layer.8.output.dense.bias": "pytorch_model-00002-of-00003.bin",
|
187 |
+
"encoder.layer.8.output.dense.weight": "pytorch_model-00002-of-00003.bin",
|
188 |
+
"encoder.layer.9.attention.output.LayerNorm.bias": "pytorch_model-00002-of-00003.bin",
|
189 |
+
"encoder.layer.9.attention.output.LayerNorm.weight": "pytorch_model-00002-of-00003.bin",
|
190 |
+
"encoder.layer.9.attention.output.dense.bias": "pytorch_model-00002-of-00003.bin",
|
191 |
+
"encoder.layer.9.attention.output.dense.weight": "pytorch_model-00002-of-00003.bin",
|
192 |
+
"encoder.layer.9.attention.self.key.bias": "pytorch_model-00002-of-00003.bin",
|
193 |
+
"encoder.layer.9.attention.self.key.weight": "pytorch_model-00002-of-00003.bin",
|
194 |
+
"encoder.layer.9.attention.self.query.bias": "pytorch_model-00002-of-00003.bin",
|
195 |
+
"encoder.layer.9.attention.self.query.weight": "pytorch_model-00002-of-00003.bin",
|
196 |
+
"encoder.layer.9.attention.self.value.bias": "pytorch_model-00002-of-00003.bin",
|
197 |
+
"encoder.layer.9.attention.self.value.weight": "pytorch_model-00002-of-00003.bin",
|
198 |
+
"encoder.layer.9.intermediate.dense.bias": "pytorch_model-00002-of-00003.bin",
|
199 |
+
"encoder.layer.9.intermediate.dense.weight": "pytorch_model-00002-of-00003.bin",
|
200 |
+
"encoder.layer.9.output.LayerNorm.bias": "pytorch_model-00002-of-00003.bin",
|
201 |
+
"encoder.layer.9.output.LayerNorm.weight": "pytorch_model-00002-of-00003.bin",
|
202 |
+
"encoder.layer.9.output.dense.bias": "pytorch_model-00002-of-00003.bin",
|
203 |
+
"encoder.layer.9.output.dense.weight": "pytorch_model-00002-of-00003.bin",
|
204 |
+
"pooler.dense.bias": "pytorch_model-00003-of-00003.bin",
|
205 |
+
"pooler.dense.weight": "pytorch_model-00003-of-00003.bin"
|
206 |
+
}
|
207 |
+
}
|