Hugging Face's logo

facebook
/
esm2_t36_3B_UR50D

Fill-Mask Transformers PyTorch TensorFlow esm Inference Endpoints
Model card Files Community
1
Rocketknight1 HF staff commited on
Commit
b28eb06
•
1 Parent(s): ef01d45

Upload EsmForMaskedLM

Browse files
Files changed (4) hide show
  1. config.json +26 -0
  2. pytorch_model-00001-of-00002.bin +3 -0
  3. pytorch_model-00002-of-00002.bin +3 -0
  4. pytorch_model.bin.index.json +631 -0
config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "EsmForMaskedLM"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.0,
6
+ "classifier_dropout": null,
7
+ "emb_layer_norm_before": false,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.0,
10
+ "hidden_size": 2560,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 10240,
13
+ "layer_norm_eps": 1e-05,
14
+ "mask_token_id": 32,
15
+ "max_position_embeddings": 1026,
16
+ "model_type": "esm",
17
+ "num_attention_heads": 40,
18
+ "num_hidden_layers": 36,
19
+ "pad_token_id": 1,
20
+ "position_embedding_type": "rotary",
21
+ "token_dropout": true,
22
+ "torch_dtype": "float32",
23
+ "transformers_version": "4.23.0.dev0",
24
+ "use_cache": true,
25
+ "vocab_size": 33
26
+ }
pytorch_model-00001-of-00002.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b4581a7ec4c133928fd007c5f7feb726802d8fd8a72f510aa198cdaa962427c
3
+ size 9976747056
pytorch_model-00002-of-00002.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f0c1c63497f348ad516f7a5e7615a3b36aef0c588ea870c9177e21ca6286cd96
3
+ size 1390343553
pytorch_model.bin.index.json ADDED
@@ -0,0 +1,631 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 11366873880
4
+ },
5
+ "weight_map": {
6
+ "esm.embeddings.position_embeddings.weight": "pytorch_model-00001-of-00002.bin",
7
+ "esm.embeddings.position_ids": "pytorch_model-00001-of-00002.bin",
8
+ "esm.embeddings.word_embeddings.weight": "pytorch_model-00001-of-00002.bin",
9
+ "esm.encoder.emb_layer_norm_after.bias": "pytorch_model-00002-of-00002.bin",
10
+ "esm.encoder.emb_layer_norm_after.weight": "pytorch_model-00002-of-00002.bin",
11
+ "esm.encoder.layer.0.LayerNorm.bias": "pytorch_model-00001-of-00002.bin",
12
+ "esm.encoder.layer.0.LayerNorm.weight": "pytorch_model-00001-of-00002.bin",
13
+ "esm.encoder.layer.0.attention.LayerNorm.bias": "pytorch_model-00001-of-00002.bin",
14
+ "esm.encoder.layer.0.attention.LayerNorm.weight": "pytorch_model-00001-of-00002.bin",
15
+ "esm.encoder.layer.0.attention.output.dense.bias": "pytorch_model-00001-of-00002.bin",
16
+ "esm.encoder.layer.0.attention.output.dense.weight": "pytorch_model-00001-of-00002.bin",
17
+ "esm.encoder.layer.0.attention.self.key.bias": "pytorch_model-00001-of-00002.bin",
18
+ "esm.encoder.layer.0.attention.self.key.weight": "pytorch_model-00001-of-00002.bin",
19
+ "esm.encoder.layer.0.attention.self.query.bias": "pytorch_model-00001-of-00002.bin",
20
+ "esm.encoder.layer.0.attention.self.query.weight": "pytorch_model-00001-of-00002.bin",
21
+ "esm.encoder.layer.0.attention.self.rotary_embeddings.inv_freq": "pytorch_model-00001-of-00002.bin",
22
+ "esm.encoder.layer.0.attention.self.value.bias": "pytorch_model-00001-of-00002.bin",
23
+ "esm.encoder.layer.0.attention.self.value.weight": "pytorch_model-00001-of-00002.bin",
24
+ "esm.encoder.layer.0.intermediate.dense.bias": "pytorch_model-00001-of-00002.bin",
25
+ "esm.encoder.layer.0.intermediate.dense.weight": "pytorch_model-00001-of-00002.bin",
26
+ "esm.encoder.layer.0.output.dense.bias": "pytorch_model-00001-of-00002.bin",
27
+ "esm.encoder.layer.0.output.dense.weight": "pytorch_model-00001-of-00002.bin",
28
+ "esm.encoder.layer.1.LayerNorm.bias": "pytorch_model-00001-of-00002.bin",
29
+ "esm.encoder.layer.1.LayerNorm.weight": "pytorch_model-00001-of-00002.bin",
30
+ "esm.encoder.layer.1.attention.LayerNorm.bias": "pytorch_model-00001-of-00002.bin",
31
+ "esm.encoder.layer.1.attention.LayerNorm.weight": "pytorch_model-00001-of-00002.bin",
32
+ "esm.encoder.layer.1.attention.output.dense.bias": "pytorch_model-00001-of-00002.bin",
33
+ "esm.encoder.layer.1.attention.output.dense.weight": "pytorch_model-00001-of-00002.bin",
34
+ "esm.encoder.layer.1.attention.self.key.bias": "pytorch_model-00001-of-00002.bin",
35
+ "esm.encoder.layer.1.attention.self.key.weight": "pytorch_model-00001-of-00002.bin",
36
+ "esm.encoder.layer.1.attention.self.query.bias": "pytorch_model-00001-of-00002.bin",
37
+ "esm.encoder.layer.1.attention.self.query.weight": "pytorch_model-00001-of-00002.bin",
38
+ "esm.encoder.layer.1.attention.self.rotary_embeddings.inv_freq": "pytorch_model-00001-of-00002.bin",
39
+ "esm.encoder.layer.1.attention.self.value.bias": "pytorch_model-00001-of-00002.bin",
40
+ "esm.encoder.layer.1.attention.self.value.weight": "pytorch_model-00001-of-00002.bin",
41
+ "esm.encoder.layer.1.intermediate.dense.bias": "pytorch_model-00001-of-00002.bin",
42
+ "esm.encoder.layer.1.intermediate.dense.weight": "pytorch_model-00001-of-00002.bin",
43
+ "esm.encoder.layer.1.output.dense.bias": "pytorch_model-00001-of-00002.bin",
44
+ "esm.encoder.layer.1.output.dense.weight": "pytorch_model-00001-of-00002.bin",
45
+ "esm.encoder.layer.10.LayerNorm.bias": "pytorch_model-00001-of-00002.bin",
46
+ "esm.encoder.layer.10.LayerNorm.weight": "pytorch_model-00001-of-00002.bin",
47
+ "esm.encoder.layer.10.attention.LayerNorm.bias": "pytorch_model-00001-of-00002.bin",
48
+ "esm.encoder.layer.10.attention.LayerNorm.weight": "pytorch_model-00001-of-00002.bin",
49
+ "esm.encoder.layer.10.attention.output.dense.bias": "pytorch_model-00001-of-00002.bin",
50
+ "esm.encoder.layer.10.attention.output.dense.weight": "pytorch_model-00001-of-00002.bin",
51
+ "esm.encoder.layer.10.attention.self.key.bias": "pytorch_model-00001-of-00002.bin",
52
+ "esm.encoder.layer.10.attention.self.key.weight": "pytorch_model-00001-of-00002.bin",
53
+ "esm.encoder.layer.10.attention.self.query.bias": "pytorch_model-00001-of-00002.bin",
54
+ "esm.encoder.layer.10.attention.self.query.weight": "pytorch_model-00001-of-00002.bin",
55
+ "esm.encoder.layer.10.attention.self.rotary_embeddings.inv_freq": "pytorch_model-00001-of-00002.bin",
56
+ "esm.encoder.layer.10.attention.self.value.bias": "pytorch_model-00001-of-00002.bin",
57
+ "esm.encoder.layer.10.attention.self.value.weight": "pytorch_model-00001-of-00002.bin",
58
+ "esm.encoder.layer.10.intermediate.dense.bias": "pytorch_model-00001-of-00002.bin",
59
+ "esm.encoder.layer.10.intermediate.dense.weight": "pytorch_model-00001-of-00002.bin",
60
+ "esm.encoder.layer.10.output.dense.bias": "pytorch_model-00001-of-00002.bin",
61
+ "esm.encoder.layer.10.output.dense.weight": "pytorch_model-00001-of-00002.bin",
62
+ "esm.encoder.layer.11.LayerNorm.bias": "pytorch_model-00001-of-00002.bin",
63
+ "esm.encoder.layer.11.LayerNorm.weight": "pytorch_model-00001-of-00002.bin",
64
+ "esm.encoder.layer.11.attention.LayerNorm.bias": "pytorch_model-00001-of-00002.bin",
65
+ "esm.encoder.layer.11.attention.LayerNorm.weight": "pytorch_model-00001-of-00002.bin",
66
+ "esm.encoder.layer.11.attention.output.dense.bias": "pytorch_model-00001-of-00002.bin",
67
+ "esm.encoder.layer.11.attention.output.dense.weight": "pytorch_model-00001-of-00002.bin",
68
+ "esm.encoder.layer.11.attention.self.key.bias": "pytorch_model-00001-of-00002.bin",
69
+ "esm.encoder.layer.11.attention.self.key.weight": "pytorch_model-00001-of-00002.bin",
70
+ "esm.encoder.layer.11.attention.self.query.bias": "pytorch_model-00001-of-00002.bin",
71
+ "esm.encoder.layer.11.attention.self.query.weight": "pytorch_model-00001-of-00002.bin",
72
+ "esm.encoder.layer.11.attention.self.rotary_embeddings.inv_freq": "pytorch_model-00001-of-00002.bin",
73
+ "esm.encoder.layer.11.attention.self.value.bias": "pytorch_model-00001-of-00002.bin",
74
+ "esm.encoder.layer.11.attention.self.value.weight": "pytorch_model-00001-of-00002.bin",
75
+ "esm.encoder.layer.11.intermediate.dense.bias": "pytorch_model-00001-of-00002.bin",
76
+ "esm.encoder.layer.11.intermediate.dense.weight": "pytorch_model-00001-of-00002.bin",
77
+ "esm.encoder.layer.11.output.dense.bias": "pytorch_model-00001-of-00002.bin",
78
+ "esm.encoder.layer.11.output.dense.weight": "pytorch_model-00001-of-00002.bin",
79
+ "esm.encoder.layer.12.LayerNorm.bias": "pytorch_model-00001-of-00002.bin",
80
+ "esm.encoder.layer.12.LayerNorm.weight": "pytorch_model-00001-of-00002.bin",
81
+ "esm.encoder.layer.12.attention.LayerNorm.bias": "pytorch_model-00001-of-00002.bin",
82
+ "esm.encoder.layer.12.attention.LayerNorm.weight": "pytorch_model-00001-of-00002.bin",
83
+ "esm.encoder.layer.12.attention.output.dense.bias": "pytorch_model-00001-of-00002.bin",
84
+ "esm.encoder.layer.12.attention.output.dense.weight": "pytorch_model-00001-of-00002.bin",
85
+ "esm.encoder.layer.12.attention.self.key.bias": "pytorch_model-00001-of-00002.bin",
86
+ "esm.encoder.layer.12.attention.self.key.weight": "pytorch_model-00001-of-00002.bin",
87
+ "esm.encoder.layer.12.attention.self.query.bias": "pytorch_model-00001-of-00002.bin",
88
+ "esm.encoder.layer.12.attention.self.query.weight": "pytorch_model-00001-of-00002.bin",
89
+ "esm.encoder.layer.12.attention.self.rotary_embeddings.inv_freq": "pytorch_model-00001-of-00002.bin",
90
+ "esm.encoder.layer.12.attention.self.value.bias": "pytorch_model-00001-of-00002.bin",
91
+ "esm.encoder.layer.12.attention.self.value.weight": "pytorch_model-00001-of-00002.bin",
92
+ "esm.encoder.layer.12.intermediate.dense.bias": "pytorch_model-00001-of-00002.bin",
93
+ "esm.encoder.layer.12.intermediate.dense.weight": "pytorch_model-00001-of-00002.bin",
94
+ "esm.encoder.layer.12.output.dense.bias": "pytorch_model-00001-of-00002.bin",
95
+ "esm.encoder.layer.12.output.dense.weight": "pytorch_model-00001-of-00002.bin",
96
+ "esm.encoder.layer.13.LayerNorm.bias": "pytorch_model-00001-of-00002.bin",
97
+ "esm.encoder.layer.13.LayerNorm.weight": "pytorch_model-00001-of-00002.bin",
98
+ "esm.encoder.layer.13.attention.LayerNorm.bias": "pytorch_model-00001-of-00002.bin",
99
+ "esm.encoder.layer.13.attention.LayerNorm.weight": "pytorch_model-00001-of-00002.bin",
100
+ "esm.encoder.layer.13.attention.output.dense.bias": "pytorch_model-00001-of-00002.bin",
101
+ "esm.encoder.layer.13.attention.output.dense.weight": "pytorch_model-00001-of-00002.bin",
102
+ "esm.encoder.layer.13.attention.self.key.bias": "pytorch_model-00001-of-00002.bin",
103
+ "esm.encoder.layer.13.attention.self.key.weight": "pytorch_model-00001-of-00002.bin",
104
+ "esm.encoder.layer.13.attention.self.query.bias": "pytorch_model-00001-of-00002.bin",
105
+ "esm.encoder.layer.13.attention.self.query.weight": "pytorch_model-00001-of-00002.bin",
106
+ "esm.encoder.layer.13.attention.self.rotary_embeddings.inv_freq": "pytorch_model-00001-of-00002.bin",
107
+ "esm.encoder.layer.13.attention.self.value.bias": "pytorch_model-00001-of-00002.bin",
108
+ "esm.encoder.layer.13.attention.self.value.weight": "pytorch_model-00001-of-00002.bin",
109
+ "esm.encoder.layer.13.intermediate.dense.bias": "pytorch_model-00001-of-00002.bin",
110
+ "esm.encoder.layer.13.intermediate.dense.weight": "pytorch_model-00001-of-00002.bin",
111
+ "esm.encoder.layer.13.output.dense.bias": "pytorch_model-00001-of-00002.bin",
112
+ "esm.encoder.layer.13.output.dense.weight": "pytorch_model-00001-of-00002.bin",
113
+ "esm.encoder.layer.14.LayerNorm.bias": "pytorch_model-00001-of-00002.bin",
114
+ "esm.encoder.layer.14.LayerNorm.weight": "pytorch_model-00001-of-00002.bin",
115
+ "esm.encoder.layer.14.attention.LayerNorm.bias": "pytorch_model-00001-of-00002.bin",
116
+ "esm.encoder.layer.14.attention.LayerNorm.weight": "pytorch_model-00001-of-00002.bin",
117
+ "esm.encoder.layer.14.attention.output.dense.bias": "pytorch_model-00001-of-00002.bin",
118
+ "esm.encoder.layer.14.attention.output.dense.weight": "pytorch_model-00001-of-00002.bin",
119
+ "esm.encoder.layer.14.attention.self.key.bias": "pytorch_model-00001-of-00002.bin",
120
+ "esm.encoder.layer.14.attention.self.key.weight": "pytorch_model-00001-of-00002.bin",
121
+ "esm.encoder.layer.14.attention.self.query.bias": "pytorch_model-00001-of-00002.bin",
122
+ "esm.encoder.layer.14.attention.self.query.weight": "pytorch_model-00001-of-00002.bin",
123
+ "esm.encoder.layer.14.attention.self.rotary_embeddings.inv_freq": "pytorch_model-00001-of-00002.bin",
124
+ "esm.encoder.layer.14.attention.self.value.bias": "pytorch_model-00001-of-00002.bin",
125
+ "esm.encoder.layer.14.attention.self.value.weight": "pytorch_model-00001-of-00002.bin",
126
+ "esm.encoder.layer.14.intermediate.dense.bias": "pytorch_model-00001-of-00002.bin",
127
+ "esm.encoder.layer.14.intermediate.dense.weight": "pytorch_model-00001-of-00002.bin",
128
+ "esm.encoder.layer.14.output.dense.bias": "pytorch_model-00001-of-00002.bin",
129
+ "esm.encoder.layer.14.output.dense.weight": "pytorch_model-00001-of-00002.bin",
130
+ "esm.encoder.layer.15.LayerNorm.bias": "pytorch_model-00001-of-00002.bin",
131
+ "esm.encoder.layer.15.LayerNorm.weight": "pytorch_model-00001-of-00002.bin",
132
+ "esm.encoder.layer.15.attention.LayerNorm.bias": "pytorch_model-00001-of-00002.bin",
133
+ "esm.encoder.layer.15.attention.LayerNorm.weight": "pytorch_model-00001-of-00002.bin",
134
+ "esm.encoder.layer.15.attention.output.dense.bias": "pytorch_model-00001-of-00002.bin",
135
+ "esm.encoder.layer.15.attention.output.dense.weight": "pytorch_model-00001-of-00002.bin",
136
+ "esm.encoder.layer.15.attention.self.key.bias": "pytorch_model-00001-of-00002.bin",
137
+ "esm.encoder.layer.15.attention.self.key.weight": "pytorch_model-00001-of-00002.bin",
138
+ "esm.encoder.layer.15.attention.self.query.bias": "pytorch_model-00001-of-00002.bin",
139
+ "esm.encoder.layer.15.attention.self.query.weight": "pytorch_model-00001-of-00002.bin",
140
+ "esm.encoder.layer.15.attention.self.rotary_embeddings.inv_freq": "pytorch_model-00001-of-00002.bin",
141
+ "esm.encoder.layer.15.attention.self.value.bias": "pytorch_model-00001-of-00002.bin",
142
+ "esm.encoder.layer.15.attention.self.value.weight": "pytorch_model-00001-of-00002.bin",
143
+ "esm.encoder.layer.15.intermediate.dense.bias": "pytorch_model-00001-of-00002.bin",
144
+ "esm.encoder.layer.15.intermediate.dense.weight": "pytorch_model-00001-of-00002.bin",
145
+ "esm.encoder.layer.15.output.dense.bias": "pytorch_model-00001-of-00002.bin",
146
+ "esm.encoder.layer.15.output.dense.weight": "pytorch_model-00001-of-00002.bin",
147
+ "esm.encoder.layer.16.LayerNorm.bias": "pytorch_model-00001-of-00002.bin",
148
+ "esm.encoder.layer.16.LayerNorm.weight": "pytorch_model-00001-of-00002.bin",
149
+ "esm.encoder.layer.16.attention.LayerNorm.bias": "pytorch_model-00001-of-00002.bin",
150
+ "esm.encoder.layer.16.attention.LayerNorm.weight": "pytorch_model-00001-of-00002.bin",
151
+ "esm.encoder.layer.16.attention.output.dense.bias": "pytorch_model-00001-of-00002.bin",
152
+ "esm.encoder.layer.16.attention.output.dense.weight": "pytorch_model-00001-of-00002.bin",
153
+ "esm.encoder.layer.16.attention.self.key.bias": "pytorch_model-00001-of-00002.bin",
154
+ "esm.encoder.layer.16.attention.self.key.weight": "pytorch_model-00001-of-00002.bin",
155
+ "esm.encoder.layer.16.attention.self.query.bias": "pytorch_model-00001-of-00002.bin",
156
+ "esm.encoder.layer.16.attention.self.query.weight": "pytorch_model-00001-of-00002.bin",
157
+ "esm.encoder.layer.16.attention.self.rotary_embeddings.inv_freq": "pytorch_model-00001-of-00002.bin",
158
+ "esm.encoder.layer.16.attention.self.value.bias": "pytorch_model-00001-of-00002.bin",
159
+ "esm.encoder.layer.16.attention.self.value.weight": "pytorch_model-00001-of-00002.bin",
160
+ "esm.encoder.layer.16.intermediate.dense.bias": "pytorch_model-00001-of-00002.bin",
161
+ "esm.encoder.layer.16.intermediate.dense.weight": "pytorch_model-00001-of-00002.bin",
162
+ "esm.encoder.layer.16.output.dense.bias": "pytorch_model-00001-of-00002.bin",
163
+ "esm.encoder.layer.16.output.dense.weight": "pytorch_model-00001-of-00002.bin",
164
+ "esm.encoder.layer.17.LayerNorm.bias": "pytorch_model-00001-of-00002.bin",
165
+ "esm.encoder.layer.17.LayerNorm.weight": "pytorch_model-00001-of-00002.bin",
166
+ "esm.encoder.layer.17.attention.LayerNorm.bias": "pytorch_model-00001-of-00002.bin",
167
+ "esm.encoder.layer.17.attention.LayerNorm.weight": "pytorch_model-00001-of-00002.bin",
168
+ "esm.encoder.layer.17.attention.output.dense.bias": "pytorch_model-00001-of-00002.bin",
169
+ "esm.encoder.layer.17.attention.output.dense.weight": "pytorch_model-00001-of-00002.bin",
170
+ "esm.encoder.layer.17.attention.self.key.bias": "pytorch_model-00001-of-00002.bin",
171
+ "esm.encoder.layer.17.attention.self.key.weight": "pytorch_model-00001-of-00002.bin",
172
+ "esm.encoder.layer.17.attention.self.query.bias": "pytorch_model-00001-of-00002.bin",
173
+ "esm.encoder.layer.17.attention.self.query.weight": "pytorch_model-00001-of-00002.bin",
174
+ "esm.encoder.layer.17.attention.self.rotary_embeddings.inv_freq": "pytorch_model-00001-of-00002.bin",
175
+ "esm.encoder.layer.17.attention.self.value.bias": "pytorch_model-00001-of-00002.bin",
176
+ "esm.encoder.layer.17.attention.self.value.weight": "pytorch_model-00001-of-00002.bin",
177
+ "esm.encoder.layer.17.intermediate.dense.bias": "pytorch_model-00001-of-00002.bin",
178
+ "esm.encoder.layer.17.intermediate.dense.weight": "pytorch_model-00001-of-00002.bin",
179
+ "esm.encoder.layer.17.output.dense.bias": "pytorch_model-00001-of-00002.bin",
180
+ "esm.encoder.layer.17.output.dense.weight": "pytorch_model-00001-of-00002.bin",
181
+ "esm.encoder.layer.18.LayerNorm.bias": "pytorch_model-00001-of-00002.bin",
182
+ "esm.encoder.layer.18.LayerNorm.weight": "pytorch_model-00001-of-00002.bin",
183
+ "esm.encoder.layer.18.attention.LayerNorm.bias": "pytorch_model-00001-of-00002.bin",
184
+ "esm.encoder.layer.18.attention.LayerNorm.weight": "pytorch_model-00001-of-00002.bin",
185
+ "esm.encoder.layer.18.attention.output.dense.bias": "pytorch_model-00001-of-00002.bin",
186
+ "esm.encoder.layer.18.attention.output.dense.weight": "pytorch_model-00001-of-00002.bin",
187
+ "esm.encoder.layer.18.attention.self.key.bias": "pytorch_model-00001-of-00002.bin",
188
+ "esm.encoder.layer.18.attention.self.key.weight": "pytorch_model-00001-of-00002.bin",
189
+ "esm.encoder.layer.18.attention.self.query.bias": "pytorch_model-00001-of-00002.bin",
190
+ "esm.encoder.layer.18.attention.self.query.weight": "pytorch_model-00001-of-00002.bin",
191
+ "esm.encoder.layer.18.attention.self.rotary_embeddings.inv_freq": "pytorch_model-00001-of-00002.bin",
192
+ "esm.encoder.layer.18.attention.self.value.bias": "pytorch_model-00001-of-00002.bin",
193
+ "esm.encoder.layer.18.attention.self.value.weight": "pytorch_model-00001-of-00002.bin",
194
+ "esm.encoder.layer.18.intermediate.dense.bias": "pytorch_model-00001-of-00002.bin",
195
+ "esm.encoder.layer.18.intermediate.dense.weight": "pytorch_model-00001-of-00002.bin",
196
+ "esm.encoder.layer.18.output.dense.bias": "pytorch_model-00001-of-00002.bin",
197
+ "esm.encoder.layer.18.output.dense.weight": "pytorch_model-00001-of-00002.bin",
198
+ "esm.encoder.layer.19.LayerNorm.bias": "pytorch_model-00001-of-00002.bin",
199
+ "esm.encoder.layer.19.LayerNorm.weight": "pytorch_model-00001-of-00002.bin",
200
+ "esm.encoder.layer.19.attention.LayerNorm.bias": "pytorch_model-00001-of-00002.bin",
201
+ "esm.encoder.layer.19.attention.LayerNorm.weight": "pytorch_model-00001-of-00002.bin",
202
+ "esm.encoder.layer.19.attention.output.dense.bias": "pytorch_model-00001-of-00002.bin",
203
+ "esm.encoder.layer.19.attention.output.dense.weight": "pytorch_model-00001-of-00002.bin",
204
+ "esm.encoder.layer.19.attention.self.key.bias": "pytorch_model-00001-of-00002.bin",
205
+ "esm.encoder.layer.19.attention.self.key.weight": "pytorch_model-00001-of-00002.bin",
206
+ "esm.encoder.layer.19.attention.self.query.bias": "pytorch_model-00001-of-00002.bin",
207
+ "esm.encoder.layer.19.attention.self.query.weight": "pytorch_model-00001-of-00002.bin",
208
+ "esm.encoder.layer.19.attention.self.rotary_embeddings.inv_freq": "pytorch_model-00001-of-00002.bin",
209
+ "esm.encoder.layer.19.attention.self.value.bias": "pytorch_model-00001-of-00002.bin",
210
+ "esm.encoder.layer.19.attention.self.value.weight": "pytorch_model-00001-of-00002.bin",
211
+ "esm.encoder.layer.19.intermediate.dense.bias": "pytorch_model-00001-of-00002.bin",
212
+ "esm.encoder.layer.19.intermediate.dense.weight": "pytorch_model-00001-of-00002.bin",
213
+ "esm.encoder.layer.19.output.dense.bias": "pytorch_model-00001-of-00002.bin",
214
+ "esm.encoder.layer.19.output.dense.weight": "pytorch_model-00001-of-00002.bin",
215
+ "esm.encoder.layer.2.LayerNorm.bias": "pytorch_model-00001-of-00002.bin",
216
+ "esm.encoder.layer.2.LayerNorm.weight": "pytorch_model-00001-of-00002.bin",
217
+ "esm.encoder.layer.2.attention.LayerNorm.bias": "pytorch_model-00001-of-00002.bin",
218
+ "esm.encoder.layer.2.attention.LayerNorm.weight": "pytorch_model-00001-of-00002.bin",
219
+ "esm.encoder.layer.2.attention.output.dense.bias": "pytorch_model-00001-of-00002.bin",
220
+ "esm.encoder.layer.2.attention.output.dense.weight": "pytorch_model-00001-of-00002.bin",
221
+ "esm.encoder.layer.2.attention.self.key.bias": "pytorch_model-00001-of-00002.bin",
222
+ "esm.encoder.layer.2.attention.self.key.weight": "pytorch_model-00001-of-00002.bin",
223
+ "esm.encoder.layer.2.attention.self.query.bias": "pytorch_model-00001-of-00002.bin",
224
+ "esm.encoder.layer.2.attention.self.query.weight": "pytorch_model-00001-of-00002.bin",
225
+ "esm.encoder.layer.2.attention.self.rotary_embeddings.inv_freq": "pytorch_model-00001-of-00002.bin",
226
+ "esm.encoder.layer.2.attention.self.value.bias": "pytorch_model-00001-of-00002.bin",
227
+ "esm.encoder.layer.2.attention.self.value.weight": "pytorch_model-00001-of-00002.bin",
228
+ "esm.encoder.layer.2.intermediate.dense.bias": "pytorch_model-00001-of-00002.bin",
229
+ "esm.encoder.layer.2.intermediate.dense.weight": "pytorch_model-00001-of-00002.bin",
230
+ "esm.encoder.layer.2.output.dense.bias": "pytorch_model-00001-of-00002.bin",
231
+ "esm.encoder.layer.2.output.dense.weight": "pytorch_model-00001-of-00002.bin",
232
+ "esm.encoder.layer.20.LayerNorm.bias": "pytorch_model-00001-of-00002.bin",
233
+ "esm.encoder.layer.20.LayerNorm.weight": "pytorch_model-00001-of-00002.bin",
234
+ "esm.encoder.layer.20.attention.LayerNorm.bias": "pytorch_model-00001-of-00002.bin",
235
+ "esm.encoder.layer.20.attention.LayerNorm.weight": "pytorch_model-00001-of-00002.bin",
236
+ "esm.encoder.layer.20.attention.output.dense.bias": "pytorch_model-00001-of-00002.bin",
237
+ "esm.encoder.layer.20.attention.output.dense.weight": "pytorch_model-00001-of-00002.bin",
238
+ "esm.encoder.layer.20.attention.self.key.bias": "pytorch_model-00001-of-00002.bin",
239
+ "esm.encoder.layer.20.attention.self.key.weight": "pytorch_model-00001-of-00002.bin",
240
+ "esm.encoder.layer.20.attention.self.query.bias": "pytorch_model-00001-of-00002.bin",
241
+ "esm.encoder.layer.20.attention.self.query.weight": "pytorch_model-00001-of-00002.bin",
242
+ "esm.encoder.layer.20.attention.self.rotary_embeddings.inv_freq": "pytorch_model-00001-of-00002.bin",
243
+ "esm.encoder.layer.20.attention.self.value.bias": "pytorch_model-00001-of-00002.bin",
244
+ "esm.encoder.layer.20.attention.self.value.weight": "pytorch_model-00001-of-00002.bin",
245
+ "esm.encoder.layer.20.intermediate.dense.bias": "pytorch_model-00001-of-00002.bin",
246
+ "esm.encoder.layer.20.intermediate.dense.weight": "pytorch_model-00001-of-00002.bin",
247
+ "esm.encoder.layer.20.output.dense.bias": "pytorch_model-00001-of-00002.bin",
248
+ "esm.encoder.layer.20.output.dense.weight": "pytorch_model-00001-of-00002.bin",
249
+ "esm.encoder.layer.21.LayerNorm.bias": "pytorch_model-00001-of-00002.bin",
250
+ "esm.encoder.layer.21.LayerNorm.weight": "pytorch_model-00001-of-00002.bin",
251
+ "esm.encoder.layer.21.attention.LayerNorm.bias": "pytorch_model-00001-of-00002.bin",
252
+ "esm.encoder.layer.21.attention.LayerNorm.weight": "pytorch_model-00001-of-00002.bin",
253
+ "esm.encoder.layer.21.attention.output.dense.bias": "pytorch_model-00001-of-00002.bin",
254
+ "esm.encoder.layer.21.attention.output.dense.weight": "pytorch_model-00001-of-00002.bin",
255
+ "esm.encoder.layer.21.attention.self.key.bias": "pytorch_model-00001-of-00002.bin",
256
+ "esm.encoder.layer.21.attention.self.key.weight": "pytorch_model-00001-of-00002.bin",
257
+ "esm.encoder.layer.21.attention.self.query.bias": "pytorch_model-00001-of-00002.bin",
258
+ "esm.encoder.layer.21.attention.self.query.weight": "pytorch_model-00001-of-00002.bin",
259
+ "esm.encoder.layer.21.attention.self.rotary_embeddings.inv_freq": "pytorch_model-00001-of-00002.bin",
260
+ "esm.encoder.layer.21.attention.self.value.bias": "pytorch_model-00001-of-00002.bin",
261
+ "esm.encoder.layer.21.attention.self.value.weight": "pytorch_model-00001-of-00002.bin",
262
+ "esm.encoder.layer.21.intermediate.dense.bias": "pytorch_model-00001-of-00002.bin",
263
+ "esm.encoder.layer.21.intermediate.dense.weight": "pytorch_model-00001-of-00002.bin",
264
+ "esm.encoder.layer.21.output.dense.bias": "pytorch_model-00001-of-00002.bin",
265
+ "esm.encoder.layer.21.output.dense.weight": "pytorch_model-00001-of-00002.bin",
266
+ "esm.encoder.layer.22.LayerNorm.bias": "pytorch_model-00001-of-00002.bin",
267
+ "esm.encoder.layer.22.LayerNorm.weight": "pytorch_model-00001-of-00002.bin",
268
+ "esm.encoder.layer.22.attention.LayerNorm.bias": "pytorch_model-00001-of-00002.bin",
269
+ "esm.encoder.layer.22.attention.LayerNorm.weight": "pytorch_model-00001-of-00002.bin",
270
+ "esm.encoder.layer.22.attention.output.dense.bias": "pytorch_model-00001-of-00002.bin",
271
+ "esm.encoder.layer.22.attention.output.dense.weight": "pytorch_model-00001-of-00002.bin",
272
+ "esm.encoder.layer.22.attention.self.key.bias": "pytorch_model-00001-of-00002.bin",
273
+ "esm.encoder.layer.22.attention.self.key.weight": "pytorch_model-00001-of-00002.bin",
274
+ "esm.encoder.layer.22.attention.self.query.bias": "pytorch_model-00001-of-00002.bin",
275
+ "esm.encoder.layer.22.attention.self.query.weight": "pytorch_model-00001-of-00002.bin",
276
+ "esm.encoder.layer.22.attention.self.rotary_embeddings.inv_freq": "pytorch_model-00001-of-00002.bin",
277
+ "esm.encoder.layer.22.attention.self.value.bias": "pytorch_model-00001-of-00002.bin",
278
+ "esm.encoder.layer.22.attention.self.value.weight": "pytorch_model-00001-of-00002.bin",
279
+ "esm.encoder.layer.22.intermediate.dense.bias": "pytorch_model-00001-of-00002.bin",
280
+ "esm.encoder.layer.22.intermediate.dense.weight": "pytorch_model-00001-of-00002.bin",
281
+ "esm.encoder.layer.22.output.dense.bias": "pytorch_model-00001-of-00002.bin",
282
+ "esm.encoder.layer.22.output.dense.weight": "pytorch_model-00001-of-00002.bin",
283
+ "esm.encoder.layer.23.LayerNorm.bias": "pytorch_model-00001-of-00002.bin",
284
+ "esm.encoder.layer.23.LayerNorm.weight": "pytorch_model-00001-of-00002.bin",
285
+ "esm.encoder.layer.23.attention.LayerNorm.bias": "pytorch_model-00001-of-00002.bin",
286
+ "esm.encoder.layer.23.attention.LayerNorm.weight": "pytorch_model-00001-of-00002.bin",
287
+ "esm.encoder.layer.23.attention.output.dense.bias": "pytorch_model-00001-of-00002.bin",
288
+ "esm.encoder.layer.23.attention.output.dense.weight": "pytorch_model-00001-of-00002.bin",
289
+ "esm.encoder.layer.23.attention.self.key.bias": "pytorch_model-00001-of-00002.bin",
290
+ "esm.encoder.layer.23.attention.self.key.weight": "pytorch_model-00001-of-00002.bin",
291
+ "esm.encoder.layer.23.attention.self.query.bias": "pytorch_model-00001-of-00002.bin",
292
+ "esm.encoder.layer.23.attention.self.query.weight": "pytorch_model-00001-of-00002.bin",
293
+ "esm.encoder.layer.23.attention.self.rotary_embeddings.inv_freq": "pytorch_model-00001-of-00002.bin",
294
+ "esm.encoder.layer.23.attention.self.value.bias": "pytorch_model-00001-of-00002.bin",
295
+ "esm.encoder.layer.23.attention.self.value.weight": "pytorch_model-00001-of-00002.bin",
296
+ "esm.encoder.layer.23.intermediate.dense.bias": "pytorch_model-00001-of-00002.bin",
297
+ "esm.encoder.layer.23.intermediate.dense.weight": "pytorch_model-00001-of-00002.bin",
298
+ "esm.encoder.layer.23.output.dense.bias": "pytorch_model-00001-of-00002.bin",
299
+ "esm.encoder.layer.23.output.dense.weight": "pytorch_model-00001-of-00002.bin",
300
+ "esm.encoder.layer.24.LayerNorm.bias": "pytorch_model-00001-of-00002.bin",
301
+ "esm.encoder.layer.24.LayerNorm.weight": "pytorch_model-00001-of-00002.bin",
302
+ "esm.encoder.layer.24.attention.LayerNorm.bias": "pytorch_model-00001-of-00002.bin",
303
+ "esm.encoder.layer.24.attention.LayerNorm.weight": "pytorch_model-00001-of-00002.bin",
304
+ "esm.encoder.layer.24.attention.output.dense.bias": "pytorch_model-00001-of-00002.bin",
305
+ "esm.encoder.layer.24.attention.output.dense.weight": "pytorch_model-00001-of-00002.bin",
306
+ "esm.encoder.layer.24.attention.self.key.bias": "pytorch_model-00001-of-00002.bin",
307
+ "esm.encoder.layer.24.attention.self.key.weight": "pytorch_model-00001-of-00002.bin",
308
+ "esm.encoder.layer.24.attention.self.query.bias": "pytorch_model-00001-of-00002.bin",
309
+ "esm.encoder.layer.24.attention.self.query.weight": "pytorch_model-00001-of-00002.bin",
310
+ "esm.encoder.layer.24.attention.self.rotary_embeddings.inv_freq": "pytorch_model-00001-of-00002.bin",
311
+ "esm.encoder.layer.24.attention.self.value.bias": "pytorch_model-00001-of-00002.bin",
312
+ "esm.encoder.layer.24.attention.self.value.weight": "pytorch_model-00001-of-00002.bin",
313
+ "esm.encoder.layer.24.intermediate.dense.bias": "pytorch_model-00001-of-00002.bin",
314
+ "esm.encoder.layer.24.intermediate.dense.weight": "pytorch_model-00001-of-00002.bin",
315
+ "esm.encoder.layer.24.output.dense.bias": "pytorch_model-00001-of-00002.bin",
316
+ "esm.encoder.layer.24.output.dense.weight": "pytorch_model-00001-of-00002.bin",
317
+ "esm.encoder.layer.25.LayerNorm.bias": "pytorch_model-00001-of-00002.bin",
318
+ "esm.encoder.layer.25.LayerNorm.weight": "pytorch_model-00001-of-00002.bin",
319
+ "esm.encoder.layer.25.attention.LayerNorm.bias": "pytorch_model-00001-of-00002.bin",
320
+ "esm.encoder.layer.25.attention.LayerNorm.weight": "pytorch_model-00001-of-00002.bin",
321
+ "esm.encoder.layer.25.attention.output.dense.bias": "pytorch_model-00001-of-00002.bin",
322
+ "esm.encoder.layer.25.attention.output.dense.weight": "pytorch_model-00001-of-00002.bin",
323
+ "esm.encoder.layer.25.attention.self.key.bias": "pytorch_model-00001-of-00002.bin",
324
+ "esm.encoder.layer.25.attention.self.key.weight": "pytorch_model-00001-of-00002.bin",
325
+ "esm.encoder.layer.25.attention.self.query.bias": "pytorch_model-00001-of-00002.bin",
326
+ "esm.encoder.layer.25.attention.self.query.weight": "pytorch_model-00001-of-00002.bin",
327
+ "esm.encoder.layer.25.attention.self.rotary_embeddings.inv_freq": "pytorch_model-00001-of-00002.bin",
328
+ "esm.encoder.layer.25.attention.self.value.bias": "pytorch_model-00001-of-00002.bin",
329
+ "esm.encoder.layer.25.attention.self.value.weight": "pytorch_model-00001-of-00002.bin",
330
+ "esm.encoder.layer.25.intermediate.dense.bias": "pytorch_model-00001-of-00002.bin",
331
+ "esm.encoder.layer.25.intermediate.dense.weight": "pytorch_model-00001-of-00002.bin",
332
+ "esm.encoder.layer.25.output.dense.bias": "pytorch_model-00001-of-00002.bin",
333
+ "esm.encoder.layer.25.output.dense.weight": "pytorch_model-00001-of-00002.bin",
334
+ "esm.encoder.layer.26.LayerNorm.bias": "pytorch_model-00001-of-00002.bin",
335
+ "esm.encoder.layer.26.LayerNorm.weight": "pytorch_model-00001-of-00002.bin",
336
+ "esm.encoder.layer.26.attention.LayerNorm.bias": "pytorch_model-00001-of-00002.bin",
337
+ "esm.encoder.layer.26.attention.LayerNorm.weight": "pytorch_model-00001-of-00002.bin",
338
+ "esm.encoder.layer.26.attention.output.dense.bias": "pytorch_model-00001-of-00002.bin",
339
+ "esm.encoder.layer.26.attention.output.dense.weight": "pytorch_model-00001-of-00002.bin",
340
+ "esm.encoder.layer.26.attention.self.key.bias": "pytorch_model-00001-of-00002.bin",
341
+ "esm.encoder.layer.26.attention.self.key.weight": "pytorch_model-00001-of-00002.bin",
342
+ "esm.encoder.layer.26.attention.self.query.bias": "pytorch_model-00001-of-00002.bin",
343
+ "esm.encoder.layer.26.attention.self.query.weight": "pytorch_model-00001-of-00002.bin",
344
+ "esm.encoder.layer.26.attention.self.rotary_embeddings.inv_freq": "pytorch_model-00001-of-00002.bin",
345
+ "esm.encoder.layer.26.attention.self.value.bias": "pytorch_model-00001-of-00002.bin",
346
+ "esm.encoder.layer.26.attention.self.value.weight": "pytorch_model-00001-of-00002.bin",
347
+ "esm.encoder.layer.26.intermediate.dense.bias": "pytorch_model-00001-of-00002.bin",
348
+ "esm.encoder.layer.26.intermediate.dense.weight": "pytorch_model-00001-of-00002.bin",
349
+ "esm.encoder.layer.26.output.dense.bias": "pytorch_model-00001-of-00002.bin",
350
+ "esm.encoder.layer.26.output.dense.weight": "pytorch_model-00001-of-00002.bin",
351
+ "esm.encoder.layer.27.LayerNorm.bias": "pytorch_model-00001-of-00002.bin",
352
+ "esm.encoder.layer.27.LayerNorm.weight": "pytorch_model-00001-of-00002.bin",
353
+ "esm.encoder.layer.27.attention.LayerNorm.bias": "pytorch_model-00001-of-00002.bin",
354
+ "esm.encoder.layer.27.attention.LayerNorm.weight": "pytorch_model-00001-of-00002.bin",
355
+ "esm.encoder.layer.27.attention.output.dense.bias": "pytorch_model-00001-of-00002.bin",
356
+ "esm.encoder.layer.27.attention.output.dense.weight": "pytorch_model-00001-of-00002.bin",
357
+ "esm.encoder.layer.27.attention.self.key.bias": "pytorch_model-00001-of-00002.bin",
358
+ "esm.encoder.layer.27.attention.self.key.weight": "pytorch_model-00001-of-00002.bin",
359
+ "esm.encoder.layer.27.attention.self.query.bias": "pytorch_model-00001-of-00002.bin",
360
+ "esm.encoder.layer.27.attention.self.query.weight": "pytorch_model-00001-of-00002.bin",
361
+ "esm.encoder.layer.27.attention.self.rotary_embeddings.inv_freq": "pytorch_model-00001-of-00002.bin",
362
+ "esm.encoder.layer.27.attention.self.value.bias": "pytorch_model-00001-of-00002.bin",
363
+ "esm.encoder.layer.27.attention.self.value.weight": "pytorch_model-00001-of-00002.bin",
364
+ "esm.encoder.layer.27.intermediate.dense.bias": "pytorch_model-00001-of-00002.bin",
365
+ "esm.encoder.layer.27.intermediate.dense.weight": "pytorch_model-00001-of-00002.bin",
366
+ "esm.encoder.layer.27.output.dense.bias": "pytorch_model-00001-of-00002.bin",
367
+ "esm.encoder.layer.27.output.dense.weight": "pytorch_model-00001-of-00002.bin",
368
+ "esm.encoder.layer.28.LayerNorm.bias": "pytorch_model-00001-of-00002.bin",
369
+ "esm.encoder.layer.28.LayerNorm.weight": "pytorch_model-00001-of-00002.bin",
370
+ "esm.encoder.layer.28.attention.LayerNorm.bias": "pytorch_model-00001-of-00002.bin",
371
+ "esm.encoder.layer.28.attention.LayerNorm.weight": "pytorch_model-00001-of-00002.bin",
372
+ "esm.encoder.layer.28.attention.output.dense.bias": "pytorch_model-00001-of-00002.bin",
373
+ "esm.encoder.layer.28.attention.output.dense.weight": "pytorch_model-00001-of-00002.bin",
374
+ "esm.encoder.layer.28.attention.self.key.bias": "pytorch_model-00001-of-00002.bin",
375
+ "esm.encoder.layer.28.attention.self.key.weight": "pytorch_model-00001-of-00002.bin",
376
+ "esm.encoder.layer.28.attention.self.query.bias": "pytorch_model-00001-of-00002.bin",
377
+ "esm.encoder.layer.28.attention.self.query.weight": "pytorch_model-00001-of-00002.bin",
378
+ "esm.encoder.layer.28.attention.self.rotary_embeddings.inv_freq": "pytorch_model-00001-of-00002.bin",
379
+ "esm.encoder.layer.28.attention.self.value.bias": "pytorch_model-00001-of-00002.bin",
380
+ "esm.encoder.layer.28.attention.self.value.weight": "pytorch_model-00001-of-00002.bin",
381
+ "esm.encoder.layer.28.intermediate.dense.bias": "pytorch_model-00001-of-00002.bin",
382
+ "esm.encoder.layer.28.intermediate.dense.weight": "pytorch_model-00001-of-00002.bin",
383
+ "esm.encoder.layer.28.output.dense.bias": "pytorch_model-00001-of-00002.bin",
384
+ "esm.encoder.layer.28.output.dense.weight": "pytorch_model-00001-of-00002.bin",
385
+ "esm.encoder.layer.29.LayerNorm.bias": "pytorch_model-00001-of-00002.bin",
386
+ "esm.encoder.layer.29.LayerNorm.weight": "pytorch_model-00001-of-00002.bin",
387
+ "esm.encoder.layer.29.attention.LayerNorm.bias": "pytorch_model-00001-of-00002.bin",
388
+ "esm.encoder.layer.29.attention.LayerNorm.weight": "pytorch_model-00001-of-00002.bin",
389
+ "esm.encoder.layer.29.attention.output.dense.bias": "pytorch_model-00001-of-00002.bin",
390
+ "esm.encoder.layer.29.attention.output.dense.weight": "pytorch_model-00001-of-00002.bin",
391
+ "esm.encoder.layer.29.attention.self.key.bias": "pytorch_model-00001-of-00002.bin",
392
+ "esm.encoder.layer.29.attention.self.key.weight": "pytorch_model-00001-of-00002.bin",
393
+ "esm.encoder.layer.29.attention.self.query.bias": "pytorch_model-00001-of-00002.bin",
394
+ "esm.encoder.layer.29.attention.self.query.weight": "pytorch_model-00001-of-00002.bin",
395
+ "esm.encoder.layer.29.attention.self.rotary_embeddings.inv_freq": "pytorch_model-00001-of-00002.bin",
396
+ "esm.encoder.layer.29.attention.self.value.bias": "pytorch_model-00001-of-00002.bin",
397
+ "esm.encoder.layer.29.attention.self.value.weight": "pytorch_model-00001-of-00002.bin",
398
+ "esm.encoder.layer.29.intermediate.dense.bias": "pytorch_model-00001-of-00002.bin",
399
+ "esm.encoder.layer.29.intermediate.dense.weight": "pytorch_model-00001-of-00002.bin",
400
+ "esm.encoder.layer.29.output.dense.bias": "pytorch_model-00001-of-00002.bin",
401
+ "esm.encoder.layer.29.output.dense.weight": "pytorch_model-00001-of-00002.bin",
402
+ "esm.encoder.layer.3.LayerNorm.bias": "pytorch_model-00001-of-00002.bin",
403
+ "esm.encoder.layer.3.LayerNorm.weight": "pytorch_model-00001-of-00002.bin",
404
+ "esm.encoder.layer.3.attention.LayerNorm.bias": "pytorch_model-00001-of-00002.bin",
405
+ "esm.encoder.layer.3.attention.LayerNorm.weight": "pytorch_model-00001-of-00002.bin",
406
+ "esm.encoder.layer.3.attention.output.dense.bias": "pytorch_model-00001-of-00002.bin",
407
+ "esm.encoder.layer.3.attention.output.dense.weight": "pytorch_model-00001-of-00002.bin",
408
+ "esm.encoder.layer.3.attention.self.key.bias": "pytorch_model-00001-of-00002.bin",
409
+ "esm.encoder.layer.3.attention.self.key.weight": "pytorch_model-00001-of-00002.bin",
410
+ "esm.encoder.layer.3.attention.self.query.bias": "pytorch_model-00001-of-00002.bin",
411
+ "esm.encoder.layer.3.attention.self.query.weight": "pytorch_model-00001-of-00002.bin",
412
+ "esm.encoder.layer.3.attention.self.rotary_embeddings.inv_freq": "pytorch_model-00001-of-00002.bin",
413
+ "esm.encoder.layer.3.attention.self.value.bias": "pytorch_model-00001-of-00002.bin",
414
+ "esm.encoder.layer.3.attention.self.value.weight": "pytorch_model-00001-of-00002.bin",
415
+ "esm.encoder.layer.3.intermediate.dense.bias": "pytorch_model-00001-of-00002.bin",
416
+ "esm.encoder.layer.3.intermediate.dense.weight": "pytorch_model-00001-of-00002.bin",
417
+ "esm.encoder.layer.3.output.dense.bias": "pytorch_model-00001-of-00002.bin",
418
+ "esm.encoder.layer.3.output.dense.weight": "pytorch_model-00001-of-00002.bin",
419
+ "esm.encoder.layer.30.LayerNorm.bias": "pytorch_model-00001-of-00002.bin",
420
+ "esm.encoder.layer.30.LayerNorm.weight": "pytorch_model-00001-of-00002.bin",
421
+ "esm.encoder.layer.30.attention.LayerNorm.bias": "pytorch_model-00001-of-00002.bin",
422
+ "esm.encoder.layer.30.attention.LayerNorm.weight": "pytorch_model-00001-of-00002.bin",
423
+ "esm.encoder.layer.30.attention.output.dense.bias": "pytorch_model-00001-of-00002.bin",
424
+ "esm.encoder.layer.30.attention.output.dense.weight": "pytorch_model-00001-of-00002.bin",
425
+ "esm.encoder.layer.30.attention.self.key.bias": "pytorch_model-00001-of-00002.bin",
426
+ "esm.encoder.layer.30.attention.self.key.weight": "pytorch_model-00001-of-00002.bin",
427
+ "esm.encoder.layer.30.attention.self.query.bias": "pytorch_model-00001-of-00002.bin",
428
+ "esm.encoder.layer.30.attention.self.query.weight": "pytorch_model-00001-of-00002.bin",
429
+ "esm.encoder.layer.30.attention.self.rotary_embeddings.inv_freq": "pytorch_model-00001-of-00002.bin",
430
+ "esm.encoder.layer.30.attention.self.value.bias": "pytorch_model-00001-of-00002.bin",
431
+ "esm.encoder.layer.30.attention.self.value.weight": "pytorch_model-00001-of-00002.bin",
432
+ "esm.encoder.layer.30.intermediate.dense.bias": "pytorch_model-00001-of-00002.bin",
433
+ "esm.encoder.layer.30.intermediate.dense.weight": "pytorch_model-00001-of-00002.bin",
434
+ "esm.encoder.layer.30.output.dense.bias": "pytorch_model-00001-of-00002.bin",
435
+ "esm.encoder.layer.30.output.dense.weight": "pytorch_model-00001-of-00002.bin",
436
+ "esm.encoder.layer.31.LayerNorm.bias": "pytorch_model-00002-of-00002.bin",
437
+ "esm.encoder.layer.31.LayerNorm.weight": "pytorch_model-00002-of-00002.bin",
438
+ "esm.encoder.layer.31.attention.LayerNorm.bias": "pytorch_model-00001-of-00002.bin",
439
+ "esm.encoder.layer.31.attention.LayerNorm.weight": "pytorch_model-00001-of-00002.bin",
440
+ "esm.encoder.layer.31.attention.output.dense.bias": "pytorch_model-00001-of-00002.bin",
441
+ "esm.encoder.layer.31.attention.output.dense.weight": "pytorch_model-00001-of-00002.bin",
442
+ "esm.encoder.layer.31.attention.self.key.bias": "pytorch_model-00001-of-00002.bin",
443
+ "esm.encoder.layer.31.attention.self.key.weight": "pytorch_model-00001-of-00002.bin",
444
+ "esm.encoder.layer.31.attention.self.query.bias": "pytorch_model-00001-of-00002.bin",
445
+ "esm.encoder.layer.31.attention.self.query.weight": "pytorch_model-00001-of-00002.bin",
446
+ "esm.encoder.layer.31.attention.self.rotary_embeddings.inv_freq": "pytorch_model-00001-of-00002.bin",
447
+ "esm.encoder.layer.31.attention.self.value.bias": "pytorch_model-00001-of-00002.bin",
448
+ "esm.encoder.layer.31.attention.self.value.weight": "pytorch_model-00001-of-00002.bin",
449
+ "esm.encoder.layer.31.intermediate.dense.bias": "pytorch_model-00001-of-00002.bin",
450
+ "esm.encoder.layer.31.intermediate.dense.weight": "pytorch_model-00001-of-00002.bin",
451
+ "esm.encoder.layer.31.output.dense.bias": "pytorch_model-00002-of-00002.bin",
452
+ "esm.encoder.layer.31.output.dense.weight": "pytorch_model-00002-of-00002.bin",
453
+ "esm.encoder.layer.32.LayerNorm.bias": "pytorch_model-00002-of-00002.bin",
454
+ "esm.encoder.layer.32.LayerNorm.weight": "pytorch_model-00002-of-00002.bin",
455
+ "esm.encoder.layer.32.attention.LayerNorm.bias": "pytorch_model-00002-of-00002.bin",
456
+ "esm.encoder.layer.32.attention.LayerNorm.weight": "pytorch_model-00002-of-00002.bin",
457
+ "esm.encoder.layer.32.attention.output.dense.bias": "pytorch_model-00002-of-00002.bin",
458
+ "esm.encoder.layer.32.attention.output.dense.weight": "pytorch_model-00002-of-00002.bin",
459
+ "esm.encoder.layer.32.attention.self.key.bias": "pytorch_model-00002-of-00002.bin",
460
+ "esm.encoder.layer.32.attention.self.key.weight": "pytorch_model-00002-of-00002.bin",
461
+ "esm.encoder.layer.32.attention.self.query.bias": "pytorch_model-00002-of-00002.bin",
462
+ "esm.encoder.layer.32.attention.self.query.weight": "pytorch_model-00002-of-00002.bin",
463
+ "esm.encoder.layer.32.attention.self.rotary_embeddings.inv_freq": "pytorch_model-00002-of-00002.bin",
464
+ "esm.encoder.layer.32.attention.self.value.bias": "pytorch_model-00002-of-00002.bin",
465
+ "esm.encoder.layer.32.attention.self.value.weight": "pytorch_model-00002-of-00002.bin",
466
+ "esm.encoder.layer.32.intermediate.dense.bias": "pytorch_model-00002-of-00002.bin",
467
+ "esm.encoder.layer.32.intermediate.dense.weight": "pytorch_model-00002-of-00002.bin",
468
+ "esm.encoder.layer.32.output.dense.bias": "pytorch_model-00002-of-00002.bin",
469
+ "esm.encoder.layer.32.output.dense.weight": "pytorch_model-00002-of-00002.bin",
470
+ "esm.encoder.layer.33.LayerNorm.bias": "pytorch_model-00002-of-00002.bin",
471
+ "esm.encoder.layer.33.LayerNorm.weight": "pytorch_model-00002-of-00002.bin",
472
+ "esm.encoder.layer.33.attention.LayerNorm.bias": "pytorch_model-00002-of-00002.bin",
473
+ "esm.encoder.layer.33.attention.LayerNorm.weight": "pytorch_model-00002-of-00002.bin",
474
+ "esm.encoder.layer.33.attention.output.dense.bias": "pytorch_model-00002-of-00002.bin",
475
+ "esm.encoder.layer.33.attention.output.dense.weight": "pytorch_model-00002-of-00002.bin",
476
+ "esm.encoder.layer.33.attention.self.key.bias": "pytorch_model-00002-of-00002.bin",
477
+ "esm.encoder.layer.33.attention.self.key.weight": "pytorch_model-00002-of-00002.bin",
478
+ "esm.encoder.layer.33.attention.self.query.bias": "pytorch_model-00002-of-00002.bin",
479
+ "esm.encoder.layer.33.attention.self.query.weight": "pytorch_model-00002-of-00002.bin",
480
+ "esm.encoder.layer.33.attention.self.rotary_embeddings.inv_freq": "pytorch_model-00002-of-00002.bin",
481
+ "esm.encoder.layer.33.attention.self.value.bias": "pytorch_model-00002-of-00002.bin",
482
+ "esm.encoder.layer.33.attention.self.value.weight": "pytorch_model-00002-of-00002.bin",
483
+ "esm.encoder.layer.33.intermediate.dense.bias": "pytorch_model-00002-of-00002.bin",
484
+ "esm.encoder.layer.33.intermediate.dense.weight": "pytorch_model-00002-of-00002.bin",
485
+ "esm.encoder.layer.33.output.dense.bias": "pytorch_model-00002-of-00002.bin",
486
+ "esm.encoder.layer.33.output.dense.weight": "pytorch_model-00002-of-00002.bin",
487
+ "esm.encoder.layer.34.LayerNorm.bias": "pytorch_model-00002-of-00002.bin",
488
+ "esm.encoder.layer.34.LayerNorm.weight": "pytorch_model-00002-of-00002.bin",
489
+ "esm.encoder.layer.34.attention.LayerNorm.bias": "pytorch_model-00002-of-00002.bin",
490
+ "esm.encoder.layer.34.attention.LayerNorm.weight": "pytorch_model-00002-of-00002.bin",
491
+ "esm.encoder.layer.34.attention.output.dense.bias": "pytorch_model-00002-of-00002.bin",
492
+ "esm.encoder.layer.34.attention.output.dense.weight": "pytorch_model-00002-of-00002.bin",
493
+ "esm.encoder.layer.34.attention.self.key.bias": "pytorch_model-00002-of-00002.bin",
494
+ "esm.encoder.layer.34.attention.self.key.weight": "pytorch_model-00002-of-00002.bin",
495
+ "esm.encoder.layer.34.attention.self.query.bias": "pytorch_model-00002-of-00002.bin",
496
+ "esm.encoder.layer.34.attention.self.query.weight": "pytorch_model-00002-of-00002.bin",
497
+ "esm.encoder.layer.34.attention.self.rotary_embeddings.inv_freq": "pytorch_model-00002-of-00002.bin",
498
+ "esm.encoder.layer.34.attention.self.value.bias": "pytorch_model-00002-of-00002.bin",
499
+ "esm.encoder.layer.34.attention.self.value.weight": "pytorch_model-00002-of-00002.bin",
500
+ "esm.encoder.layer.34.intermediate.dense.bias": "pytorch_model-00002-of-00002.bin",
501
+ "esm.encoder.layer.34.intermediate.dense.weight": "pytorch_model-00002-of-00002.bin",
502
+ "esm.encoder.layer.34.output.dense.bias": "pytorch_model-00002-of-00002.bin",
503
+ "esm.encoder.layer.34.output.dense.weight": "pytorch_model-00002-of-00002.bin",
504
+ "esm.encoder.layer.35.LayerNorm.bias": "pytorch_model-00002-of-00002.bin",
505
+ "esm.encoder.layer.35.LayerNorm.weight": "pytorch_model-00002-of-00002.bin",
506
+ "esm.encoder.layer.35.attention.LayerNorm.bias": "pytorch_model-00002-of-00002.bin",
507
+ "esm.encoder.layer.35.attention.LayerNorm.weight": "pytorch_model-00002-of-00002.bin",
508
+ "esm.encoder.layer.35.attention.output.dense.bias": "pytorch_model-00002-of-00002.bin",
509
+ "esm.encoder.layer.35.attention.output.dense.weight": "pytorch_model-00002-of-00002.bin",
510
+ "esm.encoder.layer.35.attention.self.key.bias": "pytorch_model-00002-of-00002.bin",
511
+ "esm.encoder.layer.35.attention.self.key.weight": "pytorch_model-00002-of-00002.bin",
512
+ "esm.encoder.layer.35.attention.self.query.bias": "pytorch_model-00002-of-00002.bin",
513
+ "esm.encoder.layer.35.attention.self.query.weight": "pytorch_model-00002-of-00002.bin",
514
+ "esm.encoder.layer.35.attention.self.rotary_embeddings.inv_freq": "pytorch_model-00002-of-00002.bin",
515
+ "esm.encoder.layer.35.attention.self.value.bias": "pytorch_model-00002-of-00002.bin",
516
+ "esm.encoder.layer.35.attention.self.value.weight": "pytorch_model-00002-of-00002.bin",
517
+ "esm.encoder.layer.35.intermediate.dense.bias": "pytorch_model-00002-of-00002.bin",
518
+ "esm.encoder.layer.35.intermediate.dense.weight": "pytorch_model-00002-of-00002.bin",
519
+ "esm.encoder.layer.35.output.dense.bias": "pytorch_model-00002-of-00002.bin",
520
+ "esm.encoder.layer.35.output.dense.weight": "pytorch_model-00002-of-00002.bin",
521
+ "esm.encoder.layer.4.LayerNorm.bias": "pytorch_model-00001-of-00002.bin",
522
+ "esm.encoder.layer.4.LayerNorm.weight": "pytorch_model-00001-of-00002.bin",
523
+ "esm.encoder.layer.4.attention.LayerNorm.bias": "pytorch_model-00001-of-00002.bin",
524
+ "esm.encoder.layer.4.attention.LayerNorm.weight": "pytorch_model-00001-of-00002.bin",
525
+ "esm.encoder.layer.4.attention.output.dense.bias": "pytorch_model-00001-of-00002.bin",
526
+ "esm.encoder.layer.4.attention.output.dense.weight": "pytorch_model-00001-of-00002.bin",
527
+ "esm.encoder.layer.4.attention.self.key.bias": "pytorch_model-00001-of-00002.bin",
528
+ "esm.encoder.layer.4.attention.self.key.weight": "pytorch_model-00001-of-00002.bin",
529
+ "esm.encoder.layer.4.attention.self.query.bias": "pytorch_model-00001-of-00002.bin",
530
+ "esm.encoder.layer.4.attention.self.query.weight": "pytorch_model-00001-of-00002.bin",
531
+ "esm.encoder.layer.4.attention.self.rotary_embeddings.inv_freq": "pytorch_model-00001-of-00002.bin",
532
+ "esm.encoder.layer.4.attention.self.value.bias": "pytorch_model-00001-of-00002.bin",
533
+ "esm.encoder.layer.4.attention.self.value.weight": "pytorch_model-00001-of-00002.bin",
534
+ "esm.encoder.layer.4.intermediate.dense.bias": "pytorch_model-00001-of-00002.bin",
535
+ "esm.encoder.layer.4.intermediate.dense.weight": "pytorch_model-00001-of-00002.bin",
536
+ "esm.encoder.layer.4.output.dense.bias": "pytorch_model-00001-of-00002.bin",
537
+ "esm.encoder.layer.4.output.dense.weight": "pytorch_model-00001-of-00002.bin",
538
+ "esm.encoder.layer.5.LayerNorm.bias": "pytorch_model-00001-of-00002.bin",
539
+ "esm.encoder.layer.5.LayerNorm.weight": "pytorch_model-00001-of-00002.bin",
540
+ "esm.encoder.layer.5.attention.LayerNorm.bias": "pytorch_model-00001-of-00002.bin",
541
+ "esm.encoder.layer.5.attention.LayerNorm.weight": "pytorch_model-00001-of-00002.bin",
542
+ "esm.encoder.layer.5.attention.output.dense.bias": "pytorch_model-00001-of-00002.bin",
543
+ "esm.encoder.layer.5.attention.output.dense.weight": "pytorch_model-00001-of-00002.bin",
544
+ "esm.encoder.layer.5.attention.self.key.bias": "pytorch_model-00001-of-00002.bin",
545
+ "esm.encoder.layer.5.attention.self.key.weight": "pytorch_model-00001-of-00002.bin",
546
+ "esm.encoder.layer.5.attention.self.query.bias": "pytorch_model-00001-of-00002.bin",
547
+ "esm.encoder.layer.5.attention.self.query.weight": "pytorch_model-00001-of-00002.bin",
548
+ "esm.encoder.layer.5.attention.self.rotary_embeddings.inv_freq": "pytorch_model-00001-of-00002.bin",
549
+ "esm.encoder.layer.5.attention.self.value.bias": "pytorch_model-00001-of-00002.bin",
550
+ "esm.encoder.layer.5.attention.self.value.weight": "pytorch_model-00001-of-00002.bin",
551
+ "esm.encoder.layer.5.intermediate.dense.bias": "pytorch_model-00001-of-00002.bin",
552
+ "esm.encoder.layer.5.intermediate.dense.weight": "pytorch_model-00001-of-00002.bin",
553
+ "esm.encoder.layer.5.output.dense.bias": "pytorch_model-00001-of-00002.bin",
554
+ "esm.encoder.layer.5.output.dense.weight": "pytorch_model-00001-of-00002.bin",
555
+ "esm.encoder.layer.6.LayerNorm.bias": "pytorch_model-00001-of-00002.bin",
556
+ "esm.encoder.layer.6.LayerNorm.weight": "pytorch_model-00001-of-00002.bin",
557
+ "esm.encoder.layer.6.attention.LayerNorm.bias": "pytorch_model-00001-of-00002.bin",
558
+ "esm.encoder.layer.6.attention.LayerNorm.weight": "pytorch_model-00001-of-00002.bin",
559
+ "esm.encoder.layer.6.attention.output.dense.bias": "pytorch_model-00001-of-00002.bin",
560
+ "esm.encoder.layer.6.attention.output.dense.weight": "pytorch_model-00001-of-00002.bin",
561
+ "esm.encoder.layer.6.attention.self.key.bias": "pytorch_model-00001-of-00002.bin",
562
+ "esm.encoder.layer.6.attention.self.key.weight": "pytorch_model-00001-of-00002.bin",
563
+ "esm.encoder.layer.6.attention.self.query.bias": "pytorch_model-00001-of-00002.bin",
564
+ "esm.encoder.layer.6.attention.self.query.weight": "pytorch_model-00001-of-00002.bin",
565
+ "esm.encoder.layer.6.attention.self.rotary_embeddings.inv_freq": "pytorch_model-00001-of-00002.bin",
566
+ "esm.encoder.layer.6.attention.self.value.bias": "pytorch_model-00001-of-00002.bin",
567
+ "esm.encoder.layer.6.attention.self.value.weight": "pytorch_model-00001-of-00002.bin",
568
+ "esm.encoder.layer.6.intermediate.dense.bias": "pytorch_model-00001-of-00002.bin",
569
+ "esm.encoder.layer.6.intermediate.dense.weight": "pytorch_model-00001-of-00002.bin",
570
+ "esm.encoder.layer.6.output.dense.bias": "pytorch_model-00001-of-00002.bin",
571
+ "esm.encoder.layer.6.output.dense.weight": "pytorch_model-00001-of-00002.bin",
572
+ "esm.encoder.layer.7.LayerNorm.bias": "pytorch_model-00001-of-00002.bin",
573
+ "esm.encoder.layer.7.LayerNorm.weight": "pytorch_model-00001-of-00002.bin",
574
+ "esm.encoder.layer.7.attention.LayerNorm.bias": "pytorch_model-00001-of-00002.bin",
575
+ "esm.encoder.layer.7.attention.LayerNorm.weight": "pytorch_model-00001-of-00002.bin",
576
+ "esm.encoder.layer.7.attention.output.dense.bias": "pytorch_model-00001-of-00002.bin",
577
+ "esm.encoder.layer.7.attention.output.dense.weight": "pytorch_model-00001-of-00002.bin",
578
+ "esm.encoder.layer.7.attention.self.key.bias": "pytorch_model-00001-of-00002.bin",
579
+ "esm.encoder.layer.7.attention.self.key.weight": "pytorch_model-00001-of-00002.bin",
580
+ "esm.encoder.layer.7.attention.self.query.bias": "pytorch_model-00001-of-00002.bin",
581
+ "esm.encoder.layer.7.attention.self.query.weight": "pytorch_model-00001-of-00002.bin",
582
+ "esm.encoder.layer.7.attention.self.rotary_embeddings.inv_freq": "pytorch_model-00001-of-00002.bin",
583
+ "esm.encoder.layer.7.attention.self.value.bias": "pytorch_model-00001-of-00002.bin",
584
+ "esm.encoder.layer.7.attention.self.value.weight": "pytorch_model-00001-of-00002.bin",
585
+ "esm.encoder.layer.7.intermediate.dense.bias": "pytorch_model-00001-of-00002.bin",
586
+ "esm.encoder.layer.7.intermediate.dense.weight": "pytorch_model-00001-of-00002.bin",
587
+ "esm.encoder.layer.7.output.dense.bias": "pytorch_model-00001-of-00002.bin",
588
+ "esm.encoder.layer.7.output.dense.weight": "pytorch_model-00001-of-00002.bin",
589
+ "esm.encoder.layer.8.LayerNorm.bias": "pytorch_model-00001-of-00002.bin",
590
+ "esm.encoder.layer.8.LayerNorm.weight": "pytorch_model-00001-of-00002.bin",
591
+ "esm.encoder.layer.8.attention.LayerNorm.bias": "pytorch_model-00001-of-00002.bin",
592
+ "esm.encoder.layer.8.attention.LayerNorm.weight": "pytorch_model-00001-of-00002.bin",
593
+ "esm.encoder.layer.8.attention.output.dense.bias": "pytorch_model-00001-of-00002.bin",
594
+ "esm.encoder.layer.8.attention.output.dense.weight": "pytorch_model-00001-of-00002.bin",
595
+ "esm.encoder.layer.8.attention.self.key.bias": "pytorch_model-00001-of-00002.bin",
596
+ "esm.encoder.layer.8.attention.self.key.weight": "pytorch_model-00001-of-00002.bin",
597
+ "esm.encoder.layer.8.attention.self.query.bias": "pytorch_model-00001-of-00002.bin",
598
+ "esm.encoder.layer.8.attention.self.query.weight": "pytorch_model-00001-of-00002.bin",
599
+ "esm.encoder.layer.8.attention.self.rotary_embeddings.inv_freq": "pytorch_model-00001-of-00002.bin",
600
+ "esm.encoder.layer.8.attention.self.value.bias": "pytorch_model-00001-of-00002.bin",
601
+ "esm.encoder.layer.8.attention.self.value.weight": "pytorch_model-00001-of-00002.bin",
602
+ "esm.encoder.layer.8.intermediate.dense.bias": "pytorch_model-00001-of-00002.bin",
603
+ "esm.encoder.layer.8.intermediate.dense.weight": "pytorch_model-00001-of-00002.bin",
604
+ "esm.encoder.layer.8.output.dense.bias": "pytorch_model-00001-of-00002.bin",
605
+ "esm.encoder.layer.8.output.dense.weight": "pytorch_model-00001-of-00002.bin",
606
+ "esm.encoder.layer.9.LayerNorm.bias": "pytorch_model-00001-of-00002.bin",
607
+ "esm.encoder.layer.9.LayerNorm.weight": "pytorch_model-00001-of-00002.bin",
608
+ "esm.encoder.layer.9.attention.LayerNorm.bias": "pytorch_model-00001-of-00002.bin",
609
+ "esm.encoder.layer.9.attention.LayerNorm.weight": "pytorch_model-00001-of-00002.bin",
610
+ "esm.encoder.layer.9.attention.output.dense.bias": "pytorch_model-00001-of-00002.bin",
611
+ "esm.encoder.layer.9.attention.output.dense.weight": "pytorch_model-00001-of-00002.bin",
612
+ "esm.encoder.layer.9.attention.self.key.bias": "pytorch_model-00001-of-00002.bin",
613
+ "esm.encoder.layer.9.attention.self.key.weight": "pytorch_model-00001-of-00002.bin",
614
+ "esm.encoder.layer.9.attention.self.query.bias": "pytorch_model-00001-of-00002.bin",
615
+ "esm.encoder.layer.9.attention.self.query.weight": "pytorch_model-00001-of-00002.bin",
616
+ "esm.encoder.layer.9.attention.self.rotary_embeddings.inv_freq": "pytorch_model-00001-of-00002.bin",
617
+ "esm.encoder.layer.9.attention.self.value.bias": "pytorch_model-00001-of-00002.bin",
618
+ "esm.encoder.layer.9.attention.self.value.weight": "pytorch_model-00001-of-00002.bin",
619
+ "esm.encoder.layer.9.intermediate.dense.bias": "pytorch_model-00001-of-00002.bin",
620
+ "esm.encoder.layer.9.intermediate.dense.weight": "pytorch_model-00001-of-00002.bin",
621
+ "esm.encoder.layer.9.output.dense.bias": "pytorch_model-00001-of-00002.bin",
622
+ "esm.encoder.layer.9.output.dense.weight": "pytorch_model-00001-of-00002.bin",
623
+ "lm_head.bias": "pytorch_model-00002-of-00002.bin",
624
+ "lm_head.decoder.bias": "pytorch_model-00002-of-00002.bin",
625
+ "lm_head.decoder.weight": "pytorch_model-00002-of-00002.bin",
626
+ "lm_head.dense.bias": "pytorch_model-00002-of-00002.bin",
627
+ "lm_head.dense.weight": "pytorch_model-00002-of-00002.bin",
628
+ "lm_head.layer_norm.bias": "pytorch_model-00002-of-00002.bin",
629
+ "lm_head.layer_norm.weight": "pytorch_model-00002-of-00002.bin"
630
+ }
631
+ }