oscorrea commited on
Commit
069e3a0
1 Parent(s): 8d59acb

Upload folder using huggingface_hub

Browse files
config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "tiiuae/falcon-40b",
3
+ "alibi": false,
4
+ "apply_residual_connection_post_layernorm": false,
5
+ "architectures": [
6
+ "FalconForCausalLM"
7
+ ],
8
+ "attention_dropout": 0.0,
9
+ "auto_map": {
10
+ "AutoConfig": "tiiuae/falcon-40b--configuration_falcon.FalconConfig",
11
+ "AutoModel": "tiiuae/falcon-40b--modeling_falcon.FalconModel",
12
+ "AutoModelForCausalLM": "tiiuae/falcon-40b--modeling_falcon.FalconForCausalLM",
13
+ "AutoModelForQuestionAnswering": "tiiuae/falcon-40b--modeling_falcon.FalconForQuestionAnswering",
14
+ "AutoModelForSequenceClassification": "tiiuae/falcon-40b--modeling_falcon.FalconForSequenceClassification",
15
+ "AutoModelForTokenClassification": "tiiuae/falcon-40b--modeling_falcon.FalconForTokenClassification"
16
+ },
17
+ "bias": false,
18
+ "bos_token_id": 11,
19
+ "eos_token_id": 11,
20
+ "hidden_dropout": 0.0,
21
+ "hidden_size": 8192,
22
+ "initializer_range": 0.02,
23
+ "layer_norm_epsilon": 1e-05,
24
+ "model_type": "falcon",
25
+ "multi_query": true,
26
+ "new_decoder_architecture": true,
27
+ "num_attention_heads": 128,
28
+ "num_hidden_layers": 60,
29
+ "num_kv_heads": 8,
30
+ "parallel_attn": true,
31
+ "torch_dtype": "float16",
32
+ "transformers_version": "4.31.0.dev0",
33
+ "use_cache": true,
34
+ "vocab_size": 65024
35
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 11,
4
+ "eos_token_id": 11,
5
+ "transformers_version": "4.31.0.dev0"
6
+ }
pytorch_model-00001-of-00004.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8c4055cb4dafa2bc26477a6b3db56b55e1633454ba634338abd9e875180e7c4f
3
+ size 9504704161
pytorch_model-00002-of-00004.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b0260e09bbac341ee2e11e1e5e0b4393ece3d3b1ca0f94e12ab03193c9c0c905
3
+ size 9513159919
pytorch_model-00003-of-00004.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:57d94016d58169f54acfab8ce61a69b56668a6b0d3d6c8adbfb2015dda252817
3
+ size 9513159919
pytorch_model-00004-of-00004.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:42c426b18ca8b03f92c95aa013c18cc7082623d50a754988ac426891f378ccd2
3
+ size 6509926419
pytorch_model.bin.index.json ADDED
@@ -0,0 +1,491 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 35862953984
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "pytorch_model-00001-of-00004.bin",
7
+ "transformer.h.0.ln_attn.bias": "pytorch_model-00001-of-00004.bin",
8
+ "transformer.h.0.ln_attn.weight": "pytorch_model-00001-of-00004.bin",
9
+ "transformer.h.0.ln_mlp.bias": "pytorch_model-00001-of-00004.bin",
10
+ "transformer.h.0.ln_mlp.weight": "pytorch_model-00001-of-00004.bin",
11
+ "transformer.h.0.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00004.bin",
12
+ "transformer.h.0.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00004.bin",
13
+ "transformer.h.0.self_attention.dense.weight": "pytorch_model-00001-of-00004.bin",
14
+ "transformer.h.0.self_attention.query_key_value.weight": "pytorch_model-00001-of-00004.bin",
15
+ "transformer.h.1.ln_attn.bias": "pytorch_model-00001-of-00004.bin",
16
+ "transformer.h.1.ln_attn.weight": "pytorch_model-00001-of-00004.bin",
17
+ "transformer.h.1.ln_mlp.bias": "pytorch_model-00001-of-00004.bin",
18
+ "transformer.h.1.ln_mlp.weight": "pytorch_model-00001-of-00004.bin",
19
+ "transformer.h.1.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00004.bin",
20
+ "transformer.h.1.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00004.bin",
21
+ "transformer.h.1.self_attention.dense.weight": "pytorch_model-00001-of-00004.bin",
22
+ "transformer.h.1.self_attention.query_key_value.weight": "pytorch_model-00001-of-00004.bin",
23
+ "transformer.h.10.ln_attn.bias": "pytorch_model-00002-of-00004.bin",
24
+ "transformer.h.10.ln_attn.weight": "pytorch_model-00002-of-00004.bin",
25
+ "transformer.h.10.ln_mlp.bias": "pytorch_model-00002-of-00004.bin",
26
+ "transformer.h.10.ln_mlp.weight": "pytorch_model-00002-of-00004.bin",
27
+ "transformer.h.10.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00004.bin",
28
+ "transformer.h.10.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00004.bin",
29
+ "transformer.h.10.self_attention.dense.weight": "pytorch_model-00002-of-00004.bin",
30
+ "transformer.h.10.self_attention.query_key_value.weight": "pytorch_model-00002-of-00004.bin",
31
+ "transformer.h.11.ln_attn.bias": "pytorch_model-00002-of-00004.bin",
32
+ "transformer.h.11.ln_attn.weight": "pytorch_model-00002-of-00004.bin",
33
+ "transformer.h.11.ln_mlp.bias": "pytorch_model-00002-of-00004.bin",
34
+ "transformer.h.11.ln_mlp.weight": "pytorch_model-00002-of-00004.bin",
35
+ "transformer.h.11.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00004.bin",
36
+ "transformer.h.11.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00004.bin",
37
+ "transformer.h.11.self_attention.dense.weight": "pytorch_model-00002-of-00004.bin",
38
+ "transformer.h.11.self_attention.query_key_value.weight": "pytorch_model-00002-of-00004.bin",
39
+ "transformer.h.12.ln_attn.bias": "pytorch_model-00002-of-00004.bin",
40
+ "transformer.h.12.ln_attn.weight": "pytorch_model-00002-of-00004.bin",
41
+ "transformer.h.12.ln_mlp.bias": "pytorch_model-00002-of-00004.bin",
42
+ "transformer.h.12.ln_mlp.weight": "pytorch_model-00002-of-00004.bin",
43
+ "transformer.h.12.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00004.bin",
44
+ "transformer.h.12.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00004.bin",
45
+ "transformer.h.12.self_attention.dense.weight": "pytorch_model-00002-of-00004.bin",
46
+ "transformer.h.12.self_attention.query_key_value.weight": "pytorch_model-00002-of-00004.bin",
47
+ "transformer.h.13.ln_attn.bias": "pytorch_model-00003-of-00004.bin",
48
+ "transformer.h.13.ln_attn.weight": "pytorch_model-00003-of-00004.bin",
49
+ "transformer.h.13.ln_mlp.bias": "pytorch_model-00003-of-00004.bin",
50
+ "transformer.h.13.ln_mlp.weight": "pytorch_model-00003-of-00004.bin",
51
+ "transformer.h.13.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00004.bin",
52
+ "transformer.h.13.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00004.bin",
53
+ "transformer.h.13.self_attention.dense.weight": "pytorch_model-00002-of-00004.bin",
54
+ "transformer.h.13.self_attention.query_key_value.weight": "pytorch_model-00002-of-00004.bin",
55
+ "transformer.h.14.ln_attn.bias": "pytorch_model-00003-of-00004.bin",
56
+ "transformer.h.14.ln_attn.weight": "pytorch_model-00003-of-00004.bin",
57
+ "transformer.h.14.ln_mlp.bias": "pytorch_model-00003-of-00004.bin",
58
+ "transformer.h.14.ln_mlp.weight": "pytorch_model-00003-of-00004.bin",
59
+ "transformer.h.14.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00004.bin",
60
+ "transformer.h.14.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00004.bin",
61
+ "transformer.h.14.self_attention.dense.weight": "pytorch_model-00003-of-00004.bin",
62
+ "transformer.h.14.self_attention.query_key_value.weight": "pytorch_model-00003-of-00004.bin",
63
+ "transformer.h.15.ln_attn.bias": "pytorch_model-00003-of-00004.bin",
64
+ "transformer.h.15.ln_attn.weight": "pytorch_model-00003-of-00004.bin",
65
+ "transformer.h.15.ln_mlp.bias": "pytorch_model-00003-of-00004.bin",
66
+ "transformer.h.15.ln_mlp.weight": "pytorch_model-00003-of-00004.bin",
67
+ "transformer.h.15.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00004.bin",
68
+ "transformer.h.15.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00004.bin",
69
+ "transformer.h.15.self_attention.dense.weight": "pytorch_model-00003-of-00004.bin",
70
+ "transformer.h.15.self_attention.query_key_value.weight": "pytorch_model-00003-of-00004.bin",
71
+ "transformer.h.16.ln_attn.bias": "pytorch_model-00003-of-00004.bin",
72
+ "transformer.h.16.ln_attn.weight": "pytorch_model-00003-of-00004.bin",
73
+ "transformer.h.16.ln_mlp.bias": "pytorch_model-00003-of-00004.bin",
74
+ "transformer.h.16.ln_mlp.weight": "pytorch_model-00003-of-00004.bin",
75
+ "transformer.h.16.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00004.bin",
76
+ "transformer.h.16.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00004.bin",
77
+ "transformer.h.16.self_attention.dense.weight": "pytorch_model-00003-of-00004.bin",
78
+ "transformer.h.16.self_attention.query_key_value.weight": "pytorch_model-00003-of-00004.bin",
79
+ "transformer.h.17.ln_attn.bias": "pytorch_model-00003-of-00004.bin",
80
+ "transformer.h.17.ln_attn.weight": "pytorch_model-00003-of-00004.bin",
81
+ "transformer.h.17.ln_mlp.bias": "pytorch_model-00003-of-00004.bin",
82
+ "transformer.h.17.ln_mlp.weight": "pytorch_model-00003-of-00004.bin",
83
+ "transformer.h.17.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00004.bin",
84
+ "transformer.h.17.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00004.bin",
85
+ "transformer.h.17.self_attention.dense.weight": "pytorch_model-00003-of-00004.bin",
86
+ "transformer.h.17.self_attention.query_key_value.weight": "pytorch_model-00003-of-00004.bin",
87
+ "transformer.h.18.ln_attn.bias": "pytorch_model-00003-of-00004.bin",
88
+ "transformer.h.18.ln_attn.weight": "pytorch_model-00003-of-00004.bin",
89
+ "transformer.h.18.ln_mlp.bias": "pytorch_model-00003-of-00004.bin",
90
+ "transformer.h.18.ln_mlp.weight": "pytorch_model-00003-of-00004.bin",
91
+ "transformer.h.18.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00004.bin",
92
+ "transformer.h.18.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00004.bin",
93
+ "transformer.h.18.self_attention.dense.weight": "pytorch_model-00003-of-00004.bin",
94
+ "transformer.h.18.self_attention.query_key_value.weight": "pytorch_model-00003-of-00004.bin",
95
+ "transformer.h.19.ln_attn.bias": "pytorch_model-00003-of-00004.bin",
96
+ "transformer.h.19.ln_attn.weight": "pytorch_model-00003-of-00004.bin",
97
+ "transformer.h.19.ln_mlp.bias": "pytorch_model-00003-of-00004.bin",
98
+ "transformer.h.19.ln_mlp.weight": "pytorch_model-00003-of-00004.bin",
99
+ "transformer.h.19.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00004.bin",
100
+ "transformer.h.19.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00004.bin",
101
+ "transformer.h.19.self_attention.dense.weight": "pytorch_model-00003-of-00004.bin",
102
+ "transformer.h.19.self_attention.query_key_value.weight": "pytorch_model-00003-of-00004.bin",
103
+ "transformer.h.2.ln_attn.bias": "pytorch_model-00001-of-00004.bin",
104
+ "transformer.h.2.ln_attn.weight": "pytorch_model-00001-of-00004.bin",
105
+ "transformer.h.2.ln_mlp.bias": "pytorch_model-00001-of-00004.bin",
106
+ "transformer.h.2.ln_mlp.weight": "pytorch_model-00001-of-00004.bin",
107
+ "transformer.h.2.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00004.bin",
108
+ "transformer.h.2.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00004.bin",
109
+ "transformer.h.2.self_attention.dense.weight": "pytorch_model-00001-of-00004.bin",
110
+ "transformer.h.2.self_attention.query_key_value.weight": "pytorch_model-00001-of-00004.bin",
111
+ "transformer.h.20.ln_attn.bias": "pytorch_model-00004-of-00004.bin",
112
+ "transformer.h.20.ln_attn.weight": "pytorch_model-00004-of-00004.bin",
113
+ "transformer.h.20.ln_mlp.bias": "pytorch_model-00004-of-00004.bin",
114
+ "transformer.h.20.ln_mlp.weight": "pytorch_model-00004-of-00004.bin",
115
+ "transformer.h.20.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00004.bin",
116
+ "transformer.h.20.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00004.bin",
117
+ "transformer.h.20.self_attention.dense.weight": "pytorch_model-00003-of-00004.bin",
118
+ "transformer.h.20.self_attention.query_key_value.weight": "pytorch_model-00003-of-00004.bin",
119
+ "transformer.h.21.ln_attn.bias": "pytorch_model-00004-of-00004.bin",
120
+ "transformer.h.21.ln_attn.weight": "pytorch_model-00004-of-00004.bin",
121
+ "transformer.h.21.ln_mlp.bias": "pytorch_model-00004-of-00004.bin",
122
+ "transformer.h.21.ln_mlp.weight": "pytorch_model-00004-of-00004.bin",
123
+ "transformer.h.21.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00004.bin",
124
+ "transformer.h.21.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00004.bin",
125
+ "transformer.h.21.self_attention.dense.weight": "pytorch_model-00004-of-00004.bin",
126
+ "transformer.h.21.self_attention.query_key_value.weight": "pytorch_model-00004-of-00004.bin",
127
+ "transformer.h.22.ln_attn.bias": "pytorch_model-00004-of-00004.bin",
128
+ "transformer.h.22.ln_attn.weight": "pytorch_model-00004-of-00004.bin",
129
+ "transformer.h.22.ln_mlp.bias": "pytorch_model-00004-of-00004.bin",
130
+ "transformer.h.22.ln_mlp.weight": "pytorch_model-00004-of-00004.bin",
131
+ "transformer.h.22.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00004.bin",
132
+ "transformer.h.22.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00004.bin",
133
+ "transformer.h.22.self_attention.dense.weight": "pytorch_model-00004-of-00004.bin",
134
+ "transformer.h.22.self_attention.query_key_value.weight": "pytorch_model-00004-of-00004.bin",
135
+ "transformer.h.23.ln_attn.bias": "pytorch_model-00004-of-00004.bin",
136
+ "transformer.h.23.ln_attn.weight": "pytorch_model-00004-of-00004.bin",
137
+ "transformer.h.23.ln_mlp.bias": "pytorch_model-00004-of-00004.bin",
138
+ "transformer.h.23.ln_mlp.weight": "pytorch_model-00004-of-00004.bin",
139
+ "transformer.h.23.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00004.bin",
140
+ "transformer.h.23.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00004.bin",
141
+ "transformer.h.23.self_attention.dense.weight": "pytorch_model-00004-of-00004.bin",
142
+ "transformer.h.23.self_attention.query_key_value.weight": "pytorch_model-00004-of-00004.bin",
143
+ "transformer.h.24.ln_attn.bias": "pytorch_model-00004-of-00004.bin",
144
+ "transformer.h.24.ln_attn.weight": "pytorch_model-00004-of-00004.bin",
145
+ "transformer.h.24.ln_mlp.bias": "pytorch_model-00004-of-00004.bin",
146
+ "transformer.h.24.ln_mlp.weight": "pytorch_model-00004-of-00004.bin",
147
+ "transformer.h.24.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00004.bin",
148
+ "transformer.h.24.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00004.bin",
149
+ "transformer.h.24.self_attention.dense.weight": "pytorch_model-00004-of-00004.bin",
150
+ "transformer.h.24.self_attention.query_key_value.weight": "pytorch_model-00004-of-00004.bin",
151
+ "transformer.h.25.ln_attn.bias": "pytorch_model-00004-of-00004.bin",
152
+ "transformer.h.25.ln_attn.weight": "pytorch_model-00004-of-00004.bin",
153
+ "transformer.h.25.ln_mlp.bias": "pytorch_model-00004-of-00004.bin",
154
+ "transformer.h.25.ln_mlp.weight": "pytorch_model-00004-of-00004.bin",
155
+ "transformer.h.25.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00004.bin",
156
+ "transformer.h.25.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00004.bin",
157
+ "transformer.h.25.self_attention.dense.weight": "pytorch_model-00004-of-00004.bin",
158
+ "transformer.h.25.self_attention.query_key_value.weight": "pytorch_model-00004-of-00004.bin",
159
+ "transformer.h.26.ln_attn.bias": "pytorch_model-00004-of-00004.bin",
160
+ "transformer.h.26.ln_attn.weight": "pytorch_model-00004-of-00004.bin",
161
+ "transformer.h.26.ln_mlp.bias": "pytorch_model-00004-of-00004.bin",
162
+ "transformer.h.26.ln_mlp.weight": "pytorch_model-00004-of-00004.bin",
163
+ "transformer.h.26.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00004.bin",
164
+ "transformer.h.26.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00004.bin",
165
+ "transformer.h.26.self_attention.dense.weight": "pytorch_model-00004-of-00004.bin",
166
+ "transformer.h.26.self_attention.query_key_value.weight": "pytorch_model-00004-of-00004.bin",
167
+ "transformer.h.27.ln_attn.bias": "pytorch_model-00004-of-00004.bin",
168
+ "transformer.h.27.ln_attn.weight": "pytorch_model-00004-of-00004.bin",
169
+ "transformer.h.27.ln_mlp.bias": "pytorch_model-00004-of-00004.bin",
170
+ "transformer.h.27.ln_mlp.weight": "pytorch_model-00004-of-00004.bin",
171
+ "transformer.h.27.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00004.bin",
172
+ "transformer.h.27.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00004.bin",
173
+ "transformer.h.27.self_attention.dense.weight": "pytorch_model-00004-of-00004.bin",
174
+ "transformer.h.27.self_attention.query_key_value.weight": "pytorch_model-00004-of-00004.bin",
175
+ "transformer.h.28.ln_attn.bias": "pytorch_model-00004-of-00004.bin",
176
+ "transformer.h.28.ln_attn.weight": "pytorch_model-00004-of-00004.bin",
177
+ "transformer.h.28.ln_mlp.bias": "pytorch_model-00004-of-00004.bin",
178
+ "transformer.h.28.ln_mlp.weight": "pytorch_model-00004-of-00004.bin",
179
+ "transformer.h.28.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00004.bin",
180
+ "transformer.h.28.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00004.bin",
181
+ "transformer.h.28.self_attention.dense.weight": "pytorch_model-00004-of-00004.bin",
182
+ "transformer.h.28.self_attention.query_key_value.weight": "pytorch_model-00004-of-00004.bin",
183
+ "transformer.h.29.ln_attn.bias": "pytorch_model-00004-of-00004.bin",
184
+ "transformer.h.29.ln_attn.weight": "pytorch_model-00004-of-00004.bin",
185
+ "transformer.h.29.ln_mlp.bias": "pytorch_model-00004-of-00004.bin",
186
+ "transformer.h.29.ln_mlp.weight": "pytorch_model-00004-of-00004.bin",
187
+ "transformer.h.29.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00004.bin",
188
+ "transformer.h.29.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00004.bin",
189
+ "transformer.h.29.self_attention.dense.weight": "pytorch_model-00004-of-00004.bin",
190
+ "transformer.h.29.self_attention.query_key_value.weight": "pytorch_model-00004-of-00004.bin",
191
+ "transformer.h.3.ln_attn.bias": "pytorch_model-00001-of-00004.bin",
192
+ "transformer.h.3.ln_attn.weight": "pytorch_model-00001-of-00004.bin",
193
+ "transformer.h.3.ln_mlp.bias": "pytorch_model-00001-of-00004.bin",
194
+ "transformer.h.3.ln_mlp.weight": "pytorch_model-00001-of-00004.bin",
195
+ "transformer.h.3.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00004.bin",
196
+ "transformer.h.3.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00004.bin",
197
+ "transformer.h.3.self_attention.dense.weight": "pytorch_model-00001-of-00004.bin",
198
+ "transformer.h.3.self_attention.query_key_value.weight": "pytorch_model-00001-of-00004.bin",
199
+ "transformer.h.30.ln_attn.bias": "pytorch_model-00004-of-00004.bin",
200
+ "transformer.h.30.ln_attn.weight": "pytorch_model-00004-of-00004.bin",
201
+ "transformer.h.30.ln_mlp.bias": "pytorch_model-00004-of-00004.bin",
202
+ "transformer.h.30.ln_mlp.weight": "pytorch_model-00004-of-00004.bin",
203
+ "transformer.h.30.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00004.bin",
204
+ "transformer.h.30.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00004.bin",
205
+ "transformer.h.30.self_attention.dense.weight": "pytorch_model-00004-of-00004.bin",
206
+ "transformer.h.30.self_attention.query_key_value.weight": "pytorch_model-00004-of-00004.bin",
207
+ "transformer.h.31.ln_attn.bias": "pytorch_model-00004-of-00004.bin",
208
+ "transformer.h.31.ln_attn.weight": "pytorch_model-00004-of-00004.bin",
209
+ "transformer.h.31.ln_mlp.bias": "pytorch_model-00004-of-00004.bin",
210
+ "transformer.h.31.ln_mlp.weight": "pytorch_model-00004-of-00004.bin",
211
+ "transformer.h.31.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00004.bin",
212
+ "transformer.h.31.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00004.bin",
213
+ "transformer.h.31.self_attention.dense.weight": "pytorch_model-00004-of-00004.bin",
214
+ "transformer.h.31.self_attention.query_key_value.weight": "pytorch_model-00004-of-00004.bin",
215
+ "transformer.h.32.ln_attn.bias": "pytorch_model-00004-of-00004.bin",
216
+ "transformer.h.32.ln_attn.weight": "pytorch_model-00004-of-00004.bin",
217
+ "transformer.h.32.ln_mlp.bias": "pytorch_model-00004-of-00004.bin",
218
+ "transformer.h.32.ln_mlp.weight": "pytorch_model-00004-of-00004.bin",
219
+ "transformer.h.32.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00004.bin",
220
+ "transformer.h.32.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00004.bin",
221
+ "transformer.h.32.self_attention.dense.weight": "pytorch_model-00004-of-00004.bin",
222
+ "transformer.h.32.self_attention.query_key_value.weight": "pytorch_model-00004-of-00004.bin",
223
+ "transformer.h.33.ln_attn.bias": "pytorch_model-00004-of-00004.bin",
224
+ "transformer.h.33.ln_attn.weight": "pytorch_model-00004-of-00004.bin",
225
+ "transformer.h.33.ln_mlp.bias": "pytorch_model-00004-of-00004.bin",
226
+ "transformer.h.33.ln_mlp.weight": "pytorch_model-00004-of-00004.bin",
227
+ "transformer.h.33.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00004.bin",
228
+ "transformer.h.33.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00004.bin",
229
+ "transformer.h.33.self_attention.dense.weight": "pytorch_model-00004-of-00004.bin",
230
+ "transformer.h.33.self_attention.query_key_value.weight": "pytorch_model-00004-of-00004.bin",
231
+ "transformer.h.34.ln_attn.bias": "pytorch_model-00004-of-00004.bin",
232
+ "transformer.h.34.ln_attn.weight": "pytorch_model-00004-of-00004.bin",
233
+ "transformer.h.34.ln_mlp.bias": "pytorch_model-00004-of-00004.bin",
234
+ "transformer.h.34.ln_mlp.weight": "pytorch_model-00004-of-00004.bin",
235
+ "transformer.h.34.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00004.bin",
236
+ "transformer.h.34.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00004.bin",
237
+ "transformer.h.34.self_attention.dense.weight": "pytorch_model-00004-of-00004.bin",
238
+ "transformer.h.34.self_attention.query_key_value.weight": "pytorch_model-00004-of-00004.bin",
239
+ "transformer.h.35.ln_attn.bias": "pytorch_model-00004-of-00004.bin",
240
+ "transformer.h.35.ln_attn.weight": "pytorch_model-00004-of-00004.bin",
241
+ "transformer.h.35.ln_mlp.bias": "pytorch_model-00004-of-00004.bin",
242
+ "transformer.h.35.ln_mlp.weight": "pytorch_model-00004-of-00004.bin",
243
+ "transformer.h.35.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00004.bin",
244
+ "transformer.h.35.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00004.bin",
245
+ "transformer.h.35.self_attention.dense.weight": "pytorch_model-00004-of-00004.bin",
246
+ "transformer.h.35.self_attention.query_key_value.weight": "pytorch_model-00004-of-00004.bin",
247
+ "transformer.h.36.ln_attn.bias": "pytorch_model-00004-of-00004.bin",
248
+ "transformer.h.36.ln_attn.weight": "pytorch_model-00004-of-00004.bin",
249
+ "transformer.h.36.ln_mlp.bias": "pytorch_model-00004-of-00004.bin",
250
+ "transformer.h.36.ln_mlp.weight": "pytorch_model-00004-of-00004.bin",
251
+ "transformer.h.36.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00004.bin",
252
+ "transformer.h.36.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00004.bin",
253
+ "transformer.h.36.self_attention.dense.weight": "pytorch_model-00004-of-00004.bin",
254
+ "transformer.h.36.self_attention.query_key_value.weight": "pytorch_model-00004-of-00004.bin",
255
+ "transformer.h.37.ln_attn.bias": "pytorch_model-00004-of-00004.bin",
256
+ "transformer.h.37.ln_attn.weight": "pytorch_model-00004-of-00004.bin",
257
+ "transformer.h.37.ln_mlp.bias": "pytorch_model-00004-of-00004.bin",
258
+ "transformer.h.37.ln_mlp.weight": "pytorch_model-00004-of-00004.bin",
259
+ "transformer.h.37.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00004.bin",
260
+ "transformer.h.37.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00004.bin",
261
+ "transformer.h.37.self_attention.dense.weight": "pytorch_model-00004-of-00004.bin",
262
+ "transformer.h.37.self_attention.query_key_value.weight": "pytorch_model-00004-of-00004.bin",
263
+ "transformer.h.38.ln_attn.bias": "pytorch_model-00004-of-00004.bin",
264
+ "transformer.h.38.ln_attn.weight": "pytorch_model-00004-of-00004.bin",
265
+ "transformer.h.38.ln_mlp.bias": "pytorch_model-00004-of-00004.bin",
266
+ "transformer.h.38.ln_mlp.weight": "pytorch_model-00004-of-00004.bin",
267
+ "transformer.h.38.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00004.bin",
268
+ "transformer.h.38.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00004.bin",
269
+ "transformer.h.38.self_attention.dense.weight": "pytorch_model-00004-of-00004.bin",
270
+ "transformer.h.38.self_attention.query_key_value.weight": "pytorch_model-00004-of-00004.bin",
271
+ "transformer.h.39.ln_attn.bias": "pytorch_model-00004-of-00004.bin",
272
+ "transformer.h.39.ln_attn.weight": "pytorch_model-00004-of-00004.bin",
273
+ "transformer.h.39.ln_mlp.bias": "pytorch_model-00004-of-00004.bin",
274
+ "transformer.h.39.ln_mlp.weight": "pytorch_model-00004-of-00004.bin",
275
+ "transformer.h.39.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00004.bin",
276
+ "transformer.h.39.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00004.bin",
277
+ "transformer.h.39.self_attention.dense.weight": "pytorch_model-00004-of-00004.bin",
278
+ "transformer.h.39.self_attention.query_key_value.weight": "pytorch_model-00004-of-00004.bin",
279
+ "transformer.h.4.ln_attn.bias": "pytorch_model-00001-of-00004.bin",
280
+ "transformer.h.4.ln_attn.weight": "pytorch_model-00001-of-00004.bin",
281
+ "transformer.h.4.ln_mlp.bias": "pytorch_model-00001-of-00004.bin",
282
+ "transformer.h.4.ln_mlp.weight": "pytorch_model-00001-of-00004.bin",
283
+ "transformer.h.4.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00004.bin",
284
+ "transformer.h.4.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00004.bin",
285
+ "transformer.h.4.self_attention.dense.weight": "pytorch_model-00001-of-00004.bin",
286
+ "transformer.h.4.self_attention.query_key_value.weight": "pytorch_model-00001-of-00004.bin",
287
+ "transformer.h.40.ln_attn.bias": "pytorch_model-00004-of-00004.bin",
288
+ "transformer.h.40.ln_attn.weight": "pytorch_model-00004-of-00004.bin",
289
+ "transformer.h.40.ln_mlp.bias": "pytorch_model-00004-of-00004.bin",
290
+ "transformer.h.40.ln_mlp.weight": "pytorch_model-00004-of-00004.bin",
291
+ "transformer.h.40.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00004.bin",
292
+ "transformer.h.40.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00004.bin",
293
+ "transformer.h.40.self_attention.dense.weight": "pytorch_model-00004-of-00004.bin",
294
+ "transformer.h.40.self_attention.query_key_value.weight": "pytorch_model-00004-of-00004.bin",
295
+ "transformer.h.41.ln_attn.bias": "pytorch_model-00004-of-00004.bin",
296
+ "transformer.h.41.ln_attn.weight": "pytorch_model-00004-of-00004.bin",
297
+ "transformer.h.41.ln_mlp.bias": "pytorch_model-00004-of-00004.bin",
298
+ "transformer.h.41.ln_mlp.weight": "pytorch_model-00004-of-00004.bin",
299
+ "transformer.h.41.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00004.bin",
300
+ "transformer.h.41.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00004.bin",
301
+ "transformer.h.41.self_attention.dense.weight": "pytorch_model-00004-of-00004.bin",
302
+ "transformer.h.41.self_attention.query_key_value.weight": "pytorch_model-00004-of-00004.bin",
303
+ "transformer.h.42.ln_attn.bias": "pytorch_model-00004-of-00004.bin",
304
+ "transformer.h.42.ln_attn.weight": "pytorch_model-00004-of-00004.bin",
305
+ "transformer.h.42.ln_mlp.bias": "pytorch_model-00004-of-00004.bin",
306
+ "transformer.h.42.ln_mlp.weight": "pytorch_model-00004-of-00004.bin",
307
+ "transformer.h.42.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00004.bin",
308
+ "transformer.h.42.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00004.bin",
309
+ "transformer.h.42.self_attention.dense.weight": "pytorch_model-00004-of-00004.bin",
310
+ "transformer.h.42.self_attention.query_key_value.weight": "pytorch_model-00004-of-00004.bin",
311
+ "transformer.h.43.ln_attn.bias": "pytorch_model-00004-of-00004.bin",
312
+ "transformer.h.43.ln_attn.weight": "pytorch_model-00004-of-00004.bin",
313
+ "transformer.h.43.ln_mlp.bias": "pytorch_model-00004-of-00004.bin",
314
+ "transformer.h.43.ln_mlp.weight": "pytorch_model-00004-of-00004.bin",
315
+ "transformer.h.43.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00004.bin",
316
+ "transformer.h.43.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00004.bin",
317
+ "transformer.h.43.self_attention.dense.weight": "pytorch_model-00004-of-00004.bin",
318
+ "transformer.h.43.self_attention.query_key_value.weight": "pytorch_model-00004-of-00004.bin",
319
+ "transformer.h.44.ln_attn.bias": "pytorch_model-00004-of-00004.bin",
320
+ "transformer.h.44.ln_attn.weight": "pytorch_model-00004-of-00004.bin",
321
+ "transformer.h.44.ln_mlp.bias": "pytorch_model-00004-of-00004.bin",
322
+ "transformer.h.44.ln_mlp.weight": "pytorch_model-00004-of-00004.bin",
323
+ "transformer.h.44.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00004.bin",
324
+ "transformer.h.44.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00004.bin",
325
+ "transformer.h.44.self_attention.dense.weight": "pytorch_model-00004-of-00004.bin",
326
+ "transformer.h.44.self_attention.query_key_value.weight": "pytorch_model-00004-of-00004.bin",
327
+ "transformer.h.45.ln_attn.bias": "pytorch_model-00004-of-00004.bin",
328
+ "transformer.h.45.ln_attn.weight": "pytorch_model-00004-of-00004.bin",
329
+ "transformer.h.45.ln_mlp.bias": "pytorch_model-00004-of-00004.bin",
330
+ "transformer.h.45.ln_mlp.weight": "pytorch_model-00004-of-00004.bin",
331
+ "transformer.h.45.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00004.bin",
332
+ "transformer.h.45.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00004.bin",
333
+ "transformer.h.45.self_attention.dense.weight": "pytorch_model-00004-of-00004.bin",
334
+ "transformer.h.45.self_attention.query_key_value.weight": "pytorch_model-00004-of-00004.bin",
335
+ "transformer.h.46.ln_attn.bias": "pytorch_model-00004-of-00004.bin",
336
+ "transformer.h.46.ln_attn.weight": "pytorch_model-00004-of-00004.bin",
337
+ "transformer.h.46.ln_mlp.bias": "pytorch_model-00004-of-00004.bin",
338
+ "transformer.h.46.ln_mlp.weight": "pytorch_model-00004-of-00004.bin",
339
+ "transformer.h.46.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00004.bin",
340
+ "transformer.h.46.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00004.bin",
341
+ "transformer.h.46.self_attention.dense.weight": "pytorch_model-00004-of-00004.bin",
342
+ "transformer.h.46.self_attention.query_key_value.weight": "pytorch_model-00004-of-00004.bin",
343
+ "transformer.h.47.ln_attn.bias": "pytorch_model-00004-of-00004.bin",
344
+ "transformer.h.47.ln_attn.weight": "pytorch_model-00004-of-00004.bin",
345
+ "transformer.h.47.ln_mlp.bias": "pytorch_model-00004-of-00004.bin",
346
+ "transformer.h.47.ln_mlp.weight": "pytorch_model-00004-of-00004.bin",
347
+ "transformer.h.47.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00004.bin",
348
+ "transformer.h.47.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00004.bin",
349
+ "transformer.h.47.self_attention.dense.weight": "pytorch_model-00004-of-00004.bin",
350
+ "transformer.h.47.self_attention.query_key_value.weight": "pytorch_model-00004-of-00004.bin",
351
+ "transformer.h.48.ln_attn.bias": "pytorch_model-00004-of-00004.bin",
352
+ "transformer.h.48.ln_attn.weight": "pytorch_model-00004-of-00004.bin",
353
+ "transformer.h.48.ln_mlp.bias": "pytorch_model-00004-of-00004.bin",
354
+ "transformer.h.48.ln_mlp.weight": "pytorch_model-00004-of-00004.bin",
355
+ "transformer.h.48.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00004.bin",
356
+ "transformer.h.48.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00004.bin",
357
+ "transformer.h.48.self_attention.dense.weight": "pytorch_model-00004-of-00004.bin",
358
+ "transformer.h.48.self_attention.query_key_value.weight": "pytorch_model-00004-of-00004.bin",
359
+ "transformer.h.49.ln_attn.bias": "pytorch_model-00004-of-00004.bin",
360
+ "transformer.h.49.ln_attn.weight": "pytorch_model-00004-of-00004.bin",
361
+ "transformer.h.49.ln_mlp.bias": "pytorch_model-00004-of-00004.bin",
362
+ "transformer.h.49.ln_mlp.weight": "pytorch_model-00004-of-00004.bin",
363
+ "transformer.h.49.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00004.bin",
364
+ "transformer.h.49.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00004.bin",
365
+ "transformer.h.49.self_attention.dense.weight": "pytorch_model-00004-of-00004.bin",
366
+ "transformer.h.49.self_attention.query_key_value.weight": "pytorch_model-00004-of-00004.bin",
367
+ "transformer.h.5.ln_attn.bias": "pytorch_model-00001-of-00004.bin",
368
+ "transformer.h.5.ln_attn.weight": "pytorch_model-00001-of-00004.bin",
369
+ "transformer.h.5.ln_mlp.bias": "pytorch_model-00001-of-00004.bin",
370
+ "transformer.h.5.ln_mlp.weight": "pytorch_model-00001-of-00004.bin",
371
+ "transformer.h.5.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00004.bin",
372
+ "transformer.h.5.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00004.bin",
373
+ "transformer.h.5.self_attention.dense.weight": "pytorch_model-00001-of-00004.bin",
374
+ "transformer.h.5.self_attention.query_key_value.weight": "pytorch_model-00001-of-00004.bin",
375
+ "transformer.h.50.ln_attn.bias": "pytorch_model-00004-of-00004.bin",
376
+ "transformer.h.50.ln_attn.weight": "pytorch_model-00004-of-00004.bin",
377
+ "transformer.h.50.ln_mlp.bias": "pytorch_model-00004-of-00004.bin",
378
+ "transformer.h.50.ln_mlp.weight": "pytorch_model-00004-of-00004.bin",
379
+ "transformer.h.50.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00004.bin",
380
+ "transformer.h.50.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00004.bin",
381
+ "transformer.h.50.self_attention.dense.weight": "pytorch_model-00004-of-00004.bin",
382
+ "transformer.h.50.self_attention.query_key_value.weight": "pytorch_model-00004-of-00004.bin",
383
+ "transformer.h.51.ln_attn.bias": "pytorch_model-00004-of-00004.bin",
384
+ "transformer.h.51.ln_attn.weight": "pytorch_model-00004-of-00004.bin",
385
+ "transformer.h.51.ln_mlp.bias": "pytorch_model-00004-of-00004.bin",
386
+ "transformer.h.51.ln_mlp.weight": "pytorch_model-00004-of-00004.bin",
387
+ "transformer.h.51.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00004.bin",
388
+ "transformer.h.51.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00004.bin",
389
+ "transformer.h.51.self_attention.dense.weight": "pytorch_model-00004-of-00004.bin",
390
+ "transformer.h.51.self_attention.query_key_value.weight": "pytorch_model-00004-of-00004.bin",
391
+ "transformer.h.52.ln_attn.bias": "pytorch_model-00004-of-00004.bin",
392
+ "transformer.h.52.ln_attn.weight": "pytorch_model-00004-of-00004.bin",
393
+ "transformer.h.52.ln_mlp.bias": "pytorch_model-00004-of-00004.bin",
394
+ "transformer.h.52.ln_mlp.weight": "pytorch_model-00004-of-00004.bin",
395
+ "transformer.h.52.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00004.bin",
396
+ "transformer.h.52.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00004.bin",
397
+ "transformer.h.52.self_attention.dense.weight": "pytorch_model-00004-of-00004.bin",
398
+ "transformer.h.52.self_attention.query_key_value.weight": "pytorch_model-00004-of-00004.bin",
399
+ "transformer.h.53.ln_attn.bias": "pytorch_model-00004-of-00004.bin",
400
+ "transformer.h.53.ln_attn.weight": "pytorch_model-00004-of-00004.bin",
401
+ "transformer.h.53.ln_mlp.bias": "pytorch_model-00004-of-00004.bin",
402
+ "transformer.h.53.ln_mlp.weight": "pytorch_model-00004-of-00004.bin",
403
+ "transformer.h.53.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00004.bin",
404
+ "transformer.h.53.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00004.bin",
405
+ "transformer.h.53.self_attention.dense.weight": "pytorch_model-00004-of-00004.bin",
406
+ "transformer.h.53.self_attention.query_key_value.weight": "pytorch_model-00004-of-00004.bin",
407
+ "transformer.h.54.ln_attn.bias": "pytorch_model-00004-of-00004.bin",
408
+ "transformer.h.54.ln_attn.weight": "pytorch_model-00004-of-00004.bin",
409
+ "transformer.h.54.ln_mlp.bias": "pytorch_model-00004-of-00004.bin",
410
+ "transformer.h.54.ln_mlp.weight": "pytorch_model-00004-of-00004.bin",
411
+ "transformer.h.54.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00004.bin",
412
+ "transformer.h.54.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00004.bin",
413
+ "transformer.h.54.self_attention.dense.weight": "pytorch_model-00004-of-00004.bin",
414
+ "transformer.h.54.self_attention.query_key_value.weight": "pytorch_model-00004-of-00004.bin",
415
+ "transformer.h.55.ln_attn.bias": "pytorch_model-00004-of-00004.bin",
416
+ "transformer.h.55.ln_attn.weight": "pytorch_model-00004-of-00004.bin",
417
+ "transformer.h.55.ln_mlp.bias": "pytorch_model-00004-of-00004.bin",
418
+ "transformer.h.55.ln_mlp.weight": "pytorch_model-00004-of-00004.bin",
419
+ "transformer.h.55.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00004.bin",
420
+ "transformer.h.55.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00004.bin",
421
+ "transformer.h.55.self_attention.dense.weight": "pytorch_model-00004-of-00004.bin",
422
+ "transformer.h.55.self_attention.query_key_value.weight": "pytorch_model-00004-of-00004.bin",
423
+ "transformer.h.56.ln_attn.bias": "pytorch_model-00004-of-00004.bin",
424
+ "transformer.h.56.ln_attn.weight": "pytorch_model-00004-of-00004.bin",
425
+ "transformer.h.56.ln_mlp.bias": "pytorch_model-00004-of-00004.bin",
426
+ "transformer.h.56.ln_mlp.weight": "pytorch_model-00004-of-00004.bin",
427
+ "transformer.h.56.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00004.bin",
428
+ "transformer.h.56.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00004.bin",
429
+ "transformer.h.56.self_attention.dense.weight": "pytorch_model-00004-of-00004.bin",
430
+ "transformer.h.56.self_attention.query_key_value.weight": "pytorch_model-00004-of-00004.bin",
431
+ "transformer.h.57.ln_attn.bias": "pytorch_model-00004-of-00004.bin",
432
+ "transformer.h.57.ln_attn.weight": "pytorch_model-00004-of-00004.bin",
433
+ "transformer.h.57.ln_mlp.bias": "pytorch_model-00004-of-00004.bin",
434
+ "transformer.h.57.ln_mlp.weight": "pytorch_model-00004-of-00004.bin",
435
+ "transformer.h.57.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00004.bin",
436
+ "transformer.h.57.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00004.bin",
437
+ "transformer.h.57.self_attention.dense.weight": "pytorch_model-00004-of-00004.bin",
438
+ "transformer.h.57.self_attention.query_key_value.weight": "pytorch_model-00004-of-00004.bin",
439
+ "transformer.h.58.ln_attn.bias": "pytorch_model-00004-of-00004.bin",
440
+ "transformer.h.58.ln_attn.weight": "pytorch_model-00004-of-00004.bin",
441
+ "transformer.h.58.ln_mlp.bias": "pytorch_model-00004-of-00004.bin",
442
+ "transformer.h.58.ln_mlp.weight": "pytorch_model-00004-of-00004.bin",
443
+ "transformer.h.58.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00004.bin",
444
+ "transformer.h.58.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00004.bin",
445
+ "transformer.h.58.self_attention.dense.weight": "pytorch_model-00004-of-00004.bin",
446
+ "transformer.h.58.self_attention.query_key_value.weight": "pytorch_model-00004-of-00004.bin",
447
+ "transformer.h.59.ln_attn.bias": "pytorch_model-00004-of-00004.bin",
448
+ "transformer.h.59.ln_attn.weight": "pytorch_model-00004-of-00004.bin",
449
+ "transformer.h.59.ln_mlp.bias": "pytorch_model-00004-of-00004.bin",
450
+ "transformer.h.59.ln_mlp.weight": "pytorch_model-00004-of-00004.bin",
451
+ "transformer.h.59.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00004.bin",
452
+ "transformer.h.59.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00004.bin",
453
+ "transformer.h.59.self_attention.dense.weight": "pytorch_model-00004-of-00004.bin",
454
+ "transformer.h.59.self_attention.query_key_value.weight": "pytorch_model-00004-of-00004.bin",
455
+ "transformer.h.6.ln_attn.bias": "pytorch_model-00002-of-00004.bin",
456
+ "transformer.h.6.ln_attn.weight": "pytorch_model-00002-of-00004.bin",
457
+ "transformer.h.6.ln_mlp.bias": "pytorch_model-00002-of-00004.bin",
458
+ "transformer.h.6.ln_mlp.weight": "pytorch_model-00002-of-00004.bin",
459
+ "transformer.h.6.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00004.bin",
460
+ "transformer.h.6.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00004.bin",
461
+ "transformer.h.6.self_attention.dense.weight": "pytorch_model-00001-of-00004.bin",
462
+ "transformer.h.6.self_attention.query_key_value.weight": "pytorch_model-00001-of-00004.bin",
463
+ "transformer.h.7.ln_attn.bias": "pytorch_model-00002-of-00004.bin",
464
+ "transformer.h.7.ln_attn.weight": "pytorch_model-00002-of-00004.bin",
465
+ "transformer.h.7.ln_mlp.bias": "pytorch_model-00002-of-00004.bin",
466
+ "transformer.h.7.ln_mlp.weight": "pytorch_model-00002-of-00004.bin",
467
+ "transformer.h.7.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00004.bin",
468
+ "transformer.h.7.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00004.bin",
469
+ "transformer.h.7.self_attention.dense.weight": "pytorch_model-00002-of-00004.bin",
470
+ "transformer.h.7.self_attention.query_key_value.weight": "pytorch_model-00002-of-00004.bin",
471
+ "transformer.h.8.ln_attn.bias": "pytorch_model-00002-of-00004.bin",
472
+ "transformer.h.8.ln_attn.weight": "pytorch_model-00002-of-00004.bin",
473
+ "transformer.h.8.ln_mlp.bias": "pytorch_model-00002-of-00004.bin",
474
+ "transformer.h.8.ln_mlp.weight": "pytorch_model-00002-of-00004.bin",
475
+ "transformer.h.8.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00004.bin",
476
+ "transformer.h.8.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00004.bin",
477
+ "transformer.h.8.self_attention.dense.weight": "pytorch_model-00002-of-00004.bin",
478
+ "transformer.h.8.self_attention.query_key_value.weight": "pytorch_model-00002-of-00004.bin",
479
+ "transformer.h.9.ln_attn.bias": "pytorch_model-00002-of-00004.bin",
480
+ "transformer.h.9.ln_attn.weight": "pytorch_model-00002-of-00004.bin",
481
+ "transformer.h.9.ln_mlp.bias": "pytorch_model-00002-of-00004.bin",
482
+ "transformer.h.9.ln_mlp.weight": "pytorch_model-00002-of-00004.bin",
483
+ "transformer.h.9.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00004.bin",
484
+ "transformer.h.9.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00004.bin",
485
+ "transformer.h.9.self_attention.dense.weight": "pytorch_model-00002-of-00004.bin",
486
+ "transformer.h.9.self_attention.query_key_value.weight": "pytorch_model-00002-of-00004.bin",
487
+ "transformer.ln_f.bias": "pytorch_model-00004-of-00004.bin",
488
+ "transformer.ln_f.weight": "pytorch_model-00004-of-00004.bin",
489
+ "transformer.word_embeddings.weight": "pytorch_model-00001-of-00004.bin"
490
+ }
491
+ }