samos123 commited on
Commit
a8a8d4b
1 Parent(s): 174dcec

Upload RWForCausalLM

Browse files
config.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/model/saved/",
3
+ "alibi": false,
4
+ "apply_residual_connection_post_layernorm": false,
5
+ "architectures": [
6
+ "RWForCausalLM"
7
+ ],
8
+ "attention_dropout": 0.0,
9
+ "auto_map": {
10
+ "AutoConfig": "configuration_RW.RWConfig",
11
+ "AutoModel": "modelling_RW.RWModel",
12
+ "AutoModelForCausalLM": "modelling_RW.RWForCausalLM",
13
+ "AutoModelForQuestionAnswering": "modelling_RW.RWForQuestionAnswering",
14
+ "AutoModelForSequenceClassification": "modelling_RW.RWForSequenceClassification",
15
+ "AutoModelForTokenClassification": "modelling_RW.RWForTokenClassification"
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": "RefinedWeb",
25
+ "n_head": 128,
26
+ "n_head_kv": 8,
27
+ "n_layer": 60,
28
+ "parallel_attn": true,
29
+ "quantization_config": {
30
+ "bnb_4bit_compute_dtype": "float32",
31
+ "bnb_4bit_quant_type": "fp4",
32
+ "bnb_4bit_use_double_quant": false,
33
+ "llm_int8_enable_fp32_cpu_offload": false,
34
+ "llm_int8_has_fp16_weight": false,
35
+ "llm_int8_skip_modules": null,
36
+ "llm_int8_threshold": 6.0,
37
+ "load_in_4bit": false,
38
+ "load_in_8bit": true
39
+ },
40
+ "torch_dtype": "float16",
41
+ "transformers_version": "4.31.0.dev0",
42
+ "use_cache": true,
43
+ "vocab_size": 65024
44
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "transformers_version": "4.31.0.dev0"
6
+ }
pytorch_model-00001-of-00005.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:750191fb098a1eb8f78496d9815aa0d88a74a3e7326b7d72ad9ed80b850b44de
3
+ size 9978102420
pytorch_model-00002-of-00005.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:34116d6bd6ca40b780168569acf58ad4fef63ae6ed8358128d896b35e1caa888
3
+ size 9852637003
pytorch_model-00003-of-00005.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:523a29775f781d28f402dc34921dff4de25baa5098481f8967cbb509713b5e57
3
+ size 9928140629
pytorch_model-00004-of-00005.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d1f4dd0a4e5ba94744799fbb502f0f6cec8cce1c47d274c7b1f754f459211890
3
+ size 9785494557
pytorch_model-00005-of-00005.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:322b9910844898b246a3e694290d23a2b0744a25e7c4a33207280c603ed9bb97
3
+ size 2307843551
pytorch_model.bin.index.json ADDED
@@ -0,0 +1,731 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 41851961344
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "pytorch_model-00001-of-00005.bin",
7
+ "transformer.h.0.ln_attn.bias": "pytorch_model-00001-of-00005.bin",
8
+ "transformer.h.0.ln_attn.weight": "pytorch_model-00001-of-00005.bin",
9
+ "transformer.h.0.ln_mlp.bias": "pytorch_model-00001-of-00005.bin",
10
+ "transformer.h.0.ln_mlp.weight": "pytorch_model-00001-of-00005.bin",
11
+ "transformer.h.0.mlp.dense_4h_to_h.SCB": "pytorch_model-00001-of-00005.bin",
12
+ "transformer.h.0.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00005.bin",
13
+ "transformer.h.0.mlp.dense_h_to_4h.SCB": "pytorch_model-00001-of-00005.bin",
14
+ "transformer.h.0.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00005.bin",
15
+ "transformer.h.0.self_attention.dense.SCB": "pytorch_model-00001-of-00005.bin",
16
+ "transformer.h.0.self_attention.dense.weight": "pytorch_model-00001-of-00005.bin",
17
+ "transformer.h.0.self_attention.query_key_value.SCB": "pytorch_model-00001-of-00005.bin",
18
+ "transformer.h.0.self_attention.query_key_value.weight": "pytorch_model-00001-of-00005.bin",
19
+ "transformer.h.1.ln_attn.bias": "pytorch_model-00001-of-00005.bin",
20
+ "transformer.h.1.ln_attn.weight": "pytorch_model-00001-of-00005.bin",
21
+ "transformer.h.1.ln_mlp.bias": "pytorch_model-00001-of-00005.bin",
22
+ "transformer.h.1.ln_mlp.weight": "pytorch_model-00001-of-00005.bin",
23
+ "transformer.h.1.mlp.dense_4h_to_h.SCB": "pytorch_model-00001-of-00005.bin",
24
+ "transformer.h.1.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00005.bin",
25
+ "transformer.h.1.mlp.dense_h_to_4h.SCB": "pytorch_model-00001-of-00005.bin",
26
+ "transformer.h.1.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00005.bin",
27
+ "transformer.h.1.self_attention.dense.SCB": "pytorch_model-00001-of-00005.bin",
28
+ "transformer.h.1.self_attention.dense.weight": "pytorch_model-00001-of-00005.bin",
29
+ "transformer.h.1.self_attention.query_key_value.SCB": "pytorch_model-00001-of-00005.bin",
30
+ "transformer.h.1.self_attention.query_key_value.weight": "pytorch_model-00001-of-00005.bin",
31
+ "transformer.h.10.ln_attn.bias": "pytorch_model-00001-of-00005.bin",
32
+ "transformer.h.10.ln_attn.weight": "pytorch_model-00001-of-00005.bin",
33
+ "transformer.h.10.ln_mlp.bias": "pytorch_model-00001-of-00005.bin",
34
+ "transformer.h.10.ln_mlp.weight": "pytorch_model-00001-of-00005.bin",
35
+ "transformer.h.10.mlp.dense_4h_to_h.SCB": "pytorch_model-00001-of-00005.bin",
36
+ "transformer.h.10.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00005.bin",
37
+ "transformer.h.10.mlp.dense_h_to_4h.SCB": "pytorch_model-00001-of-00005.bin",
38
+ "transformer.h.10.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00005.bin",
39
+ "transformer.h.10.self_attention.dense.SCB": "pytorch_model-00001-of-00005.bin",
40
+ "transformer.h.10.self_attention.dense.weight": "pytorch_model-00001-of-00005.bin",
41
+ "transformer.h.10.self_attention.query_key_value.SCB": "pytorch_model-00001-of-00005.bin",
42
+ "transformer.h.10.self_attention.query_key_value.weight": "pytorch_model-00001-of-00005.bin",
43
+ "transformer.h.11.ln_attn.bias": "pytorch_model-00001-of-00005.bin",
44
+ "transformer.h.11.ln_attn.weight": "pytorch_model-00001-of-00005.bin",
45
+ "transformer.h.11.ln_mlp.bias": "pytorch_model-00001-of-00005.bin",
46
+ "transformer.h.11.ln_mlp.weight": "pytorch_model-00001-of-00005.bin",
47
+ "transformer.h.11.mlp.dense_4h_to_h.SCB": "pytorch_model-00001-of-00005.bin",
48
+ "transformer.h.11.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00005.bin",
49
+ "transformer.h.11.mlp.dense_h_to_4h.SCB": "pytorch_model-00001-of-00005.bin",
50
+ "transformer.h.11.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00005.bin",
51
+ "transformer.h.11.self_attention.dense.SCB": "pytorch_model-00001-of-00005.bin",
52
+ "transformer.h.11.self_attention.dense.weight": "pytorch_model-00001-of-00005.bin",
53
+ "transformer.h.11.self_attention.query_key_value.SCB": "pytorch_model-00001-of-00005.bin",
54
+ "transformer.h.11.self_attention.query_key_value.weight": "pytorch_model-00001-of-00005.bin",
55
+ "transformer.h.12.ln_attn.bias": "pytorch_model-00001-of-00005.bin",
56
+ "transformer.h.12.ln_attn.weight": "pytorch_model-00001-of-00005.bin",
57
+ "transformer.h.12.ln_mlp.bias": "pytorch_model-00001-of-00005.bin",
58
+ "transformer.h.12.ln_mlp.weight": "pytorch_model-00001-of-00005.bin",
59
+ "transformer.h.12.mlp.dense_4h_to_h.SCB": "pytorch_model-00001-of-00005.bin",
60
+ "transformer.h.12.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00005.bin",
61
+ "transformer.h.12.mlp.dense_h_to_4h.SCB": "pytorch_model-00001-of-00005.bin",
62
+ "transformer.h.12.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00005.bin",
63
+ "transformer.h.12.self_attention.dense.SCB": "pytorch_model-00001-of-00005.bin",
64
+ "transformer.h.12.self_attention.dense.weight": "pytorch_model-00001-of-00005.bin",
65
+ "transformer.h.12.self_attention.query_key_value.SCB": "pytorch_model-00001-of-00005.bin",
66
+ "transformer.h.12.self_attention.query_key_value.weight": "pytorch_model-00001-of-00005.bin",
67
+ "transformer.h.13.ln_attn.bias": "pytorch_model-00001-of-00005.bin",
68
+ "transformer.h.13.ln_attn.weight": "pytorch_model-00001-of-00005.bin",
69
+ "transformer.h.13.ln_mlp.bias": "pytorch_model-00001-of-00005.bin",
70
+ "transformer.h.13.ln_mlp.weight": "pytorch_model-00001-of-00005.bin",
71
+ "transformer.h.13.mlp.dense_4h_to_h.SCB": "pytorch_model-00002-of-00005.bin",
72
+ "transformer.h.13.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00005.bin",
73
+ "transformer.h.13.mlp.dense_h_to_4h.SCB": "pytorch_model-00002-of-00005.bin",
74
+ "transformer.h.13.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00005.bin",
75
+ "transformer.h.13.self_attention.dense.SCB": "pytorch_model-00002-of-00005.bin",
76
+ "transformer.h.13.self_attention.dense.weight": "pytorch_model-00002-of-00005.bin",
77
+ "transformer.h.13.self_attention.query_key_value.SCB": "pytorch_model-00001-of-00005.bin",
78
+ "transformer.h.13.self_attention.query_key_value.weight": "pytorch_model-00001-of-00005.bin",
79
+ "transformer.h.14.ln_attn.bias": "pytorch_model-00002-of-00005.bin",
80
+ "transformer.h.14.ln_attn.weight": "pytorch_model-00002-of-00005.bin",
81
+ "transformer.h.14.ln_mlp.bias": "pytorch_model-00002-of-00005.bin",
82
+ "transformer.h.14.ln_mlp.weight": "pytorch_model-00002-of-00005.bin",
83
+ "transformer.h.14.mlp.dense_4h_to_h.SCB": "pytorch_model-00002-of-00005.bin",
84
+ "transformer.h.14.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00005.bin",
85
+ "transformer.h.14.mlp.dense_h_to_4h.SCB": "pytorch_model-00002-of-00005.bin",
86
+ "transformer.h.14.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00005.bin",
87
+ "transformer.h.14.self_attention.dense.SCB": "pytorch_model-00002-of-00005.bin",
88
+ "transformer.h.14.self_attention.dense.weight": "pytorch_model-00002-of-00005.bin",
89
+ "transformer.h.14.self_attention.query_key_value.SCB": "pytorch_model-00002-of-00005.bin",
90
+ "transformer.h.14.self_attention.query_key_value.weight": "pytorch_model-00002-of-00005.bin",
91
+ "transformer.h.15.ln_attn.bias": "pytorch_model-00002-of-00005.bin",
92
+ "transformer.h.15.ln_attn.weight": "pytorch_model-00002-of-00005.bin",
93
+ "transformer.h.15.ln_mlp.bias": "pytorch_model-00002-of-00005.bin",
94
+ "transformer.h.15.ln_mlp.weight": "pytorch_model-00002-of-00005.bin",
95
+ "transformer.h.15.mlp.dense_4h_to_h.SCB": "pytorch_model-00002-of-00005.bin",
96
+ "transformer.h.15.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00005.bin",
97
+ "transformer.h.15.mlp.dense_h_to_4h.SCB": "pytorch_model-00002-of-00005.bin",
98
+ "transformer.h.15.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00005.bin",
99
+ "transformer.h.15.self_attention.dense.SCB": "pytorch_model-00002-of-00005.bin",
100
+ "transformer.h.15.self_attention.dense.weight": "pytorch_model-00002-of-00005.bin",
101
+ "transformer.h.15.self_attention.query_key_value.SCB": "pytorch_model-00002-of-00005.bin",
102
+ "transformer.h.15.self_attention.query_key_value.weight": "pytorch_model-00002-of-00005.bin",
103
+ "transformer.h.16.ln_attn.bias": "pytorch_model-00002-of-00005.bin",
104
+ "transformer.h.16.ln_attn.weight": "pytorch_model-00002-of-00005.bin",
105
+ "transformer.h.16.ln_mlp.bias": "pytorch_model-00002-of-00005.bin",
106
+ "transformer.h.16.ln_mlp.weight": "pytorch_model-00002-of-00005.bin",
107
+ "transformer.h.16.mlp.dense_4h_to_h.SCB": "pytorch_model-00002-of-00005.bin",
108
+ "transformer.h.16.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00005.bin",
109
+ "transformer.h.16.mlp.dense_h_to_4h.SCB": "pytorch_model-00002-of-00005.bin",
110
+ "transformer.h.16.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00005.bin",
111
+ "transformer.h.16.self_attention.dense.SCB": "pytorch_model-00002-of-00005.bin",
112
+ "transformer.h.16.self_attention.dense.weight": "pytorch_model-00002-of-00005.bin",
113
+ "transformer.h.16.self_attention.query_key_value.SCB": "pytorch_model-00002-of-00005.bin",
114
+ "transformer.h.16.self_attention.query_key_value.weight": "pytorch_model-00002-of-00005.bin",
115
+ "transformer.h.17.ln_attn.bias": "pytorch_model-00002-of-00005.bin",
116
+ "transformer.h.17.ln_attn.weight": "pytorch_model-00002-of-00005.bin",
117
+ "transformer.h.17.ln_mlp.bias": "pytorch_model-00002-of-00005.bin",
118
+ "transformer.h.17.ln_mlp.weight": "pytorch_model-00002-of-00005.bin",
119
+ "transformer.h.17.mlp.dense_4h_to_h.SCB": "pytorch_model-00002-of-00005.bin",
120
+ "transformer.h.17.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00005.bin",
121
+ "transformer.h.17.mlp.dense_h_to_4h.SCB": "pytorch_model-00002-of-00005.bin",
122
+ "transformer.h.17.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00005.bin",
123
+ "transformer.h.17.self_attention.dense.SCB": "pytorch_model-00002-of-00005.bin",
124
+ "transformer.h.17.self_attention.dense.weight": "pytorch_model-00002-of-00005.bin",
125
+ "transformer.h.17.self_attention.query_key_value.SCB": "pytorch_model-00002-of-00005.bin",
126
+ "transformer.h.17.self_attention.query_key_value.weight": "pytorch_model-00002-of-00005.bin",
127
+ "transformer.h.18.ln_attn.bias": "pytorch_model-00002-of-00005.bin",
128
+ "transformer.h.18.ln_attn.weight": "pytorch_model-00002-of-00005.bin",
129
+ "transformer.h.18.ln_mlp.bias": "pytorch_model-00002-of-00005.bin",
130
+ "transformer.h.18.ln_mlp.weight": "pytorch_model-00002-of-00005.bin",
131
+ "transformer.h.18.mlp.dense_4h_to_h.SCB": "pytorch_model-00002-of-00005.bin",
132
+ "transformer.h.18.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00005.bin",
133
+ "transformer.h.18.mlp.dense_h_to_4h.SCB": "pytorch_model-00002-of-00005.bin",
134
+ "transformer.h.18.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00005.bin",
135
+ "transformer.h.18.self_attention.dense.SCB": "pytorch_model-00002-of-00005.bin",
136
+ "transformer.h.18.self_attention.dense.weight": "pytorch_model-00002-of-00005.bin",
137
+ "transformer.h.18.self_attention.query_key_value.SCB": "pytorch_model-00002-of-00005.bin",
138
+ "transformer.h.18.self_attention.query_key_value.weight": "pytorch_model-00002-of-00005.bin",
139
+ "transformer.h.19.ln_attn.bias": "pytorch_model-00002-of-00005.bin",
140
+ "transformer.h.19.ln_attn.weight": "pytorch_model-00002-of-00005.bin",
141
+ "transformer.h.19.ln_mlp.bias": "pytorch_model-00002-of-00005.bin",
142
+ "transformer.h.19.ln_mlp.weight": "pytorch_model-00002-of-00005.bin",
143
+ "transformer.h.19.mlp.dense_4h_to_h.SCB": "pytorch_model-00002-of-00005.bin",
144
+ "transformer.h.19.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00005.bin",
145
+ "transformer.h.19.mlp.dense_h_to_4h.SCB": "pytorch_model-00002-of-00005.bin",
146
+ "transformer.h.19.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00005.bin",
147
+ "transformer.h.19.self_attention.dense.SCB": "pytorch_model-00002-of-00005.bin",
148
+ "transformer.h.19.self_attention.dense.weight": "pytorch_model-00002-of-00005.bin",
149
+ "transformer.h.19.self_attention.query_key_value.SCB": "pytorch_model-00002-of-00005.bin",
150
+ "transformer.h.19.self_attention.query_key_value.weight": "pytorch_model-00002-of-00005.bin",
151
+ "transformer.h.2.ln_attn.bias": "pytorch_model-00001-of-00005.bin",
152
+ "transformer.h.2.ln_attn.weight": "pytorch_model-00001-of-00005.bin",
153
+ "transformer.h.2.ln_mlp.bias": "pytorch_model-00001-of-00005.bin",
154
+ "transformer.h.2.ln_mlp.weight": "pytorch_model-00001-of-00005.bin",
155
+ "transformer.h.2.mlp.dense_4h_to_h.SCB": "pytorch_model-00001-of-00005.bin",
156
+ "transformer.h.2.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00005.bin",
157
+ "transformer.h.2.mlp.dense_h_to_4h.SCB": "pytorch_model-00001-of-00005.bin",
158
+ "transformer.h.2.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00005.bin",
159
+ "transformer.h.2.self_attention.dense.SCB": "pytorch_model-00001-of-00005.bin",
160
+ "transformer.h.2.self_attention.dense.weight": "pytorch_model-00001-of-00005.bin",
161
+ "transformer.h.2.self_attention.query_key_value.SCB": "pytorch_model-00001-of-00005.bin",
162
+ "transformer.h.2.self_attention.query_key_value.weight": "pytorch_model-00001-of-00005.bin",
163
+ "transformer.h.20.ln_attn.bias": "pytorch_model-00002-of-00005.bin",
164
+ "transformer.h.20.ln_attn.weight": "pytorch_model-00002-of-00005.bin",
165
+ "transformer.h.20.ln_mlp.bias": "pytorch_model-00002-of-00005.bin",
166
+ "transformer.h.20.ln_mlp.weight": "pytorch_model-00002-of-00005.bin",
167
+ "transformer.h.20.mlp.dense_4h_to_h.SCB": "pytorch_model-00002-of-00005.bin",
168
+ "transformer.h.20.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00005.bin",
169
+ "transformer.h.20.mlp.dense_h_to_4h.SCB": "pytorch_model-00002-of-00005.bin",
170
+ "transformer.h.20.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00005.bin",
171
+ "transformer.h.20.self_attention.dense.SCB": "pytorch_model-00002-of-00005.bin",
172
+ "transformer.h.20.self_attention.dense.weight": "pytorch_model-00002-of-00005.bin",
173
+ "transformer.h.20.self_attention.query_key_value.SCB": "pytorch_model-00002-of-00005.bin",
174
+ "transformer.h.20.self_attention.query_key_value.weight": "pytorch_model-00002-of-00005.bin",
175
+ "transformer.h.21.ln_attn.bias": "pytorch_model-00002-of-00005.bin",
176
+ "transformer.h.21.ln_attn.weight": "pytorch_model-00002-of-00005.bin",
177
+ "transformer.h.21.ln_mlp.bias": "pytorch_model-00002-of-00005.bin",
178
+ "transformer.h.21.ln_mlp.weight": "pytorch_model-00002-of-00005.bin",
179
+ "transformer.h.21.mlp.dense_4h_to_h.SCB": "pytorch_model-00002-of-00005.bin",
180
+ "transformer.h.21.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00005.bin",
181
+ "transformer.h.21.mlp.dense_h_to_4h.SCB": "pytorch_model-00002-of-00005.bin",
182
+ "transformer.h.21.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00005.bin",
183
+ "transformer.h.21.self_attention.dense.SCB": "pytorch_model-00002-of-00005.bin",
184
+ "transformer.h.21.self_attention.dense.weight": "pytorch_model-00002-of-00005.bin",
185
+ "transformer.h.21.self_attention.query_key_value.SCB": "pytorch_model-00002-of-00005.bin",
186
+ "transformer.h.21.self_attention.query_key_value.weight": "pytorch_model-00002-of-00005.bin",
187
+ "transformer.h.22.ln_attn.bias": "pytorch_model-00002-of-00005.bin",
188
+ "transformer.h.22.ln_attn.weight": "pytorch_model-00002-of-00005.bin",
189
+ "transformer.h.22.ln_mlp.bias": "pytorch_model-00002-of-00005.bin",
190
+ "transformer.h.22.ln_mlp.weight": "pytorch_model-00002-of-00005.bin",
191
+ "transformer.h.22.mlp.dense_4h_to_h.SCB": "pytorch_model-00002-of-00005.bin",
192
+ "transformer.h.22.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00005.bin",
193
+ "transformer.h.22.mlp.dense_h_to_4h.SCB": "pytorch_model-00002-of-00005.bin",
194
+ "transformer.h.22.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00005.bin",
195
+ "transformer.h.22.self_attention.dense.SCB": "pytorch_model-00002-of-00005.bin",
196
+ "transformer.h.22.self_attention.dense.weight": "pytorch_model-00002-of-00005.bin",
197
+ "transformer.h.22.self_attention.query_key_value.SCB": "pytorch_model-00002-of-00005.bin",
198
+ "transformer.h.22.self_attention.query_key_value.weight": "pytorch_model-00002-of-00005.bin",
199
+ "transformer.h.23.ln_attn.bias": "pytorch_model-00002-of-00005.bin",
200
+ "transformer.h.23.ln_attn.weight": "pytorch_model-00002-of-00005.bin",
201
+ "transformer.h.23.ln_mlp.bias": "pytorch_model-00002-of-00005.bin",
202
+ "transformer.h.23.ln_mlp.weight": "pytorch_model-00002-of-00005.bin",
203
+ "transformer.h.23.mlp.dense_4h_to_h.SCB": "pytorch_model-00002-of-00005.bin",
204
+ "transformer.h.23.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00005.bin",
205
+ "transformer.h.23.mlp.dense_h_to_4h.SCB": "pytorch_model-00002-of-00005.bin",
206
+ "transformer.h.23.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00005.bin",
207
+ "transformer.h.23.self_attention.dense.SCB": "pytorch_model-00002-of-00005.bin",
208
+ "transformer.h.23.self_attention.dense.weight": "pytorch_model-00002-of-00005.bin",
209
+ "transformer.h.23.self_attention.query_key_value.SCB": "pytorch_model-00002-of-00005.bin",
210
+ "transformer.h.23.self_attention.query_key_value.weight": "pytorch_model-00002-of-00005.bin",
211
+ "transformer.h.24.ln_attn.bias": "pytorch_model-00002-of-00005.bin",
212
+ "transformer.h.24.ln_attn.weight": "pytorch_model-00002-of-00005.bin",
213
+ "transformer.h.24.ln_mlp.bias": "pytorch_model-00002-of-00005.bin",
214
+ "transformer.h.24.ln_mlp.weight": "pytorch_model-00002-of-00005.bin",
215
+ "transformer.h.24.mlp.dense_4h_to_h.SCB": "pytorch_model-00002-of-00005.bin",
216
+ "transformer.h.24.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00005.bin",
217
+ "transformer.h.24.mlp.dense_h_to_4h.SCB": "pytorch_model-00002-of-00005.bin",
218
+ "transformer.h.24.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00005.bin",
219
+ "transformer.h.24.self_attention.dense.SCB": "pytorch_model-00002-of-00005.bin",
220
+ "transformer.h.24.self_attention.dense.weight": "pytorch_model-00002-of-00005.bin",
221
+ "transformer.h.24.self_attention.query_key_value.SCB": "pytorch_model-00002-of-00005.bin",
222
+ "transformer.h.24.self_attention.query_key_value.weight": "pytorch_model-00002-of-00005.bin",
223
+ "transformer.h.25.ln_attn.bias": "pytorch_model-00002-of-00005.bin",
224
+ "transformer.h.25.ln_attn.weight": "pytorch_model-00002-of-00005.bin",
225
+ "transformer.h.25.ln_mlp.bias": "pytorch_model-00002-of-00005.bin",
226
+ "transformer.h.25.ln_mlp.weight": "pytorch_model-00002-of-00005.bin",
227
+ "transformer.h.25.mlp.dense_4h_to_h.SCB": "pytorch_model-00002-of-00005.bin",
228
+ "transformer.h.25.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00005.bin",
229
+ "transformer.h.25.mlp.dense_h_to_4h.SCB": "pytorch_model-00002-of-00005.bin",
230
+ "transformer.h.25.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00005.bin",
231
+ "transformer.h.25.self_attention.dense.SCB": "pytorch_model-00002-of-00005.bin",
232
+ "transformer.h.25.self_attention.dense.weight": "pytorch_model-00002-of-00005.bin",
233
+ "transformer.h.25.self_attention.query_key_value.SCB": "pytorch_model-00002-of-00005.bin",
234
+ "transformer.h.25.self_attention.query_key_value.weight": "pytorch_model-00002-of-00005.bin",
235
+ "transformer.h.26.ln_attn.bias": "pytorch_model-00002-of-00005.bin",
236
+ "transformer.h.26.ln_attn.weight": "pytorch_model-00002-of-00005.bin",
237
+ "transformer.h.26.ln_mlp.bias": "pytorch_model-00002-of-00005.bin",
238
+ "transformer.h.26.ln_mlp.weight": "pytorch_model-00002-of-00005.bin",
239
+ "transformer.h.26.mlp.dense_4h_to_h.SCB": "pytorch_model-00002-of-00005.bin",
240
+ "transformer.h.26.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00005.bin",
241
+ "transformer.h.26.mlp.dense_h_to_4h.SCB": "pytorch_model-00002-of-00005.bin",
242
+ "transformer.h.26.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00005.bin",
243
+ "transformer.h.26.self_attention.dense.SCB": "pytorch_model-00002-of-00005.bin",
244
+ "transformer.h.26.self_attention.dense.weight": "pytorch_model-00002-of-00005.bin",
245
+ "transformer.h.26.self_attention.query_key_value.SCB": "pytorch_model-00002-of-00005.bin",
246
+ "transformer.h.26.self_attention.query_key_value.weight": "pytorch_model-00002-of-00005.bin",
247
+ "transformer.h.27.ln_attn.bias": "pytorch_model-00002-of-00005.bin",
248
+ "transformer.h.27.ln_attn.weight": "pytorch_model-00002-of-00005.bin",
249
+ "transformer.h.27.ln_mlp.bias": "pytorch_model-00002-of-00005.bin",
250
+ "transformer.h.27.ln_mlp.weight": "pytorch_model-00002-of-00005.bin",
251
+ "transformer.h.27.mlp.dense_4h_to_h.SCB": "pytorch_model-00003-of-00005.bin",
252
+ "transformer.h.27.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00005.bin",
253
+ "transformer.h.27.mlp.dense_h_to_4h.SCB": "pytorch_model-00002-of-00005.bin",
254
+ "transformer.h.27.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00005.bin",
255
+ "transformer.h.27.self_attention.dense.SCB": "pytorch_model-00002-of-00005.bin",
256
+ "transformer.h.27.self_attention.dense.weight": "pytorch_model-00002-of-00005.bin",
257
+ "transformer.h.27.self_attention.query_key_value.SCB": "pytorch_model-00002-of-00005.bin",
258
+ "transformer.h.27.self_attention.query_key_value.weight": "pytorch_model-00002-of-00005.bin",
259
+ "transformer.h.28.ln_attn.bias": "pytorch_model-00003-of-00005.bin",
260
+ "transformer.h.28.ln_attn.weight": "pytorch_model-00003-of-00005.bin",
261
+ "transformer.h.28.ln_mlp.bias": "pytorch_model-00003-of-00005.bin",
262
+ "transformer.h.28.ln_mlp.weight": "pytorch_model-00003-of-00005.bin",
263
+ "transformer.h.28.mlp.dense_4h_to_h.SCB": "pytorch_model-00003-of-00005.bin",
264
+ "transformer.h.28.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00005.bin",
265
+ "transformer.h.28.mlp.dense_h_to_4h.SCB": "pytorch_model-00003-of-00005.bin",
266
+ "transformer.h.28.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00005.bin",
267
+ "transformer.h.28.self_attention.dense.SCB": "pytorch_model-00003-of-00005.bin",
268
+ "transformer.h.28.self_attention.dense.weight": "pytorch_model-00003-of-00005.bin",
269
+ "transformer.h.28.self_attention.query_key_value.SCB": "pytorch_model-00003-of-00005.bin",
270
+ "transformer.h.28.self_attention.query_key_value.weight": "pytorch_model-00003-of-00005.bin",
271
+ "transformer.h.29.ln_attn.bias": "pytorch_model-00003-of-00005.bin",
272
+ "transformer.h.29.ln_attn.weight": "pytorch_model-00003-of-00005.bin",
273
+ "transformer.h.29.ln_mlp.bias": "pytorch_model-00003-of-00005.bin",
274
+ "transformer.h.29.ln_mlp.weight": "pytorch_model-00003-of-00005.bin",
275
+ "transformer.h.29.mlp.dense_4h_to_h.SCB": "pytorch_model-00003-of-00005.bin",
276
+ "transformer.h.29.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00005.bin",
277
+ "transformer.h.29.mlp.dense_h_to_4h.SCB": "pytorch_model-00003-of-00005.bin",
278
+ "transformer.h.29.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00005.bin",
279
+ "transformer.h.29.self_attention.dense.SCB": "pytorch_model-00003-of-00005.bin",
280
+ "transformer.h.29.self_attention.dense.weight": "pytorch_model-00003-of-00005.bin",
281
+ "transformer.h.29.self_attention.query_key_value.SCB": "pytorch_model-00003-of-00005.bin",
282
+ "transformer.h.29.self_attention.query_key_value.weight": "pytorch_model-00003-of-00005.bin",
283
+ "transformer.h.3.ln_attn.bias": "pytorch_model-00001-of-00005.bin",
284
+ "transformer.h.3.ln_attn.weight": "pytorch_model-00001-of-00005.bin",
285
+ "transformer.h.3.ln_mlp.bias": "pytorch_model-00001-of-00005.bin",
286
+ "transformer.h.3.ln_mlp.weight": "pytorch_model-00001-of-00005.bin",
287
+ "transformer.h.3.mlp.dense_4h_to_h.SCB": "pytorch_model-00001-of-00005.bin",
288
+ "transformer.h.3.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00005.bin",
289
+ "transformer.h.3.mlp.dense_h_to_4h.SCB": "pytorch_model-00001-of-00005.bin",
290
+ "transformer.h.3.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00005.bin",
291
+ "transformer.h.3.self_attention.dense.SCB": "pytorch_model-00001-of-00005.bin",
292
+ "transformer.h.3.self_attention.dense.weight": "pytorch_model-00001-of-00005.bin",
293
+ "transformer.h.3.self_attention.query_key_value.SCB": "pytorch_model-00001-of-00005.bin",
294
+ "transformer.h.3.self_attention.query_key_value.weight": "pytorch_model-00001-of-00005.bin",
295
+ "transformer.h.30.ln_attn.bias": "pytorch_model-00003-of-00005.bin",
296
+ "transformer.h.30.ln_attn.weight": "pytorch_model-00003-of-00005.bin",
297
+ "transformer.h.30.ln_mlp.bias": "pytorch_model-00003-of-00005.bin",
298
+ "transformer.h.30.ln_mlp.weight": "pytorch_model-00003-of-00005.bin",
299
+ "transformer.h.30.mlp.dense_4h_to_h.SCB": "pytorch_model-00003-of-00005.bin",
300
+ "transformer.h.30.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00005.bin",
301
+ "transformer.h.30.mlp.dense_h_to_4h.SCB": "pytorch_model-00003-of-00005.bin",
302
+ "transformer.h.30.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00005.bin",
303
+ "transformer.h.30.self_attention.dense.SCB": "pytorch_model-00003-of-00005.bin",
304
+ "transformer.h.30.self_attention.dense.weight": "pytorch_model-00003-of-00005.bin",
305
+ "transformer.h.30.self_attention.query_key_value.SCB": "pytorch_model-00003-of-00005.bin",
306
+ "transformer.h.30.self_attention.query_key_value.weight": "pytorch_model-00003-of-00005.bin",
307
+ "transformer.h.31.ln_attn.bias": "pytorch_model-00003-of-00005.bin",
308
+ "transformer.h.31.ln_attn.weight": "pytorch_model-00003-of-00005.bin",
309
+ "transformer.h.31.ln_mlp.bias": "pytorch_model-00003-of-00005.bin",
310
+ "transformer.h.31.ln_mlp.weight": "pytorch_model-00003-of-00005.bin",
311
+ "transformer.h.31.mlp.dense_4h_to_h.SCB": "pytorch_model-00003-of-00005.bin",
312
+ "transformer.h.31.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00005.bin",
313
+ "transformer.h.31.mlp.dense_h_to_4h.SCB": "pytorch_model-00003-of-00005.bin",
314
+ "transformer.h.31.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00005.bin",
315
+ "transformer.h.31.self_attention.dense.SCB": "pytorch_model-00003-of-00005.bin",
316
+ "transformer.h.31.self_attention.dense.weight": "pytorch_model-00003-of-00005.bin",
317
+ "transformer.h.31.self_attention.query_key_value.SCB": "pytorch_model-00003-of-00005.bin",
318
+ "transformer.h.31.self_attention.query_key_value.weight": "pytorch_model-00003-of-00005.bin",
319
+ "transformer.h.32.ln_attn.bias": "pytorch_model-00003-of-00005.bin",
320
+ "transformer.h.32.ln_attn.weight": "pytorch_model-00003-of-00005.bin",
321
+ "transformer.h.32.ln_mlp.bias": "pytorch_model-00003-of-00005.bin",
322
+ "transformer.h.32.ln_mlp.weight": "pytorch_model-00003-of-00005.bin",
323
+ "transformer.h.32.mlp.dense_4h_to_h.SCB": "pytorch_model-00003-of-00005.bin",
324
+ "transformer.h.32.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00005.bin",
325
+ "transformer.h.32.mlp.dense_h_to_4h.SCB": "pytorch_model-00003-of-00005.bin",
326
+ "transformer.h.32.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00005.bin",
327
+ "transformer.h.32.self_attention.dense.SCB": "pytorch_model-00003-of-00005.bin",
328
+ "transformer.h.32.self_attention.dense.weight": "pytorch_model-00003-of-00005.bin",
329
+ "transformer.h.32.self_attention.query_key_value.SCB": "pytorch_model-00003-of-00005.bin",
330
+ "transformer.h.32.self_attention.query_key_value.weight": "pytorch_model-00003-of-00005.bin",
331
+ "transformer.h.33.ln_attn.bias": "pytorch_model-00003-of-00005.bin",
332
+ "transformer.h.33.ln_attn.weight": "pytorch_model-00003-of-00005.bin",
333
+ "transformer.h.33.ln_mlp.bias": "pytorch_model-00003-of-00005.bin",
334
+ "transformer.h.33.ln_mlp.weight": "pytorch_model-00003-of-00005.bin",
335
+ "transformer.h.33.mlp.dense_4h_to_h.SCB": "pytorch_model-00003-of-00005.bin",
336
+ "transformer.h.33.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00005.bin",
337
+ "transformer.h.33.mlp.dense_h_to_4h.SCB": "pytorch_model-00003-of-00005.bin",
338
+ "transformer.h.33.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00005.bin",
339
+ "transformer.h.33.self_attention.dense.SCB": "pytorch_model-00003-of-00005.bin",
340
+ "transformer.h.33.self_attention.dense.weight": "pytorch_model-00003-of-00005.bin",
341
+ "transformer.h.33.self_attention.query_key_value.SCB": "pytorch_model-00003-of-00005.bin",
342
+ "transformer.h.33.self_attention.query_key_value.weight": "pytorch_model-00003-of-00005.bin",
343
+ "transformer.h.34.ln_attn.bias": "pytorch_model-00003-of-00005.bin",
344
+ "transformer.h.34.ln_attn.weight": "pytorch_model-00003-of-00005.bin",
345
+ "transformer.h.34.ln_mlp.bias": "pytorch_model-00003-of-00005.bin",
346
+ "transformer.h.34.ln_mlp.weight": "pytorch_model-00003-of-00005.bin",
347
+ "transformer.h.34.mlp.dense_4h_to_h.SCB": "pytorch_model-00003-of-00005.bin",
348
+ "transformer.h.34.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00005.bin",
349
+ "transformer.h.34.mlp.dense_h_to_4h.SCB": "pytorch_model-00003-of-00005.bin",
350
+ "transformer.h.34.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00005.bin",
351
+ "transformer.h.34.self_attention.dense.SCB": "pytorch_model-00003-of-00005.bin",
352
+ "transformer.h.34.self_attention.dense.weight": "pytorch_model-00003-of-00005.bin",
353
+ "transformer.h.34.self_attention.query_key_value.SCB": "pytorch_model-00003-of-00005.bin",
354
+ "transformer.h.34.self_attention.query_key_value.weight": "pytorch_model-00003-of-00005.bin",
355
+ "transformer.h.35.ln_attn.bias": "pytorch_model-00003-of-00005.bin",
356
+ "transformer.h.35.ln_attn.weight": "pytorch_model-00003-of-00005.bin",
357
+ "transformer.h.35.ln_mlp.bias": "pytorch_model-00003-of-00005.bin",
358
+ "transformer.h.35.ln_mlp.weight": "pytorch_model-00003-of-00005.bin",
359
+ "transformer.h.35.mlp.dense_4h_to_h.SCB": "pytorch_model-00003-of-00005.bin",
360
+ "transformer.h.35.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00005.bin",
361
+ "transformer.h.35.mlp.dense_h_to_4h.SCB": "pytorch_model-00003-of-00005.bin",
362
+ "transformer.h.35.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00005.bin",
363
+ "transformer.h.35.self_attention.dense.SCB": "pytorch_model-00003-of-00005.bin",
364
+ "transformer.h.35.self_attention.dense.weight": "pytorch_model-00003-of-00005.bin",
365
+ "transformer.h.35.self_attention.query_key_value.SCB": "pytorch_model-00003-of-00005.bin",
366
+ "transformer.h.35.self_attention.query_key_value.weight": "pytorch_model-00003-of-00005.bin",
367
+ "transformer.h.36.ln_attn.bias": "pytorch_model-00003-of-00005.bin",
368
+ "transformer.h.36.ln_attn.weight": "pytorch_model-00003-of-00005.bin",
369
+ "transformer.h.36.ln_mlp.bias": "pytorch_model-00003-of-00005.bin",
370
+ "transformer.h.36.ln_mlp.weight": "pytorch_model-00003-of-00005.bin",
371
+ "transformer.h.36.mlp.dense_4h_to_h.SCB": "pytorch_model-00003-of-00005.bin",
372
+ "transformer.h.36.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00005.bin",
373
+ "transformer.h.36.mlp.dense_h_to_4h.SCB": "pytorch_model-00003-of-00005.bin",
374
+ "transformer.h.36.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00005.bin",
375
+ "transformer.h.36.self_attention.dense.SCB": "pytorch_model-00003-of-00005.bin",
376
+ "transformer.h.36.self_attention.dense.weight": "pytorch_model-00003-of-00005.bin",
377
+ "transformer.h.36.self_attention.query_key_value.SCB": "pytorch_model-00003-of-00005.bin",
378
+ "transformer.h.36.self_attention.query_key_value.weight": "pytorch_model-00003-of-00005.bin",
379
+ "transformer.h.37.ln_attn.bias": "pytorch_model-00003-of-00005.bin",
380
+ "transformer.h.37.ln_attn.weight": "pytorch_model-00003-of-00005.bin",
381
+ "transformer.h.37.ln_mlp.bias": "pytorch_model-00003-of-00005.bin",
382
+ "transformer.h.37.ln_mlp.weight": "pytorch_model-00003-of-00005.bin",
383
+ "transformer.h.37.mlp.dense_4h_to_h.SCB": "pytorch_model-00003-of-00005.bin",
384
+ "transformer.h.37.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00005.bin",
385
+ "transformer.h.37.mlp.dense_h_to_4h.SCB": "pytorch_model-00003-of-00005.bin",
386
+ "transformer.h.37.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00005.bin",
387
+ "transformer.h.37.self_attention.dense.SCB": "pytorch_model-00003-of-00005.bin",
388
+ "transformer.h.37.self_attention.dense.weight": "pytorch_model-00003-of-00005.bin",
389
+ "transformer.h.37.self_attention.query_key_value.SCB": "pytorch_model-00003-of-00005.bin",
390
+ "transformer.h.37.self_attention.query_key_value.weight": "pytorch_model-00003-of-00005.bin",
391
+ "transformer.h.38.ln_attn.bias": "pytorch_model-00003-of-00005.bin",
392
+ "transformer.h.38.ln_attn.weight": "pytorch_model-00003-of-00005.bin",
393
+ "transformer.h.38.ln_mlp.bias": "pytorch_model-00003-of-00005.bin",
394
+ "transformer.h.38.ln_mlp.weight": "pytorch_model-00003-of-00005.bin",
395
+ "transformer.h.38.mlp.dense_4h_to_h.SCB": "pytorch_model-00003-of-00005.bin",
396
+ "transformer.h.38.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00005.bin",
397
+ "transformer.h.38.mlp.dense_h_to_4h.SCB": "pytorch_model-00003-of-00005.bin",
398
+ "transformer.h.38.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00005.bin",
399
+ "transformer.h.38.self_attention.dense.SCB": "pytorch_model-00003-of-00005.bin",
400
+ "transformer.h.38.self_attention.dense.weight": "pytorch_model-00003-of-00005.bin",
401
+ "transformer.h.38.self_attention.query_key_value.SCB": "pytorch_model-00003-of-00005.bin",
402
+ "transformer.h.38.self_attention.query_key_value.weight": "pytorch_model-00003-of-00005.bin",
403
+ "transformer.h.39.ln_attn.bias": "pytorch_model-00003-of-00005.bin",
404
+ "transformer.h.39.ln_attn.weight": "pytorch_model-00003-of-00005.bin",
405
+ "transformer.h.39.ln_mlp.bias": "pytorch_model-00003-of-00005.bin",
406
+ "transformer.h.39.ln_mlp.weight": "pytorch_model-00003-of-00005.bin",
407
+ "transformer.h.39.mlp.dense_4h_to_h.SCB": "pytorch_model-00003-of-00005.bin",
408
+ "transformer.h.39.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00005.bin",
409
+ "transformer.h.39.mlp.dense_h_to_4h.SCB": "pytorch_model-00003-of-00005.bin",
410
+ "transformer.h.39.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00005.bin",
411
+ "transformer.h.39.self_attention.dense.SCB": "pytorch_model-00003-of-00005.bin",
412
+ "transformer.h.39.self_attention.dense.weight": "pytorch_model-00003-of-00005.bin",
413
+ "transformer.h.39.self_attention.query_key_value.SCB": "pytorch_model-00003-of-00005.bin",
414
+ "transformer.h.39.self_attention.query_key_value.weight": "pytorch_model-00003-of-00005.bin",
415
+ "transformer.h.4.ln_attn.bias": "pytorch_model-00001-of-00005.bin",
416
+ "transformer.h.4.ln_attn.weight": "pytorch_model-00001-of-00005.bin",
417
+ "transformer.h.4.ln_mlp.bias": "pytorch_model-00001-of-00005.bin",
418
+ "transformer.h.4.ln_mlp.weight": "pytorch_model-00001-of-00005.bin",
419
+ "transformer.h.4.mlp.dense_4h_to_h.SCB": "pytorch_model-00001-of-00005.bin",
420
+ "transformer.h.4.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00005.bin",
421
+ "transformer.h.4.mlp.dense_h_to_4h.SCB": "pytorch_model-00001-of-00005.bin",
422
+ "transformer.h.4.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00005.bin",
423
+ "transformer.h.4.self_attention.dense.SCB": "pytorch_model-00001-of-00005.bin",
424
+ "transformer.h.4.self_attention.dense.weight": "pytorch_model-00001-of-00005.bin",
425
+ "transformer.h.4.self_attention.query_key_value.SCB": "pytorch_model-00001-of-00005.bin",
426
+ "transformer.h.4.self_attention.query_key_value.weight": "pytorch_model-00001-of-00005.bin",
427
+ "transformer.h.40.ln_attn.bias": "pytorch_model-00003-of-00005.bin",
428
+ "transformer.h.40.ln_attn.weight": "pytorch_model-00003-of-00005.bin",
429
+ "transformer.h.40.ln_mlp.bias": "pytorch_model-00003-of-00005.bin",
430
+ "transformer.h.40.ln_mlp.weight": "pytorch_model-00003-of-00005.bin",
431
+ "transformer.h.40.mlp.dense_4h_to_h.SCB": "pytorch_model-00003-of-00005.bin",
432
+ "transformer.h.40.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00005.bin",
433
+ "transformer.h.40.mlp.dense_h_to_4h.SCB": "pytorch_model-00003-of-00005.bin",
434
+ "transformer.h.40.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00005.bin",
435
+ "transformer.h.40.self_attention.dense.SCB": "pytorch_model-00003-of-00005.bin",
436
+ "transformer.h.40.self_attention.dense.weight": "pytorch_model-00003-of-00005.bin",
437
+ "transformer.h.40.self_attention.query_key_value.SCB": "pytorch_model-00003-of-00005.bin",
438
+ "transformer.h.40.self_attention.query_key_value.weight": "pytorch_model-00003-of-00005.bin",
439
+ "transformer.h.41.ln_attn.bias": "pytorch_model-00003-of-00005.bin",
440
+ "transformer.h.41.ln_attn.weight": "pytorch_model-00003-of-00005.bin",
441
+ "transformer.h.41.ln_mlp.bias": "pytorch_model-00003-of-00005.bin",
442
+ "transformer.h.41.ln_mlp.weight": "pytorch_model-00003-of-00005.bin",
443
+ "transformer.h.41.mlp.dense_4h_to_h.SCB": "pytorch_model-00003-of-00005.bin",
444
+ "transformer.h.41.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00005.bin",
445
+ "transformer.h.41.mlp.dense_h_to_4h.SCB": "pytorch_model-00003-of-00005.bin",
446
+ "transformer.h.41.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00005.bin",
447
+ "transformer.h.41.self_attention.dense.SCB": "pytorch_model-00003-of-00005.bin",
448
+ "transformer.h.41.self_attention.dense.weight": "pytorch_model-00003-of-00005.bin",
449
+ "transformer.h.41.self_attention.query_key_value.SCB": "pytorch_model-00003-of-00005.bin",
450
+ "transformer.h.41.self_attention.query_key_value.weight": "pytorch_model-00003-of-00005.bin",
451
+ "transformer.h.42.ln_attn.bias": "pytorch_model-00003-of-00005.bin",
452
+ "transformer.h.42.ln_attn.weight": "pytorch_model-00003-of-00005.bin",
453
+ "transformer.h.42.ln_mlp.bias": "pytorch_model-00003-of-00005.bin",
454
+ "transformer.h.42.ln_mlp.weight": "pytorch_model-00003-of-00005.bin",
455
+ "transformer.h.42.mlp.dense_4h_to_h.SCB": "pytorch_model-00004-of-00005.bin",
456
+ "transformer.h.42.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00005.bin",
457
+ "transformer.h.42.mlp.dense_h_to_4h.SCB": "pytorch_model-00004-of-00005.bin",
458
+ "transformer.h.42.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00005.bin",
459
+ "transformer.h.42.self_attention.dense.SCB": "pytorch_model-00003-of-00005.bin",
460
+ "transformer.h.42.self_attention.dense.weight": "pytorch_model-00003-of-00005.bin",
461
+ "transformer.h.42.self_attention.query_key_value.SCB": "pytorch_model-00003-of-00005.bin",
462
+ "transformer.h.42.self_attention.query_key_value.weight": "pytorch_model-00003-of-00005.bin",
463
+ "transformer.h.43.ln_attn.bias": "pytorch_model-00004-of-00005.bin",
464
+ "transformer.h.43.ln_attn.weight": "pytorch_model-00004-of-00005.bin",
465
+ "transformer.h.43.ln_mlp.bias": "pytorch_model-00004-of-00005.bin",
466
+ "transformer.h.43.ln_mlp.weight": "pytorch_model-00004-of-00005.bin",
467
+ "transformer.h.43.mlp.dense_4h_to_h.SCB": "pytorch_model-00004-of-00005.bin",
468
+ "transformer.h.43.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00005.bin",
469
+ "transformer.h.43.mlp.dense_h_to_4h.SCB": "pytorch_model-00004-of-00005.bin",
470
+ "transformer.h.43.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00005.bin",
471
+ "transformer.h.43.self_attention.dense.SCB": "pytorch_model-00004-of-00005.bin",
472
+ "transformer.h.43.self_attention.dense.weight": "pytorch_model-00004-of-00005.bin",
473
+ "transformer.h.43.self_attention.query_key_value.SCB": "pytorch_model-00004-of-00005.bin",
474
+ "transformer.h.43.self_attention.query_key_value.weight": "pytorch_model-00004-of-00005.bin",
475
+ "transformer.h.44.ln_attn.bias": "pytorch_model-00004-of-00005.bin",
476
+ "transformer.h.44.ln_attn.weight": "pytorch_model-00004-of-00005.bin",
477
+ "transformer.h.44.ln_mlp.bias": "pytorch_model-00004-of-00005.bin",
478
+ "transformer.h.44.ln_mlp.weight": "pytorch_model-00004-of-00005.bin",
479
+ "transformer.h.44.mlp.dense_4h_to_h.SCB": "pytorch_model-00004-of-00005.bin",
480
+ "transformer.h.44.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00005.bin",
481
+ "transformer.h.44.mlp.dense_h_to_4h.SCB": "pytorch_model-00004-of-00005.bin",
482
+ "transformer.h.44.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00005.bin",
483
+ "transformer.h.44.self_attention.dense.SCB": "pytorch_model-00004-of-00005.bin",
484
+ "transformer.h.44.self_attention.dense.weight": "pytorch_model-00004-of-00005.bin",
485
+ "transformer.h.44.self_attention.query_key_value.SCB": "pytorch_model-00004-of-00005.bin",
486
+ "transformer.h.44.self_attention.query_key_value.weight": "pytorch_model-00004-of-00005.bin",
487
+ "transformer.h.45.ln_attn.bias": "pytorch_model-00004-of-00005.bin",
488
+ "transformer.h.45.ln_attn.weight": "pytorch_model-00004-of-00005.bin",
489
+ "transformer.h.45.ln_mlp.bias": "pytorch_model-00004-of-00005.bin",
490
+ "transformer.h.45.ln_mlp.weight": "pytorch_model-00004-of-00005.bin",
491
+ "transformer.h.45.mlp.dense_4h_to_h.SCB": "pytorch_model-00004-of-00005.bin",
492
+ "transformer.h.45.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00005.bin",
493
+ "transformer.h.45.mlp.dense_h_to_4h.SCB": "pytorch_model-00004-of-00005.bin",
494
+ "transformer.h.45.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00005.bin",
495
+ "transformer.h.45.self_attention.dense.SCB": "pytorch_model-00004-of-00005.bin",
496
+ "transformer.h.45.self_attention.dense.weight": "pytorch_model-00004-of-00005.bin",
497
+ "transformer.h.45.self_attention.query_key_value.SCB": "pytorch_model-00004-of-00005.bin",
498
+ "transformer.h.45.self_attention.query_key_value.weight": "pytorch_model-00004-of-00005.bin",
499
+ "transformer.h.46.ln_attn.bias": "pytorch_model-00004-of-00005.bin",
500
+ "transformer.h.46.ln_attn.weight": "pytorch_model-00004-of-00005.bin",
501
+ "transformer.h.46.ln_mlp.bias": "pytorch_model-00004-of-00005.bin",
502
+ "transformer.h.46.ln_mlp.weight": "pytorch_model-00004-of-00005.bin",
503
+ "transformer.h.46.mlp.dense_4h_to_h.SCB": "pytorch_model-00004-of-00005.bin",
504
+ "transformer.h.46.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00005.bin",
505
+ "transformer.h.46.mlp.dense_h_to_4h.SCB": "pytorch_model-00004-of-00005.bin",
506
+ "transformer.h.46.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00005.bin",
507
+ "transformer.h.46.self_attention.dense.SCB": "pytorch_model-00004-of-00005.bin",
508
+ "transformer.h.46.self_attention.dense.weight": "pytorch_model-00004-of-00005.bin",
509
+ "transformer.h.46.self_attention.query_key_value.SCB": "pytorch_model-00004-of-00005.bin",
510
+ "transformer.h.46.self_attention.query_key_value.weight": "pytorch_model-00004-of-00005.bin",
511
+ "transformer.h.47.ln_attn.bias": "pytorch_model-00004-of-00005.bin",
512
+ "transformer.h.47.ln_attn.weight": "pytorch_model-00004-of-00005.bin",
513
+ "transformer.h.47.ln_mlp.bias": "pytorch_model-00004-of-00005.bin",
514
+ "transformer.h.47.ln_mlp.weight": "pytorch_model-00004-of-00005.bin",
515
+ "transformer.h.47.mlp.dense_4h_to_h.SCB": "pytorch_model-00004-of-00005.bin",
516
+ "transformer.h.47.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00005.bin",
517
+ "transformer.h.47.mlp.dense_h_to_4h.SCB": "pytorch_model-00004-of-00005.bin",
518
+ "transformer.h.47.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00005.bin",
519
+ "transformer.h.47.self_attention.dense.SCB": "pytorch_model-00004-of-00005.bin",
520
+ "transformer.h.47.self_attention.dense.weight": "pytorch_model-00004-of-00005.bin",
521
+ "transformer.h.47.self_attention.query_key_value.SCB": "pytorch_model-00004-of-00005.bin",
522
+ "transformer.h.47.self_attention.query_key_value.weight": "pytorch_model-00004-of-00005.bin",
523
+ "transformer.h.48.ln_attn.bias": "pytorch_model-00004-of-00005.bin",
524
+ "transformer.h.48.ln_attn.weight": "pytorch_model-00004-of-00005.bin",
525
+ "transformer.h.48.ln_mlp.bias": "pytorch_model-00004-of-00005.bin",
526
+ "transformer.h.48.ln_mlp.weight": "pytorch_model-00004-of-00005.bin",
527
+ "transformer.h.48.mlp.dense_4h_to_h.SCB": "pytorch_model-00004-of-00005.bin",
528
+ "transformer.h.48.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00005.bin",
529
+ "transformer.h.48.mlp.dense_h_to_4h.SCB": "pytorch_model-00004-of-00005.bin",
530
+ "transformer.h.48.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00005.bin",
531
+ "transformer.h.48.self_attention.dense.SCB": "pytorch_model-00004-of-00005.bin",
532
+ "transformer.h.48.self_attention.dense.weight": "pytorch_model-00004-of-00005.bin",
533
+ "transformer.h.48.self_attention.query_key_value.SCB": "pytorch_model-00004-of-00005.bin",
534
+ "transformer.h.48.self_attention.query_key_value.weight": "pytorch_model-00004-of-00005.bin",
535
+ "transformer.h.49.ln_attn.bias": "pytorch_model-00004-of-00005.bin",
536
+ "transformer.h.49.ln_attn.weight": "pytorch_model-00004-of-00005.bin",
537
+ "transformer.h.49.ln_mlp.bias": "pytorch_model-00004-of-00005.bin",
538
+ "transformer.h.49.ln_mlp.weight": "pytorch_model-00004-of-00005.bin",
539
+ "transformer.h.49.mlp.dense_4h_to_h.SCB": "pytorch_model-00004-of-00005.bin",
540
+ "transformer.h.49.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00005.bin",
541
+ "transformer.h.49.mlp.dense_h_to_4h.SCB": "pytorch_model-00004-of-00005.bin",
542
+ "transformer.h.49.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00005.bin",
543
+ "transformer.h.49.self_attention.dense.SCB": "pytorch_model-00004-of-00005.bin",
544
+ "transformer.h.49.self_attention.dense.weight": "pytorch_model-00004-of-00005.bin",
545
+ "transformer.h.49.self_attention.query_key_value.SCB": "pytorch_model-00004-of-00005.bin",
546
+ "transformer.h.49.self_attention.query_key_value.weight": "pytorch_model-00004-of-00005.bin",
547
+ "transformer.h.5.ln_attn.bias": "pytorch_model-00001-of-00005.bin",
548
+ "transformer.h.5.ln_attn.weight": "pytorch_model-00001-of-00005.bin",
549
+ "transformer.h.5.ln_mlp.bias": "pytorch_model-00001-of-00005.bin",
550
+ "transformer.h.5.ln_mlp.weight": "pytorch_model-00001-of-00005.bin",
551
+ "transformer.h.5.mlp.dense_4h_to_h.SCB": "pytorch_model-00001-of-00005.bin",
552
+ "transformer.h.5.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00005.bin",
553
+ "transformer.h.5.mlp.dense_h_to_4h.SCB": "pytorch_model-00001-of-00005.bin",
554
+ "transformer.h.5.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00005.bin",
555
+ "transformer.h.5.self_attention.dense.SCB": "pytorch_model-00001-of-00005.bin",
556
+ "transformer.h.5.self_attention.dense.weight": "pytorch_model-00001-of-00005.bin",
557
+ "transformer.h.5.self_attention.query_key_value.SCB": "pytorch_model-00001-of-00005.bin",
558
+ "transformer.h.5.self_attention.query_key_value.weight": "pytorch_model-00001-of-00005.bin",
559
+ "transformer.h.50.ln_attn.bias": "pytorch_model-00004-of-00005.bin",
560
+ "transformer.h.50.ln_attn.weight": "pytorch_model-00004-of-00005.bin",
561
+ "transformer.h.50.ln_mlp.bias": "pytorch_model-00004-of-00005.bin",
562
+ "transformer.h.50.ln_mlp.weight": "pytorch_model-00004-of-00005.bin",
563
+ "transformer.h.50.mlp.dense_4h_to_h.SCB": "pytorch_model-00004-of-00005.bin",
564
+ "transformer.h.50.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00005.bin",
565
+ "transformer.h.50.mlp.dense_h_to_4h.SCB": "pytorch_model-00004-of-00005.bin",
566
+ "transformer.h.50.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00005.bin",
567
+ "transformer.h.50.self_attention.dense.SCB": "pytorch_model-00004-of-00005.bin",
568
+ "transformer.h.50.self_attention.dense.weight": "pytorch_model-00004-of-00005.bin",
569
+ "transformer.h.50.self_attention.query_key_value.SCB": "pytorch_model-00004-of-00005.bin",
570
+ "transformer.h.50.self_attention.query_key_value.weight": "pytorch_model-00004-of-00005.bin",
571
+ "transformer.h.51.ln_attn.bias": "pytorch_model-00004-of-00005.bin",
572
+ "transformer.h.51.ln_attn.weight": "pytorch_model-00004-of-00005.bin",
573
+ "transformer.h.51.ln_mlp.bias": "pytorch_model-00004-of-00005.bin",
574
+ "transformer.h.51.ln_mlp.weight": "pytorch_model-00004-of-00005.bin",
575
+ "transformer.h.51.mlp.dense_4h_to_h.SCB": "pytorch_model-00004-of-00005.bin",
576
+ "transformer.h.51.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00005.bin",
577
+ "transformer.h.51.mlp.dense_h_to_4h.SCB": "pytorch_model-00004-of-00005.bin",
578
+ "transformer.h.51.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00005.bin",
579
+ "transformer.h.51.self_attention.dense.SCB": "pytorch_model-00004-of-00005.bin",
580
+ "transformer.h.51.self_attention.dense.weight": "pytorch_model-00004-of-00005.bin",
581
+ "transformer.h.51.self_attention.query_key_value.SCB": "pytorch_model-00004-of-00005.bin",
582
+ "transformer.h.51.self_attention.query_key_value.weight": "pytorch_model-00004-of-00005.bin",
583
+ "transformer.h.52.ln_attn.bias": "pytorch_model-00004-of-00005.bin",
584
+ "transformer.h.52.ln_attn.weight": "pytorch_model-00004-of-00005.bin",
585
+ "transformer.h.52.ln_mlp.bias": "pytorch_model-00004-of-00005.bin",
586
+ "transformer.h.52.ln_mlp.weight": "pytorch_model-00004-of-00005.bin",
587
+ "transformer.h.52.mlp.dense_4h_to_h.SCB": "pytorch_model-00004-of-00005.bin",
588
+ "transformer.h.52.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00005.bin",
589
+ "transformer.h.52.mlp.dense_h_to_4h.SCB": "pytorch_model-00004-of-00005.bin",
590
+ "transformer.h.52.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00005.bin",
591
+ "transformer.h.52.self_attention.dense.SCB": "pytorch_model-00004-of-00005.bin",
592
+ "transformer.h.52.self_attention.dense.weight": "pytorch_model-00004-of-00005.bin",
593
+ "transformer.h.52.self_attention.query_key_value.SCB": "pytorch_model-00004-of-00005.bin",
594
+ "transformer.h.52.self_attention.query_key_value.weight": "pytorch_model-00004-of-00005.bin",
595
+ "transformer.h.53.ln_attn.bias": "pytorch_model-00004-of-00005.bin",
596
+ "transformer.h.53.ln_attn.weight": "pytorch_model-00004-of-00005.bin",
597
+ "transformer.h.53.ln_mlp.bias": "pytorch_model-00004-of-00005.bin",
598
+ "transformer.h.53.ln_mlp.weight": "pytorch_model-00004-of-00005.bin",
599
+ "transformer.h.53.mlp.dense_4h_to_h.SCB": "pytorch_model-00004-of-00005.bin",
600
+ "transformer.h.53.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00005.bin",
601
+ "transformer.h.53.mlp.dense_h_to_4h.SCB": "pytorch_model-00004-of-00005.bin",
602
+ "transformer.h.53.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00005.bin",
603
+ "transformer.h.53.self_attention.dense.SCB": "pytorch_model-00004-of-00005.bin",
604
+ "transformer.h.53.self_attention.dense.weight": "pytorch_model-00004-of-00005.bin",
605
+ "transformer.h.53.self_attention.query_key_value.SCB": "pytorch_model-00004-of-00005.bin",
606
+ "transformer.h.53.self_attention.query_key_value.weight": "pytorch_model-00004-of-00005.bin",
607
+ "transformer.h.54.ln_attn.bias": "pytorch_model-00004-of-00005.bin",
608
+ "transformer.h.54.ln_attn.weight": "pytorch_model-00004-of-00005.bin",
609
+ "transformer.h.54.ln_mlp.bias": "pytorch_model-00004-of-00005.bin",
610
+ "transformer.h.54.ln_mlp.weight": "pytorch_model-00004-of-00005.bin",
611
+ "transformer.h.54.mlp.dense_4h_to_h.SCB": "pytorch_model-00004-of-00005.bin",
612
+ "transformer.h.54.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00005.bin",
613
+ "transformer.h.54.mlp.dense_h_to_4h.SCB": "pytorch_model-00004-of-00005.bin",
614
+ "transformer.h.54.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00005.bin",
615
+ "transformer.h.54.self_attention.dense.SCB": "pytorch_model-00004-of-00005.bin",
616
+ "transformer.h.54.self_attention.dense.weight": "pytorch_model-00004-of-00005.bin",
617
+ "transformer.h.54.self_attention.query_key_value.SCB": "pytorch_model-00004-of-00005.bin",
618
+ "transformer.h.54.self_attention.query_key_value.weight": "pytorch_model-00004-of-00005.bin",
619
+ "transformer.h.55.ln_attn.bias": "pytorch_model-00004-of-00005.bin",
620
+ "transformer.h.55.ln_attn.weight": "pytorch_model-00004-of-00005.bin",
621
+ "transformer.h.55.ln_mlp.bias": "pytorch_model-00004-of-00005.bin",
622
+ "transformer.h.55.ln_mlp.weight": "pytorch_model-00004-of-00005.bin",
623
+ "transformer.h.55.mlp.dense_4h_to_h.SCB": "pytorch_model-00004-of-00005.bin",
624
+ "transformer.h.55.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00005.bin",
625
+ "transformer.h.55.mlp.dense_h_to_4h.SCB": "pytorch_model-00004-of-00005.bin",
626
+ "transformer.h.55.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00005.bin",
627
+ "transformer.h.55.self_attention.dense.SCB": "pytorch_model-00004-of-00005.bin",
628
+ "transformer.h.55.self_attention.dense.weight": "pytorch_model-00004-of-00005.bin",
629
+ "transformer.h.55.self_attention.query_key_value.SCB": "pytorch_model-00004-of-00005.bin",
630
+ "transformer.h.55.self_attention.query_key_value.weight": "pytorch_model-00004-of-00005.bin",
631
+ "transformer.h.56.ln_attn.bias": "pytorch_model-00004-of-00005.bin",
632
+ "transformer.h.56.ln_attn.weight": "pytorch_model-00004-of-00005.bin",
633
+ "transformer.h.56.ln_mlp.bias": "pytorch_model-00004-of-00005.bin",
634
+ "transformer.h.56.ln_mlp.weight": "pytorch_model-00004-of-00005.bin",
635
+ "transformer.h.56.mlp.dense_4h_to_h.SCB": "pytorch_model-00005-of-00005.bin",
636
+ "transformer.h.56.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00005.bin",
637
+ "transformer.h.56.mlp.dense_h_to_4h.SCB": "pytorch_model-00004-of-00005.bin",
638
+ "transformer.h.56.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00005.bin",
639
+ "transformer.h.56.self_attention.dense.SCB": "pytorch_model-00004-of-00005.bin",
640
+ "transformer.h.56.self_attention.dense.weight": "pytorch_model-00004-of-00005.bin",
641
+ "transformer.h.56.self_attention.query_key_value.SCB": "pytorch_model-00004-of-00005.bin",
642
+ "transformer.h.56.self_attention.query_key_value.weight": "pytorch_model-00004-of-00005.bin",
643
+ "transformer.h.57.ln_attn.bias": "pytorch_model-00005-of-00005.bin",
644
+ "transformer.h.57.ln_attn.weight": "pytorch_model-00005-of-00005.bin",
645
+ "transformer.h.57.ln_mlp.bias": "pytorch_model-00005-of-00005.bin",
646
+ "transformer.h.57.ln_mlp.weight": "pytorch_model-00005-of-00005.bin",
647
+ "transformer.h.57.mlp.dense_4h_to_h.SCB": "pytorch_model-00005-of-00005.bin",
648
+ "transformer.h.57.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00005.bin",
649
+ "transformer.h.57.mlp.dense_h_to_4h.SCB": "pytorch_model-00005-of-00005.bin",
650
+ "transformer.h.57.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00005.bin",
651
+ "transformer.h.57.self_attention.dense.SCB": "pytorch_model-00005-of-00005.bin",
652
+ "transformer.h.57.self_attention.dense.weight": "pytorch_model-00005-of-00005.bin",
653
+ "transformer.h.57.self_attention.query_key_value.SCB": "pytorch_model-00005-of-00005.bin",
654
+ "transformer.h.57.self_attention.query_key_value.weight": "pytorch_model-00005-of-00005.bin",
655
+ "transformer.h.58.ln_attn.bias": "pytorch_model-00005-of-00005.bin",
656
+ "transformer.h.58.ln_attn.weight": "pytorch_model-00005-of-00005.bin",
657
+ "transformer.h.58.ln_mlp.bias": "pytorch_model-00005-of-00005.bin",
658
+ "transformer.h.58.ln_mlp.weight": "pytorch_model-00005-of-00005.bin",
659
+ "transformer.h.58.mlp.dense_4h_to_h.SCB": "pytorch_model-00005-of-00005.bin",
660
+ "transformer.h.58.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00005.bin",
661
+ "transformer.h.58.mlp.dense_h_to_4h.SCB": "pytorch_model-00005-of-00005.bin",
662
+ "transformer.h.58.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00005.bin",
663
+ "transformer.h.58.self_attention.dense.SCB": "pytorch_model-00005-of-00005.bin",
664
+ "transformer.h.58.self_attention.dense.weight": "pytorch_model-00005-of-00005.bin",
665
+ "transformer.h.58.self_attention.query_key_value.SCB": "pytorch_model-00005-of-00005.bin",
666
+ "transformer.h.58.self_attention.query_key_value.weight": "pytorch_model-00005-of-00005.bin",
667
+ "transformer.h.59.ln_attn.bias": "pytorch_model-00005-of-00005.bin",
668
+ "transformer.h.59.ln_attn.weight": "pytorch_model-00005-of-00005.bin",
669
+ "transformer.h.59.ln_mlp.bias": "pytorch_model-00005-of-00005.bin",
670
+ "transformer.h.59.ln_mlp.weight": "pytorch_model-00005-of-00005.bin",
671
+ "transformer.h.59.mlp.dense_4h_to_h.SCB": "pytorch_model-00005-of-00005.bin",
672
+ "transformer.h.59.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00005.bin",
673
+ "transformer.h.59.mlp.dense_h_to_4h.SCB": "pytorch_model-00005-of-00005.bin",
674
+ "transformer.h.59.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00005.bin",
675
+ "transformer.h.59.self_attention.dense.SCB": "pytorch_model-00005-of-00005.bin",
676
+ "transformer.h.59.self_attention.dense.weight": "pytorch_model-00005-of-00005.bin",
677
+ "transformer.h.59.self_attention.query_key_value.SCB": "pytorch_model-00005-of-00005.bin",
678
+ "transformer.h.59.self_attention.query_key_value.weight": "pytorch_model-00005-of-00005.bin",
679
+ "transformer.h.6.ln_attn.bias": "pytorch_model-00001-of-00005.bin",
680
+ "transformer.h.6.ln_attn.weight": "pytorch_model-00001-of-00005.bin",
681
+ "transformer.h.6.ln_mlp.bias": "pytorch_model-00001-of-00005.bin",
682
+ "transformer.h.6.ln_mlp.weight": "pytorch_model-00001-of-00005.bin",
683
+ "transformer.h.6.mlp.dense_4h_to_h.SCB": "pytorch_model-00001-of-00005.bin",
684
+ "transformer.h.6.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00005.bin",
685
+ "transformer.h.6.mlp.dense_h_to_4h.SCB": "pytorch_model-00001-of-00005.bin",
686
+ "transformer.h.6.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00005.bin",
687
+ "transformer.h.6.self_attention.dense.SCB": "pytorch_model-00001-of-00005.bin",
688
+ "transformer.h.6.self_attention.dense.weight": "pytorch_model-00001-of-00005.bin",
689
+ "transformer.h.6.self_attention.query_key_value.SCB": "pytorch_model-00001-of-00005.bin",
690
+ "transformer.h.6.self_attention.query_key_value.weight": "pytorch_model-00001-of-00005.bin",
691
+ "transformer.h.7.ln_attn.bias": "pytorch_model-00001-of-00005.bin",
692
+ "transformer.h.7.ln_attn.weight": "pytorch_model-00001-of-00005.bin",
693
+ "transformer.h.7.ln_mlp.bias": "pytorch_model-00001-of-00005.bin",
694
+ "transformer.h.7.ln_mlp.weight": "pytorch_model-00001-of-00005.bin",
695
+ "transformer.h.7.mlp.dense_4h_to_h.SCB": "pytorch_model-00001-of-00005.bin",
696
+ "transformer.h.7.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00005.bin",
697
+ "transformer.h.7.mlp.dense_h_to_4h.SCB": "pytorch_model-00001-of-00005.bin",
698
+ "transformer.h.7.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00005.bin",
699
+ "transformer.h.7.self_attention.dense.SCB": "pytorch_model-00001-of-00005.bin",
700
+ "transformer.h.7.self_attention.dense.weight": "pytorch_model-00001-of-00005.bin",
701
+ "transformer.h.7.self_attention.query_key_value.SCB": "pytorch_model-00001-of-00005.bin",
702
+ "transformer.h.7.self_attention.query_key_value.weight": "pytorch_model-00001-of-00005.bin",
703
+ "transformer.h.8.ln_attn.bias": "pytorch_model-00001-of-00005.bin",
704
+ "transformer.h.8.ln_attn.weight": "pytorch_model-00001-of-00005.bin",
705
+ "transformer.h.8.ln_mlp.bias": "pytorch_model-00001-of-00005.bin",
706
+ "transformer.h.8.ln_mlp.weight": "pytorch_model-00001-of-00005.bin",
707
+ "transformer.h.8.mlp.dense_4h_to_h.SCB": "pytorch_model-00001-of-00005.bin",
708
+ "transformer.h.8.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00005.bin",
709
+ "transformer.h.8.mlp.dense_h_to_4h.SCB": "pytorch_model-00001-of-00005.bin",
710
+ "transformer.h.8.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00005.bin",
711
+ "transformer.h.8.self_attention.dense.SCB": "pytorch_model-00001-of-00005.bin",
712
+ "transformer.h.8.self_attention.dense.weight": "pytorch_model-00001-of-00005.bin",
713
+ "transformer.h.8.self_attention.query_key_value.SCB": "pytorch_model-00001-of-00005.bin",
714
+ "transformer.h.8.self_attention.query_key_value.weight": "pytorch_model-00001-of-00005.bin",
715
+ "transformer.h.9.ln_attn.bias": "pytorch_model-00001-of-00005.bin",
716
+ "transformer.h.9.ln_attn.weight": "pytorch_model-00001-of-00005.bin",
717
+ "transformer.h.9.ln_mlp.bias": "pytorch_model-00001-of-00005.bin",
718
+ "transformer.h.9.ln_mlp.weight": "pytorch_model-00001-of-00005.bin",
719
+ "transformer.h.9.mlp.dense_4h_to_h.SCB": "pytorch_model-00001-of-00005.bin",
720
+ "transformer.h.9.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00005.bin",
721
+ "transformer.h.9.mlp.dense_h_to_4h.SCB": "pytorch_model-00001-of-00005.bin",
722
+ "transformer.h.9.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00005.bin",
723
+ "transformer.h.9.self_attention.dense.SCB": "pytorch_model-00001-of-00005.bin",
724
+ "transformer.h.9.self_attention.dense.weight": "pytorch_model-00001-of-00005.bin",
725
+ "transformer.h.9.self_attention.query_key_value.SCB": "pytorch_model-00001-of-00005.bin",
726
+ "transformer.h.9.self_attention.query_key_value.weight": "pytorch_model-00001-of-00005.bin",
727
+ "transformer.ln_f.bias": "pytorch_model-00005-of-00005.bin",
728
+ "transformer.ln_f.weight": "pytorch_model-00005-of-00005.bin",
729
+ "transformer.word_embeddings.weight": "pytorch_model-00001-of-00005.bin"
730
+ }
731
+ }