Hugging Face's logo

sayril007
/
finoma-secondtokenizer

Text Generation
Transformers
PyTorch
TensorFlow
JAX
opt
text-generation-inference
Inference Endpoints
Model card Files Community
sayril007 commited on
Commit
b215f88
·
1 Parent(s): 502a3eb

Upload 9 files

Browse files

secondtokenizer

Files changed (9) hide show
  1. config.json +28 -0
  2. flax_model.msgpack.index.json +523 -0
  3. generation_config.json +7 -0
  4. merges.txt +0 -0
  5. pytorch_model.bin.index.json +523 -0
  6. special_tokens_map.json +1 -0
  7. tf_model.h5.index.json +523 -0
  8. tokenizer_config.json +1 -0
  9. vocab.json +0 -0
config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_remove_final_layer_norm": false,
3
+ "activation_dropout": 0.0,
4
+ "activation_function": "relu",
5
+ "architectures": [
6
+ "finomaForCausalLM"
7
+ ],
8
+ "attention_dropout": 0.0,
9
+ "bos_token_id": 2,
10
+ "do_layer_norm_before": true,
11
+ "dropout": 0.1,
12
+ "eos_token_id": 2,
13
+ "ffn_dim": 16384,
14
+ "hidden_size": 4096,
15
+ "init_std": 0.02,
16
+ "layerdrop": 0.0,
17
+ "max_position_embeddings": 2048,
18
+ "model_type": "finoma",
19
+ "num_attention_heads": 32,
20
+ "num_hidden_layers": 32,
21
+ "pad_token_id": 1,
22
+ "prefix": "</s>",
23
+ "torch_dtype": "float16",
24
+ "transformers_version": "4.21.0.dev0",
25
+ "use_cache": true,
26
+ "vocab_size": 50272,
27
+ "word_embed_proj_dim": 4096
28
+ }
flax_model.msgpack.index.json ADDED
@@ -0,0 +1,523 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 13316947968
4
+ },
5
+ "weight_map": {
6
+ "model/decoder/embed_positions/embedding": "flax_model-00001-of-00002.msgpack",
7
+ "model/decoder/embed_tokens/embedding": "flax_model-00001-of-00002.msgpack",
8
+ "model/decoder/final_layer_norm/bias": "flax_model-00001-of-00002.msgpack",
9
+ "model/decoder/final_layer_norm/scale": "flax_model-00001-of-00002.msgpack",
10
+ "model/decoder/layers/0/fc1/bias": "flax_model-00001-of-00002.msgpack",
11
+ "model/decoder/layers/0/fc1/kernel": "flax_model-00001-of-00002.msgpack",
12
+ "model/decoder/layers/0/fc2/bias": "flax_model-00001-of-00002.msgpack",
13
+ "model/decoder/layers/0/fc2/kernel": "flax_model-00001-of-00002.msgpack",
14
+ "model/decoder/layers/0/final_layer_norm/bias": "flax_model-00001-of-00002.msgpack",
15
+ "model/decoder/layers/0/final_layer_norm/scale": "flax_model-00001-of-00002.msgpack",
16
+ "model/decoder/layers/0/self_attn/k_proj/bias": "flax_model-00001-of-00002.msgpack",
17
+ "model/decoder/layers/0/self_attn/k_proj/kernel": "flax_model-00001-of-00002.msgpack",
18
+ "model/decoder/layers/0/self_attn/out_proj/bias": "flax_model-00001-of-00002.msgpack",
19
+ "model/decoder/layers/0/self_attn/out_proj/kernel": "flax_model-00001-of-00002.msgpack",
20
+ "model/decoder/layers/0/self_attn/q_proj/bias": "flax_model-00001-of-00002.msgpack",
21
+ "model/decoder/layers/0/self_attn/q_proj/kernel": "flax_model-00001-of-00002.msgpack",
22
+ "model/decoder/layers/0/self_attn/v_proj/bias": "flax_model-00001-of-00002.msgpack",
23
+ "model/decoder/layers/0/self_attn/v_proj/kernel": "flax_model-00001-of-00002.msgpack",
24
+ "model/decoder/layers/0/self_attn_layer_norm/bias": "flax_model-00001-of-00002.msgpack",
25
+ "model/decoder/layers/0/self_attn_layer_norm/scale": "flax_model-00001-of-00002.msgpack",
26
+ "model/decoder/layers/1/fc1/bias": "flax_model-00001-of-00002.msgpack",
27
+ "model/decoder/layers/1/fc1/kernel": "flax_model-00001-of-00002.msgpack",
28
+ "model/decoder/layers/1/fc2/bias": "flax_model-00001-of-00002.msgpack",
29
+ "model/decoder/layers/1/fc2/kernel": "flax_model-00001-of-00002.msgpack",
30
+ "model/decoder/layers/1/final_layer_norm/bias": "flax_model-00001-of-00002.msgpack",
31
+ "model/decoder/layers/1/final_layer_norm/scale": "flax_model-00001-of-00002.msgpack",
32
+ "model/decoder/layers/1/self_attn/k_proj/bias": "flax_model-00001-of-00002.msgpack",
33
+ "model/decoder/layers/1/self_attn/k_proj/kernel": "flax_model-00001-of-00002.msgpack",
34
+ "model/decoder/layers/1/self_attn/out_proj/bias": "flax_model-00001-of-00002.msgpack",
35
+ "model/decoder/layers/1/self_attn/out_proj/kernel": "flax_model-00001-of-00002.msgpack",
36
+ "model/decoder/layers/1/self_attn/q_proj/bias": "flax_model-00001-of-00002.msgpack",
37
+ "model/decoder/layers/1/self_attn/q_proj/kernel": "flax_model-00001-of-00002.msgpack",
38
+ "model/decoder/layers/1/self_attn/v_proj/bias": "flax_model-00001-of-00002.msgpack",
39
+ "model/decoder/layers/1/self_attn/v_proj/kernel": "flax_model-00001-of-00002.msgpack",
40
+ "model/decoder/layers/1/self_attn_layer_norm/bias": "flax_model-00001-of-00002.msgpack",
41
+ "model/decoder/layers/1/self_attn_layer_norm/scale": "flax_model-00001-of-00002.msgpack",
42
+ "model/decoder/layers/10/fc1/bias": "flax_model-00001-of-00002.msgpack",
43
+ "model/decoder/layers/10/fc1/kernel": "flax_model-00001-of-00002.msgpack",
44
+ "model/decoder/layers/10/fc2/bias": "flax_model-00001-of-00002.msgpack",
45
+ "model/decoder/layers/10/fc2/kernel": "flax_model-00001-of-00002.msgpack",
46
+ "model/decoder/layers/10/final_layer_norm/bias": "flax_model-00001-of-00002.msgpack",
47
+ "model/decoder/layers/10/final_layer_norm/scale": "flax_model-00001-of-00002.msgpack",
48
+ "model/decoder/layers/10/self_attn/k_proj/bias": "flax_model-00001-of-00002.msgpack",
49
+ "model/decoder/layers/10/self_attn/k_proj/kernel": "flax_model-00001-of-00002.msgpack",
50
+ "model/decoder/layers/10/self_attn/out_proj/bias": "flax_model-00001-of-00002.msgpack",
51
+ "model/decoder/layers/10/self_attn/out_proj/kernel": "flax_model-00001-of-00002.msgpack",
52
+ "model/decoder/layers/10/self_attn/q_proj/bias": "flax_model-00001-of-00002.msgpack",
53
+ "model/decoder/layers/10/self_attn/q_proj/kernel": "flax_model-00001-of-00002.msgpack",
54
+ "model/decoder/layers/10/self_attn/v_proj/bias": "flax_model-00001-of-00002.msgpack",
55
+ "model/decoder/layers/10/self_attn/v_proj/kernel": "flax_model-00001-of-00002.msgpack",
56
+ "model/decoder/layers/10/self_attn_layer_norm/bias": "flax_model-00001-of-00002.msgpack",
57
+ "model/decoder/layers/10/self_attn_layer_norm/scale": "flax_model-00001-of-00002.msgpack",
58
+ "model/decoder/layers/11/fc1/bias": "flax_model-00001-of-00002.msgpack",
59
+ "model/decoder/layers/11/fc1/kernel": "flax_model-00001-of-00002.msgpack",
60
+ "model/decoder/layers/11/fc2/bias": "flax_model-00001-of-00002.msgpack",
61
+ "model/decoder/layers/11/fc2/kernel": "flax_model-00001-of-00002.msgpack",
62
+ "model/decoder/layers/11/final_layer_norm/bias": "flax_model-00001-of-00002.msgpack",
63
+ "model/decoder/layers/11/final_layer_norm/scale": "flax_model-00001-of-00002.msgpack",
64
+ "model/decoder/layers/11/self_attn/k_proj/bias": "flax_model-00001-of-00002.msgpack",
65
+ "model/decoder/layers/11/self_attn/k_proj/kernel": "flax_model-00001-of-00002.msgpack",
66
+ "model/decoder/layers/11/self_attn/out_proj/bias": "flax_model-00001-of-00002.msgpack",
67
+ "model/decoder/layers/11/self_attn/out_proj/kernel": "flax_model-00001-of-00002.msgpack",
68
+ "model/decoder/layers/11/self_attn/q_proj/bias": "flax_model-00001-of-00002.msgpack",
69
+ "model/decoder/layers/11/self_attn/q_proj/kernel": "flax_model-00001-of-00002.msgpack",
70
+ "model/decoder/layers/11/self_attn/v_proj/bias": "flax_model-00001-of-00002.msgpack",
71
+ "model/decoder/layers/11/self_attn/v_proj/kernel": "flax_model-00001-of-00002.msgpack",
72
+ "model/decoder/layers/11/self_attn_layer_norm/bias": "flax_model-00001-of-00002.msgpack",
73
+ "model/decoder/layers/11/self_attn_layer_norm/scale": "flax_model-00001-of-00002.msgpack",
74
+ "model/decoder/layers/12/fc1/bias": "flax_model-00001-of-00002.msgpack",
75
+ "model/decoder/layers/12/fc1/kernel": "flax_model-00001-of-00002.msgpack",
76
+ "model/decoder/layers/12/fc2/bias": "flax_model-00001-of-00002.msgpack",
77
+ "model/decoder/layers/12/fc2/kernel": "flax_model-00001-of-00002.msgpack",
78
+ "model/decoder/layers/12/final_layer_norm/bias": "flax_model-00001-of-00002.msgpack",
79
+ "model/decoder/layers/12/final_layer_norm/scale": "flax_model-00001-of-00002.msgpack",
80
+ "model/decoder/layers/12/self_attn/k_proj/bias": "flax_model-00001-of-00002.msgpack",
81
+ "model/decoder/layers/12/self_attn/k_proj/kernel": "flax_model-00001-of-00002.msgpack",
82
+ "model/decoder/layers/12/self_attn/out_proj/bias": "flax_model-00001-of-00002.msgpack",
83
+ "model/decoder/layers/12/self_attn/out_proj/kernel": "flax_model-00001-of-00002.msgpack",
84
+ "model/decoder/layers/12/self_attn/q_proj/bias": "flax_model-00001-of-00002.msgpack",
85
+ "model/decoder/layers/12/self_attn/q_proj/kernel": "flax_model-00001-of-00002.msgpack",
86
+ "model/decoder/layers/12/self_attn/v_proj/bias": "flax_model-00001-of-00002.msgpack",
87
+ "model/decoder/layers/12/self_attn/v_proj/kernel": "flax_model-00001-of-00002.msgpack",
88
+ "model/decoder/layers/12/self_attn_layer_norm/bias": "flax_model-00001-of-00002.msgpack",
89
+ "model/decoder/layers/12/self_attn_layer_norm/scale": "flax_model-00001-of-00002.msgpack",
90
+ "model/decoder/layers/13/fc1/bias": "flax_model-00001-of-00002.msgpack",
91
+ "model/decoder/layers/13/fc1/kernel": "flax_model-00001-of-00002.msgpack",
92
+ "model/decoder/layers/13/fc2/bias": "flax_model-00001-of-00002.msgpack",
93
+ "model/decoder/layers/13/fc2/kernel": "flax_model-00001-of-00002.msgpack",
94
+ "model/decoder/layers/13/final_layer_norm/bias": "flax_model-00001-of-00002.msgpack",
95
+ "model/decoder/layers/13/final_layer_norm/scale": "flax_model-00001-of-00002.msgpack",
96
+ "model/decoder/layers/13/self_attn/k_proj/bias": "flax_model-00001-of-00002.msgpack",
97
+ "model/decoder/layers/13/self_attn/k_proj/kernel": "flax_model-00001-of-00002.msgpack",
98
+ "model/decoder/layers/13/self_attn/out_proj/bias": "flax_model-00001-of-00002.msgpack",
99
+ "model/decoder/layers/13/self_attn/out_proj/kernel": "flax_model-00001-of-00002.msgpack",
100
+ "model/decoder/layers/13/self_attn/q_proj/bias": "flax_model-00001-of-00002.msgpack",
101
+ "model/decoder/layers/13/self_attn/q_proj/kernel": "flax_model-00001-of-00002.msgpack",
102
+ "model/decoder/layers/13/self_attn/v_proj/bias": "flax_model-00001-of-00002.msgpack",
103
+ "model/decoder/layers/13/self_attn/v_proj/kernel": "flax_model-00001-of-00002.msgpack",
104
+ "model/decoder/layers/13/self_attn_layer_norm/bias": "flax_model-00001-of-00002.msgpack",
105
+ "model/decoder/layers/13/self_attn_layer_norm/scale": "flax_model-00001-of-00002.msgpack",
106
+ "model/decoder/layers/14/fc1/bias": "flax_model-00001-of-00002.msgpack",
107
+ "model/decoder/layers/14/fc1/kernel": "flax_model-00001-of-00002.msgpack",
108
+ "model/decoder/layers/14/fc2/bias": "flax_model-00001-of-00002.msgpack",
109
+ "model/decoder/layers/14/fc2/kernel": "flax_model-00001-of-00002.msgpack",
110
+ "model/decoder/layers/14/final_layer_norm/bias": "flax_model-00001-of-00002.msgpack",
111
+ "model/decoder/layers/14/final_layer_norm/scale": "flax_model-00001-of-00002.msgpack",
112
+ "model/decoder/layers/14/self_attn/k_proj/bias": "flax_model-00001-of-00002.msgpack",
113
+ "model/decoder/layers/14/self_attn/k_proj/kernel": "flax_model-00001-of-00002.msgpack",
114
+ "model/decoder/layers/14/self_attn/out_proj/bias": "flax_model-00001-of-00002.msgpack",
115
+ "model/decoder/layers/14/self_attn/out_proj/kernel": "flax_model-00001-of-00002.msgpack",
116
+ "model/decoder/layers/14/self_attn/q_proj/bias": "flax_model-00001-of-00002.msgpack",
117
+ "model/decoder/layers/14/self_attn/q_proj/kernel": "flax_model-00001-of-00002.msgpack",
118
+ "model/decoder/layers/14/self_attn/v_proj/bias": "flax_model-00001-of-00002.msgpack",
119
+ "model/decoder/layers/14/self_attn/v_proj/kernel": "flax_model-00001-of-00002.msgpack",
120
+ "model/decoder/layers/14/self_attn_layer_norm/bias": "flax_model-00001-of-00002.msgpack",
121
+ "model/decoder/layers/14/self_attn_layer_norm/scale": "flax_model-00001-of-00002.msgpack",
122
+ "model/decoder/layers/15/fc1/bias": "flax_model-00001-of-00002.msgpack",
123
+ "model/decoder/layers/15/fc1/kernel": "flax_model-00001-of-00002.msgpack",
124
+ "model/decoder/layers/15/fc2/bias": "flax_model-00001-of-00002.msgpack",
125
+ "model/decoder/layers/15/fc2/kernel": "flax_model-00001-of-00002.msgpack",
126
+ "model/decoder/layers/15/final_layer_norm/bias": "flax_model-00001-of-00002.msgpack",
127
+ "model/decoder/layers/15/final_layer_norm/scale": "flax_model-00001-of-00002.msgpack",
128
+ "model/decoder/layers/15/self_attn/k_proj/bias": "flax_model-00001-of-00002.msgpack",
129
+ "model/decoder/layers/15/self_attn/k_proj/kernel": "flax_model-00001-of-00002.msgpack",
130
+ "model/decoder/layers/15/self_attn/out_proj/bias": "flax_model-00001-of-00002.msgpack",
131
+ "model/decoder/layers/15/self_attn/out_proj/kernel": "flax_model-00001-of-00002.msgpack",
132
+ "model/decoder/layers/15/self_attn/q_proj/bias": "flax_model-00001-of-00002.msgpack",
133
+ "model/decoder/layers/15/self_attn/q_proj/kernel": "flax_model-00001-of-00002.msgpack",
134
+ "model/decoder/layers/15/self_attn/v_proj/bias": "flax_model-00001-of-00002.msgpack",
135
+ "model/decoder/layers/15/self_attn/v_proj/kernel": "flax_model-00001-of-00002.msgpack",
136
+ "model/decoder/layers/15/self_attn_layer_norm/bias": "flax_model-00001-of-00002.msgpack",
137
+ "model/decoder/layers/15/self_attn_layer_norm/scale": "flax_model-00001-of-00002.msgpack",
138
+ "model/decoder/layers/16/fc1/bias": "flax_model-00001-of-00002.msgpack",
139
+ "model/decoder/layers/16/fc1/kernel": "flax_model-00001-of-00002.msgpack",
140
+ "model/decoder/layers/16/fc2/bias": "flax_model-00001-of-00002.msgpack",
141
+ "model/decoder/layers/16/fc2/kernel": "flax_model-00001-of-00002.msgpack",
142
+ "model/decoder/layers/16/final_layer_norm/bias": "flax_model-00001-of-00002.msgpack",
143
+ "model/decoder/layers/16/final_layer_norm/scale": "flax_model-00001-of-00002.msgpack",
144
+ "model/decoder/layers/16/self_attn/k_proj/bias": "flax_model-00001-of-00002.msgpack",
145
+ "model/decoder/layers/16/self_attn/k_proj/kernel": "flax_model-00001-of-00002.msgpack",
146
+ "model/decoder/layers/16/self_attn/out_proj/bias": "flax_model-00001-of-00002.msgpack",
147
+ "model/decoder/layers/16/self_attn/out_proj/kernel": "flax_model-00001-of-00002.msgpack",
148
+ "model/decoder/layers/16/self_attn/q_proj/bias": "flax_model-00001-of-00002.msgpack",
149
+ "model/decoder/layers/16/self_attn/q_proj/kernel": "flax_model-00001-of-00002.msgpack",
150
+ "model/decoder/layers/16/self_attn/v_proj/bias": "flax_model-00001-of-00002.msgpack",
151
+ "model/decoder/layers/16/self_attn/v_proj/kernel": "flax_model-00001-of-00002.msgpack",
152
+ "model/decoder/layers/16/self_attn_layer_norm/bias": "flax_model-00001-of-00002.msgpack",
153
+ "model/decoder/layers/16/self_attn_layer_norm/scale": "flax_model-00001-of-00002.msgpack",
154
+ "model/decoder/layers/17/fc1/bias": "flax_model-00001-of-00002.msgpack",
155
+ "model/decoder/layers/17/fc1/kernel": "flax_model-00001-of-00002.msgpack",
156
+ "model/decoder/layers/17/fc2/bias": "flax_model-00001-of-00002.msgpack",
157
+ "model/decoder/layers/17/fc2/kernel": "flax_model-00001-of-00002.msgpack",
158
+ "model/decoder/layers/17/final_layer_norm/bias": "flax_model-00001-of-00002.msgpack",
159
+ "model/decoder/layers/17/final_layer_norm/scale": "flax_model-00001-of-00002.msgpack",
160
+ "model/decoder/layers/17/self_attn/k_proj/bias": "flax_model-00001-of-00002.msgpack",
161
+ "model/decoder/layers/17/self_attn/k_proj/kernel": "flax_model-00001-of-00002.msgpack",
162
+ "model/decoder/layers/17/self_attn/out_proj/bias": "flax_model-00001-of-00002.msgpack",
163
+ "model/decoder/layers/17/self_attn/out_proj/kernel": "flax_model-00001-of-00002.msgpack",
164
+ "model/decoder/layers/17/self_attn/q_proj/bias": "flax_model-00001-of-00002.msgpack",
165
+ "model/decoder/layers/17/self_attn/q_proj/kernel": "flax_model-00001-of-00002.msgpack",
166
+ "model/decoder/layers/17/self_attn/v_proj/bias": "flax_model-00001-of-00002.msgpack",
167
+ "model/decoder/layers/17/self_attn/v_proj/kernel": "flax_model-00001-of-00002.msgpack",
168
+ "model/decoder/layers/17/self_attn_layer_norm/bias": "flax_model-00001-of-00002.msgpack",
169
+ "model/decoder/layers/17/self_attn_layer_norm/scale": "flax_model-00001-of-00002.msgpack",
170
+ "model/decoder/layers/18/fc1/bias": "flax_model-00001-of-00002.msgpack",
171
+ "model/decoder/layers/18/fc1/kernel": "flax_model-00001-of-00002.msgpack",
172
+ "model/decoder/layers/18/fc2/bias": "flax_model-00001-of-00002.msgpack",
173
+ "model/decoder/layers/18/fc2/kernel": "flax_model-00001-of-00002.msgpack",
174
+ "model/decoder/layers/18/final_layer_norm/bias": "flax_model-00001-of-00002.msgpack",
175
+ "model/decoder/layers/18/final_layer_norm/scale": "flax_model-00001-of-00002.msgpack",
176
+ "model/decoder/layers/18/self_attn/k_proj/bias": "flax_model-00001-of-00002.msgpack",
177
+ "model/decoder/layers/18/self_attn/k_proj/kernel": "flax_model-00001-of-00002.msgpack",
178
+ "model/decoder/layers/18/self_attn/out_proj/bias": "flax_model-00001-of-00002.msgpack",
179
+ "model/decoder/layers/18/self_attn/out_proj/kernel": "flax_model-00001-of-00002.msgpack",
180
+ "model/decoder/layers/18/self_attn/q_proj/bias": "flax_model-00001-of-00002.msgpack",
181
+ "model/decoder/layers/18/self_attn/q_proj/kernel": "flax_model-00001-of-00002.msgpack",
182
+ "model/decoder/layers/18/self_attn/v_proj/bias": "flax_model-00001-of-00002.msgpack",
183
+ "model/decoder/layers/18/self_attn/v_proj/kernel": "flax_model-00001-of-00002.msgpack",
184
+ "model/decoder/layers/18/self_attn_layer_norm/bias": "flax_model-00001-of-00002.msgpack",
185
+ "model/decoder/layers/18/self_attn_layer_norm/scale": "flax_model-00001-of-00002.msgpack",
186
+ "model/decoder/layers/19/fc1/bias": "flax_model-00001-of-00002.msgpack",
187
+ "model/decoder/layers/19/fc1/kernel": "flax_model-00001-of-00002.msgpack",
188
+ "model/decoder/layers/19/fc2/bias": "flax_model-00001-of-00002.msgpack",
189
+ "model/decoder/layers/19/fc2/kernel": "flax_model-00001-of-00002.msgpack",
190
+ "model/decoder/layers/19/final_layer_norm/bias": "flax_model-00001-of-00002.msgpack",
191
+ "model/decoder/layers/19/final_layer_norm/scale": "flax_model-00001-of-00002.msgpack",
192
+ "model/decoder/layers/19/self_attn/k_proj/bias": "flax_model-00001-of-00002.msgpack",
193
+ "model/decoder/layers/19/self_attn/k_proj/kernel": "flax_model-00001-of-00002.msgpack",
194
+ "model/decoder/layers/19/self_attn/out_proj/bias": "flax_model-00001-of-00002.msgpack",
195
+ "model/decoder/layers/19/self_attn/out_proj/kernel": "flax_model-00001-of-00002.msgpack",
196
+ "model/decoder/layers/19/self_attn/q_proj/bias": "flax_model-00001-of-00002.msgpack",
197
+ "model/decoder/layers/19/self_attn/q_proj/kernel": "flax_model-00001-of-00002.msgpack",
198
+ "model/decoder/layers/19/self_attn/v_proj/bias": "flax_model-00001-of-00002.msgpack",
199
+ "model/decoder/layers/19/self_attn/v_proj/kernel": "flax_model-00001-of-00002.msgpack",
200
+ "model/decoder/layers/19/self_attn_layer_norm/bias": "flax_model-00001-of-00002.msgpack",
201
+ "model/decoder/layers/19/self_attn_layer_norm/scale": "flax_model-00001-of-00002.msgpack",
202
+ "model/decoder/layers/2/fc1/bias": "flax_model-00001-of-00002.msgpack",
203
+ "model/decoder/layers/2/fc1/kernel": "flax_model-00001-of-00002.msgpack",
204
+ "model/decoder/layers/2/fc2/bias": "flax_model-00001-of-00002.msgpack",
205
+ "model/decoder/layers/2/fc2/kernel": "flax_model-00001-of-00002.msgpack",
206
+ "model/decoder/layers/2/final_layer_norm/bias": "flax_model-00001-of-00002.msgpack",
207
+ "model/decoder/layers/2/final_layer_norm/scale": "flax_model-00001-of-00002.msgpack",
208
+ "model/decoder/layers/2/self_attn/k_proj/bias": "flax_model-00001-of-00002.msgpack",
209
+ "model/decoder/layers/2/self_attn/k_proj/kernel": "flax_model-00001-of-00002.msgpack",
210
+ "model/decoder/layers/2/self_attn/out_proj/bias": "flax_model-00001-of-00002.msgpack",
211
+ "model/decoder/layers/2/self_attn/out_proj/kernel": "flax_model-00001-of-00002.msgpack",
212
+ "model/decoder/layers/2/self_attn/q_proj/bias": "flax_model-00001-of-00002.msgpack",
213
+ "model/decoder/layers/2/self_attn/q_proj/kernel": "flax_model-00001-of-00002.msgpack",
214
+ "model/decoder/layers/2/self_attn/v_proj/bias": "flax_model-00001-of-00002.msgpack",
215
+ "model/decoder/layers/2/self_attn/v_proj/kernel": "flax_model-00001-of-00002.msgpack",
216
+ "model/decoder/layers/2/self_attn_layer_norm/bias": "flax_model-00001-of-00002.msgpack",
217
+ "model/decoder/layers/2/self_attn_layer_norm/scale": "flax_model-00001-of-00002.msgpack",
218
+ "model/decoder/layers/20/fc1/bias": "flax_model-00001-of-00002.msgpack",
219
+ "model/decoder/layers/20/fc1/kernel": "flax_model-00001-of-00002.msgpack",
220
+ "model/decoder/layers/20/fc2/bias": "flax_model-00001-of-00002.msgpack",
221
+ "model/decoder/layers/20/fc2/kernel": "flax_model-00001-of-00002.msgpack",
222
+ "model/decoder/layers/20/final_layer_norm/bias": "flax_model-00001-of-00002.msgpack",
223
+ "model/decoder/layers/20/final_layer_norm/scale": "flax_model-00001-of-00002.msgpack",
224
+ "model/decoder/layers/20/self_attn/k_proj/bias": "flax_model-00001-of-00002.msgpack",
225
+ "model/decoder/layers/20/self_attn/k_proj/kernel": "flax_model-00001-of-00002.msgpack",
226
+ "model/decoder/layers/20/self_attn/out_proj/bias": "flax_model-00001-of-00002.msgpack",
227
+ "model/decoder/layers/20/self_attn/out_proj/kernel": "flax_model-00001-of-00002.msgpack",
228
+ "model/decoder/layers/20/self_attn/q_proj/bias": "flax_model-00001-of-00002.msgpack",
229
+ "model/decoder/layers/20/self_attn/q_proj/kernel": "flax_model-00001-of-00002.msgpack",
230
+ "model/decoder/layers/20/self_attn/v_proj/bias": "flax_model-00001-of-00002.msgpack",
231
+ "model/decoder/layers/20/self_attn/v_proj/kernel": "flax_model-00001-of-00002.msgpack",
232
+ "model/decoder/layers/20/self_attn_layer_norm/bias": "flax_model-00001-of-00002.msgpack",
233
+ "model/decoder/layers/20/self_attn_layer_norm/scale": "flax_model-00001-of-00002.msgpack",
234
+ "model/decoder/layers/21/fc1/bias": "flax_model-00001-of-00002.msgpack",
235
+ "model/decoder/layers/21/fc1/kernel": "flax_model-00001-of-00002.msgpack",
236
+ "model/decoder/layers/21/fc2/bias": "flax_model-00001-of-00002.msgpack",
237
+ "model/decoder/layers/21/fc2/kernel": "flax_model-00001-of-00002.msgpack",
238
+ "model/decoder/layers/21/final_layer_norm/bias": "flax_model-00001-of-00002.msgpack",
239
+ "model/decoder/layers/21/final_layer_norm/scale": "flax_model-00001-of-00002.msgpack",
240
+ "model/decoder/layers/21/self_attn/k_proj/bias": "flax_model-00001-of-00002.msgpack",
241
+ "model/decoder/layers/21/self_attn/k_proj/kernel": "flax_model-00001-of-00002.msgpack",
242
+ "model/decoder/layers/21/self_attn/out_proj/bias": "flax_model-00001-of-00002.msgpack",
243
+ "model/decoder/layers/21/self_attn/out_proj/kernel": "flax_model-00001-of-00002.msgpack",
244
+ "model/decoder/layers/21/self_attn/q_proj/bias": "flax_model-00001-of-00002.msgpack",
245
+ "model/decoder/layers/21/self_attn/q_proj/kernel": "flax_model-00001-of-00002.msgpack",
246
+ "model/decoder/layers/21/self_attn/v_proj/bias": "flax_model-00001-of-00002.msgpack",
247
+ "model/decoder/layers/21/self_attn/v_proj/kernel": "flax_model-00001-of-00002.msgpack",
248
+ "model/decoder/layers/21/self_attn_layer_norm/bias": "flax_model-00001-of-00002.msgpack",
249
+ "model/decoder/layers/21/self_attn_layer_norm/scale": "flax_model-00001-of-00002.msgpack",
250
+ "model/decoder/layers/22/fc1/bias": "flax_model-00001-of-00002.msgpack",
251
+ "model/decoder/layers/22/fc1/kernel": "flax_model-00001-of-00002.msgpack",
252
+ "model/decoder/layers/22/fc2/bias": "flax_model-00001-of-00002.msgpack",
253
+ "model/decoder/layers/22/fc2/kernel": "flax_model-00001-of-00002.msgpack",
254
+ "model/decoder/layers/22/final_layer_norm/bias": "flax_model-00001-of-00002.msgpack",
255
+ "model/decoder/layers/22/final_layer_norm/scale": "flax_model-00001-of-00002.msgpack",
256
+ "model/decoder/layers/22/self_attn/k_proj/bias": "flax_model-00001-of-00002.msgpack",
257
+ "model/decoder/layers/22/self_attn/k_proj/kernel": "flax_model-00001-of-00002.msgpack",
258
+ "model/decoder/layers/22/self_attn/out_proj/bias": "flax_model-00001-of-00002.msgpack",
259
+ "model/decoder/layers/22/self_attn/out_proj/kernel": "flax_model-00001-of-00002.msgpack",
260
+ "model/decoder/layers/22/self_attn/q_proj/bias": "flax_model-00001-of-00002.msgpack",
261
+ "model/decoder/layers/22/self_attn/q_proj/kernel": "flax_model-00001-of-00002.msgpack",
262
+ "model/decoder/layers/22/self_attn/v_proj/bias": "flax_model-00001-of-00002.msgpack",
263
+ "model/decoder/layers/22/self_attn/v_proj/kernel": "flax_model-00001-of-00002.msgpack",
264
+ "model/decoder/layers/22/self_attn_layer_norm/bias": "flax_model-00001-of-00002.msgpack",
265
+ "model/decoder/layers/22/self_attn_layer_norm/scale": "flax_model-00001-of-00002.msgpack",
266
+ "model/decoder/layers/23/fc1/bias": "flax_model-00001-of-00002.msgpack",
267
+ "model/decoder/layers/23/fc1/kernel": "flax_model-00001-of-00002.msgpack",
268
+ "model/decoder/layers/23/fc2/bias": "flax_model-00001-of-00002.msgpack",
269
+ "model/decoder/layers/23/fc2/kernel": "flax_model-00001-of-00002.msgpack",
270
+ "model/decoder/layers/23/final_layer_norm/bias": "flax_model-00001-of-00002.msgpack",
271
+ "model/decoder/layers/23/final_layer_norm/scale": "flax_model-00001-of-00002.msgpack",
272
+ "model/decoder/layers/23/self_attn/k_proj/bias": "flax_model-00001-of-00002.msgpack",
273
+ "model/decoder/layers/23/self_attn/k_proj/kernel": "flax_model-00001-of-00002.msgpack",
274
+ "model/decoder/layers/23/self_attn/out_proj/bias": "flax_model-00001-of-00002.msgpack",
275
+ "model/decoder/layers/23/self_attn/out_proj/kernel": "flax_model-00001-of-00002.msgpack",
276
+ "model/decoder/layers/23/self_attn/q_proj/bias": "flax_model-00001-of-00002.msgpack",
277
+ "model/decoder/layers/23/self_attn/q_proj/kernel": "flax_model-00001-of-00002.msgpack",
278
+ "model/decoder/layers/23/self_attn/v_proj/bias": "flax_model-00001-of-00002.msgpack",
279
+ "model/decoder/layers/23/self_attn/v_proj/kernel": "flax_model-00001-of-00002.msgpack",
280
+ "model/decoder/layers/23/self_attn_layer_norm/bias": "flax_model-00001-of-00002.msgpack",
281
+ "model/decoder/layers/23/self_attn_layer_norm/scale": "flax_model-00001-of-00002.msgpack",
282
+ "model/decoder/layers/24/fc1/bias": "flax_model-00001-of-00002.msgpack",
283
+ "model/decoder/layers/24/fc1/kernel": "flax_model-00001-of-00002.msgpack",
284
+ "model/decoder/layers/24/fc2/bias": "flax_model-00001-of-00002.msgpack",
285
+ "model/decoder/layers/24/fc2/kernel": "flax_model-00001-of-00002.msgpack",
286
+ "model/decoder/layers/24/final_layer_norm/bias": "flax_model-00001-of-00002.msgpack",
287
+ "model/decoder/layers/24/final_layer_norm/scale": "flax_model-00001-of-00002.msgpack",
288
+ "model/decoder/layers/24/self_attn/k_proj/bias": "flax_model-00001-of-00002.msgpack",
289
+ "model/decoder/layers/24/self_attn/k_proj/kernel": "flax_model-00001-of-00002.msgpack",
290
+ "model/decoder/layers/24/self_attn/out_proj/bias": "flax_model-00001-of-00002.msgpack",
291
+ "model/decoder/layers/24/self_attn/out_proj/kernel": "flax_model-00001-of-00002.msgpack",
292
+ "model/decoder/layers/24/self_attn/q_proj/bias": "flax_model-00001-of-00002.msgpack",
293
+ "model/decoder/layers/24/self_attn/q_proj/kernel": "flax_model-00001-of-00002.msgpack",
294
+ "model/decoder/layers/24/self_attn/v_proj/bias": "flax_model-00001-of-00002.msgpack",
295
+ "model/decoder/layers/24/self_attn/v_proj/kernel": "flax_model-00001-of-00002.msgpack",
296
+ "model/decoder/layers/24/self_attn_layer_norm/bias": "flax_model-00001-of-00002.msgpack",
297
+ "model/decoder/layers/24/self_attn_layer_norm/scale": "flax_model-00001-of-00002.msgpack",
298
+ "model/decoder/layers/25/fc1/bias": "flax_model-00001-of-00002.msgpack",
299
+ "model/decoder/layers/25/fc1/kernel": "flax_model-00001-of-00002.msgpack",
300
+ "model/decoder/layers/25/fc2/bias": "flax_model-00001-of-00002.msgpack",
301
+ "model/decoder/layers/25/fc2/kernel": "flax_model-00001-of-00002.msgpack",
302
+ "model/decoder/layers/25/final_layer_norm/bias": "flax_model-00001-of-00002.msgpack",
303
+ "model/decoder/layers/25/final_layer_norm/scale": "flax_model-00001-of-00002.msgpack",
304
+ "model/decoder/layers/25/self_attn/k_proj/bias": "flax_model-00001-of-00002.msgpack",
305
+ "model/decoder/layers/25/self_attn/k_proj/kernel": "flax_model-00001-of-00002.msgpack",
306
+ "model/decoder/layers/25/self_attn/out_proj/bias": "flax_model-00001-of-00002.msgpack",
307
+ "model/decoder/layers/25/self_attn/out_proj/kernel": "flax_model-00001-of-00002.msgpack",
308
+ "model/decoder/layers/25/self_attn/q_proj/bias": "flax_model-00001-of-00002.msgpack",
309
+ "model/decoder/layers/25/self_attn/q_proj/kernel": "flax_model-00001-of-00002.msgpack",
310
+ "model/decoder/layers/25/self_attn/v_proj/bias": "flax_model-00001-of-00002.msgpack",
311
+ "model/decoder/layers/25/self_attn/v_proj/kernel": "flax_model-00001-of-00002.msgpack",
312
+ "model/decoder/layers/25/self_attn_layer_norm/bias": "flax_model-00001-of-00002.msgpack",
313
+ "model/decoder/layers/25/self_attn_layer_norm/scale": "flax_model-00001-of-00002.msgpack",
314
+ "model/decoder/layers/26/fc1/bias": "flax_model-00001-of-00002.msgpack",
315
+ "model/decoder/layers/26/fc1/kernel": "flax_model-00001-of-00002.msgpack",
316
+ "model/decoder/layers/26/fc2/bias": "flax_model-00001-of-00002.msgpack",
317
+ "model/decoder/layers/26/fc2/kernel": "flax_model-00001-of-00002.msgpack",
318
+ "model/decoder/layers/26/final_layer_norm/bias": "flax_model-00001-of-00002.msgpack",
319
+ "model/decoder/layers/26/final_layer_norm/scale": "flax_model-00001-of-00002.msgpack",
320
+ "model/decoder/layers/26/self_attn/k_proj/bias": "flax_model-00001-of-00002.msgpack",
321
+ "model/decoder/layers/26/self_attn/k_proj/kernel": "flax_model-00001-of-00002.msgpack",
322
+ "model/decoder/layers/26/self_attn/out_proj/bias": "flax_model-00001-of-00002.msgpack",
323
+ "model/decoder/layers/26/self_attn/out_proj/kernel": "flax_model-00001-of-00002.msgpack",
324
+ "model/decoder/layers/26/self_attn/q_proj/bias": "flax_model-00001-of-00002.msgpack",
325
+ "model/decoder/layers/26/self_attn/q_proj/kernel": "flax_model-00001-of-00002.msgpack",
326
+ "model/decoder/layers/26/self_attn/v_proj/bias": "flax_model-00001-of-00002.msgpack",
327
+ "model/decoder/layers/26/self_attn/v_proj/kernel": "flax_model-00001-of-00002.msgpack",
328
+ "model/decoder/layers/26/self_attn_layer_norm/bias": "flax_model-00001-of-00002.msgpack",
329
+ "model/decoder/layers/26/self_attn_layer_norm/scale": "flax_model-00001-of-00002.msgpack",
330
+ "model/decoder/layers/27/fc1/bias": "flax_model-00001-of-00002.msgpack",
331
+ "model/decoder/layers/27/fc1/kernel": "flax_model-00001-of-00002.msgpack",
332
+ "model/decoder/layers/27/fc2/bias": "flax_model-00001-of-00002.msgpack",
333
+ "model/decoder/layers/27/fc2/kernel": "flax_model-00001-of-00002.msgpack",
334
+ "model/decoder/layers/27/final_layer_norm/bias": "flax_model-00001-of-00002.msgpack",
335
+ "model/decoder/layers/27/final_layer_norm/scale": "flax_model-00001-of-00002.msgpack",
336
+ "model/decoder/layers/27/self_attn/k_proj/bias": "flax_model-00001-of-00002.msgpack",
337
+ "model/decoder/layers/27/self_attn/k_proj/kernel": "flax_model-00001-of-00002.msgpack",
338
+ "model/decoder/layers/27/self_attn/out_proj/bias": "flax_model-00001-of-00002.msgpack",
339
+ "model/decoder/layers/27/self_attn/out_proj/kernel": "flax_model-00001-of-00002.msgpack",
340
+ "model/decoder/layers/27/self_attn/q_proj/bias": "flax_model-00001-of-00002.msgpack",
341
+ "model/decoder/layers/27/self_attn/q_proj/kernel": "flax_model-00001-of-00002.msgpack",
342
+ "model/decoder/layers/27/self_attn/v_proj/bias": "flax_model-00001-of-00002.msgpack",
343
+ "model/decoder/layers/27/self_attn/v_proj/kernel": "flax_model-00001-of-00002.msgpack",
344
+ "model/decoder/layers/27/self_attn_layer_norm/bias": "flax_model-00001-of-00002.msgpack",
345
+ "model/decoder/layers/27/self_attn_layer_norm/scale": "flax_model-00001-of-00002.msgpack",
346
+ "model/decoder/layers/28/fc1/bias": "flax_model-00001-of-00002.msgpack",
347
+ "model/decoder/layers/28/fc1/kernel": "flax_model-00001-of-00002.msgpack",
348
+ "model/decoder/layers/28/fc2/bias": "flax_model-00001-of-00002.msgpack",
349
+ "model/decoder/layers/28/fc2/kernel": "flax_model-00001-of-00002.msgpack",
350
+ "model/decoder/layers/28/final_layer_norm/bias": "flax_model-00001-of-00002.msgpack",
351
+ "model/decoder/layers/28/final_layer_norm/scale": "flax_model-00001-of-00002.msgpack",
352
+ "model/decoder/layers/28/self_attn/k_proj/bias": "flax_model-00001-of-00002.msgpack",
353
+ "model/decoder/layers/28/self_attn/k_proj/kernel": "flax_model-00001-of-00002.msgpack",
354
+ "model/decoder/layers/28/self_attn/out_proj/bias": "flax_model-00001-of-00002.msgpack",
355
+ "model/decoder/layers/28/self_attn/out_proj/kernel": "flax_model-00001-of-00002.msgpack",
356
+ "model/decoder/layers/28/self_attn/q_proj/bias": "flax_model-00001-of-00002.msgpack",
357
+ "model/decoder/layers/28/self_attn/q_proj/kernel": "flax_model-00001-of-00002.msgpack",
358
+ "model/decoder/layers/28/self_attn/v_proj/bias": "flax_model-00001-of-00002.msgpack",
359
+ "model/decoder/layers/28/self_attn/v_proj/kernel": "flax_model-00001-of-00002.msgpack",
360
+ "model/decoder/layers/28/self_attn_layer_norm/bias": "flax_model-00001-of-00002.msgpack",
361
+ "model/decoder/layers/28/self_attn_layer_norm/scale": "flax_model-00001-of-00002.msgpack",
362
+ "model/decoder/layers/29/fc1/bias": "flax_model-00001-of-00002.msgpack",
363
+ "model/decoder/layers/29/fc1/kernel": "flax_model-00001-of-00002.msgpack",
364
+ "model/decoder/layers/29/fc2/bias": "flax_model-00001-of-00002.msgpack",
365
+ "model/decoder/layers/29/fc2/kernel": "flax_model-00001-of-00002.msgpack",
366
+ "model/decoder/layers/29/final_layer_norm/bias": "flax_model-00001-of-00002.msgpack",
367
+ "model/decoder/layers/29/final_layer_norm/scale": "flax_model-00001-of-00002.msgpack",
368
+ "model/decoder/layers/29/self_attn/k_proj/bias": "flax_model-00001-of-00002.msgpack",
369
+ "model/decoder/layers/29/self_attn/k_proj/kernel": "flax_model-00001-of-00002.msgpack",
370
+ "model/decoder/layers/29/self_attn/out_proj/bias": "flax_model-00001-of-00002.msgpack",
371
+ "model/decoder/layers/29/self_attn/out_proj/kernel": "flax_model-00001-of-00002.msgpack",
372
+ "model/decoder/layers/29/self_attn/q_proj/bias": "flax_model-00001-of-00002.msgpack",
373
+ "model/decoder/layers/29/self_attn/q_proj/kernel": "flax_model-00001-of-00002.msgpack",
374
+ "model/decoder/layers/29/self_attn/v_proj/bias": "flax_model-00001-of-00002.msgpack",
375
+ "model/decoder/layers/29/self_attn/v_proj/kernel": "flax_model-00001-of-00002.msgpack",
376
+ "model/decoder/layers/29/self_attn_layer_norm/bias": "flax_model-00001-of-00002.msgpack",
377
+ "model/decoder/layers/29/self_attn_layer_norm/scale": "flax_model-00001-of-00002.msgpack",
378
+ "model/decoder/layers/3/fc1/bias": "flax_model-00001-of-00002.msgpack",
379
+ "model/decoder/layers/3/fc1/kernel": "flax_model-00001-of-00002.msgpack",
380
+ "model/decoder/layers/3/fc2/bias": "flax_model-00001-of-00002.msgpack",
381
+ "model/decoder/layers/3/fc2/kernel": "flax_model-00001-of-00002.msgpack",
382
+ "model/decoder/layers/3/final_layer_norm/bias": "flax_model-00001-of-00002.msgpack",
383
+ "model/decoder/layers/3/final_layer_norm/scale": "flax_model-00001-of-00002.msgpack",
384
+ "model/decoder/layers/3/self_attn/k_proj/bias": "flax_model-00001-of-00002.msgpack",
385
+ "model/decoder/layers/3/self_attn/k_proj/kernel": "flax_model-00001-of-00002.msgpack",
386
+ "model/decoder/layers/3/self_attn/out_proj/bias": "flax_model-00001-of-00002.msgpack",
387
+ "model/decoder/layers/3/self_attn/out_proj/kernel": "flax_model-00002-of-00002.msgpack",
388
+ "model/decoder/layers/3/self_attn/q_proj/bias": "flax_model-00002-of-00002.msgpack",
389
+ "model/decoder/layers/3/self_attn/q_proj/kernel": "flax_model-00002-of-00002.msgpack",
390
+ "model/decoder/layers/3/self_attn/v_proj/bias": "flax_model-00002-of-00002.msgpack",
391
+ "model/decoder/layers/3/self_attn/v_proj/kernel": "flax_model-00002-of-00002.msgpack",
392
+ "model/decoder/layers/3/self_attn_layer_norm/bias": "flax_model-00002-of-00002.msgpack",
393
+ "model/decoder/layers/3/self_attn_layer_norm/scale": "flax_model-00002-of-00002.msgpack",
394
+ "model/decoder/layers/30/fc1/bias": "flax_model-00002-of-00002.msgpack",
395
+ "model/decoder/layers/30/fc1/kernel": "flax_model-00002-of-00002.msgpack",
396
+ "model/decoder/layers/30/fc2/bias": "flax_model-00002-of-00002.msgpack",
397
+ "model/decoder/layers/30/fc2/kernel": "flax_model-00002-of-00002.msgpack",
398
+ "model/decoder/layers/30/final_layer_norm/bias": "flax_model-00002-of-00002.msgpack",
399
+ "model/decoder/layers/30/final_layer_norm/scale": "flax_model-00002-of-00002.msgpack",
400
+ "model/decoder/layers/30/self_attn/k_proj/bias": "flax_model-00002-of-00002.msgpack",
401
+ "model/decoder/layers/30/self_attn/k_proj/kernel": "flax_model-00002-of-00002.msgpack",
402
+ "model/decoder/layers/30/self_attn/out_proj/bias": "flax_model-00002-of-00002.msgpack",
403
+ "model/decoder/layers/30/self_attn/out_proj/kernel": "flax_model-00002-of-00002.msgpack",
404
+ "model/decoder/layers/30/self_attn/q_proj/bias": "flax_model-00002-of-00002.msgpack",
405
+ "model/decoder/layers/30/self_attn/q_proj/kernel": "flax_model-00002-of-00002.msgpack",
406
+ "model/decoder/layers/30/self_attn/v_proj/bias": "flax_model-00002-of-00002.msgpack",
407
+ "model/decoder/layers/30/self_attn/v_proj/kernel": "flax_model-00002-of-00002.msgpack",
408
+ "model/decoder/layers/30/self_attn_layer_norm/bias": "flax_model-00002-of-00002.msgpack",
409
+ "model/decoder/layers/30/self_attn_layer_norm/scale": "flax_model-00002-of-00002.msgpack",
410
+ "model/decoder/layers/31/fc1/bias": "flax_model-00002-of-00002.msgpack",
411
+ "model/decoder/layers/31/fc1/kernel": "flax_model-00002-of-00002.msgpack",
412
+ "model/decoder/layers/31/fc2/bias": "flax_model-00002-of-00002.msgpack",
413
+ "model/decoder/layers/31/fc2/kernel": "flax_model-00002-of-00002.msgpack",
414
+ "model/decoder/layers/31/final_layer_norm/bias": "flax_model-00002-of-00002.msgpack",
415
+ "model/decoder/layers/31/final_layer_norm/scale": "flax_model-00002-of-00002.msgpack",
416
+ "model/decoder/layers/31/self_attn/k_proj/bias": "flax_model-00002-of-00002.msgpack",
417
+ "model/decoder/layers/31/self_attn/k_proj/kernel": "flax_model-00002-of-00002.msgpack",
418
+ "model/decoder/layers/31/self_attn/out_proj/bias": "flax_model-00002-of-00002.msgpack",
419
+ "model/decoder/layers/31/self_attn/out_proj/kernel": "flax_model-00002-of-00002.msgpack",
420
+ "model/decoder/layers/31/self_attn/q_proj/bias": "flax_model-00002-of-00002.msgpack",
421
+ "model/decoder/layers/31/self_attn/q_proj/kernel": "flax_model-00002-of-00002.msgpack",
422
+ "model/decoder/layers/31/self_attn/v_proj/bias": "flax_model-00002-of-00002.msgpack",
423
+ "model/decoder/layers/31/self_attn/v_proj/kernel": "flax_model-00002-of-00002.msgpack",
424
+ "model/decoder/layers/31/self_attn_layer_norm/bias": "flax_model-00002-of-00002.msgpack",
425
+ "model/decoder/layers/31/self_attn_layer_norm/scale": "flax_model-00002-of-00002.msgpack",
426
+ "model/decoder/layers/4/fc1/bias": "flax_model-00002-of-00002.msgpack",
427
+ "model/decoder/layers/4/fc1/kernel": "flax_model-00002-of-00002.msgpack",
428
+ "model/decoder/layers/4/fc2/bias": "flax_model-00002-of-00002.msgpack",
429
+ "model/decoder/layers/4/fc2/kernel": "flax_model-00002-of-00002.msgpack",
430
+ "model/decoder/layers/4/final_layer_norm/bias": "flax_model-00002-of-00002.msgpack",
431
+ "model/decoder/layers/4/final_layer_norm/scale": "flax_model-00002-of-00002.msgpack",
432
+ "model/decoder/layers/4/self_attn/k_proj/bias": "flax_model-00002-of-00002.msgpack",
433
+ "model/decoder/layers/4/self_attn/k_proj/kernel": "flax_model-00002-of-00002.msgpack",
434
+ "model/decoder/layers/4/self_attn/out_proj/bias": "flax_model-00002-of-00002.msgpack",
435
+ "model/decoder/layers/4/self_attn/out_proj/kernel": "flax_model-00002-of-00002.msgpack",
436
+ "model/decoder/layers/4/self_attn/q_proj/bias": "flax_model-00002-of-00002.msgpack",
437
+ "model/decoder/layers/4/self_attn/q_proj/kernel": "flax_model-00002-of-00002.msgpack",
438
+ "model/decoder/layers/4/self_attn/v_proj/bias": "flax_model-00002-of-00002.msgpack",
439
+ "model/decoder/layers/4/self_attn/v_proj/kernel": "flax_model-00002-of-00002.msgpack",
440
+ "model/decoder/layers/4/self_attn_layer_norm/bias": "flax_model-00002-of-00002.msgpack",
441
+ "model/decoder/layers/4/self_attn_layer_norm/scale": "flax_model-00002-of-00002.msgpack",
442
+ "model/decoder/layers/5/fc1/bias": "flax_model-00002-of-00002.msgpack",
443
+ "model/decoder/layers/5/fc1/kernel": "flax_model-00002-of-00002.msgpack",
444
+ "model/decoder/layers/5/fc2/bias": "flax_model-00002-of-00002.msgpack",
445
+ "model/decoder/layers/5/fc2/kernel": "flax_model-00002-of-00002.msgpack",
446
+ "model/decoder/layers/5/final_layer_norm/bias": "flax_model-00002-of-00002.msgpack",
447
+ "model/decoder/layers/5/final_layer_norm/scale": "flax_model-00002-of-00002.msgpack",
448
+ "model/decoder/layers/5/self_attn/k_proj/bias": "flax_model-00002-of-00002.msgpack",
449
+ "model/decoder/layers/5/self_attn/k_proj/kernel": "flax_model-00002-of-00002.msgpack",
450
+ "model/decoder/layers/5/self_attn/out_proj/bias": "flax_model-00002-of-00002.msgpack",
451
+ "model/decoder/layers/5/self_attn/out_proj/kernel": "flax_model-00002-of-00002.msgpack",
452
+ "model/decoder/layers/5/self_attn/q_proj/bias": "flax_model-00002-of-00002.msgpack",
453
+ "model/decoder/layers/5/self_attn/q_proj/kernel": "flax_model-00002-of-00002.msgpack",
454
+ "model/decoder/layers/5/self_attn/v_proj/bias": "flax_model-00002-of-00002.msgpack",
455
+ "model/decoder/layers/5/self_attn/v_proj/kernel": "flax_model-00002-of-00002.msgpack",
456
+ "model/decoder/layers/5/self_attn_layer_norm/bias": "flax_model-00002-of-00002.msgpack",
457
+ "model/decoder/layers/5/self_attn_layer_norm/scale": "flax_model-00002-of-00002.msgpack",
458
+ "model/decoder/layers/6/fc1/bias": "flax_model-00002-of-00002.msgpack",
459
+ "model/decoder/layers/6/fc1/kernel": "flax_model-00002-of-00002.msgpack",
460
+ "model/decoder/layers/6/fc2/bias": "flax_model-00002-of-00002.msgpack",
461
+ "model/decoder/layers/6/fc2/kernel": "flax_model-00002-of-00002.msgpack",
462
+ "model/decoder/layers/6/final_layer_norm/bias": "flax_model-00002-of-00002.msgpack",
463
+ "model/decoder/layers/6/final_layer_norm/scale": "flax_model-00002-of-00002.msgpack",
464
+ "model/decoder/layers/6/self_attn/k_proj/bias": "flax_model-00002-of-00002.msgpack",
465
+ "model/decoder/layers/6/self_attn/k_proj/kernel": "flax_model-00002-of-00002.msgpack",
466
+ "model/decoder/layers/6/self_attn/out_proj/bias": "flax_model-00002-of-00002.msgpack",
467
+ "model/decoder/layers/6/self_attn/out_proj/kernel": "flax_model-00002-of-00002.msgpack",
468
+ "model/decoder/layers/6/self_attn/q_proj/bias": "flax_model-00002-of-00002.msgpack",
469
+ "model/decoder/layers/6/self_attn/q_proj/kernel": "flax_model-00002-of-00002.msgpack",
470
+ "model/decoder/layers/6/self_attn/v_proj/bias": "flax_model-00002-of-00002.msgpack",
471
+ "model/decoder/layers/6/self_attn/v_proj/kernel": "flax_model-00002-of-00002.msgpack",
472
+ "model/decoder/layers/6/self_attn_layer_norm/bias": "flax_model-00002-of-00002.msgpack",
473
+ "model/decoder/layers/6/self_attn_layer_norm/scale": "flax_model-00002-of-00002.msgpack",
474
+ "model/decoder/layers/7/fc1/bias": "flax_model-00002-of-00002.msgpack",
475
+ "model/decoder/layers/7/fc1/kernel": "flax_model-00002-of-00002.msgpack",
476
+ "model/decoder/layers/7/fc2/bias": "flax_model-00002-of-00002.msgpack",
477
+ "model/decoder/layers/7/fc2/kernel": "flax_model-00002-of-00002.msgpack",
478
+ "model/decoder/layers/7/final_layer_norm/bias": "flax_model-00002-of-00002.msgpack",
479
+ "model/decoder/layers/7/final_layer_norm/scale": "flax_model-00002-of-00002.msgpack",
480
+ "model/decoder/layers/7/self_attn/k_proj/bias": "flax_model-00002-of-00002.msgpack",
481
+ "model/decoder/layers/7/self_attn/k_proj/kernel": "flax_model-00002-of-00002.msgpack",
482
+ "model/decoder/layers/7/self_attn/out_proj/bias": "flax_model-00002-of-00002.msgpack",
483
+ "model/decoder/layers/7/self_attn/out_proj/kernel": "flax_model-00002-of-00002.msgpack",
484
+ "model/decoder/layers/7/self_attn/q_proj/bias": "flax_model-00002-of-00002.msgpack",
485
+ "model/decoder/layers/7/self_attn/q_proj/kernel": "flax_model-00002-of-00002.msgpack",
486
+ "model/decoder/layers/7/self_attn/v_proj/bias": "flax_model-00002-of-00002.msgpack",
487
+ "model/decoder/layers/7/self_attn/v_proj/kernel": "flax_model-00002-of-00002.msgpack",
488
+ "model/decoder/layers/7/self_attn_layer_norm/bias": "flax_model-00002-of-00002.msgpack",
489
+ "model/decoder/layers/7/self_attn_layer_norm/scale": "flax_model-00002-of-00002.msgpack",
490
+ "model/decoder/layers/8/fc1/bias": "flax_model-00002-of-00002.msgpack",
491
+ "model/decoder/layers/8/fc1/kernel": "flax_model-00002-of-00002.msgpack",
492
+ "model/decoder/layers/8/fc2/bias": "flax_model-00002-of-00002.msgpack",
493
+ "model/decoder/layers/8/fc2/kernel": "flax_model-00002-of-00002.msgpack",
494
+ "model/decoder/layers/8/final_layer_norm/bias": "flax_model-00002-of-00002.msgpack",
495
+ "model/decoder/layers/8/final_layer_norm/scale": "flax_model-00002-of-00002.msgpack",
496
+ "model/decoder/layers/8/self_attn/k_proj/bias": "flax_model-00002-of-00002.msgpack",
497
+ "model/decoder/layers/8/self_attn/k_proj/kernel": "flax_model-00002-of-00002.msgpack",
498
+ "model/decoder/layers/8/self_attn/out_proj/bias": "flax_model-00002-of-00002.msgpack",
499
+ "model/decoder/layers/8/self_attn/out_proj/kernel": "flax_model-00002-of-00002.msgpack",
500
+ "model/decoder/layers/8/self_attn/q_proj/bias": "flax_model-00002-of-00002.msgpack",
501
+ "model/decoder/layers/8/self_attn/q_proj/kernel": "flax_model-00002-of-00002.msgpack",
502
+ "model/decoder/layers/8/self_attn/v_proj/bias": "flax_model-00002-of-00002.msgpack",
503
+ "model/decoder/layers/8/self_attn/v_proj/kernel": "flax_model-00002-of-00002.msgpack",
504
+ "model/decoder/layers/8/self_attn_layer_norm/bias": "flax_model-00002-of-00002.msgpack",
505
+ "model/decoder/layers/8/self_attn_layer_norm/scale": "flax_model-00002-of-00002.msgpack",
506
+ "model/decoder/layers/9/fc1/bias": "flax_model-00002-of-00002.msgpack",
507
+ "model/decoder/layers/9/fc1/kernel": "flax_model-00002-of-00002.msgpack",
508
+ "model/decoder/layers/9/fc2/bias": "flax_model-00002-of-00002.msgpack",
509
+ "model/decoder/layers/9/fc2/kernel": "flax_model-00002-of-00002.msgpack",
510
+ "model/decoder/layers/9/final_layer_norm/bias": "flax_model-00002-of-00002.msgpack",
511
+ "model/decoder/layers/9/final_layer_norm/scale": "flax_model-00002-of-00002.msgpack",
512
+ "model/decoder/layers/9/self_attn/k_proj/bias": "flax_model-00002-of-00002.msgpack",
513
+ "model/decoder/layers/9/self_attn/k_proj/kernel": "flax_model-00002-of-00002.msgpack",
514
+ "model/decoder/layers/9/self_attn/out_proj/bias": "flax_model-00002-of-00002.msgpack",
515
+ "model/decoder/layers/9/self_attn/out_proj/kernel": "flax_model-00002-of-00002.msgpack",
516
+ "model/decoder/layers/9/self_attn/q_proj/bias": "flax_model-00002-of-00002.msgpack",
517
+ "model/decoder/layers/9/self_attn/q_proj/kernel": "flax_model-00002-of-00002.msgpack",
518
+ "model/decoder/layers/9/self_attn/v_proj/bias": "flax_model-00002-of-00002.msgpack",
519
+ "model/decoder/layers/9/self_attn/v_proj/kernel": "flax_model-00002-of-00002.msgpack",
520
+ "model/decoder/layers/9/self_attn_layer_norm/bias": "flax_model-00002-of-00002.msgpack",
521
+ "model/decoder/layers/9/self_attn_layer_norm/scale": "flax_model-00002-of-00002.msgpack"
522
+ }
523
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 2,
4
+ "eos_token_id": 2,
5
+ "pad_token_id": 1,
6
+ "transformers_version": "4.27.0.dev0"
7
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
pytorch_model.bin.index.json ADDED
@@ -0,0 +1,523 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 13316947968
4
+ },
5
+ "weight_map": {
6
+ "decoder.embed_positions.weight": "pytorch_model-00001-of-00002.bin",
7
+ "decoder.embed_tokens.weight": "pytorch_model-00001-of-00002.bin",
8
+ "decoder.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
9
+ "decoder.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
10
+ "decoder.layers.0.fc1.bias": "pytorch_model-00001-of-00002.bin",
11
+ "decoder.layers.0.fc1.weight": "pytorch_model-00001-of-00002.bin",
12
+ "decoder.layers.0.fc2.bias": "pytorch_model-00001-of-00002.bin",
13
+ "decoder.layers.0.fc2.weight": "pytorch_model-00001-of-00002.bin",
14
+ "decoder.layers.0.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
15
+ "decoder.layers.0.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
16
+ "decoder.layers.0.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
17
+ "decoder.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
18
+ "decoder.layers.0.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
19
+ "decoder.layers.0.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
20
+ "decoder.layers.0.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
21
+ "decoder.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
22
+ "decoder.layers.0.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
23
+ "decoder.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
24
+ "decoder.layers.0.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
25
+ "decoder.layers.0.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
26
+ "decoder.layers.1.fc1.bias": "pytorch_model-00001-of-00002.bin",
27
+ "decoder.layers.1.fc1.weight": "pytorch_model-00001-of-00002.bin",
28
+ "decoder.layers.1.fc2.bias": "pytorch_model-00001-of-00002.bin",
29
+ "decoder.layers.1.fc2.weight": "pytorch_model-00001-of-00002.bin",
30
+ "decoder.layers.1.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
31
+ "decoder.layers.1.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
32
+ "decoder.layers.1.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
33
+ "decoder.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
34
+ "decoder.layers.1.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
35
+ "decoder.layers.1.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
36
+ "decoder.layers.1.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
37
+ "decoder.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
38
+ "decoder.layers.1.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
39
+ "decoder.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
40
+ "decoder.layers.1.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
41
+ "decoder.layers.1.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
42
+ "decoder.layers.10.fc1.bias": "pytorch_model-00001-of-00002.bin",
43
+ "decoder.layers.10.fc1.weight": "pytorch_model-00001-of-00002.bin",
44
+ "decoder.layers.10.fc2.bias": "pytorch_model-00001-of-00002.bin",
45
+ "decoder.layers.10.fc2.weight": "pytorch_model-00001-of-00002.bin",
46
+ "decoder.layers.10.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
47
+ "decoder.layers.10.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
48
+ "decoder.layers.10.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
49
+ "decoder.layers.10.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
50
+ "decoder.layers.10.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
51
+ "decoder.layers.10.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
52
+ "decoder.layers.10.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
53
+ "decoder.layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
54
+ "decoder.layers.10.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
55
+ "decoder.layers.10.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
56
+ "decoder.layers.10.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
57
+ "decoder.layers.10.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
58
+ "decoder.layers.11.fc1.bias": "pytorch_model-00001-of-00002.bin",
59
+ "decoder.layers.11.fc1.weight": "pytorch_model-00001-of-00002.bin",
60
+ "decoder.layers.11.fc2.bias": "pytorch_model-00001-of-00002.bin",
61
+ "decoder.layers.11.fc2.weight": "pytorch_model-00001-of-00002.bin",
62
+ "decoder.layers.11.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
63
+ "decoder.layers.11.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
64
+ "decoder.layers.11.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
65
+ "decoder.layers.11.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
66
+ "decoder.layers.11.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
67
+ "decoder.layers.11.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
68
+ "decoder.layers.11.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
69
+ "decoder.layers.11.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
70
+ "decoder.layers.11.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
71
+ "decoder.layers.11.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
72
+ "decoder.layers.11.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
73
+ "decoder.layers.11.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
74
+ "decoder.layers.12.fc1.bias": "pytorch_model-00001-of-00002.bin",
75
+ "decoder.layers.12.fc1.weight": "pytorch_model-00001-of-00002.bin",
76
+ "decoder.layers.12.fc2.bias": "pytorch_model-00001-of-00002.bin",
77
+ "decoder.layers.12.fc2.weight": "pytorch_model-00001-of-00002.bin",
78
+ "decoder.layers.12.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
79
+ "decoder.layers.12.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
80
+ "decoder.layers.12.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
81
+ "decoder.layers.12.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
82
+ "decoder.layers.12.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
83
+ "decoder.layers.12.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
84
+ "decoder.layers.12.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
85
+ "decoder.layers.12.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
86
+ "decoder.layers.12.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
87
+ "decoder.layers.12.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
88
+ "decoder.layers.12.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
89
+ "decoder.layers.12.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
90
+ "decoder.layers.13.fc1.bias": "pytorch_model-00001-of-00002.bin",
91
+ "decoder.layers.13.fc1.weight": "pytorch_model-00001-of-00002.bin",
92
+ "decoder.layers.13.fc2.bias": "pytorch_model-00001-of-00002.bin",
93
+ "decoder.layers.13.fc2.weight": "pytorch_model-00001-of-00002.bin",
94
+ "decoder.layers.13.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
95
+ "decoder.layers.13.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
96
+ "decoder.layers.13.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
97
+ "decoder.layers.13.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
98
+ "decoder.layers.13.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
99
+ "decoder.layers.13.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
100
+ "decoder.layers.13.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
101
+ "decoder.layers.13.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
102
+ "decoder.layers.13.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
103
+ "decoder.layers.13.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
104
+ "decoder.layers.13.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
105
+ "decoder.layers.13.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
106
+ "decoder.layers.14.fc1.bias": "pytorch_model-00001-of-00002.bin",
107
+ "decoder.layers.14.fc1.weight": "pytorch_model-00001-of-00002.bin",
108
+ "decoder.layers.14.fc2.bias": "pytorch_model-00001-of-00002.bin",
109
+ "decoder.layers.14.fc2.weight": "pytorch_model-00001-of-00002.bin",
110
+ "decoder.layers.14.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
111
+ "decoder.layers.14.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
112
+ "decoder.layers.14.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
113
+ "decoder.layers.14.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
114
+ "decoder.layers.14.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
115
+ "decoder.layers.14.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
116
+ "decoder.layers.14.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
117
+ "decoder.layers.14.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
118
+ "decoder.layers.14.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
119
+ "decoder.layers.14.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
120
+ "decoder.layers.14.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
121
+ "decoder.layers.14.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
122
+ "decoder.layers.15.fc1.bias": "pytorch_model-00001-of-00002.bin",
123
+ "decoder.layers.15.fc1.weight": "pytorch_model-00001-of-00002.bin",
124
+ "decoder.layers.15.fc2.bias": "pytorch_model-00001-of-00002.bin",
125
+ "decoder.layers.15.fc2.weight": "pytorch_model-00001-of-00002.bin",
126
+ "decoder.layers.15.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
127
+ "decoder.layers.15.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
128
+ "decoder.layers.15.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
129
+ "decoder.layers.15.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
130
+ "decoder.layers.15.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
131
+ "decoder.layers.15.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
132
+ "decoder.layers.15.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
133
+ "decoder.layers.15.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
134
+ "decoder.layers.15.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
135
+ "decoder.layers.15.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
136
+ "decoder.layers.15.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
137
+ "decoder.layers.15.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
138
+ "decoder.layers.16.fc1.bias": "pytorch_model-00001-of-00002.bin",
139
+ "decoder.layers.16.fc1.weight": "pytorch_model-00001-of-00002.bin",
140
+ "decoder.layers.16.fc2.bias": "pytorch_model-00001-of-00002.bin",
141
+ "decoder.layers.16.fc2.weight": "pytorch_model-00001-of-00002.bin",
142
+ "decoder.layers.16.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
143
+ "decoder.layers.16.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
144
+ "decoder.layers.16.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
145
+ "decoder.layers.16.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
146
+ "decoder.layers.16.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
147
+ "decoder.layers.16.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
148
+ "decoder.layers.16.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
149
+ "decoder.layers.16.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
150
+ "decoder.layers.16.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
151
+ "decoder.layers.16.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
152
+ "decoder.layers.16.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
153
+ "decoder.layers.16.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
154
+ "decoder.layers.17.fc1.bias": "pytorch_model-00001-of-00002.bin",
155
+ "decoder.layers.17.fc1.weight": "pytorch_model-00001-of-00002.bin",
156
+ "decoder.layers.17.fc2.bias": "pytorch_model-00001-of-00002.bin",
157
+ "decoder.layers.17.fc2.weight": "pytorch_model-00001-of-00002.bin",
158
+ "decoder.layers.17.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
159
+ "decoder.layers.17.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
160
+ "decoder.layers.17.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
161
+ "decoder.layers.17.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
162
+ "decoder.layers.17.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
163
+ "decoder.layers.17.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
164
+ "decoder.layers.17.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
165
+ "decoder.layers.17.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
166
+ "decoder.layers.17.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
167
+ "decoder.layers.17.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
168
+ "decoder.layers.17.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
169
+ "decoder.layers.17.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
170
+ "decoder.layers.18.fc1.bias": "pytorch_model-00001-of-00002.bin",
171
+ "decoder.layers.18.fc1.weight": "pytorch_model-00001-of-00002.bin",
172
+ "decoder.layers.18.fc2.bias": "pytorch_model-00001-of-00002.bin",
173
+ "decoder.layers.18.fc2.weight": "pytorch_model-00001-of-00002.bin",
174
+ "decoder.layers.18.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
175
+ "decoder.layers.18.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
176
+ "decoder.layers.18.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
177
+ "decoder.layers.18.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
178
+ "decoder.layers.18.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
179
+ "decoder.layers.18.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
180
+ "decoder.layers.18.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
181
+ "decoder.layers.18.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
182
+ "decoder.layers.18.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
183
+ "decoder.layers.18.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
184
+ "decoder.layers.18.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
185
+ "decoder.layers.18.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
186
+ "decoder.layers.19.fc1.bias": "pytorch_model-00001-of-00002.bin",
187
+ "decoder.layers.19.fc1.weight": "pytorch_model-00001-of-00002.bin",
188
+ "decoder.layers.19.fc2.bias": "pytorch_model-00001-of-00002.bin",
189
+ "decoder.layers.19.fc2.weight": "pytorch_model-00001-of-00002.bin",
190
+ "decoder.layers.19.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
191
+ "decoder.layers.19.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
192
+ "decoder.layers.19.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
193
+ "decoder.layers.19.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
194
+ "decoder.layers.19.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
195
+ "decoder.layers.19.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
196
+ "decoder.layers.19.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
197
+ "decoder.layers.19.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
198
+ "decoder.layers.19.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
199
+ "decoder.layers.19.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
200
+ "decoder.layers.19.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
201
+ "decoder.layers.19.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
202
+ "decoder.layers.2.fc1.bias": "pytorch_model-00001-of-00002.bin",
203
+ "decoder.layers.2.fc1.weight": "pytorch_model-00001-of-00002.bin",
204
+ "decoder.layers.2.fc2.bias": "pytorch_model-00001-of-00002.bin",
205
+ "decoder.layers.2.fc2.weight": "pytorch_model-00001-of-00002.bin",
206
+ "decoder.layers.2.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
207
+ "decoder.layers.2.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
208
+ "decoder.layers.2.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
209
+ "decoder.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
210
+ "decoder.layers.2.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
211
+ "decoder.layers.2.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
212
+ "decoder.layers.2.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
213
+ "decoder.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
214
+ "decoder.layers.2.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
215
+ "decoder.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
216
+ "decoder.layers.2.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
217
+ "decoder.layers.2.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
218
+ "decoder.layers.20.fc1.bias": "pytorch_model-00001-of-00002.bin",
219
+ "decoder.layers.20.fc1.weight": "pytorch_model-00001-of-00002.bin",
220
+ "decoder.layers.20.fc2.bias": "pytorch_model-00001-of-00002.bin",
221
+ "decoder.layers.20.fc2.weight": "pytorch_model-00001-of-00002.bin",
222
+ "decoder.layers.20.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
223
+ "decoder.layers.20.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
224
+ "decoder.layers.20.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
225
+ "decoder.layers.20.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
226
+ "decoder.layers.20.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
227
+ "decoder.layers.20.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
228
+ "decoder.layers.20.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
229
+ "decoder.layers.20.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
230
+ "decoder.layers.20.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
231
+ "decoder.layers.20.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
232
+ "decoder.layers.20.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
233
+ "decoder.layers.20.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
234
+ "decoder.layers.21.fc1.bias": "pytorch_model-00001-of-00002.bin",
235
+ "decoder.layers.21.fc1.weight": "pytorch_model-00001-of-00002.bin",
236
+ "decoder.layers.21.fc2.bias": "pytorch_model-00001-of-00002.bin",
237
+ "decoder.layers.21.fc2.weight": "pytorch_model-00001-of-00002.bin",
238
+ "decoder.layers.21.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
239
+ "decoder.layers.21.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
240
+ "decoder.layers.21.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
241
+ "decoder.layers.21.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
242
+ "decoder.layers.21.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
243
+ "decoder.layers.21.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
244
+ "decoder.layers.21.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
245
+ "decoder.layers.21.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
246
+ "decoder.layers.21.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
247
+ "decoder.layers.21.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
248
+ "decoder.layers.21.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
249
+ "decoder.layers.21.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
250
+ "decoder.layers.22.fc1.bias": "pytorch_model-00001-of-00002.bin",
251
+ "decoder.layers.22.fc1.weight": "pytorch_model-00001-of-00002.bin",
252
+ "decoder.layers.22.fc2.bias": "pytorch_model-00001-of-00002.bin",
253
+ "decoder.layers.22.fc2.weight": "pytorch_model-00001-of-00002.bin",
254
+ "decoder.layers.22.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
255
+ "decoder.layers.22.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
256
+ "decoder.layers.22.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
257
+ "decoder.layers.22.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
258
+ "decoder.layers.22.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
259
+ "decoder.layers.22.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
260
+ "decoder.layers.22.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
261
+ "decoder.layers.22.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
262
+ "decoder.layers.22.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
263
+ "decoder.layers.22.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
264
+ "decoder.layers.22.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
265
+ "decoder.layers.22.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
266
+ "decoder.layers.23.fc1.bias": "pytorch_model-00001-of-00002.bin",
267
+ "decoder.layers.23.fc1.weight": "pytorch_model-00001-of-00002.bin",
268
+ "decoder.layers.23.fc2.bias": "pytorch_model-00002-of-00002.bin",
269
+ "decoder.layers.23.fc2.weight": "pytorch_model-00002-of-00002.bin",
270
+ "decoder.layers.23.final_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
271
+ "decoder.layers.23.final_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
272
+ "decoder.layers.23.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
273
+ "decoder.layers.23.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
274
+ "decoder.layers.23.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
275
+ "decoder.layers.23.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
276
+ "decoder.layers.23.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
277
+ "decoder.layers.23.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
278
+ "decoder.layers.23.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
279
+ "decoder.layers.23.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
280
+ "decoder.layers.23.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
281
+ "decoder.layers.23.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
282
+ "decoder.layers.24.fc1.bias": "pytorch_model-00002-of-00002.bin",
283
+ "decoder.layers.24.fc1.weight": "pytorch_model-00002-of-00002.bin",
284
+ "decoder.layers.24.fc2.bias": "pytorch_model-00002-of-00002.bin",
285
+ "decoder.layers.24.fc2.weight": "pytorch_model-00002-of-00002.bin",
286
+ "decoder.layers.24.final_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
287
+ "decoder.layers.24.final_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
288
+ "decoder.layers.24.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
289
+ "decoder.layers.24.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
290
+ "decoder.layers.24.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
291
+ "decoder.layers.24.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
292
+ "decoder.layers.24.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
293
+ "decoder.layers.24.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
294
+ "decoder.layers.24.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
295
+ "decoder.layers.24.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
296
+ "decoder.layers.24.self_attn_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
297
+ "decoder.layers.24.self_attn_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
298
+ "decoder.layers.25.fc1.bias": "pytorch_model-00002-of-00002.bin",
299
+ "decoder.layers.25.fc1.weight": "pytorch_model-00002-of-00002.bin",
300
+ "decoder.layers.25.fc2.bias": "pytorch_model-00002-of-00002.bin",
301
+ "decoder.layers.25.fc2.weight": "pytorch_model-00002-of-00002.bin",
302
+ "decoder.layers.25.final_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
303
+ "decoder.layers.25.final_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
304
+ "decoder.layers.25.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
305
+ "decoder.layers.25.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
306
+ "decoder.layers.25.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
307
+ "decoder.layers.25.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
308
+ "decoder.layers.25.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
309
+ "decoder.layers.25.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
310
+ "decoder.layers.25.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
311
+ "decoder.layers.25.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
312
+ "decoder.layers.25.self_attn_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
313
+ "decoder.layers.25.self_attn_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
314
+ "decoder.layers.26.fc1.bias": "pytorch_model-00002-of-00002.bin",
315
+ "decoder.layers.26.fc1.weight": "pytorch_model-00002-of-00002.bin",
316
+ "decoder.layers.26.fc2.bias": "pytorch_model-00002-of-00002.bin",
317
+ "decoder.layers.26.fc2.weight": "pytorch_model-00002-of-00002.bin",
318
+ "decoder.layers.26.final_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
319
+ "decoder.layers.26.final_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
320
+ "decoder.layers.26.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
321
+ "decoder.layers.26.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
322
+ "decoder.layers.26.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
323
+ "decoder.layers.26.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
324
+ "decoder.layers.26.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
325
+ "decoder.layers.26.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
326
+ "decoder.layers.26.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
327
+ "decoder.layers.26.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
328
+ "decoder.layers.26.self_attn_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
329
+ "decoder.layers.26.self_attn_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
330
+ "decoder.layers.27.fc1.bias": "pytorch_model-00002-of-00002.bin",
331
+ "decoder.layers.27.fc1.weight": "pytorch_model-00002-of-00002.bin",
332
+ "decoder.layers.27.fc2.bias": "pytorch_model-00002-of-00002.bin",
333
+ "decoder.layers.27.fc2.weight": "pytorch_model-00002-of-00002.bin",
334
+ "decoder.layers.27.final_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
335
+ "decoder.layers.27.final_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
336
+ "decoder.layers.27.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
337
+ "decoder.layers.27.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
338
+ "decoder.layers.27.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
339
+ "decoder.layers.27.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
340
+ "decoder.layers.27.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
341
+ "decoder.layers.27.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
342
+ "decoder.layers.27.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
343
+ "decoder.layers.27.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
344
+ "decoder.layers.27.self_attn_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
345
+ "decoder.layers.27.self_attn_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
346
+ "decoder.layers.28.fc1.bias": "pytorch_model-00002-of-00002.bin",
347
+ "decoder.layers.28.fc1.weight": "pytorch_model-00002-of-00002.bin",
348
+ "decoder.layers.28.fc2.bias": "pytorch_model-00002-of-00002.bin",
349
+ "decoder.layers.28.fc2.weight": "pytorch_model-00002-of-00002.bin",
350
+ "decoder.layers.28.final_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
351
+ "decoder.layers.28.final_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
352
+ "decoder.layers.28.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
353
+ "decoder.layers.28.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
354
+ "decoder.layers.28.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
355
+ "decoder.layers.28.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
356
+ "decoder.layers.28.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
357
+ "decoder.layers.28.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
358
+ "decoder.layers.28.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
359
+ "decoder.layers.28.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
360
+ "decoder.layers.28.self_attn_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
361
+ "decoder.layers.28.self_attn_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
362
+ "decoder.layers.29.fc1.bias": "pytorch_model-00002-of-00002.bin",
363
+ "decoder.layers.29.fc1.weight": "pytorch_model-00002-of-00002.bin",
364
+ "decoder.layers.29.fc2.bias": "pytorch_model-00002-of-00002.bin",
365
+ "decoder.layers.29.fc2.weight": "pytorch_model-00002-of-00002.bin",
366
+ "decoder.layers.29.final_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
367
+ "decoder.layers.29.final_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
368
+ "decoder.layers.29.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
369
+ "decoder.layers.29.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
370
+ "decoder.layers.29.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
371
+ "decoder.layers.29.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
372
+ "decoder.layers.29.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
373
+ "decoder.layers.29.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
374
+ "decoder.layers.29.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
375
+ "decoder.layers.29.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
376
+ "decoder.layers.29.self_attn_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
377
+ "decoder.layers.29.self_attn_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
378
+ "decoder.layers.3.fc1.bias": "pytorch_model-00001-of-00002.bin",
379
+ "decoder.layers.3.fc1.weight": "pytorch_model-00001-of-00002.bin",
380
+ "decoder.layers.3.fc2.bias": "pytorch_model-00001-of-00002.bin",
381
+ "decoder.layers.3.fc2.weight": "pytorch_model-00001-of-00002.bin",
382
+ "decoder.layers.3.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
383
+ "decoder.layers.3.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
384
+ "decoder.layers.3.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
385
+ "decoder.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
386
+ "decoder.layers.3.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
387
+ "decoder.layers.3.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
388
+ "decoder.layers.3.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
389
+ "decoder.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
390
+ "decoder.layers.3.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
391
+ "decoder.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
392
+ "decoder.layers.3.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
393
+ "decoder.layers.3.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
394
+ "decoder.layers.30.fc1.bias": "pytorch_model-00002-of-00002.bin",
395
+ "decoder.layers.30.fc1.weight": "pytorch_model-00002-of-00002.bin",
396
+ "decoder.layers.30.fc2.bias": "pytorch_model-00002-of-00002.bin",
397
+ "decoder.layers.30.fc2.weight": "pytorch_model-00002-of-00002.bin",
398
+ "decoder.layers.30.final_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
399
+ "decoder.layers.30.final_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
400
+ "decoder.layers.30.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
401
+ "decoder.layers.30.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
402
+ "decoder.layers.30.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
403
+ "decoder.layers.30.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
404
+ "decoder.layers.30.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
405
+ "decoder.layers.30.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
406
+ "decoder.layers.30.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
407
+ "decoder.layers.30.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
408
+ "decoder.layers.30.self_attn_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
409
+ "decoder.layers.30.self_attn_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
410
+ "decoder.layers.31.fc1.bias": "pytorch_model-00002-of-00002.bin",
411
+ "decoder.layers.31.fc1.weight": "pytorch_model-00002-of-00002.bin",
412
+ "decoder.layers.31.fc2.bias": "pytorch_model-00002-of-00002.bin",
413
+ "decoder.layers.31.fc2.weight": "pytorch_model-00002-of-00002.bin",
414
+ "decoder.layers.31.final_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
415
+ "decoder.layers.31.final_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
416
+ "decoder.layers.31.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
417
+ "decoder.layers.31.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
418
+ "decoder.layers.31.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
419
+ "decoder.layers.31.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
420
+ "decoder.layers.31.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
421
+ "decoder.layers.31.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
422
+ "decoder.layers.31.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
423
+ "decoder.layers.31.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
424
+ "decoder.layers.31.self_attn_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
425
+ "decoder.layers.31.self_attn_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
426
+ "decoder.layers.4.fc1.bias": "pytorch_model-00001-of-00002.bin",
427
+ "decoder.layers.4.fc1.weight": "pytorch_model-00001-of-00002.bin",
428
+ "decoder.layers.4.fc2.bias": "pytorch_model-00001-of-00002.bin",
429
+ "decoder.layers.4.fc2.weight": "pytorch_model-00001-of-00002.bin",
430
+ "decoder.layers.4.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
431
+ "decoder.layers.4.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
432
+ "decoder.layers.4.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
433
+ "decoder.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
434
+ "decoder.layers.4.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
435
+ "decoder.layers.4.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
436
+ "decoder.layers.4.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
437
+ "decoder.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
438
+ "decoder.layers.4.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
439
+ "decoder.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
440
+ "decoder.layers.4.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
441
+ "decoder.layers.4.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
442
+ "decoder.layers.5.fc1.bias": "pytorch_model-00001-of-00002.bin",
443
+ "decoder.layers.5.fc1.weight": "pytorch_model-00001-of-00002.bin",
444
+ "decoder.layers.5.fc2.bias": "pytorch_model-00001-of-00002.bin",
445
+ "decoder.layers.5.fc2.weight": "pytorch_model-00001-of-00002.bin",
446
+ "decoder.layers.5.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
447
+ "decoder.layers.5.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
448
+ "decoder.layers.5.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
449
+ "decoder.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
450
+ "decoder.layers.5.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
451
+ "decoder.layers.5.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
452
+ "decoder.layers.5.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
453
+ "decoder.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
454
+ "decoder.layers.5.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
455
+ "decoder.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
456
+ "decoder.layers.5.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
457
+ "decoder.layers.5.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
458
+ "decoder.layers.6.fc1.bias": "pytorch_model-00001-of-00002.bin",
459
+ "decoder.layers.6.fc1.weight": "pytorch_model-00001-of-00002.bin",
460
+ "decoder.layers.6.fc2.bias": "pytorch_model-00001-of-00002.bin",
461
+ "decoder.layers.6.fc2.weight": "pytorch_model-00001-of-00002.bin",
462
+ "decoder.layers.6.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
463
+ "decoder.layers.6.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
464
+ "decoder.layers.6.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
465
+ "decoder.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
466
+ "decoder.layers.6.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
467
+ "decoder.layers.6.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
468
+ "decoder.layers.6.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
469
+ "decoder.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
470
+ "decoder.layers.6.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
471
+ "decoder.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
472
+ "decoder.layers.6.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
473
+ "decoder.layers.6.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
474
+ "decoder.layers.7.fc1.bias": "pytorch_model-00001-of-00002.bin",
475
+ "decoder.layers.7.fc1.weight": "pytorch_model-00001-of-00002.bin",
476
+ "decoder.layers.7.fc2.bias": "pytorch_model-00001-of-00002.bin",
477
+ "decoder.layers.7.fc2.weight": "pytorch_model-00001-of-00002.bin",
478
+ "decoder.layers.7.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
479
+ "decoder.layers.7.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
480
+ "decoder.layers.7.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
481
+ "decoder.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
482
+ "decoder.layers.7.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
483
+ "decoder.layers.7.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
484
+ "decoder.layers.7.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
485
+ "decoder.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
486
+ "decoder.layers.7.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
487
+ "decoder.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
488
+ "decoder.layers.7.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
489
+ "decoder.layers.7.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
490
+ "decoder.layers.8.fc1.bias": "pytorch_model-00001-of-00002.bin",
491
+ "decoder.layers.8.fc1.weight": "pytorch_model-00001-of-00002.bin",
492
+ "decoder.layers.8.fc2.bias": "pytorch_model-00001-of-00002.bin",
493
+ "decoder.layers.8.fc2.weight": "pytorch_model-00001-of-00002.bin",
494
+ "decoder.layers.8.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
495
+ "decoder.layers.8.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
496
+ "decoder.layers.8.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
497
+ "decoder.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
498
+ "decoder.layers.8.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
499
+ "decoder.layers.8.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
500
+ "decoder.layers.8.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
501
+ "decoder.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
502
+ "decoder.layers.8.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
503
+ "decoder.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
504
+ "decoder.layers.8.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
505
+ "decoder.layers.8.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
506
+ "decoder.layers.9.fc1.bias": "pytorch_model-00001-of-00002.bin",
507
+ "decoder.layers.9.fc1.weight": "pytorch_model-00001-of-00002.bin",
508
+ "decoder.layers.9.fc2.bias": "pytorch_model-00001-of-00002.bin",
509
+ "decoder.layers.9.fc2.weight": "pytorch_model-00001-of-00002.bin",
510
+ "decoder.layers.9.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
511
+ "decoder.layers.9.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
512
+ "decoder.layers.9.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
513
+ "decoder.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
514
+ "decoder.layers.9.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
515
+ "decoder.layers.9.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
516
+ "decoder.layers.9.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
517
+ "decoder.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
518
+ "decoder.layers.9.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
519
+ "decoder.layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
520
+ "decoder.layers.9.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
521
+ "decoder.layers.9.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin"
522
+ }
523
+ }
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"bos_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "eos_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "unk_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "pad_token": {"content": "<pad>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}}
tf_model.h5.index.json ADDED
@@ -0,0 +1,523 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 13316947968
4
+ },
5
+ "weight_map": {
6
+ "tfopt_for_causal_lm/model/decoder/embed_positions/weight:0": "tf_model-00001-of-00002.h5",
7
+ "tfopt_for_causal_lm/model/decoder/embed_tokens/weight:0": "tf_model-00001-of-00002.h5",
8
+ "tfopt_for_causal_lm/model/decoder/final_layer_norm/beta:0": "tf_model-00001-of-00002.h5",
9
+ "tfopt_for_causal_lm/model/decoder/final_layer_norm/gamma:0": "tf_model-00001-of-00002.h5",
10
+ "tfopt_for_causal_lm/model/decoder/layers.0/fc1/bias:0": "tf_model-00001-of-00002.h5",
11
+ "tfopt_for_causal_lm/model/decoder/layers.0/fc1/kernel:0": "tf_model-00001-of-00002.h5",
12
+ "tfopt_for_causal_lm/model/decoder/layers.0/fc2/bias:0": "tf_model-00001-of-00002.h5",
13
+ "tfopt_for_causal_lm/model/decoder/layers.0/fc2/kernel:0": "tf_model-00001-of-00002.h5",
14
+ "tfopt_for_causal_lm/model/decoder/layers.0/final_layer_norm/beta:0": "tf_model-00001-of-00002.h5",
15
+ "tfopt_for_causal_lm/model/decoder/layers.0/final_layer_norm/gamma:0": "tf_model-00001-of-00002.h5",
16
+ "tfopt_for_causal_lm/model/decoder/layers.0/self_attn/k_proj/bias:0": "tf_model-00001-of-00002.h5",
17
+ "tfopt_for_causal_lm/model/decoder/layers.0/self_attn/k_proj/kernel:0": "tf_model-00001-of-00002.h5",
18
+ "tfopt_for_causal_lm/model/decoder/layers.0/self_attn/out_proj/bias:0": "tf_model-00001-of-00002.h5",
19
+ "tfopt_for_causal_lm/model/decoder/layers.0/self_attn/out_proj/kernel:0": "tf_model-00001-of-00002.h5",
20
+ "tfopt_for_causal_lm/model/decoder/layers.0/self_attn/q_proj/bias:0": "tf_model-00001-of-00002.h5",
21
+ "tfopt_for_causal_lm/model/decoder/layers.0/self_attn/q_proj/kernel:0": "tf_model-00001-of-00002.h5",
22
+ "tfopt_for_causal_lm/model/decoder/layers.0/self_attn/v_proj/bias:0": "tf_model-00001-of-00002.h5",
23
+ "tfopt_for_causal_lm/model/decoder/layers.0/self_attn/v_proj/kernel:0": "tf_model-00001-of-00002.h5",
24
+ "tfopt_for_causal_lm/model/decoder/layers.0/self_attn_layer_norm/beta:0": "tf_model-00001-of-00002.h5",
25
+ "tfopt_for_causal_lm/model/decoder/layers.0/self_attn_layer_norm/gamma:0": "tf_model-00001-of-00002.h5",
26
+ "tfopt_for_causal_lm/model/decoder/layers.1/fc1/bias:0": "tf_model-00001-of-00002.h5",
27
+ "tfopt_for_causal_lm/model/decoder/layers.1/fc1/kernel:0": "tf_model-00001-of-00002.h5",
28
+ "tfopt_for_causal_lm/model/decoder/layers.1/fc2/bias:0": "tf_model-00001-of-00002.h5",
29
+ "tfopt_for_causal_lm/model/decoder/layers.1/fc2/kernel:0": "tf_model-00001-of-00002.h5",
30
+ "tfopt_for_causal_lm/model/decoder/layers.1/final_layer_norm/beta:0": "tf_model-00001-of-00002.h5",
31
+ "tfopt_for_causal_lm/model/decoder/layers.1/final_layer_norm/gamma:0": "tf_model-00001-of-00002.h5",
32
+ "tfopt_for_causal_lm/model/decoder/layers.1/self_attn/k_proj/bias:0": "tf_model-00001-of-00002.h5",
33
+ "tfopt_for_causal_lm/model/decoder/layers.1/self_attn/k_proj/kernel:0": "tf_model-00001-of-00002.h5",
34
+ "tfopt_for_causal_lm/model/decoder/layers.1/self_attn/out_proj/bias:0": "tf_model-00001-of-00002.h5",
35
+ "tfopt_for_causal_lm/model/decoder/layers.1/self_attn/out_proj/kernel:0": "tf_model-00001-of-00002.h5",
36
+ "tfopt_for_causal_lm/model/decoder/layers.1/self_attn/q_proj/bias:0": "tf_model-00001-of-00002.h5",
37
+ "tfopt_for_causal_lm/model/decoder/layers.1/self_attn/q_proj/kernel:0": "tf_model-00001-of-00002.h5",
38
+ "tfopt_for_causal_lm/model/decoder/layers.1/self_attn/v_proj/bias:0": "tf_model-00001-of-00002.h5",
39
+ "tfopt_for_causal_lm/model/decoder/layers.1/self_attn/v_proj/kernel:0": "tf_model-00001-of-00002.h5",
40
+ "tfopt_for_causal_lm/model/decoder/layers.1/self_attn_layer_norm/beta:0": "tf_model-00001-of-00002.h5",
41
+ "tfopt_for_causal_lm/model/decoder/layers.1/self_attn_layer_norm/gamma:0": "tf_model-00001-of-00002.h5",
42
+ "tfopt_for_causal_lm/model/decoder/layers.10/fc1/bias:0": "tf_model-00001-of-00002.h5",
43
+ "tfopt_for_causal_lm/model/decoder/layers.10/fc1/kernel:0": "tf_model-00001-of-00002.h5",
44
+ "tfopt_for_causal_lm/model/decoder/layers.10/fc2/bias:0": "tf_model-00001-of-00002.h5",
45
+ "tfopt_for_causal_lm/model/decoder/layers.10/fc2/kernel:0": "tf_model-00001-of-00002.h5",
46
+ "tfopt_for_causal_lm/model/decoder/layers.10/final_layer_norm/beta:0": "tf_model-00001-of-00002.h5",
47
+ "tfopt_for_causal_lm/model/decoder/layers.10/final_layer_norm/gamma:0": "tf_model-00001-of-00002.h5",
48
+ "tfopt_for_causal_lm/model/decoder/layers.10/self_attn/k_proj/bias:0": "tf_model-00001-of-00002.h5",
49
+ "tfopt_for_causal_lm/model/decoder/layers.10/self_attn/k_proj/kernel:0": "tf_model-00001-of-00002.h5",
50
+ "tfopt_for_causal_lm/model/decoder/layers.10/self_attn/out_proj/bias:0": "tf_model-00001-of-00002.h5",
51
+ "tfopt_for_causal_lm/model/decoder/layers.10/self_attn/out_proj/kernel:0": "tf_model-00001-of-00002.h5",
52
+ "tfopt_for_causal_lm/model/decoder/layers.10/self_attn/q_proj/bias:0": "tf_model-00001-of-00002.h5",
53
+ "tfopt_for_causal_lm/model/decoder/layers.10/self_attn/q_proj/kernel:0": "tf_model-00001-of-00002.h5",
54
+ "tfopt_for_causal_lm/model/decoder/layers.10/self_attn/v_proj/bias:0": "tf_model-00001-of-00002.h5",
55
+ "tfopt_for_causal_lm/model/decoder/layers.10/self_attn/v_proj/kernel:0": "tf_model-00001-of-00002.h5",
56
+ "tfopt_for_causal_lm/model/decoder/layers.10/self_attn_layer_norm/beta:0": "tf_model-00001-of-00002.h5",
57
+ "tfopt_for_causal_lm/model/decoder/layers.10/self_attn_layer_norm/gamma:0": "tf_model-00001-of-00002.h5",
58
+ "tfopt_for_causal_lm/model/decoder/layers.11/fc1/bias:0": "tf_model-00001-of-00002.h5",
59
+ "tfopt_for_causal_lm/model/decoder/layers.11/fc1/kernel:0": "tf_model-00001-of-00002.h5",
60
+ "tfopt_for_causal_lm/model/decoder/layers.11/fc2/bias:0": "tf_model-00001-of-00002.h5",
61
+ "tfopt_for_causal_lm/model/decoder/layers.11/fc2/kernel:0": "tf_model-00001-of-00002.h5",
62
+ "tfopt_for_causal_lm/model/decoder/layers.11/final_layer_norm/beta:0": "tf_model-00001-of-00002.h5",
63
+ "tfopt_for_causal_lm/model/decoder/layers.11/final_layer_norm/gamma:0": "tf_model-00001-of-00002.h5",
64
+ "tfopt_for_causal_lm/model/decoder/layers.11/self_attn/k_proj/bias:0": "tf_model-00001-of-00002.h5",
65
+ "tfopt_for_causal_lm/model/decoder/layers.11/self_attn/k_proj/kernel:0": "tf_model-00001-of-00002.h5",
66
+ "tfopt_for_causal_lm/model/decoder/layers.11/self_attn/out_proj/bias:0": "tf_model-00001-of-00002.h5",
67
+ "tfopt_for_causal_lm/model/decoder/layers.11/self_attn/out_proj/kernel:0": "tf_model-00001-of-00002.h5",
68
+ "tfopt_for_causal_lm/model/decoder/layers.11/self_attn/q_proj/bias:0": "tf_model-00001-of-00002.h5",
69
+ "tfopt_for_causal_lm/model/decoder/layers.11/self_attn/q_proj/kernel:0": "tf_model-00001-of-00002.h5",
70
+ "tfopt_for_causal_lm/model/decoder/layers.11/self_attn/v_proj/bias:0": "tf_model-00001-of-00002.h5",
71
+ "tfopt_for_causal_lm/model/decoder/layers.11/self_attn/v_proj/kernel:0": "tf_model-00001-of-00002.h5",
72
+ "tfopt_for_causal_lm/model/decoder/layers.11/self_attn_layer_norm/beta:0": "tf_model-00001-of-00002.h5",
73
+ "tfopt_for_causal_lm/model/decoder/layers.11/self_attn_layer_norm/gamma:0": "tf_model-00001-of-00002.h5",
74
+ "tfopt_for_causal_lm/model/decoder/layers.12/fc1/bias:0": "tf_model-00001-of-00002.h5",
75
+ "tfopt_for_causal_lm/model/decoder/layers.12/fc1/kernel:0": "tf_model-00001-of-00002.h5",
76
+ "tfopt_for_causal_lm/model/decoder/layers.12/fc2/bias:0": "tf_model-00001-of-00002.h5",
77
+ "tfopt_for_causal_lm/model/decoder/layers.12/fc2/kernel:0": "tf_model-00001-of-00002.h5",
78
+ "tfopt_for_causal_lm/model/decoder/layers.12/final_layer_norm/beta:0": "tf_model-00001-of-00002.h5",
79
+ "tfopt_for_causal_lm/model/decoder/layers.12/final_layer_norm/gamma:0": "tf_model-00001-of-00002.h5",
80
+ "tfopt_for_causal_lm/model/decoder/layers.12/self_attn/k_proj/bias:0": "tf_model-00001-of-00002.h5",
81
+ "tfopt_for_causal_lm/model/decoder/layers.12/self_attn/k_proj/kernel:0": "tf_model-00001-of-00002.h5",
82
+ "tfopt_for_causal_lm/model/decoder/layers.12/self_attn/out_proj/bias:0": "tf_model-00001-of-00002.h5",
83
+ "tfopt_for_causal_lm/model/decoder/layers.12/self_attn/out_proj/kernel:0": "tf_model-00001-of-00002.h5",
84
+ "tfopt_for_causal_lm/model/decoder/layers.12/self_attn/q_proj/bias:0": "tf_model-00001-of-00002.h5",
85
+ "tfopt_for_causal_lm/model/decoder/layers.12/self_attn/q_proj/kernel:0": "tf_model-00001-of-00002.h5",
86
+ "tfopt_for_causal_lm/model/decoder/layers.12/self_attn/v_proj/bias:0": "tf_model-00001-of-00002.h5",
87
+ "tfopt_for_causal_lm/model/decoder/layers.12/self_attn/v_proj/kernel:0": "tf_model-00001-of-00002.h5",
88
+ "tfopt_for_causal_lm/model/decoder/layers.12/self_attn_layer_norm/beta:0": "tf_model-00001-of-00002.h5",
89
+ "tfopt_for_causal_lm/model/decoder/layers.12/self_attn_layer_norm/gamma:0": "tf_model-00001-of-00002.h5",
90
+ "tfopt_for_causal_lm/model/decoder/layers.13/fc1/bias:0": "tf_model-00001-of-00002.h5",
91
+ "tfopt_for_causal_lm/model/decoder/layers.13/fc1/kernel:0": "tf_model-00001-of-00002.h5",
92
+ "tfopt_for_causal_lm/model/decoder/layers.13/fc2/bias:0": "tf_model-00001-of-00002.h5",
93
+ "tfopt_for_causal_lm/model/decoder/layers.13/fc2/kernel:0": "tf_model-00001-of-00002.h5",
94
+ "tfopt_for_causal_lm/model/decoder/layers.13/final_layer_norm/beta:0": "tf_model-00001-of-00002.h5",
95
+ "tfopt_for_causal_lm/model/decoder/layers.13/final_layer_norm/gamma:0": "tf_model-00001-of-00002.h5",
96
+ "tfopt_for_causal_lm/model/decoder/layers.13/self_attn/k_proj/bias:0": "tf_model-00001-of-00002.h5",
97
+ "tfopt_for_causal_lm/model/decoder/layers.13/self_attn/k_proj/kernel:0": "tf_model-00001-of-00002.h5",
98
+ "tfopt_for_causal_lm/model/decoder/layers.13/self_attn/out_proj/bias:0": "tf_model-00001-of-00002.h5",
99
+ "tfopt_for_causal_lm/model/decoder/layers.13/self_attn/out_proj/kernel:0": "tf_model-00001-of-00002.h5",
100
+ "tfopt_for_causal_lm/model/decoder/layers.13/self_attn/q_proj/bias:0": "tf_model-00001-of-00002.h5",
101
+ "tfopt_for_causal_lm/model/decoder/layers.13/self_attn/q_proj/kernel:0": "tf_model-00001-of-00002.h5",
102
+ "tfopt_for_causal_lm/model/decoder/layers.13/self_attn/v_proj/bias:0": "tf_model-00001-of-00002.h5",
103
+ "tfopt_for_causal_lm/model/decoder/layers.13/self_attn/v_proj/kernel:0": "tf_model-00001-of-00002.h5",
104
+ "tfopt_for_causal_lm/model/decoder/layers.13/self_attn_layer_norm/beta:0": "tf_model-00001-of-00002.h5",
105
+ "tfopt_for_causal_lm/model/decoder/layers.13/self_attn_layer_norm/gamma:0": "tf_model-00001-of-00002.h5",
106
+ "tfopt_for_causal_lm/model/decoder/layers.14/fc1/bias:0": "tf_model-00001-of-00002.h5",
107
+ "tfopt_for_causal_lm/model/decoder/layers.14/fc1/kernel:0": "tf_model-00001-of-00002.h5",
108
+ "tfopt_for_causal_lm/model/decoder/layers.14/fc2/bias:0": "tf_model-00001-of-00002.h5",
109
+ "tfopt_for_causal_lm/model/decoder/layers.14/fc2/kernel:0": "tf_model-00001-of-00002.h5",
110
+ "tfopt_for_causal_lm/model/decoder/layers.14/final_layer_norm/beta:0": "tf_model-00001-of-00002.h5",
111
+ "tfopt_for_causal_lm/model/decoder/layers.14/final_layer_norm/gamma:0": "tf_model-00001-of-00002.h5",
112
+ "tfopt_for_causal_lm/model/decoder/layers.14/self_attn/k_proj/bias:0": "tf_model-00001-of-00002.h5",
113
+ "tfopt_for_causal_lm/model/decoder/layers.14/self_attn/k_proj/kernel:0": "tf_model-00001-of-00002.h5",
114
+ "tfopt_for_causal_lm/model/decoder/layers.14/self_attn/out_proj/bias:0": "tf_model-00001-of-00002.h5",
115
+ "tfopt_for_causal_lm/model/decoder/layers.14/self_attn/out_proj/kernel:0": "tf_model-00001-of-00002.h5",
116
+ "tfopt_for_causal_lm/model/decoder/layers.14/self_attn/q_proj/bias:0": "tf_model-00001-of-00002.h5",
117
+ "tfopt_for_causal_lm/model/decoder/layers.14/self_attn/q_proj/kernel:0": "tf_model-00001-of-00002.h5",
118
+ "tfopt_for_causal_lm/model/decoder/layers.14/self_attn/v_proj/bias:0": "tf_model-00001-of-00002.h5",
119
+ "tfopt_for_causal_lm/model/decoder/layers.14/self_attn/v_proj/kernel:0": "tf_model-00001-of-00002.h5",
120
+ "tfopt_for_causal_lm/model/decoder/layers.14/self_attn_layer_norm/beta:0": "tf_model-00001-of-00002.h5",
121
+ "tfopt_for_causal_lm/model/decoder/layers.14/self_attn_layer_norm/gamma:0": "tf_model-00001-of-00002.h5",
122
+ "tfopt_for_causal_lm/model/decoder/layers.15/fc1/bias:0": "tf_model-00001-of-00002.h5",
123
+ "tfopt_for_causal_lm/model/decoder/layers.15/fc1/kernel:0": "tf_model-00001-of-00002.h5",
124
+ "tfopt_for_causal_lm/model/decoder/layers.15/fc2/bias:0": "tf_model-00001-of-00002.h5",
125
+ "tfopt_for_causal_lm/model/decoder/layers.15/fc2/kernel:0": "tf_model-00001-of-00002.h5",
126
+ "tfopt_for_causal_lm/model/decoder/layers.15/final_layer_norm/beta:0": "tf_model-00001-of-00002.h5",
127
+ "tfopt_for_causal_lm/model/decoder/layers.15/final_layer_norm/gamma:0": "tf_model-00001-of-00002.h5",
128
+ "tfopt_for_causal_lm/model/decoder/layers.15/self_attn/k_proj/bias:0": "tf_model-00001-of-00002.h5",
129
+ "tfopt_for_causal_lm/model/decoder/layers.15/self_attn/k_proj/kernel:0": "tf_model-00001-of-00002.h5",
130
+ "tfopt_for_causal_lm/model/decoder/layers.15/self_attn/out_proj/bias:0": "tf_model-00001-of-00002.h5",
131
+ "tfopt_for_causal_lm/model/decoder/layers.15/self_attn/out_proj/kernel:0": "tf_model-00001-of-00002.h5",
132
+ "tfopt_for_causal_lm/model/decoder/layers.15/self_attn/q_proj/bias:0": "tf_model-00001-of-00002.h5",
133
+ "tfopt_for_causal_lm/model/decoder/layers.15/self_attn/q_proj/kernel:0": "tf_model-00001-of-00002.h5",
134
+ "tfopt_for_causal_lm/model/decoder/layers.15/self_attn/v_proj/bias:0": "tf_model-00001-of-00002.h5",
135
+ "tfopt_for_causal_lm/model/decoder/layers.15/self_attn/v_proj/kernel:0": "tf_model-00001-of-00002.h5",
136
+ "tfopt_for_causal_lm/model/decoder/layers.15/self_attn_layer_norm/beta:0": "tf_model-00001-of-00002.h5",
137
+ "tfopt_for_causal_lm/model/decoder/layers.15/self_attn_layer_norm/gamma:0": "tf_model-00001-of-00002.h5",
138
+ "tfopt_for_causal_lm/model/decoder/layers.16/fc1/bias:0": "tf_model-00001-of-00002.h5",
139
+ "tfopt_for_causal_lm/model/decoder/layers.16/fc1/kernel:0": "tf_model-00001-of-00002.h5",
140
+ "tfopt_for_causal_lm/model/decoder/layers.16/fc2/bias:0": "tf_model-00001-of-00002.h5",
141
+ "tfopt_for_causal_lm/model/decoder/layers.16/fc2/kernel:0": "tf_model-00001-of-00002.h5",
142
+ "tfopt_for_causal_lm/model/decoder/layers.16/final_layer_norm/beta:0": "tf_model-00001-of-00002.h5",
143
+ "tfopt_for_causal_lm/model/decoder/layers.16/final_layer_norm/gamma:0": "tf_model-00001-of-00002.h5",
144
+ "tfopt_for_causal_lm/model/decoder/layers.16/self_attn/k_proj/bias:0": "tf_model-00001-of-00002.h5",
145
+ "tfopt_for_causal_lm/model/decoder/layers.16/self_attn/k_proj/kernel:0": "tf_model-00001-of-00002.h5",
146
+ "tfopt_for_causal_lm/model/decoder/layers.16/self_attn/out_proj/bias:0": "tf_model-00001-of-00002.h5",
147
+ "tfopt_for_causal_lm/model/decoder/layers.16/self_attn/out_proj/kernel:0": "tf_model-00001-of-00002.h5",
148
+ "tfopt_for_causal_lm/model/decoder/layers.16/self_attn/q_proj/bias:0": "tf_model-00001-of-00002.h5",
149
+ "tfopt_for_causal_lm/model/decoder/layers.16/self_attn/q_proj/kernel:0": "tf_model-00001-of-00002.h5",
150
+ "tfopt_for_causal_lm/model/decoder/layers.16/self_attn/v_proj/bias:0": "tf_model-00001-of-00002.h5",
151
+ "tfopt_for_causal_lm/model/decoder/layers.16/self_attn/v_proj/kernel:0": "tf_model-00001-of-00002.h5",
152
+ "tfopt_for_causal_lm/model/decoder/layers.16/self_attn_layer_norm/beta:0": "tf_model-00001-of-00002.h5",
153
+ "tfopt_for_causal_lm/model/decoder/layers.16/self_attn_layer_norm/gamma:0": "tf_model-00001-of-00002.h5",
154
+ "tfopt_for_causal_lm/model/decoder/layers.17/fc1/bias:0": "tf_model-00001-of-00002.h5",
155
+ "tfopt_for_causal_lm/model/decoder/layers.17/fc1/kernel:0": "tf_model-00001-of-00002.h5",
156
+ "tfopt_for_causal_lm/model/decoder/layers.17/fc2/bias:0": "tf_model-00001-of-00002.h5",
157
+ "tfopt_for_causal_lm/model/decoder/layers.17/fc2/kernel:0": "tf_model-00001-of-00002.h5",
158
+ "tfopt_for_causal_lm/model/decoder/layers.17/final_layer_norm/beta:0": "tf_model-00001-of-00002.h5",
159
+ "tfopt_for_causal_lm/model/decoder/layers.17/final_layer_norm/gamma:0": "tf_model-00001-of-00002.h5",
160
+ "tfopt_for_causal_lm/model/decoder/layers.17/self_attn/k_proj/bias:0": "tf_model-00001-of-00002.h5",
161
+ "tfopt_for_causal_lm/model/decoder/layers.17/self_attn/k_proj/kernel:0": "tf_model-00001-of-00002.h5",
162
+ "tfopt_for_causal_lm/model/decoder/layers.17/self_attn/out_proj/bias:0": "tf_model-00001-of-00002.h5",
163
+ "tfopt_for_causal_lm/model/decoder/layers.17/self_attn/out_proj/kernel:0": "tf_model-00001-of-00002.h5",
164
+ "tfopt_for_causal_lm/model/decoder/layers.17/self_attn/q_proj/bias:0": "tf_model-00001-of-00002.h5",
165
+ "tfopt_for_causal_lm/model/decoder/layers.17/self_attn/q_proj/kernel:0": "tf_model-00001-of-00002.h5",
166
+ "tfopt_for_causal_lm/model/decoder/layers.17/self_attn/v_proj/bias:0": "tf_model-00001-of-00002.h5",
167
+ "tfopt_for_causal_lm/model/decoder/layers.17/self_attn/v_proj/kernel:0": "tf_model-00001-of-00002.h5",
168
+ "tfopt_for_causal_lm/model/decoder/layers.17/self_attn_layer_norm/beta:0": "tf_model-00001-of-00002.h5",
169
+ "tfopt_for_causal_lm/model/decoder/layers.17/self_attn_layer_norm/gamma:0": "tf_model-00001-of-00002.h5",
170
+ "tfopt_for_causal_lm/model/decoder/layers.18/fc1/bias:0": "tf_model-00001-of-00002.h5",
171
+ "tfopt_for_causal_lm/model/decoder/layers.18/fc1/kernel:0": "tf_model-00001-of-00002.h5",
172
+ "tfopt_for_causal_lm/model/decoder/layers.18/fc2/bias:0": "tf_model-00001-of-00002.h5",
173
+ "tfopt_for_causal_lm/model/decoder/layers.18/fc2/kernel:0": "tf_model-00001-of-00002.h5",
174
+ "tfopt_for_causal_lm/model/decoder/layers.18/final_layer_norm/beta:0": "tf_model-00001-of-00002.h5",
175
+ "tfopt_for_causal_lm/model/decoder/layers.18/final_layer_norm/gamma:0": "tf_model-00001-of-00002.h5",
176
+ "tfopt_for_causal_lm/model/decoder/layers.18/self_attn/k_proj/bias:0": "tf_model-00001-of-00002.h5",
177
+ "tfopt_for_causal_lm/model/decoder/layers.18/self_attn/k_proj/kernel:0": "tf_model-00001-of-00002.h5",
178
+ "tfopt_for_causal_lm/model/decoder/layers.18/self_attn/out_proj/bias:0": "tf_model-00001-of-00002.h5",
179
+ "tfopt_for_causal_lm/model/decoder/layers.18/self_attn/out_proj/kernel:0": "tf_model-00001-of-00002.h5",
180
+ "tfopt_for_causal_lm/model/decoder/layers.18/self_attn/q_proj/bias:0": "tf_model-00001-of-00002.h5",
181
+ "tfopt_for_causal_lm/model/decoder/layers.18/self_attn/q_proj/kernel:0": "tf_model-00001-of-00002.h5",
182
+ "tfopt_for_causal_lm/model/decoder/layers.18/self_attn/v_proj/bias:0": "tf_model-00001-of-00002.h5",
183
+ "tfopt_for_causal_lm/model/decoder/layers.18/self_attn/v_proj/kernel:0": "tf_model-00001-of-00002.h5",
184
+ "tfopt_for_causal_lm/model/decoder/layers.18/self_attn_layer_norm/beta:0": "tf_model-00001-of-00002.h5",
185
+ "tfopt_for_causal_lm/model/decoder/layers.18/self_attn_layer_norm/gamma:0": "tf_model-00001-of-00002.h5",
186
+ "tfopt_for_causal_lm/model/decoder/layers.19/fc1/bias:0": "tf_model-00001-of-00002.h5",
187
+ "tfopt_for_causal_lm/model/decoder/layers.19/fc1/kernel:0": "tf_model-00001-of-00002.h5",
188
+ "tfopt_for_causal_lm/model/decoder/layers.19/fc2/bias:0": "tf_model-00001-of-00002.h5",
189
+ "tfopt_for_causal_lm/model/decoder/layers.19/fc2/kernel:0": "tf_model-00001-of-00002.h5",
190
+ "tfopt_for_causal_lm/model/decoder/layers.19/final_layer_norm/beta:0": "tf_model-00001-of-00002.h5",
191
+ "tfopt_for_causal_lm/model/decoder/layers.19/final_layer_norm/gamma:0": "tf_model-00001-of-00002.h5",
192
+ "tfopt_for_causal_lm/model/decoder/layers.19/self_attn/k_proj/bias:0": "tf_model-00001-of-00002.h5",
193
+ "tfopt_for_causal_lm/model/decoder/layers.19/self_attn/k_proj/kernel:0": "tf_model-00001-of-00002.h5",
194
+ "tfopt_for_causal_lm/model/decoder/layers.19/self_attn/out_proj/bias:0": "tf_model-00001-of-00002.h5",
195
+ "tfopt_for_causal_lm/model/decoder/layers.19/self_attn/out_proj/kernel:0": "tf_model-00001-of-00002.h5",
196
+ "tfopt_for_causal_lm/model/decoder/layers.19/self_attn/q_proj/bias:0": "tf_model-00001-of-00002.h5",
197
+ "tfopt_for_causal_lm/model/decoder/layers.19/self_attn/q_proj/kernel:0": "tf_model-00001-of-00002.h5",
198
+ "tfopt_for_causal_lm/model/decoder/layers.19/self_attn/v_proj/bias:0": "tf_model-00001-of-00002.h5",
199
+ "tfopt_for_causal_lm/model/decoder/layers.19/self_attn/v_proj/kernel:0": "tf_model-00001-of-00002.h5",
200
+ "tfopt_for_causal_lm/model/decoder/layers.19/self_attn_layer_norm/beta:0": "tf_model-00001-of-00002.h5",
201
+ "tfopt_for_causal_lm/model/decoder/layers.19/self_attn_layer_norm/gamma:0": "tf_model-00001-of-00002.h5",
202
+ "tfopt_for_causal_lm/model/decoder/layers.2/fc1/bias:0": "tf_model-00001-of-00002.h5",
203
+ "tfopt_for_causal_lm/model/decoder/layers.2/fc1/kernel:0": "tf_model-00001-of-00002.h5",
204
+ "tfopt_for_causal_lm/model/decoder/layers.2/fc2/bias:0": "tf_model-00001-of-00002.h5",
205
+ "tfopt_for_causal_lm/model/decoder/layers.2/fc2/kernel:0": "tf_model-00001-of-00002.h5",
206
+ "tfopt_for_causal_lm/model/decoder/layers.2/final_layer_norm/beta:0": "tf_model-00001-of-00002.h5",
207
+ "tfopt_for_causal_lm/model/decoder/layers.2/final_layer_norm/gamma:0": "tf_model-00001-of-00002.h5",
208
+ "tfopt_for_causal_lm/model/decoder/layers.2/self_attn/k_proj/bias:0": "tf_model-00001-of-00002.h5",
209
+ "tfopt_for_causal_lm/model/decoder/layers.2/self_attn/k_proj/kernel:0": "tf_model-00001-of-00002.h5",
210
+ "tfopt_for_causal_lm/model/decoder/layers.2/self_attn/out_proj/bias:0": "tf_model-00001-of-00002.h5",
211
+ "tfopt_for_causal_lm/model/decoder/layers.2/self_attn/out_proj/kernel:0": "tf_model-00001-of-00002.h5",
212
+ "tfopt_for_causal_lm/model/decoder/layers.2/self_attn/q_proj/bias:0": "tf_model-00001-of-00002.h5",
213
+ "tfopt_for_causal_lm/model/decoder/layers.2/self_attn/q_proj/kernel:0": "tf_model-00001-of-00002.h5",
214
+ "tfopt_for_causal_lm/model/decoder/layers.2/self_attn/v_proj/bias:0": "tf_model-00001-of-00002.h5",
215
+ "tfopt_for_causal_lm/model/decoder/layers.2/self_attn/v_proj/kernel:0": "tf_model-00001-of-00002.h5",
216
+ "tfopt_for_causal_lm/model/decoder/layers.2/self_attn_layer_norm/beta:0": "tf_model-00001-of-00002.h5",
217
+ "tfopt_for_causal_lm/model/decoder/layers.2/self_attn_layer_norm/gamma:0": "tf_model-00001-of-00002.h5",
218
+ "tfopt_for_causal_lm/model/decoder/layers.20/fc1/bias:0": "tf_model-00001-of-00002.h5",
219
+ "tfopt_for_causal_lm/model/decoder/layers.20/fc1/kernel:0": "tf_model-00001-of-00002.h5",
220
+ "tfopt_for_causal_lm/model/decoder/layers.20/fc2/bias:0": "tf_model-00001-of-00002.h5",
221
+ "tfopt_for_causal_lm/model/decoder/layers.20/fc2/kernel:0": "tf_model-00001-of-00002.h5",
222
+ "tfopt_for_causal_lm/model/decoder/layers.20/final_layer_norm/beta:0": "tf_model-00001-of-00002.h5",
223
+ "tfopt_for_causal_lm/model/decoder/layers.20/final_layer_norm/gamma:0": "tf_model-00001-of-00002.h5",
224
+ "tfopt_for_causal_lm/model/decoder/layers.20/self_attn/k_proj/bias:0": "tf_model-00001-of-00002.h5",
225
+ "tfopt_for_causal_lm/model/decoder/layers.20/self_attn/k_proj/kernel:0": "tf_model-00001-of-00002.h5",
226
+ "tfopt_for_causal_lm/model/decoder/layers.20/self_attn/out_proj/bias:0": "tf_model-00001-of-00002.h5",
227
+ "tfopt_for_causal_lm/model/decoder/layers.20/self_attn/out_proj/kernel:0": "tf_model-00001-of-00002.h5",
228
+ "tfopt_for_causal_lm/model/decoder/layers.20/self_attn/q_proj/bias:0": "tf_model-00001-of-00002.h5",
229
+ "tfopt_for_causal_lm/model/decoder/layers.20/self_attn/q_proj/kernel:0": "tf_model-00001-of-00002.h5",
230
+ "tfopt_for_causal_lm/model/decoder/layers.20/self_attn/v_proj/bias:0": "tf_model-00001-of-00002.h5",
231
+ "tfopt_for_causal_lm/model/decoder/layers.20/self_attn/v_proj/kernel:0": "tf_model-00001-of-00002.h5",
232
+ "tfopt_for_causal_lm/model/decoder/layers.20/self_attn_layer_norm/beta:0": "tf_model-00001-of-00002.h5",
233
+ "tfopt_for_causal_lm/model/decoder/layers.20/self_attn_layer_norm/gamma:0": "tf_model-00001-of-00002.h5",
234
+ "tfopt_for_causal_lm/model/decoder/layers.21/fc1/bias:0": "tf_model-00001-of-00002.h5",
235
+ "tfopt_for_causal_lm/model/decoder/layers.21/fc1/kernel:0": "tf_model-00001-of-00002.h5",
236
+ "tfopt_for_causal_lm/model/decoder/layers.21/fc2/bias:0": "tf_model-00001-of-00002.h5",
237
+ "tfopt_for_causal_lm/model/decoder/layers.21/fc2/kernel:0": "tf_model-00001-of-00002.h5",
238
+ "tfopt_for_causal_lm/model/decoder/layers.21/final_layer_norm/beta:0": "tf_model-00001-of-00002.h5",
239
+ "tfopt_for_causal_lm/model/decoder/layers.21/final_layer_norm/gamma:0": "tf_model-00001-of-00002.h5",
240
+ "tfopt_for_causal_lm/model/decoder/layers.21/self_attn/k_proj/bias:0": "tf_model-00001-of-00002.h5",
241
+ "tfopt_for_causal_lm/model/decoder/layers.21/self_attn/k_proj/kernel:0": "tf_model-00001-of-00002.h5",
242
+ "tfopt_for_causal_lm/model/decoder/layers.21/self_attn/out_proj/bias:0": "tf_model-00001-of-00002.h5",
243
+ "tfopt_for_causal_lm/model/decoder/layers.21/self_attn/out_proj/kernel:0": "tf_model-00001-of-00002.h5",
244
+ "tfopt_for_causal_lm/model/decoder/layers.21/self_attn/q_proj/bias:0": "tf_model-00001-of-00002.h5",
245
+ "tfopt_for_causal_lm/model/decoder/layers.21/self_attn/q_proj/kernel:0": "tf_model-00001-of-00002.h5",
246
+ "tfopt_for_causal_lm/model/decoder/layers.21/self_attn/v_proj/bias:0": "tf_model-00001-of-00002.h5",
247
+ "tfopt_for_causal_lm/model/decoder/layers.21/self_attn/v_proj/kernel:0": "tf_model-00001-of-00002.h5",
248
+ "tfopt_for_causal_lm/model/decoder/layers.21/self_attn_layer_norm/beta:0": "tf_model-00001-of-00002.h5",
249
+ "tfopt_for_causal_lm/model/decoder/layers.21/self_attn_layer_norm/gamma:0": "tf_model-00001-of-00002.h5",
250
+ "tfopt_for_causal_lm/model/decoder/layers.22/fc1/bias:0": "tf_model-00001-of-00002.h5",
251
+ "tfopt_for_causal_lm/model/decoder/layers.22/fc1/kernel:0": "tf_model-00001-of-00002.h5",
252
+ "tfopt_for_causal_lm/model/decoder/layers.22/fc2/bias:0": "tf_model-00001-of-00002.h5",
253
+ "tfopt_for_causal_lm/model/decoder/layers.22/fc2/kernel:0": "tf_model-00001-of-00002.h5",
254
+ "tfopt_for_causal_lm/model/decoder/layers.22/final_layer_norm/beta:0": "tf_model-00001-of-00002.h5",
255
+ "tfopt_for_causal_lm/model/decoder/layers.22/final_layer_norm/gamma:0": "tf_model-00001-of-00002.h5",
256
+ "tfopt_for_causal_lm/model/decoder/layers.22/self_attn/k_proj/bias:0": "tf_model-00001-of-00002.h5",
257
+ "tfopt_for_causal_lm/model/decoder/layers.22/self_attn/k_proj/kernel:0": "tf_model-00001-of-00002.h5",
258
+ "tfopt_for_causal_lm/model/decoder/layers.22/self_attn/out_proj/bias:0": "tf_model-00001-of-00002.h5",
259
+ "tfopt_for_causal_lm/model/decoder/layers.22/self_attn/out_proj/kernel:0": "tf_model-00001-of-00002.h5",
260
+ "tfopt_for_causal_lm/model/decoder/layers.22/self_attn/q_proj/bias:0": "tf_model-00001-of-00002.h5",
261
+ "tfopt_for_causal_lm/model/decoder/layers.22/self_attn/q_proj/kernel:0": "tf_model-00001-of-00002.h5",
262
+ "tfopt_for_causal_lm/model/decoder/layers.22/self_attn/v_proj/bias:0": "tf_model-00001-of-00002.h5",
263
+ "tfopt_for_causal_lm/model/decoder/layers.22/self_attn/v_proj/kernel:0": "tf_model-00001-of-00002.h5",
264
+ "tfopt_for_causal_lm/model/decoder/layers.22/self_attn_layer_norm/beta:0": "tf_model-00001-of-00002.h5",
265
+ "tfopt_for_causal_lm/model/decoder/layers.22/self_attn_layer_norm/gamma:0": "tf_model-00001-of-00002.h5",
266
+ "tfopt_for_causal_lm/model/decoder/layers.23/fc1/bias:0": "tf_model-00001-of-00002.h5",
267
+ "tfopt_for_causal_lm/model/decoder/layers.23/fc1/kernel:0": "tf_model-00001-of-00002.h5",
268
+ "tfopt_for_causal_lm/model/decoder/layers.23/fc2/bias:0": "tf_model-00002-of-00002.h5",
269
+ "tfopt_for_causal_lm/model/decoder/layers.23/fc2/kernel:0": "tf_model-00002-of-00002.h5",
270
+ "tfopt_for_causal_lm/model/decoder/layers.23/final_layer_norm/beta:0": "tf_model-00002-of-00002.h5",
271
+ "tfopt_for_causal_lm/model/decoder/layers.23/final_layer_norm/gamma:0": "tf_model-00002-of-00002.h5",
272
+ "tfopt_for_causal_lm/model/decoder/layers.23/self_attn/k_proj/bias:0": "tf_model-00001-of-00002.h5",
273
+ "tfopt_for_causal_lm/model/decoder/layers.23/self_attn/k_proj/kernel:0": "tf_model-00001-of-00002.h5",
274
+ "tfopt_for_causal_lm/model/decoder/layers.23/self_attn/out_proj/bias:0": "tf_model-00001-of-00002.h5",
275
+ "tfopt_for_causal_lm/model/decoder/layers.23/self_attn/out_proj/kernel:0": "tf_model-00001-of-00002.h5",
276
+ "tfopt_for_causal_lm/model/decoder/layers.23/self_attn/q_proj/bias:0": "tf_model-00001-of-00002.h5",
277
+ "tfopt_for_causal_lm/model/decoder/layers.23/self_attn/q_proj/kernel:0": "tf_model-00001-of-00002.h5",
278
+ "tfopt_for_causal_lm/model/decoder/layers.23/self_attn/v_proj/bias:0": "tf_model-00001-of-00002.h5",
279
+ "tfopt_for_causal_lm/model/decoder/layers.23/self_attn/v_proj/kernel:0": "tf_model-00001-of-00002.h5",
280
+ "tfopt_for_causal_lm/model/decoder/layers.23/self_attn_layer_norm/beta:0": "tf_model-00001-of-00002.h5",
281
+ "tfopt_for_causal_lm/model/decoder/layers.23/self_attn_layer_norm/gamma:0": "tf_model-00001-of-00002.h5",
282
+ "tfopt_for_causal_lm/model/decoder/layers.24/fc1/bias:0": "tf_model-00002-of-00002.h5",
283
+ "tfopt_for_causal_lm/model/decoder/layers.24/fc1/kernel:0": "tf_model-00002-of-00002.h5",
284
+ "tfopt_for_causal_lm/model/decoder/layers.24/fc2/bias:0": "tf_model-00002-of-00002.h5",
285
+ "tfopt_for_causal_lm/model/decoder/layers.24/fc2/kernel:0": "tf_model-00002-of-00002.h5",
286
+ "tfopt_for_causal_lm/model/decoder/layers.24/final_layer_norm/beta:0": "tf_model-00002-of-00002.h5",
287
+ "tfopt_for_causal_lm/model/decoder/layers.24/final_layer_norm/gamma:0": "tf_model-00002-of-00002.h5",
288
+ "tfopt_for_causal_lm/model/decoder/layers.24/self_attn/k_proj/bias:0": "tf_model-00002-of-00002.h5",
289
+ "tfopt_for_causal_lm/model/decoder/layers.24/self_attn/k_proj/kernel:0": "tf_model-00002-of-00002.h5",
290
+ "tfopt_for_causal_lm/model/decoder/layers.24/self_attn/out_proj/bias:0": "tf_model-00002-of-00002.h5",
291
+ "tfopt_for_causal_lm/model/decoder/layers.24/self_attn/out_proj/kernel:0": "tf_model-00002-of-00002.h5",
292
+ "tfopt_for_causal_lm/model/decoder/layers.24/self_attn/q_proj/bias:0": "tf_model-00002-of-00002.h5",
293
+ "tfopt_for_causal_lm/model/decoder/layers.24/self_attn/q_proj/kernel:0": "tf_model-00002-of-00002.h5",
294
+ "tfopt_for_causal_lm/model/decoder/layers.24/self_attn/v_proj/bias:0": "tf_model-00002-of-00002.h5",
295
+ "tfopt_for_causal_lm/model/decoder/layers.24/self_attn/v_proj/kernel:0": "tf_model-00002-of-00002.h5",
296
+ "tfopt_for_causal_lm/model/decoder/layers.24/self_attn_layer_norm/beta:0": "tf_model-00002-of-00002.h5",
297
+ "tfopt_for_causal_lm/model/decoder/layers.24/self_attn_layer_norm/gamma:0": "tf_model-00002-of-00002.h5",
298
+ "tfopt_for_causal_lm/model/decoder/layers.25/fc1/bias:0": "tf_model-00002-of-00002.h5",
299
+ "tfopt_for_causal_lm/model/decoder/layers.25/fc1/kernel:0": "tf_model-00002-of-00002.h5",
300
+ "tfopt_for_causal_lm/model/decoder/layers.25/fc2/bias:0": "tf_model-00002-of-00002.h5",
301
+ "tfopt_for_causal_lm/model/decoder/layers.25/fc2/kernel:0": "tf_model-00002-of-00002.h5",
302
+ "tfopt_for_causal_lm/model/decoder/layers.25/final_layer_norm/beta:0": "tf_model-00002-of-00002.h5",
303
+ "tfopt_for_causal_lm/model/decoder/layers.25/final_layer_norm/gamma:0": "tf_model-00002-of-00002.h5",
304
+ "tfopt_for_causal_lm/model/decoder/layers.25/self_attn/k_proj/bias:0": "tf_model-00002-of-00002.h5",
305
+ "tfopt_for_causal_lm/model/decoder/layers.25/self_attn/k_proj/kernel:0": "tf_model-00002-of-00002.h5",
306
+ "tfopt_for_causal_lm/model/decoder/layers.25/self_attn/out_proj/bias:0": "tf_model-00002-of-00002.h5",
307
+ "tfopt_for_causal_lm/model/decoder/layers.25/self_attn/out_proj/kernel:0": "tf_model-00002-of-00002.h5",
308
+ "tfopt_for_causal_lm/model/decoder/layers.25/self_attn/q_proj/bias:0": "tf_model-00002-of-00002.h5",
309
+ "tfopt_for_causal_lm/model/decoder/layers.25/self_attn/q_proj/kernel:0": "tf_model-00002-of-00002.h5",
310
+ "tfopt_for_causal_lm/model/decoder/layers.25/self_attn/v_proj/bias:0": "tf_model-00002-of-00002.h5",
311
+ "tfopt_for_causal_lm/model/decoder/layers.25/self_attn/v_proj/kernel:0": "tf_model-00002-of-00002.h5",
312
+ "tfopt_for_causal_lm/model/decoder/layers.25/self_attn_layer_norm/beta:0": "tf_model-00002-of-00002.h5",
313
+ "tfopt_for_causal_lm/model/decoder/layers.25/self_attn_layer_norm/gamma:0": "tf_model-00002-of-00002.h5",
314
+ "tfopt_for_causal_lm/model/decoder/layers.26/fc1/bias:0": "tf_model-00002-of-00002.h5",
315
+ "tfopt_for_causal_lm/model/decoder/layers.26/fc1/kernel:0": "tf_model-00002-of-00002.h5",
316
+ "tfopt_for_causal_lm/model/decoder/layers.26/fc2/bias:0": "tf_model-00002-of-00002.h5",
317
+ "tfopt_for_causal_lm/model/decoder/layers.26/fc2/kernel:0": "tf_model-00002-of-00002.h5",
318
+ "tfopt_for_causal_lm/model/decoder/layers.26/final_layer_norm/beta:0": "tf_model-00002-of-00002.h5",
319
+ "tfopt_for_causal_lm/model/decoder/layers.26/final_layer_norm/gamma:0": "tf_model-00002-of-00002.h5",
320
+ "tfopt_for_causal_lm/model/decoder/layers.26/self_attn/k_proj/bias:0": "tf_model-00002-of-00002.h5",
321
+ "tfopt_for_causal_lm/model/decoder/layers.26/self_attn/k_proj/kernel:0": "tf_model-00002-of-00002.h5",
322
+ "tfopt_for_causal_lm/model/decoder/layers.26/self_attn/out_proj/bias:0": "tf_model-00002-of-00002.h5",
323
+ "tfopt_for_causal_lm/model/decoder/layers.26/self_attn/out_proj/kernel:0": "tf_model-00002-of-00002.h5",
324
+ "tfopt_for_causal_lm/model/decoder/layers.26/self_attn/q_proj/bias:0": "tf_model-00002-of-00002.h5",
325
+ "tfopt_for_causal_lm/model/decoder/layers.26/self_attn/q_proj/kernel:0": "tf_model-00002-of-00002.h5",
326
+ "tfopt_for_causal_lm/model/decoder/layers.26/self_attn/v_proj/bias:0": "tf_model-00002-of-00002.h5",
327
+ "tfopt_for_causal_lm/model/decoder/layers.26/self_attn/v_proj/kernel:0": "tf_model-00002-of-00002.h5",
328
+ "tfopt_for_causal_lm/model/decoder/layers.26/self_attn_layer_norm/beta:0": "tf_model-00002-of-00002.h5",
329
+ "tfopt_for_causal_lm/model/decoder/layers.26/self_attn_layer_norm/gamma:0": "tf_model-00002-of-00002.h5",
330
+ "tfopt_for_causal_lm/model/decoder/layers.27/fc1/bias:0": "tf_model-00002-of-00002.h5",
331
+ "tfopt_for_causal_lm/model/decoder/layers.27/fc1/kernel:0": "tf_model-00002-of-00002.h5",
332
+ "tfopt_for_causal_lm/model/decoder/layers.27/fc2/bias:0": "tf_model-00002-of-00002.h5",
333
+ "tfopt_for_causal_lm/model/decoder/layers.27/fc2/kernel:0": "tf_model-00002-of-00002.h5",
334
+ "tfopt_for_causal_lm/model/decoder/layers.27/final_layer_norm/beta:0": "tf_model-00002-of-00002.h5",
335
+ "tfopt_for_causal_lm/model/decoder/layers.27/final_layer_norm/gamma:0": "tf_model-00002-of-00002.h5",
336
+ "tfopt_for_causal_lm/model/decoder/layers.27/self_attn/k_proj/bias:0": "tf_model-00002-of-00002.h5",
337
+ "tfopt_for_causal_lm/model/decoder/layers.27/self_attn/k_proj/kernel:0": "tf_model-00002-of-00002.h5",
338
+ "tfopt_for_causal_lm/model/decoder/layers.27/self_attn/out_proj/bias:0": "tf_model-00002-of-00002.h5",
339
+ "tfopt_for_causal_lm/model/decoder/layers.27/self_attn/out_proj/kernel:0": "tf_model-00002-of-00002.h5",
340
+ "tfopt_for_causal_lm/model/decoder/layers.27/self_attn/q_proj/bias:0": "tf_model-00002-of-00002.h5",
341
+ "tfopt_for_causal_lm/model/decoder/layers.27/self_attn/q_proj/kernel:0": "tf_model-00002-of-00002.h5",
342
+ "tfopt_for_causal_lm/model/decoder/layers.27/self_attn/v_proj/bias:0": "tf_model-00002-of-00002.h5",
343
+ "tfopt_for_causal_lm/model/decoder/layers.27/self_attn/v_proj/kernel:0": "tf_model-00002-of-00002.h5",
344
+ "tfopt_for_causal_lm/model/decoder/layers.27/self_attn_layer_norm/beta:0": "tf_model-00002-of-00002.h5",
345
+ "tfopt_for_causal_lm/model/decoder/layers.27/self_attn_layer_norm/gamma:0": "tf_model-00002-of-00002.h5",
346
+ "tfopt_for_causal_lm/model/decoder/layers.28/fc1/bias:0": "tf_model-00002-of-00002.h5",
347
+ "tfopt_for_causal_lm/model/decoder/layers.28/fc1/kernel:0": "tf_model-00002-of-00002.h5",
348
+ "tfopt_for_causal_lm/model/decoder/layers.28/fc2/bias:0": "tf_model-00002-of-00002.h5",
349
+ "tfopt_for_causal_lm/model/decoder/layers.28/fc2/kernel:0": "tf_model-00002-of-00002.h5",
350
+ "tfopt_for_causal_lm/model/decoder/layers.28/final_layer_norm/beta:0": "tf_model-00002-of-00002.h5",
351
+ "tfopt_for_causal_lm/model/decoder/layers.28/final_layer_norm/gamma:0": "tf_model-00002-of-00002.h5",
352
+ "tfopt_for_causal_lm/model/decoder/layers.28/self_attn/k_proj/bias:0": "tf_model-00002-of-00002.h5",
353
+ "tfopt_for_causal_lm/model/decoder/layers.28/self_attn/k_proj/kernel:0": "tf_model-00002-of-00002.h5",
354
+ "tfopt_for_causal_lm/model/decoder/layers.28/self_attn/out_proj/bias:0": "tf_model-00002-of-00002.h5",
355
+ "tfopt_for_causal_lm/model/decoder/layers.28/self_attn/out_proj/kernel:0": "tf_model-00002-of-00002.h5",
356
+ "tfopt_for_causal_lm/model/decoder/layers.28/self_attn/q_proj/bias:0": "tf_model-00002-of-00002.h5",
357
+ "tfopt_for_causal_lm/model/decoder/layers.28/self_attn/q_proj/kernel:0": "tf_model-00002-of-00002.h5",
358
+ "tfopt_for_causal_lm/model/decoder/layers.28/self_attn/v_proj/bias:0": "tf_model-00002-of-00002.h5",
359
+ "tfopt_for_causal_lm/model/decoder/layers.28/self_attn/v_proj/kernel:0": "tf_model-00002-of-00002.h5",
360
+ "tfopt_for_causal_lm/model/decoder/layers.28/self_attn_layer_norm/beta:0": "tf_model-00002-of-00002.h5",
361
+ "tfopt_for_causal_lm/model/decoder/layers.28/self_attn_layer_norm/gamma:0": "tf_model-00002-of-00002.h5",
362
+ "tfopt_for_causal_lm/model/decoder/layers.29/fc1/bias:0": "tf_model-00002-of-00002.h5",
363
+ "tfopt_for_causal_lm/model/decoder/layers.29/fc1/kernel:0": "tf_model-00002-of-00002.h5",
364
+ "tfopt_for_causal_lm/model/decoder/layers.29/fc2/bias:0": "tf_model-00002-of-00002.h5",
365
+ "tfopt_for_causal_lm/model/decoder/layers.29/fc2/kernel:0": "tf_model-00002-of-00002.h5",
366
+ "tfopt_for_causal_lm/model/decoder/layers.29/final_layer_norm/beta:0": "tf_model-00002-of-00002.h5",
367
+ "tfopt_for_causal_lm/model/decoder/layers.29/final_layer_norm/gamma:0": "tf_model-00002-of-00002.h5",
368
+ "tfopt_for_causal_lm/model/decoder/layers.29/self_attn/k_proj/bias:0": "tf_model-00002-of-00002.h5",
369
+ "tfopt_for_causal_lm/model/decoder/layers.29/self_attn/k_proj/kernel:0": "tf_model-00002-of-00002.h5",
370
+ "tfopt_for_causal_lm/model/decoder/layers.29/self_attn/out_proj/bias:0": "tf_model-00002-of-00002.h5",
371
+ "tfopt_for_causal_lm/model/decoder/layers.29/self_attn/out_proj/kernel:0": "tf_model-00002-of-00002.h5",
372
+ "tfopt_for_causal_lm/model/decoder/layers.29/self_attn/q_proj/bias:0": "tf_model-00002-of-00002.h5",
373
+ "tfopt_for_causal_lm/model/decoder/layers.29/self_attn/q_proj/kernel:0": "tf_model-00002-of-00002.h5",
374
+ "tfopt_for_causal_lm/model/decoder/layers.29/self_attn/v_proj/bias:0": "tf_model-00002-of-00002.h5",
375
+ "tfopt_for_causal_lm/model/decoder/layers.29/self_attn/v_proj/kernel:0": "tf_model-00002-of-00002.h5",
376
+ "tfopt_for_causal_lm/model/decoder/layers.29/self_attn_layer_norm/beta:0": "tf_model-00002-of-00002.h5",
377
+ "tfopt_for_causal_lm/model/decoder/layers.29/self_attn_layer_norm/gamma:0": "tf_model-00002-of-00002.h5",
378
+ "tfopt_for_causal_lm/model/decoder/layers.3/fc1/bias:0": "tf_model-00001-of-00002.h5",
379
+ "tfopt_for_causal_lm/model/decoder/layers.3/fc1/kernel:0": "tf_model-00001-of-00002.h5",
380
+ "tfopt_for_causal_lm/model/decoder/layers.3/fc2/bias:0": "tf_model-00001-of-00002.h5",
381
+ "tfopt_for_causal_lm/model/decoder/layers.3/fc2/kernel:0": "tf_model-00001-of-00002.h5",
382
+ "tfopt_for_causal_lm/model/decoder/layers.3/final_layer_norm/beta:0": "tf_model-00001-of-00002.h5",
383
+ "tfopt_for_causal_lm/model/decoder/layers.3/final_layer_norm/gamma:0": "tf_model-00001-of-00002.h5",
384
+ "tfopt_for_causal_lm/model/decoder/layers.3/self_attn/k_proj/bias:0": "tf_model-00001-of-00002.h5",
385
+ "tfopt_for_causal_lm/model/decoder/layers.3/self_attn/k_proj/kernel:0": "tf_model-00001-of-00002.h5",
386
+ "tfopt_for_causal_lm/model/decoder/layers.3/self_attn/out_proj/bias:0": "tf_model-00001-of-00002.h5",
387
+ "tfopt_for_causal_lm/model/decoder/layers.3/self_attn/out_proj/kernel:0": "tf_model-00001-of-00002.h5",
388
+ "tfopt_for_causal_lm/model/decoder/layers.3/self_attn/q_proj/bias:0": "tf_model-00001-of-00002.h5",
389
+ "tfopt_for_causal_lm/model/decoder/layers.3/self_attn/q_proj/kernel:0": "tf_model-00001-of-00002.h5",
390
+ "tfopt_for_causal_lm/model/decoder/layers.3/self_attn/v_proj/bias:0": "tf_model-00001-of-00002.h5",
391
+ "tfopt_for_causal_lm/model/decoder/layers.3/self_attn/v_proj/kernel:0": "tf_model-00001-of-00002.h5",
392
+ "tfopt_for_causal_lm/model/decoder/layers.3/self_attn_layer_norm/beta:0": "tf_model-00001-of-00002.h5",
393
+ "tfopt_for_causal_lm/model/decoder/layers.3/self_attn_layer_norm/gamma:0": "tf_model-00001-of-00002.h5",
394
+ "tfopt_for_causal_lm/model/decoder/layers.30/fc1/bias:0": "tf_model-00002-of-00002.h5",
395
+ "tfopt_for_causal_lm/model/decoder/layers.30/fc1/kernel:0": "tf_model-00002-of-00002.h5",
396
+ "tfopt_for_causal_lm/model/decoder/layers.30/fc2/bias:0": "tf_model-00002-of-00002.h5",
397
+ "tfopt_for_causal_lm/model/decoder/layers.30/fc2/kernel:0": "tf_model-00002-of-00002.h5",
398
+ "tfopt_for_causal_lm/model/decoder/layers.30/final_layer_norm/beta:0": "tf_model-00002-of-00002.h5",
399
+ "tfopt_for_causal_lm/model/decoder/layers.30/final_layer_norm/gamma:0": "tf_model-00002-of-00002.h5",
400
+ "tfopt_for_causal_lm/model/decoder/layers.30/self_attn/k_proj/bias:0": "tf_model-00002-of-00002.h5",
401
+ "tfopt_for_causal_lm/model/decoder/layers.30/self_attn/k_proj/kernel:0": "tf_model-00002-of-00002.h5",
402
+ "tfopt_for_causal_lm/model/decoder/layers.30/self_attn/out_proj/bias:0": "tf_model-00002-of-00002.h5",
403
+ "tfopt_for_causal_lm/model/decoder/layers.30/self_attn/out_proj/kernel:0": "tf_model-00002-of-00002.h5",
404
+ "tfopt_for_causal_lm/model/decoder/layers.30/self_attn/q_proj/bias:0": "tf_model-00002-of-00002.h5",
405
+ "tfopt_for_causal_lm/model/decoder/layers.30/self_attn/q_proj/kernel:0": "tf_model-00002-of-00002.h5",
406
+ "tfopt_for_causal_lm/model/decoder/layers.30/self_attn/v_proj/bias:0": "tf_model-00002-of-00002.h5",
407
+ "tfopt_for_causal_lm/model/decoder/layers.30/self_attn/v_proj/kernel:0": "tf_model-00002-of-00002.h5",
408
+ "tfopt_for_causal_lm/model/decoder/layers.30/self_attn_layer_norm/beta:0": "tf_model-00002-of-00002.h5",
409
+ "tfopt_for_causal_lm/model/decoder/layers.30/self_attn_layer_norm/gamma:0": "tf_model-00002-of-00002.h5",
410
+ "tfopt_for_causal_lm/model/decoder/layers.31/fc1/bias:0": "tf_model-00002-of-00002.h5",
411
+ "tfopt_for_causal_lm/model/decoder/layers.31/fc1/kernel:0": "tf_model-00002-of-00002.h5",
412
+ "tfopt_for_causal_lm/model/decoder/layers.31/fc2/bias:0": "tf_model-00002-of-00002.h5",
413
+ "tfopt_for_causal_lm/model/decoder/layers.31/fc2/kernel:0": "tf_model-00002-of-00002.h5",
414
+ "tfopt_for_causal_lm/model/decoder/layers.31/final_layer_norm/beta:0": "tf_model-00002-of-00002.h5",
415
+ "tfopt_for_causal_lm/model/decoder/layers.31/final_layer_norm/gamma:0": "tf_model-00002-of-00002.h5",
416
+ "tfopt_for_causal_lm/model/decoder/layers.31/self_attn/k_proj/bias:0": "tf_model-00002-of-00002.h5",
417
+ "tfopt_for_causal_lm/model/decoder/layers.31/self_attn/k_proj/kernel:0": "tf_model-00002-of-00002.h5",
418
+ "tfopt_for_causal_lm/model/decoder/layers.31/self_attn/out_proj/bias:0": "tf_model-00002-of-00002.h5",
419
+ "tfopt_for_causal_lm/model/decoder/layers.31/self_attn/out_proj/kernel:0": "tf_model-00002-of-00002.h5",
420
+ "tfopt_for_causal_lm/model/decoder/layers.31/self_attn/q_proj/bias:0": "tf_model-00002-of-00002.h5",
421
+ "tfopt_for_causal_lm/model/decoder/layers.31/self_attn/q_proj/kernel:0": "tf_model-00002-of-00002.h5",
422
+ "tfopt_for_causal_lm/model/decoder/layers.31/self_attn/v_proj/bias:0": "tf_model-00002-of-00002.h5",
423
+ "tfopt_for_causal_lm/model/decoder/layers.31/self_attn/v_proj/kernel:0": "tf_model-00002-of-00002.h5",
424
+ "tfopt_for_causal_lm/model/decoder/layers.31/self_attn_layer_norm/beta:0": "tf_model-00002-of-00002.h5",
425
+ "tfopt_for_causal_lm/model/decoder/layers.31/self_attn_layer_norm/gamma:0": "tf_model-00002-of-00002.h5",
426
+ "tfopt_for_causal_lm/model/decoder/layers.4/fc1/bias:0": "tf_model-00001-of-00002.h5",
427
+ "tfopt_for_causal_lm/model/decoder/layers.4/fc1/kernel:0": "tf_model-00001-of-00002.h5",
428
+ "tfopt_for_causal_lm/model/decoder/layers.4/fc2/bias:0": "tf_model-00001-of-00002.h5",
429
+ "tfopt_for_causal_lm/model/decoder/layers.4/fc2/kernel:0": "tf_model-00001-of-00002.h5",
430
+ "tfopt_for_causal_lm/model/decoder/layers.4/final_layer_norm/beta:0": "tf_model-00001-of-00002.h5",
431
+ "tfopt_for_causal_lm/model/decoder/layers.4/final_layer_norm/gamma:0": "tf_model-00001-of-00002.h5",
432
+ "tfopt_for_causal_lm/model/decoder/layers.4/self_attn/k_proj/bias:0": "tf_model-00001-of-00002.h5",
433
+ "tfopt_for_causal_lm/model/decoder/layers.4/self_attn/k_proj/kernel:0": "tf_model-00001-of-00002.h5",
434
+ "tfopt_for_causal_lm/model/decoder/layers.4/self_attn/out_proj/bias:0": "tf_model-00001-of-00002.h5",
435
+ "tfopt_for_causal_lm/model/decoder/layers.4/self_attn/out_proj/kernel:0": "tf_model-00001-of-00002.h5",
436
+ "tfopt_for_causal_lm/model/decoder/layers.4/self_attn/q_proj/bias:0": "tf_model-00001-of-00002.h5",
437
+ "tfopt_for_causal_lm/model/decoder/layers.4/self_attn/q_proj/kernel:0": "tf_model-00001-of-00002.h5",
438
+ "tfopt_for_causal_lm/model/decoder/layers.4/self_attn/v_proj/bias:0": "tf_model-00001-of-00002.h5",
439
+ "tfopt_for_causal_lm/model/decoder/layers.4/self_attn/v_proj/kernel:0": "tf_model-00001-of-00002.h5",
440
+ "tfopt_for_causal_lm/model/decoder/layers.4/self_attn_layer_norm/beta:0": "tf_model-00001-of-00002.h5",
441
+ "tfopt_for_causal_lm/model/decoder/layers.4/self_attn_layer_norm/gamma:0": "tf_model-00001-of-00002.h5",
442
+ "tfopt_for_causal_lm/model/decoder/layers.5/fc1/bias:0": "tf_model-00001-of-00002.h5",
443
+ "tfopt_for_causal_lm/model/decoder/layers.5/fc1/kernel:0": "tf_model-00001-of-00002.h5",
444
+ "tfopt_for_causal_lm/model/decoder/layers.5/fc2/bias:0": "tf_model-00001-of-00002.h5",
445
+ "tfopt_for_causal_lm/model/decoder/layers.5/fc2/kernel:0": "tf_model-00001-of-00002.h5",
446
+ "tfopt_for_causal_lm/model/decoder/layers.5/final_layer_norm/beta:0": "tf_model-00001-of-00002.h5",
447
+ "tfopt_for_causal_lm/model/decoder/layers.5/final_layer_norm/gamma:0": "tf_model-00001-of-00002.h5",
448
+ "tfopt_for_causal_lm/model/decoder/layers.5/self_attn/k_proj/bias:0": "tf_model-00001-of-00002.h5",
449
+ "tfopt_for_causal_lm/model/decoder/layers.5/self_attn/k_proj/kernel:0": "tf_model-00001-of-00002.h5",
450
+ "tfopt_for_causal_lm/model/decoder/layers.5/self_attn/out_proj/bias:0": "tf_model-00001-of-00002.h5",
451
+ "tfopt_for_causal_lm/model/decoder/layers.5/self_attn/out_proj/kernel:0": "tf_model-00001-of-00002.h5",
452
+ "tfopt_for_causal_lm/model/decoder/layers.5/self_attn/q_proj/bias:0": "tf_model-00001-of-00002.h5",
453
+ "tfopt_for_causal_lm/model/decoder/layers.5/self_attn/q_proj/kernel:0": "tf_model-00001-of-00002.h5",
454
+ "tfopt_for_causal_lm/model/decoder/layers.5/self_attn/v_proj/bias:0": "tf_model-00001-of-00002.h5",
455
+ "tfopt_for_causal_lm/model/decoder/layers.5/self_attn/v_proj/kernel:0": "tf_model-00001-of-00002.h5",
456
+ "tfopt_for_causal_lm/model/decoder/layers.5/self_attn_layer_norm/beta:0": "tf_model-00001-of-00002.h5",
457
+ "tfopt_for_causal_lm/model/decoder/layers.5/self_attn_layer_norm/gamma:0": "tf_model-00001-of-00002.h5",
458
+ "tfopt_for_causal_lm/model/decoder/layers.6/fc1/bias:0": "tf_model-00001-of-00002.h5",
459
+ "tfopt_for_causal_lm/model/decoder/layers.6/fc1/kernel:0": "tf_model-00001-of-00002.h5",
460
+ "tfopt_for_causal_lm/model/decoder/layers.6/fc2/bias:0": "tf_model-00001-of-00002.h5",
461
+ "tfopt_for_causal_lm/model/decoder/layers.6/fc2/kernel:0": "tf_model-00001-of-00002.h5",
462
+ "tfopt_for_causal_lm/model/decoder/layers.6/final_layer_norm/beta:0": "tf_model-00001-of-00002.h5",
463
+ "tfopt_for_causal_lm/model/decoder/layers.6/final_layer_norm/gamma:0": "tf_model-00001-of-00002.h5",
464
+ "tfopt_for_causal_lm/model/decoder/layers.6/self_attn/k_proj/bias:0": "tf_model-00001-of-00002.h5",
465
+ "tfopt_for_causal_lm/model/decoder/layers.6/self_attn/k_proj/kernel:0": "tf_model-00001-of-00002.h5",
466
+ "tfopt_for_causal_lm/model/decoder/layers.6/self_attn/out_proj/bias:0": "tf_model-00001-of-00002.h5",
467
+ "tfopt_for_causal_lm/model/decoder/layers.6/self_attn/out_proj/kernel:0": "tf_model-00001-of-00002.h5",
468
+ "tfopt_for_causal_lm/model/decoder/layers.6/self_attn/q_proj/bias:0": "tf_model-00001-of-00002.h5",
469
+ "tfopt_for_causal_lm/model/decoder/layers.6/self_attn/q_proj/kernel:0": "tf_model-00001-of-00002.h5",
470
+ "tfopt_for_causal_lm/model/decoder/layers.6/self_attn/v_proj/bias:0": "tf_model-00001-of-00002.h5",
471
+ "tfopt_for_causal_lm/model/decoder/layers.6/self_attn/v_proj/kernel:0": "tf_model-00001-of-00002.h5",
472
+ "tfopt_for_causal_lm/model/decoder/layers.6/self_attn_layer_norm/beta:0": "tf_model-00001-of-00002.h5",
473
+ "tfopt_for_causal_lm/model/decoder/layers.6/self_attn_layer_norm/gamma:0": "tf_model-00001-of-00002.h5",
474
+ "tfopt_for_causal_lm/model/decoder/layers.7/fc1/bias:0": "tf_model-00001-of-00002.h5",
475
+ "tfopt_for_causal_lm/model/decoder/layers.7/fc1/kernel:0": "tf_model-00001-of-00002.h5",
476
+ "tfopt_for_causal_lm/model/decoder/layers.7/fc2/bias:0": "tf_model-00001-of-00002.h5",
477
+ "tfopt_for_causal_lm/model/decoder/layers.7/fc2/kernel:0": "tf_model-00001-of-00002.h5",
478
+ "tfopt_for_causal_lm/model/decoder/layers.7/final_layer_norm/beta:0": "tf_model-00001-of-00002.h5",
479
+ "tfopt_for_causal_lm/model/decoder/layers.7/final_layer_norm/gamma:0": "tf_model-00001-of-00002.h5",
480
+ "tfopt_for_causal_lm/model/decoder/layers.7/self_attn/k_proj/bias:0": "tf_model-00001-of-00002.h5",
481
+ "tfopt_for_causal_lm/model/decoder/layers.7/self_attn/k_proj/kernel:0": "tf_model-00001-of-00002.h5",
482
+ "tfopt_for_causal_lm/model/decoder/layers.7/self_attn/out_proj/bias:0": "tf_model-00001-of-00002.h5",
483
+ "tfopt_for_causal_lm/model/decoder/layers.7/self_attn/out_proj/kernel:0": "tf_model-00001-of-00002.h5",
484
+ "tfopt_for_causal_lm/model/decoder/layers.7/self_attn/q_proj/bias:0": "tf_model-00001-of-00002.h5",
485
+ "tfopt_for_causal_lm/model/decoder/layers.7/self_attn/q_proj/kernel:0": "tf_model-00001-of-00002.h5",
486
+ "tfopt_for_causal_lm/model/decoder/layers.7/self_attn/v_proj/bias:0": "tf_model-00001-of-00002.h5",
487
+ "tfopt_for_causal_lm/model/decoder/layers.7/self_attn/v_proj/kernel:0": "tf_model-00001-of-00002.h5",
488
+ "tfopt_for_causal_lm/model/decoder/layers.7/self_attn_layer_norm/beta:0": "tf_model-00001-of-00002.h5",
489
+ "tfopt_for_causal_lm/model/decoder/layers.7/self_attn_layer_norm/gamma:0": "tf_model-00001-of-00002.h5",
490
+ "tfopt_for_causal_lm/model/decoder/layers.8/fc1/bias:0": "tf_model-00001-of-00002.h5",
491
+ "tfopt_for_causal_lm/model/decoder/layers.8/fc1/kernel:0": "tf_model-00001-of-00002.h5",
492
+ "tfopt_for_causal_lm/model/decoder/layers.8/fc2/bias:0": "tf_model-00001-of-00002.h5",
493
+ "tfopt_for_causal_lm/model/decoder/layers.8/fc2/kernel:0": "tf_model-00001-of-00002.h5",
494
+ "tfopt_for_causal_lm/model/decoder/layers.8/final_layer_norm/beta:0": "tf_model-00001-of-00002.h5",
495
+ "tfopt_for_causal_lm/model/decoder/layers.8/final_layer_norm/gamma:0": "tf_model-00001-of-00002.h5",
496
+ "tfopt_for_causal_lm/model/decoder/layers.8/self_attn/k_proj/bias:0": "tf_model-00001-of-00002.h5",
497
+ "tfopt_for_causal_lm/model/decoder/layers.8/self_attn/k_proj/kernel:0": "tf_model-00001-of-00002.h5",
498
+ "tfopt_for_causal_lm/model/decoder/layers.8/self_attn/out_proj/bias:0": "tf_model-00001-of-00002.h5",
499
+ "tfopt_for_causal_lm/model/decoder/layers.8/self_attn/out_proj/kernel:0": "tf_model-00001-of-00002.h5",
500
+ "tfopt_for_causal_lm/model/decoder/layers.8/self_attn/q_proj/bias:0": "tf_model-00001-of-00002.h5",
501
+ "tfopt_for_causal_lm/model/decoder/layers.8/self_attn/q_proj/kernel:0": "tf_model-00001-of-00002.h5",
502
+ "tfopt_for_causal_lm/model/decoder/layers.8/self_attn/v_proj/bias:0": "tf_model-00001-of-00002.h5",
503
+ "tfopt_for_causal_lm/model/decoder/layers.8/self_attn/v_proj/kernel:0": "tf_model-00001-of-00002.h5",
504
+ "tfopt_for_causal_lm/model/decoder/layers.8/self_attn_layer_norm/beta:0": "tf_model-00001-of-00002.h5",
505
+ "tfopt_for_causal_lm/model/decoder/layers.8/self_attn_layer_norm/gamma:0": "tf_model-00001-of-00002.h5",
506
+ "tfopt_for_causal_lm/model/decoder/layers.9/fc1/bias:0": "tf_model-00001-of-00002.h5",
507
+ "tfopt_for_causal_lm/model/decoder/layers.9/fc1/kernel:0": "tf_model-00001-of-00002.h5",
508
+ "tfopt_for_causal_lm/model/decoder/layers.9/fc2/bias:0": "tf_model-00001-of-00002.h5",
509
+ "tfopt_for_causal_lm/model/decoder/layers.9/fc2/kernel:0": "tf_model-00001-of-00002.h5",
510
+ "tfopt_for_causal_lm/model/decoder/layers.9/final_layer_norm/beta:0": "tf_model-00001-of-00002.h5",
511
+ "tfopt_for_causal_lm/model/decoder/layers.9/final_layer_norm/gamma:0": "tf_model-00001-of-00002.h5",
512
+ "tfopt_for_causal_lm/model/decoder/layers.9/self_attn/k_proj/bias:0": "tf_model-00001-of-00002.h5",
513
+ "tfopt_for_causal_lm/model/decoder/layers.9/self_attn/k_proj/kernel:0": "tf_model-00001-of-00002.h5",
514
+ "tfopt_for_causal_lm/model/decoder/layers.9/self_attn/out_proj/bias:0": "tf_model-00001-of-00002.h5",
515
+ "tfopt_for_causal_lm/model/decoder/layers.9/self_attn/out_proj/kernel:0": "tf_model-00001-of-00002.h5",
516
+ "tfopt_for_causal_lm/model/decoder/layers.9/self_attn/q_proj/bias:0": "tf_model-00001-of-00002.h5",
517
+ "tfopt_for_causal_lm/model/decoder/layers.9/self_attn/q_proj/kernel:0": "tf_model-00001-of-00002.h5",
518
+ "tfopt_for_causal_lm/model/decoder/layers.9/self_attn/v_proj/bias:0": "tf_model-00001-of-00002.h5",
519
+ "tfopt_for_causal_lm/model/decoder/layers.9/self_attn/v_proj/kernel:0": "tf_model-00001-of-00002.h5",
520
+ "tfopt_for_causal_lm/model/decoder/layers.9/self_attn_layer_norm/beta:0": "tf_model-00001-of-00002.h5",
521
+ "tfopt_for_causal_lm/model/decoder/layers.9/self_attn_layer_norm/gamma:0": "tf_model-00001-of-00002.h5"
522
+ }
523
+ }
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"errors": "replace", "unk_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "bos_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "eos_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "pad_token": {"content": "<pad>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "add_prefix_space": false, "add_bos_token": true, "special_tokens_map_file": null, "name_or_path": "sayril007/finoma-tokeinzer-main"}
vocab.json ADDED
The diff for this file is too large to render. See raw diff