ehartford commited on
Commit
895467e
1 Parent(s): d74b1cb

Upload folder using huggingface_hub

Browse files
added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "<|im_end|>": 49152,
3
+ "<|im_start|>": 49153
4
+ }
config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/home/ubuntu/models/starcoder2-15b",
3
+ "architectures": [
4
+ "Starcoder2ForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 0,
8
+ "embedding_dropout": 0.0,
9
+ "eos_token_id": 0,
10
+ "hidden_act": "gelu_pytorch_tanh",
11
+ "hidden_size": 6144,
12
+ "initializer_range": 0.01275,
13
+ "intermediate_size": 24576,
14
+ "max_position_embeddings": 16384,
15
+ "mlp_type": "default",
16
+ "model_type": "starcoder2",
17
+ "norm_epsilon": 1e-05,
18
+ "norm_type": "layer_norm",
19
+ "num_attention_heads": 48,
20
+ "num_hidden_layers": 40,
21
+ "num_key_value_heads": 4,
22
+ "residual_dropout": 0.0,
23
+ "rms_norm_eps": 1e-05,
24
+ "rope_theta": 100000,
25
+ "sliding_window": 4096,
26
+ "tie_word_embeddings": false,
27
+ "torch_dtype": "bfloat16",
28
+ "transformers_version": "4.39.0.dev0",
29
+ "use_bias": true,
30
+ "use_cache": false,
31
+ "vocab_size": 49154
32
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 50256,
4
+ "do_sample": true,
5
+ "eos_token_id": 50256,
6
+ "transformers_version": "4.39.0.dev0"
7
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
pytorch_model-00001-of-00007.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f1414ca0cd503eeedf3870d3b123102ad65bd6d3b68e15f203b77e7890c48ff
3
+ size 4908152736
pytorch_model-00002-of-00007.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4269051c492354399dfa12ff801be01d28ab6ffe007ded8f5d165694a8d9bfda
3
+ size 4996351634
pytorch_model-00003-of-00007.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:597d0af842e44651a3222663179ae4d00d78661132de4ebd1e936c09d5508398
3
+ size 4983751762
pytorch_model-00004-of-00007.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d5557359a9d16a4492a62476e6e87987f81479d6c018e36fc5a4327ebda111be
3
+ size 4996351698
pytorch_model-00005-of-00007.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:78503484662eb7031a9490aa1a81b2b33cd80714da27edf77cf3635fdef1a135
3
+ size 4983751762
pytorch_model-00006-of-00007.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6acc382c1e5aca6ef8594b608b2073d206b22a6837afa37dfec7df40918becc0
3
+ size 4996351698
pytorch_model-00007-of-00007.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd2612589a81fa3be40e9bbfb086a018f590b4a8c86709a9c6692165b9594075
3
+ size 2051333876
pytorch_model.bin.index.json ADDED
@@ -0,0 +1,651 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 31915827200
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "pytorch_model-00007-of-00007.bin",
7
+ "model.embed_tokens.weight": "pytorch_model-00001-of-00007.bin",
8
+ "model.layers.0.input_layernorm.bias": "pytorch_model-00001-of-00007.bin",
9
+ "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00007.bin",
10
+ "model.layers.0.mlp.c_fc.bias": "pytorch_model-00001-of-00007.bin",
11
+ "model.layers.0.mlp.c_fc.weight": "pytorch_model-00001-of-00007.bin",
12
+ "model.layers.0.mlp.c_proj.bias": "pytorch_model-00001-of-00007.bin",
13
+ "model.layers.0.mlp.c_proj.weight": "pytorch_model-00001-of-00007.bin",
14
+ "model.layers.0.post_attention_layernorm.bias": "pytorch_model-00001-of-00007.bin",
15
+ "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00007.bin",
16
+ "model.layers.0.self_attn.k_proj.bias": "pytorch_model-00001-of-00007.bin",
17
+ "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00007.bin",
18
+ "model.layers.0.self_attn.o_proj.bias": "pytorch_model-00001-of-00007.bin",
19
+ "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00007.bin",
20
+ "model.layers.0.self_attn.q_proj.bias": "pytorch_model-00001-of-00007.bin",
21
+ "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00007.bin",
22
+ "model.layers.0.self_attn.v_proj.bias": "pytorch_model-00001-of-00007.bin",
23
+ "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00007.bin",
24
+ "model.layers.1.input_layernorm.bias": "pytorch_model-00001-of-00007.bin",
25
+ "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00007.bin",
26
+ "model.layers.1.mlp.c_fc.bias": "pytorch_model-00001-of-00007.bin",
27
+ "model.layers.1.mlp.c_fc.weight": "pytorch_model-00001-of-00007.bin",
28
+ "model.layers.1.mlp.c_proj.bias": "pytorch_model-00001-of-00007.bin",
29
+ "model.layers.1.mlp.c_proj.weight": "pytorch_model-00001-of-00007.bin",
30
+ "model.layers.1.post_attention_layernorm.bias": "pytorch_model-00001-of-00007.bin",
31
+ "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00007.bin",
32
+ "model.layers.1.self_attn.k_proj.bias": "pytorch_model-00001-of-00007.bin",
33
+ "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00007.bin",
34
+ "model.layers.1.self_attn.o_proj.bias": "pytorch_model-00001-of-00007.bin",
35
+ "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00007.bin",
36
+ "model.layers.1.self_attn.q_proj.bias": "pytorch_model-00001-of-00007.bin",
37
+ "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00007.bin",
38
+ "model.layers.1.self_attn.v_proj.bias": "pytorch_model-00001-of-00007.bin",
39
+ "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00007.bin",
40
+ "model.layers.10.input_layernorm.bias": "pytorch_model-00002-of-00007.bin",
41
+ "model.layers.10.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
42
+ "model.layers.10.mlp.c_fc.bias": "pytorch_model-00002-of-00007.bin",
43
+ "model.layers.10.mlp.c_fc.weight": "pytorch_model-00002-of-00007.bin",
44
+ "model.layers.10.mlp.c_proj.bias": "pytorch_model-00002-of-00007.bin",
45
+ "model.layers.10.mlp.c_proj.weight": "pytorch_model-00002-of-00007.bin",
46
+ "model.layers.10.post_attention_layernorm.bias": "pytorch_model-00002-of-00007.bin",
47
+ "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin",
48
+ "model.layers.10.self_attn.k_proj.bias": "pytorch_model-00002-of-00007.bin",
49
+ "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00002-of-00007.bin",
50
+ "model.layers.10.self_attn.o_proj.bias": "pytorch_model-00002-of-00007.bin",
51
+ "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00002-of-00007.bin",
52
+ "model.layers.10.self_attn.q_proj.bias": "pytorch_model-00002-of-00007.bin",
53
+ "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00002-of-00007.bin",
54
+ "model.layers.10.self_attn.v_proj.bias": "pytorch_model-00002-of-00007.bin",
55
+ "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00002-of-00007.bin",
56
+ "model.layers.11.input_layernorm.bias": "pytorch_model-00002-of-00007.bin",
57
+ "model.layers.11.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
58
+ "model.layers.11.mlp.c_fc.bias": "pytorch_model-00002-of-00007.bin",
59
+ "model.layers.11.mlp.c_fc.weight": "pytorch_model-00002-of-00007.bin",
60
+ "model.layers.11.mlp.c_proj.bias": "pytorch_model-00002-of-00007.bin",
61
+ "model.layers.11.mlp.c_proj.weight": "pytorch_model-00002-of-00007.bin",
62
+ "model.layers.11.post_attention_layernorm.bias": "pytorch_model-00002-of-00007.bin",
63
+ "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin",
64
+ "model.layers.11.self_attn.k_proj.bias": "pytorch_model-00002-of-00007.bin",
65
+ "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00002-of-00007.bin",
66
+ "model.layers.11.self_attn.o_proj.bias": "pytorch_model-00002-of-00007.bin",
67
+ "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00002-of-00007.bin",
68
+ "model.layers.11.self_attn.q_proj.bias": "pytorch_model-00002-of-00007.bin",
69
+ "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00002-of-00007.bin",
70
+ "model.layers.11.self_attn.v_proj.bias": "pytorch_model-00002-of-00007.bin",
71
+ "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00002-of-00007.bin",
72
+ "model.layers.12.input_layernorm.bias": "pytorch_model-00003-of-00007.bin",
73
+ "model.layers.12.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
74
+ "model.layers.12.mlp.c_fc.bias": "pytorch_model-00003-of-00007.bin",
75
+ "model.layers.12.mlp.c_fc.weight": "pytorch_model-00003-of-00007.bin",
76
+ "model.layers.12.mlp.c_proj.bias": "pytorch_model-00003-of-00007.bin",
77
+ "model.layers.12.mlp.c_proj.weight": "pytorch_model-00003-of-00007.bin",
78
+ "model.layers.12.post_attention_layernorm.bias": "pytorch_model-00003-of-00007.bin",
79
+ "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin",
80
+ "model.layers.12.self_attn.k_proj.bias": "pytorch_model-00002-of-00007.bin",
81
+ "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00002-of-00007.bin",
82
+ "model.layers.12.self_attn.o_proj.bias": "pytorch_model-00003-of-00007.bin",
83
+ "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00003-of-00007.bin",
84
+ "model.layers.12.self_attn.q_proj.bias": "pytorch_model-00002-of-00007.bin",
85
+ "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00002-of-00007.bin",
86
+ "model.layers.12.self_attn.v_proj.bias": "pytorch_model-00002-of-00007.bin",
87
+ "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00002-of-00007.bin",
88
+ "model.layers.13.input_layernorm.bias": "pytorch_model-00003-of-00007.bin",
89
+ "model.layers.13.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
90
+ "model.layers.13.mlp.c_fc.bias": "pytorch_model-00003-of-00007.bin",
91
+ "model.layers.13.mlp.c_fc.weight": "pytorch_model-00003-of-00007.bin",
92
+ "model.layers.13.mlp.c_proj.bias": "pytorch_model-00003-of-00007.bin",
93
+ "model.layers.13.mlp.c_proj.weight": "pytorch_model-00003-of-00007.bin",
94
+ "model.layers.13.post_attention_layernorm.bias": "pytorch_model-00003-of-00007.bin",
95
+ "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin",
96
+ "model.layers.13.self_attn.k_proj.bias": "pytorch_model-00003-of-00007.bin",
97
+ "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00003-of-00007.bin",
98
+ "model.layers.13.self_attn.o_proj.bias": "pytorch_model-00003-of-00007.bin",
99
+ "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00003-of-00007.bin",
100
+ "model.layers.13.self_attn.q_proj.bias": "pytorch_model-00003-of-00007.bin",
101
+ "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00003-of-00007.bin",
102
+ "model.layers.13.self_attn.v_proj.bias": "pytorch_model-00003-of-00007.bin",
103
+ "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00003-of-00007.bin",
104
+ "model.layers.14.input_layernorm.bias": "pytorch_model-00003-of-00007.bin",
105
+ "model.layers.14.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
106
+ "model.layers.14.mlp.c_fc.bias": "pytorch_model-00003-of-00007.bin",
107
+ "model.layers.14.mlp.c_fc.weight": "pytorch_model-00003-of-00007.bin",
108
+ "model.layers.14.mlp.c_proj.bias": "pytorch_model-00003-of-00007.bin",
109
+ "model.layers.14.mlp.c_proj.weight": "pytorch_model-00003-of-00007.bin",
110
+ "model.layers.14.post_attention_layernorm.bias": "pytorch_model-00003-of-00007.bin",
111
+ "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin",
112
+ "model.layers.14.self_attn.k_proj.bias": "pytorch_model-00003-of-00007.bin",
113
+ "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00003-of-00007.bin",
114
+ "model.layers.14.self_attn.o_proj.bias": "pytorch_model-00003-of-00007.bin",
115
+ "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00003-of-00007.bin",
116
+ "model.layers.14.self_attn.q_proj.bias": "pytorch_model-00003-of-00007.bin",
117
+ "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00003-of-00007.bin",
118
+ "model.layers.14.self_attn.v_proj.bias": "pytorch_model-00003-of-00007.bin",
119
+ "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00003-of-00007.bin",
120
+ "model.layers.15.input_layernorm.bias": "pytorch_model-00003-of-00007.bin",
121
+ "model.layers.15.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
122
+ "model.layers.15.mlp.c_fc.bias": "pytorch_model-00003-of-00007.bin",
123
+ "model.layers.15.mlp.c_fc.weight": "pytorch_model-00003-of-00007.bin",
124
+ "model.layers.15.mlp.c_proj.bias": "pytorch_model-00003-of-00007.bin",
125
+ "model.layers.15.mlp.c_proj.weight": "pytorch_model-00003-of-00007.bin",
126
+ "model.layers.15.post_attention_layernorm.bias": "pytorch_model-00003-of-00007.bin",
127
+ "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin",
128
+ "model.layers.15.self_attn.k_proj.bias": "pytorch_model-00003-of-00007.bin",
129
+ "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00003-of-00007.bin",
130
+ "model.layers.15.self_attn.o_proj.bias": "pytorch_model-00003-of-00007.bin",
131
+ "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00003-of-00007.bin",
132
+ "model.layers.15.self_attn.q_proj.bias": "pytorch_model-00003-of-00007.bin",
133
+ "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00003-of-00007.bin",
134
+ "model.layers.15.self_attn.v_proj.bias": "pytorch_model-00003-of-00007.bin",
135
+ "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00003-of-00007.bin",
136
+ "model.layers.16.input_layernorm.bias": "pytorch_model-00003-of-00007.bin",
137
+ "model.layers.16.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
138
+ "model.layers.16.mlp.c_fc.bias": "pytorch_model-00003-of-00007.bin",
139
+ "model.layers.16.mlp.c_fc.weight": "pytorch_model-00003-of-00007.bin",
140
+ "model.layers.16.mlp.c_proj.bias": "pytorch_model-00003-of-00007.bin",
141
+ "model.layers.16.mlp.c_proj.weight": "pytorch_model-00003-of-00007.bin",
142
+ "model.layers.16.post_attention_layernorm.bias": "pytorch_model-00003-of-00007.bin",
143
+ "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin",
144
+ "model.layers.16.self_attn.k_proj.bias": "pytorch_model-00003-of-00007.bin",
145
+ "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00003-of-00007.bin",
146
+ "model.layers.16.self_attn.o_proj.bias": "pytorch_model-00003-of-00007.bin",
147
+ "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00003-of-00007.bin",
148
+ "model.layers.16.self_attn.q_proj.bias": "pytorch_model-00003-of-00007.bin",
149
+ "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00003-of-00007.bin",
150
+ "model.layers.16.self_attn.v_proj.bias": "pytorch_model-00003-of-00007.bin",
151
+ "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00003-of-00007.bin",
152
+ "model.layers.17.input_layernorm.bias": "pytorch_model-00003-of-00007.bin",
153
+ "model.layers.17.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
154
+ "model.layers.17.mlp.c_fc.bias": "pytorch_model-00003-of-00007.bin",
155
+ "model.layers.17.mlp.c_fc.weight": "pytorch_model-00003-of-00007.bin",
156
+ "model.layers.17.mlp.c_proj.bias": "pytorch_model-00003-of-00007.bin",
157
+ "model.layers.17.mlp.c_proj.weight": "pytorch_model-00003-of-00007.bin",
158
+ "model.layers.17.post_attention_layernorm.bias": "pytorch_model-00003-of-00007.bin",
159
+ "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin",
160
+ "model.layers.17.self_attn.k_proj.bias": "pytorch_model-00003-of-00007.bin",
161
+ "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00003-of-00007.bin",
162
+ "model.layers.17.self_attn.o_proj.bias": "pytorch_model-00003-of-00007.bin",
163
+ "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00003-of-00007.bin",
164
+ "model.layers.17.self_attn.q_proj.bias": "pytorch_model-00003-of-00007.bin",
165
+ "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00003-of-00007.bin",
166
+ "model.layers.17.self_attn.v_proj.bias": "pytorch_model-00003-of-00007.bin",
167
+ "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00003-of-00007.bin",
168
+ "model.layers.18.input_layernorm.bias": "pytorch_model-00004-of-00007.bin",
169
+ "model.layers.18.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
170
+ "model.layers.18.mlp.c_fc.bias": "pytorch_model-00003-of-00007.bin",
171
+ "model.layers.18.mlp.c_fc.weight": "pytorch_model-00003-of-00007.bin",
172
+ "model.layers.18.mlp.c_proj.bias": "pytorch_model-00004-of-00007.bin",
173
+ "model.layers.18.mlp.c_proj.weight": "pytorch_model-00004-of-00007.bin",
174
+ "model.layers.18.post_attention_layernorm.bias": "pytorch_model-00004-of-00007.bin",
175
+ "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin",
176
+ "model.layers.18.self_attn.k_proj.bias": "pytorch_model-00003-of-00007.bin",
177
+ "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00003-of-00007.bin",
178
+ "model.layers.18.self_attn.o_proj.bias": "pytorch_model-00003-of-00007.bin",
179
+ "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00003-of-00007.bin",
180
+ "model.layers.18.self_attn.q_proj.bias": "pytorch_model-00003-of-00007.bin",
181
+ "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00003-of-00007.bin",
182
+ "model.layers.18.self_attn.v_proj.bias": "pytorch_model-00003-of-00007.bin",
183
+ "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00003-of-00007.bin",
184
+ "model.layers.19.input_layernorm.bias": "pytorch_model-00004-of-00007.bin",
185
+ "model.layers.19.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
186
+ "model.layers.19.mlp.c_fc.bias": "pytorch_model-00004-of-00007.bin",
187
+ "model.layers.19.mlp.c_fc.weight": "pytorch_model-00004-of-00007.bin",
188
+ "model.layers.19.mlp.c_proj.bias": "pytorch_model-00004-of-00007.bin",
189
+ "model.layers.19.mlp.c_proj.weight": "pytorch_model-00004-of-00007.bin",
190
+ "model.layers.19.post_attention_layernorm.bias": "pytorch_model-00004-of-00007.bin",
191
+ "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin",
192
+ "model.layers.19.self_attn.k_proj.bias": "pytorch_model-00004-of-00007.bin",
193
+ "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00004-of-00007.bin",
194
+ "model.layers.19.self_attn.o_proj.bias": "pytorch_model-00004-of-00007.bin",
195
+ "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00004-of-00007.bin",
196
+ "model.layers.19.self_attn.q_proj.bias": "pytorch_model-00004-of-00007.bin",
197
+ "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00004-of-00007.bin",
198
+ "model.layers.19.self_attn.v_proj.bias": "pytorch_model-00004-of-00007.bin",
199
+ "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00004-of-00007.bin",
200
+ "model.layers.2.input_layernorm.bias": "pytorch_model-00001-of-00007.bin",
201
+ "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00007.bin",
202
+ "model.layers.2.mlp.c_fc.bias": "pytorch_model-00001-of-00007.bin",
203
+ "model.layers.2.mlp.c_fc.weight": "pytorch_model-00001-of-00007.bin",
204
+ "model.layers.2.mlp.c_proj.bias": "pytorch_model-00001-of-00007.bin",
205
+ "model.layers.2.mlp.c_proj.weight": "pytorch_model-00001-of-00007.bin",
206
+ "model.layers.2.post_attention_layernorm.bias": "pytorch_model-00001-of-00007.bin",
207
+ "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00007.bin",
208
+ "model.layers.2.self_attn.k_proj.bias": "pytorch_model-00001-of-00007.bin",
209
+ "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00007.bin",
210
+ "model.layers.2.self_attn.o_proj.bias": "pytorch_model-00001-of-00007.bin",
211
+ "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00007.bin",
212
+ "model.layers.2.self_attn.q_proj.bias": "pytorch_model-00001-of-00007.bin",
213
+ "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00007.bin",
214
+ "model.layers.2.self_attn.v_proj.bias": "pytorch_model-00001-of-00007.bin",
215
+ "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00007.bin",
216
+ "model.layers.20.input_layernorm.bias": "pytorch_model-00004-of-00007.bin",
217
+ "model.layers.20.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
218
+ "model.layers.20.mlp.c_fc.bias": "pytorch_model-00004-of-00007.bin",
219
+ "model.layers.20.mlp.c_fc.weight": "pytorch_model-00004-of-00007.bin",
220
+ "model.layers.20.mlp.c_proj.bias": "pytorch_model-00004-of-00007.bin",
221
+ "model.layers.20.mlp.c_proj.weight": "pytorch_model-00004-of-00007.bin",
222
+ "model.layers.20.post_attention_layernorm.bias": "pytorch_model-00004-of-00007.bin",
223
+ "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin",
224
+ "model.layers.20.self_attn.k_proj.bias": "pytorch_model-00004-of-00007.bin",
225
+ "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00004-of-00007.bin",
226
+ "model.layers.20.self_attn.o_proj.bias": "pytorch_model-00004-of-00007.bin",
227
+ "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00004-of-00007.bin",
228
+ "model.layers.20.self_attn.q_proj.bias": "pytorch_model-00004-of-00007.bin",
229
+ "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00004-of-00007.bin",
230
+ "model.layers.20.self_attn.v_proj.bias": "pytorch_model-00004-of-00007.bin",
231
+ "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00004-of-00007.bin",
232
+ "model.layers.21.input_layernorm.bias": "pytorch_model-00004-of-00007.bin",
233
+ "model.layers.21.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
234
+ "model.layers.21.mlp.c_fc.bias": "pytorch_model-00004-of-00007.bin",
235
+ "model.layers.21.mlp.c_fc.weight": "pytorch_model-00004-of-00007.bin",
236
+ "model.layers.21.mlp.c_proj.bias": "pytorch_model-00004-of-00007.bin",
237
+ "model.layers.21.mlp.c_proj.weight": "pytorch_model-00004-of-00007.bin",
238
+ "model.layers.21.post_attention_layernorm.bias": "pytorch_model-00004-of-00007.bin",
239
+ "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin",
240
+ "model.layers.21.self_attn.k_proj.bias": "pytorch_model-00004-of-00007.bin",
241
+ "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00004-of-00007.bin",
242
+ "model.layers.21.self_attn.o_proj.bias": "pytorch_model-00004-of-00007.bin",
243
+ "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00004-of-00007.bin",
244
+ "model.layers.21.self_attn.q_proj.bias": "pytorch_model-00004-of-00007.bin",
245
+ "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00004-of-00007.bin",
246
+ "model.layers.21.self_attn.v_proj.bias": "pytorch_model-00004-of-00007.bin",
247
+ "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00004-of-00007.bin",
248
+ "model.layers.22.input_layernorm.bias": "pytorch_model-00004-of-00007.bin",
249
+ "model.layers.22.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
250
+ "model.layers.22.mlp.c_fc.bias": "pytorch_model-00004-of-00007.bin",
251
+ "model.layers.22.mlp.c_fc.weight": "pytorch_model-00004-of-00007.bin",
252
+ "model.layers.22.mlp.c_proj.bias": "pytorch_model-00004-of-00007.bin",
253
+ "model.layers.22.mlp.c_proj.weight": "pytorch_model-00004-of-00007.bin",
254
+ "model.layers.22.post_attention_layernorm.bias": "pytorch_model-00004-of-00007.bin",
255
+ "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin",
256
+ "model.layers.22.self_attn.k_proj.bias": "pytorch_model-00004-of-00007.bin",
257
+ "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00004-of-00007.bin",
258
+ "model.layers.22.self_attn.o_proj.bias": "pytorch_model-00004-of-00007.bin",
259
+ "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00004-of-00007.bin",
260
+ "model.layers.22.self_attn.q_proj.bias": "pytorch_model-00004-of-00007.bin",
261
+ "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00004-of-00007.bin",
262
+ "model.layers.22.self_attn.v_proj.bias": "pytorch_model-00004-of-00007.bin",
263
+ "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00004-of-00007.bin",
264
+ "model.layers.23.input_layernorm.bias": "pytorch_model-00004-of-00007.bin",
265
+ "model.layers.23.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
266
+ "model.layers.23.mlp.c_fc.bias": "pytorch_model-00004-of-00007.bin",
267
+ "model.layers.23.mlp.c_fc.weight": "pytorch_model-00004-of-00007.bin",
268
+ "model.layers.23.mlp.c_proj.bias": "pytorch_model-00004-of-00007.bin",
269
+ "model.layers.23.mlp.c_proj.weight": "pytorch_model-00004-of-00007.bin",
270
+ "model.layers.23.post_attention_layernorm.bias": "pytorch_model-00004-of-00007.bin",
271
+ "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin",
272
+ "model.layers.23.self_attn.k_proj.bias": "pytorch_model-00004-of-00007.bin",
273
+ "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00004-of-00007.bin",
274
+ "model.layers.23.self_attn.o_proj.bias": "pytorch_model-00004-of-00007.bin",
275
+ "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00004-of-00007.bin",
276
+ "model.layers.23.self_attn.q_proj.bias": "pytorch_model-00004-of-00007.bin",
277
+ "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00004-of-00007.bin",
278
+ "model.layers.23.self_attn.v_proj.bias": "pytorch_model-00004-of-00007.bin",
279
+ "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00004-of-00007.bin",
280
+ "model.layers.24.input_layernorm.bias": "pytorch_model-00004-of-00007.bin",
281
+ "model.layers.24.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
282
+ "model.layers.24.mlp.c_fc.bias": "pytorch_model-00004-of-00007.bin",
283
+ "model.layers.24.mlp.c_fc.weight": "pytorch_model-00004-of-00007.bin",
284
+ "model.layers.24.mlp.c_proj.bias": "pytorch_model-00004-of-00007.bin",
285
+ "model.layers.24.mlp.c_proj.weight": "pytorch_model-00004-of-00007.bin",
286
+ "model.layers.24.post_attention_layernorm.bias": "pytorch_model-00004-of-00007.bin",
287
+ "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin",
288
+ "model.layers.24.self_attn.k_proj.bias": "pytorch_model-00004-of-00007.bin",
289
+ "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00004-of-00007.bin",
290
+ "model.layers.24.self_attn.o_proj.bias": "pytorch_model-00004-of-00007.bin",
291
+ "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00004-of-00007.bin",
292
+ "model.layers.24.self_attn.q_proj.bias": "pytorch_model-00004-of-00007.bin",
293
+ "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00004-of-00007.bin",
294
+ "model.layers.24.self_attn.v_proj.bias": "pytorch_model-00004-of-00007.bin",
295
+ "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00004-of-00007.bin",
296
+ "model.layers.25.input_layernorm.bias": "pytorch_model-00005-of-00007.bin",
297
+ "model.layers.25.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
298
+ "model.layers.25.mlp.c_fc.bias": "pytorch_model-00005-of-00007.bin",
299
+ "model.layers.25.mlp.c_fc.weight": "pytorch_model-00005-of-00007.bin",
300
+ "model.layers.25.mlp.c_proj.bias": "pytorch_model-00005-of-00007.bin",
301
+ "model.layers.25.mlp.c_proj.weight": "pytorch_model-00005-of-00007.bin",
302
+ "model.layers.25.post_attention_layernorm.bias": "pytorch_model-00005-of-00007.bin",
303
+ "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00005-of-00007.bin",
304
+ "model.layers.25.self_attn.k_proj.bias": "pytorch_model-00004-of-00007.bin",
305
+ "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00004-of-00007.bin",
306
+ "model.layers.25.self_attn.o_proj.bias": "pytorch_model-00005-of-00007.bin",
307
+ "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00005-of-00007.bin",
308
+ "model.layers.25.self_attn.q_proj.bias": "pytorch_model-00004-of-00007.bin",
309
+ "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00004-of-00007.bin",
310
+ "model.layers.25.self_attn.v_proj.bias": "pytorch_model-00004-of-00007.bin",
311
+ "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00004-of-00007.bin",
312
+ "model.layers.26.input_layernorm.bias": "pytorch_model-00005-of-00007.bin",
313
+ "model.layers.26.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
314
+ "model.layers.26.mlp.c_fc.bias": "pytorch_model-00005-of-00007.bin",
315
+ "model.layers.26.mlp.c_fc.weight": "pytorch_model-00005-of-00007.bin",
316
+ "model.layers.26.mlp.c_proj.bias": "pytorch_model-00005-of-00007.bin",
317
+ "model.layers.26.mlp.c_proj.weight": "pytorch_model-00005-of-00007.bin",
318
+ "model.layers.26.post_attention_layernorm.bias": "pytorch_model-00005-of-00007.bin",
319
+ "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00005-of-00007.bin",
320
+ "model.layers.26.self_attn.k_proj.bias": "pytorch_model-00005-of-00007.bin",
321
+ "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00005-of-00007.bin",
322
+ "model.layers.26.self_attn.o_proj.bias": "pytorch_model-00005-of-00007.bin",
323
+ "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00005-of-00007.bin",
324
+ "model.layers.26.self_attn.q_proj.bias": "pytorch_model-00005-of-00007.bin",
325
+ "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00005-of-00007.bin",
326
+ "model.layers.26.self_attn.v_proj.bias": "pytorch_model-00005-of-00007.bin",
327
+ "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00005-of-00007.bin",
328
+ "model.layers.27.input_layernorm.bias": "pytorch_model-00005-of-00007.bin",
329
+ "model.layers.27.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
330
+ "model.layers.27.mlp.c_fc.bias": "pytorch_model-00005-of-00007.bin",
331
+ "model.layers.27.mlp.c_fc.weight": "pytorch_model-00005-of-00007.bin",
332
+ "model.layers.27.mlp.c_proj.bias": "pytorch_model-00005-of-00007.bin",
333
+ "model.layers.27.mlp.c_proj.weight": "pytorch_model-00005-of-00007.bin",
334
+ "model.layers.27.post_attention_layernorm.bias": "pytorch_model-00005-of-00007.bin",
335
+ "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00005-of-00007.bin",
336
+ "model.layers.27.self_attn.k_proj.bias": "pytorch_model-00005-of-00007.bin",
337
+ "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00005-of-00007.bin",
338
+ "model.layers.27.self_attn.o_proj.bias": "pytorch_model-00005-of-00007.bin",
339
+ "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00005-of-00007.bin",
340
+ "model.layers.27.self_attn.q_proj.bias": "pytorch_model-00005-of-00007.bin",
341
+ "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00005-of-00007.bin",
342
+ "model.layers.27.self_attn.v_proj.bias": "pytorch_model-00005-of-00007.bin",
343
+ "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00005-of-00007.bin",
344
+ "model.layers.28.input_layernorm.bias": "pytorch_model-00005-of-00007.bin",
345
+ "model.layers.28.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
346
+ "model.layers.28.mlp.c_fc.bias": "pytorch_model-00005-of-00007.bin",
347
+ "model.layers.28.mlp.c_fc.weight": "pytorch_model-00005-of-00007.bin",
348
+ "model.layers.28.mlp.c_proj.bias": "pytorch_model-00005-of-00007.bin",
349
+ "model.layers.28.mlp.c_proj.weight": "pytorch_model-00005-of-00007.bin",
350
+ "model.layers.28.post_attention_layernorm.bias": "pytorch_model-00005-of-00007.bin",
351
+ "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00005-of-00007.bin",
352
+ "model.layers.28.self_attn.k_proj.bias": "pytorch_model-00005-of-00007.bin",
353
+ "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00005-of-00007.bin",
354
+ "model.layers.28.self_attn.o_proj.bias": "pytorch_model-00005-of-00007.bin",
355
+ "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00005-of-00007.bin",
356
+ "model.layers.28.self_attn.q_proj.bias": "pytorch_model-00005-of-00007.bin",
357
+ "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00005-of-00007.bin",
358
+ "model.layers.28.self_attn.v_proj.bias": "pytorch_model-00005-of-00007.bin",
359
+ "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00005-of-00007.bin",
360
+ "model.layers.29.input_layernorm.bias": "pytorch_model-00005-of-00007.bin",
361
+ "model.layers.29.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
362
+ "model.layers.29.mlp.c_fc.bias": "pytorch_model-00005-of-00007.bin",
363
+ "model.layers.29.mlp.c_fc.weight": "pytorch_model-00005-of-00007.bin",
364
+ "model.layers.29.mlp.c_proj.bias": "pytorch_model-00005-of-00007.bin",
365
+ "model.layers.29.mlp.c_proj.weight": "pytorch_model-00005-of-00007.bin",
366
+ "model.layers.29.post_attention_layernorm.bias": "pytorch_model-00005-of-00007.bin",
367
+ "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00005-of-00007.bin",
368
+ "model.layers.29.self_attn.k_proj.bias": "pytorch_model-00005-of-00007.bin",
369
+ "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00005-of-00007.bin",
370
+ "model.layers.29.self_attn.o_proj.bias": "pytorch_model-00005-of-00007.bin",
371
+ "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00005-of-00007.bin",
372
+ "model.layers.29.self_attn.q_proj.bias": "pytorch_model-00005-of-00007.bin",
373
+ "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00005-of-00007.bin",
374
+ "model.layers.29.self_attn.v_proj.bias": "pytorch_model-00005-of-00007.bin",
375
+ "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00005-of-00007.bin",
376
+ "model.layers.3.input_layernorm.bias": "pytorch_model-00001-of-00007.bin",
377
+ "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00007.bin",
378
+ "model.layers.3.mlp.c_fc.bias": "pytorch_model-00001-of-00007.bin",
379
+ "model.layers.3.mlp.c_fc.weight": "pytorch_model-00001-of-00007.bin",
380
+ "model.layers.3.mlp.c_proj.bias": "pytorch_model-00001-of-00007.bin",
381
+ "model.layers.3.mlp.c_proj.weight": "pytorch_model-00001-of-00007.bin",
382
+ "model.layers.3.post_attention_layernorm.bias": "pytorch_model-00001-of-00007.bin",
383
+ "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00007.bin",
384
+ "model.layers.3.self_attn.k_proj.bias": "pytorch_model-00001-of-00007.bin",
385
+ "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00007.bin",
386
+ "model.layers.3.self_attn.o_proj.bias": "pytorch_model-00001-of-00007.bin",
387
+ "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00007.bin",
388
+ "model.layers.3.self_attn.q_proj.bias": "pytorch_model-00001-of-00007.bin",
389
+ "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00007.bin",
390
+ "model.layers.3.self_attn.v_proj.bias": "pytorch_model-00001-of-00007.bin",
391
+ "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00007.bin",
392
+ "model.layers.30.input_layernorm.bias": "pytorch_model-00005-of-00007.bin",
393
+ "model.layers.30.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
394
+ "model.layers.30.mlp.c_fc.bias": "pytorch_model-00005-of-00007.bin",
395
+ "model.layers.30.mlp.c_fc.weight": "pytorch_model-00005-of-00007.bin",
396
+ "model.layers.30.mlp.c_proj.bias": "pytorch_model-00005-of-00007.bin",
397
+ "model.layers.30.mlp.c_proj.weight": "pytorch_model-00005-of-00007.bin",
398
+ "model.layers.30.post_attention_layernorm.bias": "pytorch_model-00005-of-00007.bin",
399
+ "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00005-of-00007.bin",
400
+ "model.layers.30.self_attn.k_proj.bias": "pytorch_model-00005-of-00007.bin",
401
+ "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00005-of-00007.bin",
402
+ "model.layers.30.self_attn.o_proj.bias": "pytorch_model-00005-of-00007.bin",
403
+ "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00005-of-00007.bin",
404
+ "model.layers.30.self_attn.q_proj.bias": "pytorch_model-00005-of-00007.bin",
405
+ "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00005-of-00007.bin",
406
+ "model.layers.30.self_attn.v_proj.bias": "pytorch_model-00005-of-00007.bin",
407
+ "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00005-of-00007.bin",
408
+ "model.layers.31.input_layernorm.bias": "pytorch_model-00006-of-00007.bin",
409
+ "model.layers.31.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
410
+ "model.layers.31.mlp.c_fc.bias": "pytorch_model-00005-of-00007.bin",
411
+ "model.layers.31.mlp.c_fc.weight": "pytorch_model-00005-of-00007.bin",
412
+ "model.layers.31.mlp.c_proj.bias": "pytorch_model-00006-of-00007.bin",
413
+ "model.layers.31.mlp.c_proj.weight": "pytorch_model-00006-of-00007.bin",
414
+ "model.layers.31.post_attention_layernorm.bias": "pytorch_model-00006-of-00007.bin",
415
+ "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
416
+ "model.layers.31.self_attn.k_proj.bias": "pytorch_model-00005-of-00007.bin",
417
+ "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00005-of-00007.bin",
418
+ "model.layers.31.self_attn.o_proj.bias": "pytorch_model-00005-of-00007.bin",
419
+ "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00005-of-00007.bin",
420
+ "model.layers.31.self_attn.q_proj.bias": "pytorch_model-00005-of-00007.bin",
421
+ "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00005-of-00007.bin",
422
+ "model.layers.31.self_attn.v_proj.bias": "pytorch_model-00005-of-00007.bin",
423
+ "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00005-of-00007.bin",
424
+ "model.layers.32.input_layernorm.bias": "pytorch_model-00006-of-00007.bin",
425
+ "model.layers.32.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
426
+ "model.layers.32.mlp.c_fc.bias": "pytorch_model-00006-of-00007.bin",
427
+ "model.layers.32.mlp.c_fc.weight": "pytorch_model-00006-of-00007.bin",
428
+ "model.layers.32.mlp.c_proj.bias": "pytorch_model-00006-of-00007.bin",
429
+ "model.layers.32.mlp.c_proj.weight": "pytorch_model-00006-of-00007.bin",
430
+ "model.layers.32.post_attention_layernorm.bias": "pytorch_model-00006-of-00007.bin",
431
+ "model.layers.32.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
432
+ "model.layers.32.self_attn.k_proj.bias": "pytorch_model-00006-of-00007.bin",
433
+ "model.layers.32.self_attn.k_proj.weight": "pytorch_model-00006-of-00007.bin",
434
+ "model.layers.32.self_attn.o_proj.bias": "pytorch_model-00006-of-00007.bin",
435
+ "model.layers.32.self_attn.o_proj.weight": "pytorch_model-00006-of-00007.bin",
436
+ "model.layers.32.self_attn.q_proj.bias": "pytorch_model-00006-of-00007.bin",
437
+ "model.layers.32.self_attn.q_proj.weight": "pytorch_model-00006-of-00007.bin",
438
+ "model.layers.32.self_attn.v_proj.bias": "pytorch_model-00006-of-00007.bin",
439
+ "model.layers.32.self_attn.v_proj.weight": "pytorch_model-00006-of-00007.bin",
440
+ "model.layers.33.input_layernorm.bias": "pytorch_model-00006-of-00007.bin",
441
+ "model.layers.33.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
442
+ "model.layers.33.mlp.c_fc.bias": "pytorch_model-00006-of-00007.bin",
443
+ "model.layers.33.mlp.c_fc.weight": "pytorch_model-00006-of-00007.bin",
444
+ "model.layers.33.mlp.c_proj.bias": "pytorch_model-00006-of-00007.bin",
445
+ "model.layers.33.mlp.c_proj.weight": "pytorch_model-00006-of-00007.bin",
446
+ "model.layers.33.post_attention_layernorm.bias": "pytorch_model-00006-of-00007.bin",
447
+ "model.layers.33.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
448
+ "model.layers.33.self_attn.k_proj.bias": "pytorch_model-00006-of-00007.bin",
449
+ "model.layers.33.self_attn.k_proj.weight": "pytorch_model-00006-of-00007.bin",
450
+ "model.layers.33.self_attn.o_proj.bias": "pytorch_model-00006-of-00007.bin",
451
+ "model.layers.33.self_attn.o_proj.weight": "pytorch_model-00006-of-00007.bin",
452
+ "model.layers.33.self_attn.q_proj.bias": "pytorch_model-00006-of-00007.bin",
453
+ "model.layers.33.self_attn.q_proj.weight": "pytorch_model-00006-of-00007.bin",
454
+ "model.layers.33.self_attn.v_proj.bias": "pytorch_model-00006-of-00007.bin",
455
+ "model.layers.33.self_attn.v_proj.weight": "pytorch_model-00006-of-00007.bin",
456
+ "model.layers.34.input_layernorm.bias": "pytorch_model-00006-of-00007.bin",
457
+ "model.layers.34.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
458
+ "model.layers.34.mlp.c_fc.bias": "pytorch_model-00006-of-00007.bin",
459
+ "model.layers.34.mlp.c_fc.weight": "pytorch_model-00006-of-00007.bin",
460
+ "model.layers.34.mlp.c_proj.bias": "pytorch_model-00006-of-00007.bin",
461
+ "model.layers.34.mlp.c_proj.weight": "pytorch_model-00006-of-00007.bin",
462
+ "model.layers.34.post_attention_layernorm.bias": "pytorch_model-00006-of-00007.bin",
463
+ "model.layers.34.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
464
+ "model.layers.34.self_attn.k_proj.bias": "pytorch_model-00006-of-00007.bin",
465
+ "model.layers.34.self_attn.k_proj.weight": "pytorch_model-00006-of-00007.bin",
466
+ "model.layers.34.self_attn.o_proj.bias": "pytorch_model-00006-of-00007.bin",
467
+ "model.layers.34.self_attn.o_proj.weight": "pytorch_model-00006-of-00007.bin",
468
+ "model.layers.34.self_attn.q_proj.bias": "pytorch_model-00006-of-00007.bin",
469
+ "model.layers.34.self_attn.q_proj.weight": "pytorch_model-00006-of-00007.bin",
470
+ "model.layers.34.self_attn.v_proj.bias": "pytorch_model-00006-of-00007.bin",
471
+ "model.layers.34.self_attn.v_proj.weight": "pytorch_model-00006-of-00007.bin",
472
+ "model.layers.35.input_layernorm.bias": "pytorch_model-00006-of-00007.bin",
473
+ "model.layers.35.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
474
+ "model.layers.35.mlp.c_fc.bias": "pytorch_model-00006-of-00007.bin",
475
+ "model.layers.35.mlp.c_fc.weight": "pytorch_model-00006-of-00007.bin",
476
+ "model.layers.35.mlp.c_proj.bias": "pytorch_model-00006-of-00007.bin",
477
+ "model.layers.35.mlp.c_proj.weight": "pytorch_model-00006-of-00007.bin",
478
+ "model.layers.35.post_attention_layernorm.bias": "pytorch_model-00006-of-00007.bin",
479
+ "model.layers.35.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
480
+ "model.layers.35.self_attn.k_proj.bias": "pytorch_model-00006-of-00007.bin",
481
+ "model.layers.35.self_attn.k_proj.weight": "pytorch_model-00006-of-00007.bin",
482
+ "model.layers.35.self_attn.o_proj.bias": "pytorch_model-00006-of-00007.bin",
483
+ "model.layers.35.self_attn.o_proj.weight": "pytorch_model-00006-of-00007.bin",
484
+ "model.layers.35.self_attn.q_proj.bias": "pytorch_model-00006-of-00007.bin",
485
+ "model.layers.35.self_attn.q_proj.weight": "pytorch_model-00006-of-00007.bin",
486
+ "model.layers.35.self_attn.v_proj.bias": "pytorch_model-00006-of-00007.bin",
487
+ "model.layers.35.self_attn.v_proj.weight": "pytorch_model-00006-of-00007.bin",
488
+ "model.layers.36.input_layernorm.bias": "pytorch_model-00006-of-00007.bin",
489
+ "model.layers.36.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
490
+ "model.layers.36.mlp.c_fc.bias": "pytorch_model-00006-of-00007.bin",
491
+ "model.layers.36.mlp.c_fc.weight": "pytorch_model-00006-of-00007.bin",
492
+ "model.layers.36.mlp.c_proj.bias": "pytorch_model-00006-of-00007.bin",
493
+ "model.layers.36.mlp.c_proj.weight": "pytorch_model-00006-of-00007.bin",
494
+ "model.layers.36.post_attention_layernorm.bias": "pytorch_model-00006-of-00007.bin",
495
+ "model.layers.36.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
496
+ "model.layers.36.self_attn.k_proj.bias": "pytorch_model-00006-of-00007.bin",
497
+ "model.layers.36.self_attn.k_proj.weight": "pytorch_model-00006-of-00007.bin",
498
+ "model.layers.36.self_attn.o_proj.bias": "pytorch_model-00006-of-00007.bin",
499
+ "model.layers.36.self_attn.o_proj.weight": "pytorch_model-00006-of-00007.bin",
500
+ "model.layers.36.self_attn.q_proj.bias": "pytorch_model-00006-of-00007.bin",
501
+ "model.layers.36.self_attn.q_proj.weight": "pytorch_model-00006-of-00007.bin",
502
+ "model.layers.36.self_attn.v_proj.bias": "pytorch_model-00006-of-00007.bin",
503
+ "model.layers.36.self_attn.v_proj.weight": "pytorch_model-00006-of-00007.bin",
504
+ "model.layers.37.input_layernorm.bias": "pytorch_model-00006-of-00007.bin",
505
+ "model.layers.37.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
506
+ "model.layers.37.mlp.c_fc.bias": "pytorch_model-00006-of-00007.bin",
507
+ "model.layers.37.mlp.c_fc.weight": "pytorch_model-00006-of-00007.bin",
508
+ "model.layers.37.mlp.c_proj.bias": "pytorch_model-00006-of-00007.bin",
509
+ "model.layers.37.mlp.c_proj.weight": "pytorch_model-00006-of-00007.bin",
510
+ "model.layers.37.post_attention_layernorm.bias": "pytorch_model-00006-of-00007.bin",
511
+ "model.layers.37.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
512
+ "model.layers.37.self_attn.k_proj.bias": "pytorch_model-00006-of-00007.bin",
513
+ "model.layers.37.self_attn.k_proj.weight": "pytorch_model-00006-of-00007.bin",
514
+ "model.layers.37.self_attn.o_proj.bias": "pytorch_model-00006-of-00007.bin",
515
+ "model.layers.37.self_attn.o_proj.weight": "pytorch_model-00006-of-00007.bin",
516
+ "model.layers.37.self_attn.q_proj.bias": "pytorch_model-00006-of-00007.bin",
517
+ "model.layers.37.self_attn.q_proj.weight": "pytorch_model-00006-of-00007.bin",
518
+ "model.layers.37.self_attn.v_proj.bias": "pytorch_model-00006-of-00007.bin",
519
+ "model.layers.37.self_attn.v_proj.weight": "pytorch_model-00006-of-00007.bin",
520
+ "model.layers.38.input_layernorm.bias": "pytorch_model-00007-of-00007.bin",
521
+ "model.layers.38.input_layernorm.weight": "pytorch_model-00007-of-00007.bin",
522
+ "model.layers.38.mlp.c_fc.bias": "pytorch_model-00007-of-00007.bin",
523
+ "model.layers.38.mlp.c_fc.weight": "pytorch_model-00007-of-00007.bin",
524
+ "model.layers.38.mlp.c_proj.bias": "pytorch_model-00007-of-00007.bin",
525
+ "model.layers.38.mlp.c_proj.weight": "pytorch_model-00007-of-00007.bin",
526
+ "model.layers.38.post_attention_layernorm.bias": "pytorch_model-00007-of-00007.bin",
527
+ "model.layers.38.post_attention_layernorm.weight": "pytorch_model-00007-of-00007.bin",
528
+ "model.layers.38.self_attn.k_proj.bias": "pytorch_model-00006-of-00007.bin",
529
+ "model.layers.38.self_attn.k_proj.weight": "pytorch_model-00006-of-00007.bin",
530
+ "model.layers.38.self_attn.o_proj.bias": "pytorch_model-00007-of-00007.bin",
531
+ "model.layers.38.self_attn.o_proj.weight": "pytorch_model-00007-of-00007.bin",
532
+ "model.layers.38.self_attn.q_proj.bias": "pytorch_model-00006-of-00007.bin",
533
+ "model.layers.38.self_attn.q_proj.weight": "pytorch_model-00006-of-00007.bin",
534
+ "model.layers.38.self_attn.v_proj.bias": "pytorch_model-00006-of-00007.bin",
535
+ "model.layers.38.self_attn.v_proj.weight": "pytorch_model-00006-of-00007.bin",
536
+ "model.layers.39.input_layernorm.bias": "pytorch_model-00007-of-00007.bin",
537
+ "model.layers.39.input_layernorm.weight": "pytorch_model-00007-of-00007.bin",
538
+ "model.layers.39.mlp.c_fc.bias": "pytorch_model-00007-of-00007.bin",
539
+ "model.layers.39.mlp.c_fc.weight": "pytorch_model-00007-of-00007.bin",
540
+ "model.layers.39.mlp.c_proj.bias": "pytorch_model-00007-of-00007.bin",
541
+ "model.layers.39.mlp.c_proj.weight": "pytorch_model-00007-of-00007.bin",
542
+ "model.layers.39.post_attention_layernorm.bias": "pytorch_model-00007-of-00007.bin",
543
+ "model.layers.39.post_attention_layernorm.weight": "pytorch_model-00007-of-00007.bin",
544
+ "model.layers.39.self_attn.k_proj.bias": "pytorch_model-00007-of-00007.bin",
545
+ "model.layers.39.self_attn.k_proj.weight": "pytorch_model-00007-of-00007.bin",
546
+ "model.layers.39.self_attn.o_proj.bias": "pytorch_model-00007-of-00007.bin",
547
+ "model.layers.39.self_attn.o_proj.weight": "pytorch_model-00007-of-00007.bin",
548
+ "model.layers.39.self_attn.q_proj.bias": "pytorch_model-00007-of-00007.bin",
549
+ "model.layers.39.self_attn.q_proj.weight": "pytorch_model-00007-of-00007.bin",
550
+ "model.layers.39.self_attn.v_proj.bias": "pytorch_model-00007-of-00007.bin",
551
+ "model.layers.39.self_attn.v_proj.weight": "pytorch_model-00007-of-00007.bin",
552
+ "model.layers.4.input_layernorm.bias": "pytorch_model-00001-of-00007.bin",
553
+ "model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00007.bin",
554
+ "model.layers.4.mlp.c_fc.bias": "pytorch_model-00001-of-00007.bin",
555
+ "model.layers.4.mlp.c_fc.weight": "pytorch_model-00001-of-00007.bin",
556
+ "model.layers.4.mlp.c_proj.bias": "pytorch_model-00001-of-00007.bin",
557
+ "model.layers.4.mlp.c_proj.weight": "pytorch_model-00001-of-00007.bin",
558
+ "model.layers.4.post_attention_layernorm.bias": "pytorch_model-00001-of-00007.bin",
559
+ "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00007.bin",
560
+ "model.layers.4.self_attn.k_proj.bias": "pytorch_model-00001-of-00007.bin",
561
+ "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00007.bin",
562
+ "model.layers.4.self_attn.o_proj.bias": "pytorch_model-00001-of-00007.bin",
563
+ "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00007.bin",
564
+ "model.layers.4.self_attn.q_proj.bias": "pytorch_model-00001-of-00007.bin",
565
+ "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00007.bin",
566
+ "model.layers.4.self_attn.v_proj.bias": "pytorch_model-00001-of-00007.bin",
567
+ "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00007.bin",
568
+ "model.layers.5.input_layernorm.bias": "pytorch_model-00002-of-00007.bin",
569
+ "model.layers.5.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
570
+ "model.layers.5.mlp.c_fc.bias": "pytorch_model-00001-of-00007.bin",
571
+ "model.layers.5.mlp.c_fc.weight": "pytorch_model-00001-of-00007.bin",
572
+ "model.layers.5.mlp.c_proj.bias": "pytorch_model-00002-of-00007.bin",
573
+ "model.layers.5.mlp.c_proj.weight": "pytorch_model-00002-of-00007.bin",
574
+ "model.layers.5.post_attention_layernorm.bias": "pytorch_model-00002-of-00007.bin",
575
+ "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin",
576
+ "model.layers.5.self_attn.k_proj.bias": "pytorch_model-00001-of-00007.bin",
577
+ "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00007.bin",
578
+ "model.layers.5.self_attn.o_proj.bias": "pytorch_model-00001-of-00007.bin",
579
+ "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00007.bin",
580
+ "model.layers.5.self_attn.q_proj.bias": "pytorch_model-00001-of-00007.bin",
581
+ "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00007.bin",
582
+ "model.layers.5.self_attn.v_proj.bias": "pytorch_model-00001-of-00007.bin",
583
+ "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00007.bin",
584
+ "model.layers.6.input_layernorm.bias": "pytorch_model-00002-of-00007.bin",
585
+ "model.layers.6.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
586
+ "model.layers.6.mlp.c_fc.bias": "pytorch_model-00002-of-00007.bin",
587
+ "model.layers.6.mlp.c_fc.weight": "pytorch_model-00002-of-00007.bin",
588
+ "model.layers.6.mlp.c_proj.bias": "pytorch_model-00002-of-00007.bin",
589
+ "model.layers.6.mlp.c_proj.weight": "pytorch_model-00002-of-00007.bin",
590
+ "model.layers.6.post_attention_layernorm.bias": "pytorch_model-00002-of-00007.bin",
591
+ "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin",
592
+ "model.layers.6.self_attn.k_proj.bias": "pytorch_model-00002-of-00007.bin",
593
+ "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00002-of-00007.bin",
594
+ "model.layers.6.self_attn.o_proj.bias": "pytorch_model-00002-of-00007.bin",
595
+ "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00002-of-00007.bin",
596
+ "model.layers.6.self_attn.q_proj.bias": "pytorch_model-00002-of-00007.bin",
597
+ "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00002-of-00007.bin",
598
+ "model.layers.6.self_attn.v_proj.bias": "pytorch_model-00002-of-00007.bin",
599
+ "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00002-of-00007.bin",
600
+ "model.layers.7.input_layernorm.bias": "pytorch_model-00002-of-00007.bin",
601
+ "model.layers.7.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
602
+ "model.layers.7.mlp.c_fc.bias": "pytorch_model-00002-of-00007.bin",
603
+ "model.layers.7.mlp.c_fc.weight": "pytorch_model-00002-of-00007.bin",
604
+ "model.layers.7.mlp.c_proj.bias": "pytorch_model-00002-of-00007.bin",
605
+ "model.layers.7.mlp.c_proj.weight": "pytorch_model-00002-of-00007.bin",
606
+ "model.layers.7.post_attention_layernorm.bias": "pytorch_model-00002-of-00007.bin",
607
+ "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin",
608
+ "model.layers.7.self_attn.k_proj.bias": "pytorch_model-00002-of-00007.bin",
609
+ "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00002-of-00007.bin",
610
+ "model.layers.7.self_attn.o_proj.bias": "pytorch_model-00002-of-00007.bin",
611
+ "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00002-of-00007.bin",
612
+ "model.layers.7.self_attn.q_proj.bias": "pytorch_model-00002-of-00007.bin",
613
+ "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00002-of-00007.bin",
614
+ "model.layers.7.self_attn.v_proj.bias": "pytorch_model-00002-of-00007.bin",
615
+ "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00002-of-00007.bin",
616
+ "model.layers.8.input_layernorm.bias": "pytorch_model-00002-of-00007.bin",
617
+ "model.layers.8.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
618
+ "model.layers.8.mlp.c_fc.bias": "pytorch_model-00002-of-00007.bin",
619
+ "model.layers.8.mlp.c_fc.weight": "pytorch_model-00002-of-00007.bin",
620
+ "model.layers.8.mlp.c_proj.bias": "pytorch_model-00002-of-00007.bin",
621
+ "model.layers.8.mlp.c_proj.weight": "pytorch_model-00002-of-00007.bin",
622
+ "model.layers.8.post_attention_layernorm.bias": "pytorch_model-00002-of-00007.bin",
623
+ "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin",
624
+ "model.layers.8.self_attn.k_proj.bias": "pytorch_model-00002-of-00007.bin",
625
+ "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00002-of-00007.bin",
626
+ "model.layers.8.self_attn.o_proj.bias": "pytorch_model-00002-of-00007.bin",
627
+ "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00002-of-00007.bin",
628
+ "model.layers.8.self_attn.q_proj.bias": "pytorch_model-00002-of-00007.bin",
629
+ "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00002-of-00007.bin",
630
+ "model.layers.8.self_attn.v_proj.bias": "pytorch_model-00002-of-00007.bin",
631
+ "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00002-of-00007.bin",
632
+ "model.layers.9.input_layernorm.bias": "pytorch_model-00002-of-00007.bin",
633
+ "model.layers.9.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
634
+ "model.layers.9.mlp.c_fc.bias": "pytorch_model-00002-of-00007.bin",
635
+ "model.layers.9.mlp.c_fc.weight": "pytorch_model-00002-of-00007.bin",
636
+ "model.layers.9.mlp.c_proj.bias": "pytorch_model-00002-of-00007.bin",
637
+ "model.layers.9.mlp.c_proj.weight": "pytorch_model-00002-of-00007.bin",
638
+ "model.layers.9.post_attention_layernorm.bias": "pytorch_model-00002-of-00007.bin",
639
+ "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin",
640
+ "model.layers.9.self_attn.k_proj.bias": "pytorch_model-00002-of-00007.bin",
641
+ "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00002-of-00007.bin",
642
+ "model.layers.9.self_attn.o_proj.bias": "pytorch_model-00002-of-00007.bin",
643
+ "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00002-of-00007.bin",
644
+ "model.layers.9.self_attn.q_proj.bias": "pytorch_model-00002-of-00007.bin",
645
+ "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00002-of-00007.bin",
646
+ "model.layers.9.self_attn.v_proj.bias": "pytorch_model-00002-of-00007.bin",
647
+ "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00002-of-00007.bin",
648
+ "model.norm.bias": "pytorch_model-00007-of-00007.bin",
649
+ "model.norm.weight": "pytorch_model-00007-of-00007.bin"
650
+ }
651
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,70 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|endoftext|>",
4
+ "<fim_prefix>",
5
+ "<fim_middle>",
6
+ "<fim_suffix>",
7
+ "<fim_pad>",
8
+ "<repo_name>",
9
+ "<file_sep>",
10
+ "<issue_start>",
11
+ "<issue_comment>",
12
+ "<issue_closed>",
13
+ "<jupyter_start>",
14
+ "<jupyter_text>",
15
+ "<jupyter_code>",
16
+ "<jupyter_output>",
17
+ "<jupyter_script>",
18
+ "<empty_output>",
19
+ "<code_to_intermediate>",
20
+ "<intermediate_to_code>",
21
+ "<pr>",
22
+ "<pr_status>",
23
+ "<pr_is_merged>",
24
+ "<pr_base>",
25
+ "<pr_file>",
26
+ "<pr_base_code>",
27
+ "<pr_diff>",
28
+ "<pr_diff_hunk>",
29
+ "<pr_comment>",
30
+ "<pr_event_id>",
31
+ "<pr_review>",
32
+ "<pr_review_state>",
33
+ "<pr_review_comment>",
34
+ "<pr_in_reply_to_review_id>",
35
+ "<pr_in_reply_to_comment_id>",
36
+ "<pr_diff_hunk_comment_line>",
37
+ "<NAME>",
38
+ "<EMAIL>",
39
+ "<KEY>",
40
+ "<PASSWORD>"
41
+ ],
42
+ "bos_token": {
43
+ "content": "<|endoftext|>",
44
+ "lstrip": false,
45
+ "normalized": false,
46
+ "rstrip": false,
47
+ "single_word": false
48
+ },
49
+ "eos_token": {
50
+ "content": "<|im_end|>",
51
+ "lstrip": false,
52
+ "normalized": false,
53
+ "rstrip": false,
54
+ "single_word": false
55
+ },
56
+ "pad_token": {
57
+ "content": "<|endoftext|>",
58
+ "lstrip": false,
59
+ "normalized": false,
60
+ "rstrip": false,
61
+ "single_word": false
62
+ },
63
+ "unk_token": {
64
+ "content": "<|endoftext|>",
65
+ "lstrip": false,
66
+ "normalized": false,
67
+ "rstrip": false,
68
+ "single_word": false
69
+ }
70
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,374 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "<fim_prefix>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "<fim_middle>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": "<fim_suffix>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "4": {
37
+ "content": "<fim_pad>",
38
+ "lstrip": false,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "5": {
45
+ "content": "<repo_name>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": true
51
+ },
52
+ "6": {
53
+ "content": "<file_sep>",
54
+ "lstrip": false,
55
+ "normalized": false,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": true
59
+ },
60
+ "7": {
61
+ "content": "<issue_start>",
62
+ "lstrip": false,
63
+ "normalized": false,
64
+ "rstrip": false,
65
+ "single_word": false,
66
+ "special": true
67
+ },
68
+ "8": {
69
+ "content": "<issue_comment>",
70
+ "lstrip": false,
71
+ "normalized": false,
72
+ "rstrip": false,
73
+ "single_word": false,
74
+ "special": true
75
+ },
76
+ "9": {
77
+ "content": "<issue_closed>",
78
+ "lstrip": false,
79
+ "normalized": false,
80
+ "rstrip": false,
81
+ "single_word": false,
82
+ "special": true
83
+ },
84
+ "10": {
85
+ "content": "<jupyter_start>",
86
+ "lstrip": false,
87
+ "normalized": false,
88
+ "rstrip": false,
89
+ "single_word": false,
90
+ "special": true
91
+ },
92
+ "11": {
93
+ "content": "<jupyter_text>",
94
+ "lstrip": false,
95
+ "normalized": false,
96
+ "rstrip": false,
97
+ "single_word": false,
98
+ "special": true
99
+ },
100
+ "12": {
101
+ "content": "<jupyter_code>",
102
+ "lstrip": false,
103
+ "normalized": false,
104
+ "rstrip": false,
105
+ "single_word": false,
106
+ "special": true
107
+ },
108
+ "13": {
109
+ "content": "<jupyter_output>",
110
+ "lstrip": false,
111
+ "normalized": false,
112
+ "rstrip": false,
113
+ "single_word": false,
114
+ "special": true
115
+ },
116
+ "14": {
117
+ "content": "<jupyter_script>",
118
+ "lstrip": false,
119
+ "normalized": false,
120
+ "rstrip": false,
121
+ "single_word": false,
122
+ "special": true
123
+ },
124
+ "15": {
125
+ "content": "<empty_output>",
126
+ "lstrip": false,
127
+ "normalized": false,
128
+ "rstrip": false,
129
+ "single_word": false,
130
+ "special": true
131
+ },
132
+ "16": {
133
+ "content": "<code_to_intermediate>",
134
+ "lstrip": false,
135
+ "normalized": false,
136
+ "rstrip": false,
137
+ "single_word": false,
138
+ "special": true
139
+ },
140
+ "17": {
141
+ "content": "<intermediate_to_code>",
142
+ "lstrip": false,
143
+ "normalized": false,
144
+ "rstrip": false,
145
+ "single_word": false,
146
+ "special": true
147
+ },
148
+ "18": {
149
+ "content": "<pr>",
150
+ "lstrip": false,
151
+ "normalized": false,
152
+ "rstrip": false,
153
+ "single_word": false,
154
+ "special": true
155
+ },
156
+ "19": {
157
+ "content": "<pr_status>",
158
+ "lstrip": false,
159
+ "normalized": false,
160
+ "rstrip": false,
161
+ "single_word": false,
162
+ "special": true
163
+ },
164
+ "20": {
165
+ "content": "<pr_is_merged>",
166
+ "lstrip": false,
167
+ "normalized": false,
168
+ "rstrip": false,
169
+ "single_word": false,
170
+ "special": true
171
+ },
172
+ "21": {
173
+ "content": "<pr_base>",
174
+ "lstrip": false,
175
+ "normalized": false,
176
+ "rstrip": false,
177
+ "single_word": false,
178
+ "special": true
179
+ },
180
+ "22": {
181
+ "content": "<pr_file>",
182
+ "lstrip": false,
183
+ "normalized": false,
184
+ "rstrip": false,
185
+ "single_word": false,
186
+ "special": true
187
+ },
188
+ "23": {
189
+ "content": "<pr_base_code>",
190
+ "lstrip": false,
191
+ "normalized": false,
192
+ "rstrip": false,
193
+ "single_word": false,
194
+ "special": true
195
+ },
196
+ "24": {
197
+ "content": "<pr_diff>",
198
+ "lstrip": false,
199
+ "normalized": false,
200
+ "rstrip": false,
201
+ "single_word": false,
202
+ "special": true
203
+ },
204
+ "25": {
205
+ "content": "<pr_diff_hunk>",
206
+ "lstrip": false,
207
+ "normalized": false,
208
+ "rstrip": false,
209
+ "single_word": false,
210
+ "special": true
211
+ },
212
+ "26": {
213
+ "content": "<pr_comment>",
214
+ "lstrip": false,
215
+ "normalized": false,
216
+ "rstrip": false,
217
+ "single_word": false,
218
+ "special": true
219
+ },
220
+ "27": {
221
+ "content": "<pr_event_id>",
222
+ "lstrip": false,
223
+ "normalized": false,
224
+ "rstrip": false,
225
+ "single_word": false,
226
+ "special": true
227
+ },
228
+ "28": {
229
+ "content": "<pr_review>",
230
+ "lstrip": false,
231
+ "normalized": false,
232
+ "rstrip": false,
233
+ "single_word": false,
234
+ "special": true
235
+ },
236
+ "29": {
237
+ "content": "<pr_review_state>",
238
+ "lstrip": false,
239
+ "normalized": false,
240
+ "rstrip": false,
241
+ "single_word": false,
242
+ "special": true
243
+ },
244
+ "30": {
245
+ "content": "<pr_review_comment>",
246
+ "lstrip": false,
247
+ "normalized": false,
248
+ "rstrip": false,
249
+ "single_word": false,
250
+ "special": true
251
+ },
252
+ "31": {
253
+ "content": "<pr_in_reply_to_review_id>",
254
+ "lstrip": false,
255
+ "normalized": false,
256
+ "rstrip": false,
257
+ "single_word": false,
258
+ "special": true
259
+ },
260
+ "32": {
261
+ "content": "<pr_in_reply_to_comment_id>",
262
+ "lstrip": false,
263
+ "normalized": false,
264
+ "rstrip": false,
265
+ "single_word": false,
266
+ "special": true
267
+ },
268
+ "33": {
269
+ "content": "<pr_diff_hunk_comment_line>",
270
+ "lstrip": false,
271
+ "normalized": false,
272
+ "rstrip": false,
273
+ "single_word": false,
274
+ "special": true
275
+ },
276
+ "34": {
277
+ "content": "<NAME>",
278
+ "lstrip": false,
279
+ "normalized": false,
280
+ "rstrip": false,
281
+ "single_word": false,
282
+ "special": true
283
+ },
284
+ "35": {
285
+ "content": "<EMAIL>",
286
+ "lstrip": false,
287
+ "normalized": false,
288
+ "rstrip": false,
289
+ "single_word": false,
290
+ "special": true
291
+ },
292
+ "36": {
293
+ "content": "<KEY>",
294
+ "lstrip": false,
295
+ "normalized": false,
296
+ "rstrip": false,
297
+ "single_word": false,
298
+ "special": true
299
+ },
300
+ "37": {
301
+ "content": "<PASSWORD>",
302
+ "lstrip": false,
303
+ "normalized": false,
304
+ "rstrip": false,
305
+ "single_word": false,
306
+ "special": true
307
+ },
308
+ "49152": {
309
+ "content": "<|im_end|>",
310
+ "lstrip": false,
311
+ "normalized": false,
312
+ "rstrip": false,
313
+ "single_word": false,
314
+ "special": false
315
+ },
316
+ "49153": {
317
+ "content": "<|im_start|>",
318
+ "lstrip": false,
319
+ "normalized": false,
320
+ "rstrip": false,
321
+ "single_word": false,
322
+ "special": false
323
+ }
324
+ },
325
+ "additional_special_tokens": [
326
+ "<|endoftext|>",
327
+ "<fim_prefix>",
328
+ "<fim_middle>",
329
+ "<fim_suffix>",
330
+ "<fim_pad>",
331
+ "<repo_name>",
332
+ "<file_sep>",
333
+ "<issue_start>",
334
+ "<issue_comment>",
335
+ "<issue_closed>",
336
+ "<jupyter_start>",
337
+ "<jupyter_text>",
338
+ "<jupyter_code>",
339
+ "<jupyter_output>",
340
+ "<jupyter_script>",
341
+ "<empty_output>",
342
+ "<code_to_intermediate>",
343
+ "<intermediate_to_code>",
344
+ "<pr>",
345
+ "<pr_status>",
346
+ "<pr_is_merged>",
347
+ "<pr_base>",
348
+ "<pr_file>",
349
+ "<pr_base_code>",
350
+ "<pr_diff>",
351
+ "<pr_diff_hunk>",
352
+ "<pr_comment>",
353
+ "<pr_event_id>",
354
+ "<pr_review>",
355
+ "<pr_review_state>",
356
+ "<pr_review_comment>",
357
+ "<pr_in_reply_to_review_id>",
358
+ "<pr_in_reply_to_comment_id>",
359
+ "<pr_diff_hunk_comment_line>",
360
+ "<NAME>",
361
+ "<EMAIL>",
362
+ "<KEY>",
363
+ "<PASSWORD>"
364
+ ],
365
+ "bos_token": "<|endoftext|>",
366
+ "chat_template": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% set system_message = 'You are a helpful assistant.' %}{% endif %}{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in loop_messages %}{% if loop.index0 == 0 %}{{'<|im_start|>system\n' + system_message + '<|im_end|>\n'}}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
367
+ "clean_up_tokenization_spaces": true,
368
+ "eos_token": "<|im_end|>",
369
+ "model_max_length": 1000000000000000019884624838656,
370
+ "pad_token": "<|endoftext|>",
371
+ "tokenizer_class": "GPT2Tokenizer",
372
+ "unk_token": "<|endoftext|>",
373
+ "vocab_size": 49152
374
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff