Hugging Face's logo

doas
/
test5

Feature Extraction
Transformers
PyTorch
llama
text-generation-inference
Inference Endpoints
Model card Files Community
2
doas commited on
Commit
7314045
•
1 Parent(s): aaa13d5

Upload model

Browse files
Files changed (8) hide show
  1. config.json +26 -0
  2. pytorch_model-00001-of-00006.bin +3 -0
  3. pytorch_model-00002-of-00006.bin +3 -0
  4. pytorch_model-00003-of-00006.bin +3 -0
  5. pytorch_model-00004-of-00006.bin +3 -0
  6. pytorch_model-00005-of-00006.bin +3 -0
  7. pytorch_model-00006-of-00006.bin +3 -0
  8. pytorch_model.bin.index.json +409 -0
config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "./output/Llama-2-13b-chat-hf/truthfulqa_gpt4_2023_08_14_11:45:59/checkpoint-9",
3
+ "architectures": [
4
+ "LlamaModel"
5
+ ],
6
+ "bos_token_id": 1,
7
+ "eos_token_id": 2,
8
+ "hidden_act": "silu",
9
+ "hidden_size": 5120,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 13824,
12
+ "max_position_embeddings": 4096,
13
+ "model_type": "llama",
14
+ "num_attention_heads": 40,
15
+ "num_hidden_layers": 40,
16
+ "num_key_value_heads": 40,
17
+ "pad_token_id": 0,
18
+ "pretraining_tp": 1,
19
+ "rms_norm_eps": 1e-05,
20
+ "rope_scaling": null,
21
+ "tie_word_embeddings": false,
22
+ "torch_dtype": "float32",
23
+ "transformers_version": "4.31.0",
24
+ "use_cache": false,
25
+ "vocab_size": 32001
26
+ }
pytorch_model-00001-of-00006.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c0026669a9ec86014be5fd7a6a8444e3acaeaf9c313449cf40c54afe7540c016
3
+ size 9956563915
pytorch_model-00002-of-00006.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:50f71f1be95124263f407f084f99a08e6b7a9084de8e29e59cb42744f1ae6180
3
+ size 9940855873
pytorch_model-00003-of-00006.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:30e8d8b7e5452f0b9b5e3f1c15719db3b2ec5ba7321d0bf8b9fa3dd406bfa5bc
3
+ size 9940856495
pytorch_model-00004-of-00006.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1ee03783905740c281a5a25f54598ed3333e9aaf0ebccdc4ed48fac301ba28d9
3
+ size 9867414841
pytorch_model-00005-of-00006.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff9fa1daab2cbeda2d1ab5abc9d3bc58d965970e7c0883d31989ac65d4e3d095
3
+ size 9867456513
pytorch_model-00006-of-00006.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5ca5a60322ee47fea6894d279ba10f263d5676d9d92075681667a6fb47e13094
3
+ size 1835115869
pytorch_model.bin.index.json ADDED
@@ -0,0 +1,409 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 51408128000
4
+ },
5
+ "weight_map": {
6
+ "embed_tokens.weight": "pytorch_model-00001-of-00006.bin",
7
+ "layers.0.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
8
+ "layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin",
9
+ "layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin",
10
+ "layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin",
11
+ "layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
12
+ "layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
13
+ "layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
14
+ "layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
15
+ "layers.0.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00006.bin",
16
+ "layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
17
+ "layers.1.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
18
+ "layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin",
19
+ "layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin",
20
+ "layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin",
21
+ "layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
22
+ "layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
23
+ "layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
24
+ "layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
25
+ "layers.1.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00006.bin",
26
+ "layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
27
+ "layers.10.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
28
+ "layers.10.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
29
+ "layers.10.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
30
+ "layers.10.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
31
+ "layers.10.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
32
+ "layers.10.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
33
+ "layers.10.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
34
+ "layers.10.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
35
+ "layers.10.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00006.bin",
36
+ "layers.10.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
37
+ "layers.11.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
38
+ "layers.11.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
39
+ "layers.11.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
40
+ "layers.11.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
41
+ "layers.11.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
42
+ "layers.11.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
43
+ "layers.11.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
44
+ "layers.11.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
45
+ "layers.11.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00006.bin",
46
+ "layers.11.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
47
+ "layers.12.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
48
+ "layers.12.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
49
+ "layers.12.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
50
+ "layers.12.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
51
+ "layers.12.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
52
+ "layers.12.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
53
+ "layers.12.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
54
+ "layers.12.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
55
+ "layers.12.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00006.bin",
56
+ "layers.12.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
57
+ "layers.13.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
58
+ "layers.13.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
59
+ "layers.13.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
60
+ "layers.13.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
61
+ "layers.13.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
62
+ "layers.13.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
63
+ "layers.13.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
64
+ "layers.13.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
65
+ "layers.13.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00006.bin",
66
+ "layers.13.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
67
+ "layers.14.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
68
+ "layers.14.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
69
+ "layers.14.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
70
+ "layers.14.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
71
+ "layers.14.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
72
+ "layers.14.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
73
+ "layers.14.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
74
+ "layers.14.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
75
+ "layers.14.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00006.bin",
76
+ "layers.14.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
77
+ "layers.15.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
78
+ "layers.15.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
79
+ "layers.15.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
80
+ "layers.15.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
81
+ "layers.15.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
82
+ "layers.15.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
83
+ "layers.15.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
84
+ "layers.15.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
85
+ "layers.15.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00006.bin",
86
+ "layers.15.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
87
+ "layers.16.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
88
+ "layers.16.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
89
+ "layers.16.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
90
+ "layers.16.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
91
+ "layers.16.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
92
+ "layers.16.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
93
+ "layers.16.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
94
+ "layers.16.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
95
+ "layers.16.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00006.bin",
96
+ "layers.16.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
97
+ "layers.17.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
98
+ "layers.17.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
99
+ "layers.17.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
100
+ "layers.17.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
101
+ "layers.17.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
102
+ "layers.17.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
103
+ "layers.17.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
104
+ "layers.17.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
105
+ "layers.17.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00006.bin",
106
+ "layers.17.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
107
+ "layers.18.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
108
+ "layers.18.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
109
+ "layers.18.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
110
+ "layers.18.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
111
+ "layers.18.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
112
+ "layers.18.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
113
+ "layers.18.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
114
+ "layers.18.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
115
+ "layers.18.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00006.bin",
116
+ "layers.18.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
117
+ "layers.19.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
118
+ "layers.19.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
119
+ "layers.19.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
120
+ "layers.19.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
121
+ "layers.19.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
122
+ "layers.19.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
123
+ "layers.19.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
124
+ "layers.19.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
125
+ "layers.19.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00006.bin",
126
+ "layers.19.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
127
+ "layers.2.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
128
+ "layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin",
129
+ "layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin",
130
+ "layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin",
131
+ "layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
132
+ "layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
133
+ "layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
134
+ "layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
135
+ "layers.2.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00006.bin",
136
+ "layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
137
+ "layers.20.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
138
+ "layers.20.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
139
+ "layers.20.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
140
+ "layers.20.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
141
+ "layers.20.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
142
+ "layers.20.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
143
+ "layers.20.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
144
+ "layers.20.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
145
+ "layers.20.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00006.bin",
146
+ "layers.20.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
147
+ "layers.21.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
148
+ "layers.21.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
149
+ "layers.21.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
150
+ "layers.21.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
151
+ "layers.21.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
152
+ "layers.21.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
153
+ "layers.21.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
154
+ "layers.21.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
155
+ "layers.21.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00006.bin",
156
+ "layers.21.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
157
+ "layers.22.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
158
+ "layers.22.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
159
+ "layers.22.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
160
+ "layers.22.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
161
+ "layers.22.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
162
+ "layers.22.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
163
+ "layers.22.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
164
+ "layers.22.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
165
+ "layers.22.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00006.bin",
166
+ "layers.22.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
167
+ "layers.23.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
168
+ "layers.23.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
169
+ "layers.23.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
170
+ "layers.23.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
171
+ "layers.23.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
172
+ "layers.23.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
173
+ "layers.23.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
174
+ "layers.23.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
175
+ "layers.23.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00006.bin",
176
+ "layers.23.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
177
+ "layers.24.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
178
+ "layers.24.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
179
+ "layers.24.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
180
+ "layers.24.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
181
+ "layers.24.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
182
+ "layers.24.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
183
+ "layers.24.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
184
+ "layers.24.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
185
+ "layers.24.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00006.bin",
186
+ "layers.24.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
187
+ "layers.25.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
188
+ "layers.25.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
189
+ "layers.25.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
190
+ "layers.25.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
191
+ "layers.25.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
192
+ "layers.25.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
193
+ "layers.25.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
194
+ "layers.25.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
195
+ "layers.25.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00006.bin",
196
+ "layers.25.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
197
+ "layers.26.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
198
+ "layers.26.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
199
+ "layers.26.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
200
+ "layers.26.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
201
+ "layers.26.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
202
+ "layers.26.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
203
+ "layers.26.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
204
+ "layers.26.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
205
+ "layers.26.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00006.bin",
206
+ "layers.26.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
207
+ "layers.27.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
208
+ "layers.27.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
209
+ "layers.27.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
210
+ "layers.27.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
211
+ "layers.27.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
212
+ "layers.27.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
213
+ "layers.27.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
214
+ "layers.27.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
215
+ "layers.27.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00006.bin",
216
+ "layers.27.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
217
+ "layers.28.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
218
+ "layers.28.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
219
+ "layers.28.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
220
+ "layers.28.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
221
+ "layers.28.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
222
+ "layers.28.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
223
+ "layers.28.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
224
+ "layers.28.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
225
+ "layers.28.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00006.bin",
226
+ "layers.28.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
227
+ "layers.29.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
228
+ "layers.29.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
229
+ "layers.29.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
230
+ "layers.29.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
231
+ "layers.29.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
232
+ "layers.29.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
233
+ "layers.29.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
234
+ "layers.29.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
235
+ "layers.29.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00006.bin",
236
+ "layers.29.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
237
+ "layers.3.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
238
+ "layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin",
239
+ "layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin",
240
+ "layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin",
241
+ "layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
242
+ "layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
243
+ "layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
244
+ "layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
245
+ "layers.3.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00006.bin",
246
+ "layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
247
+ "layers.30.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
248
+ "layers.30.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
249
+ "layers.30.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
250
+ "layers.30.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
251
+ "layers.30.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
252
+ "layers.30.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
253
+ "layers.30.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
254
+ "layers.30.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
255
+ "layers.30.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00006.bin",
256
+ "layers.30.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
257
+ "layers.31.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
258
+ "layers.31.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
259
+ "layers.31.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
260
+ "layers.31.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
261
+ "layers.31.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
262
+ "layers.31.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
263
+ "layers.31.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
264
+ "layers.31.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
265
+ "layers.31.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00006.bin",
266
+ "layers.31.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
267
+ "layers.32.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
268
+ "layers.32.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
269
+ "layers.32.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
270
+ "layers.32.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
271
+ "layers.32.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
272
+ "layers.32.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
273
+ "layers.32.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
274
+ "layers.32.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
275
+ "layers.32.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00006.bin",
276
+ "layers.32.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
277
+ "layers.33.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
278
+ "layers.33.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
279
+ "layers.33.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
280
+ "layers.33.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
281
+ "layers.33.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
282
+ "layers.33.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
283
+ "layers.33.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
284
+ "layers.33.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
285
+ "layers.33.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00006.bin",
286
+ "layers.33.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
287
+ "layers.34.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
288
+ "layers.34.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
289
+ "layers.34.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
290
+ "layers.34.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
291
+ "layers.34.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
292
+ "layers.34.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
293
+ "layers.34.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
294
+ "layers.34.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
295
+ "layers.34.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00006.bin",
296
+ "layers.34.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
297
+ "layers.35.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
298
+ "layers.35.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
299
+ "layers.35.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
300
+ "layers.35.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
301
+ "layers.35.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
302
+ "layers.35.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
303
+ "layers.35.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
304
+ "layers.35.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
305
+ "layers.35.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00006.bin",
306
+ "layers.35.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
307
+ "layers.36.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
308
+ "layers.36.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
309
+ "layers.36.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
310
+ "layers.36.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
311
+ "layers.36.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
312
+ "layers.36.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
313
+ "layers.36.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
314
+ "layers.36.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
315
+ "layers.36.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00006.bin",
316
+ "layers.36.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
317
+ "layers.37.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
318
+ "layers.37.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
319
+ "layers.37.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
320
+ "layers.37.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
321
+ "layers.37.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
322
+ "layers.37.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
323
+ "layers.37.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
324
+ "layers.37.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
325
+ "layers.37.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00006.bin",
326
+ "layers.37.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
327
+ "layers.38.input_layernorm.weight": "pytorch_model-00006-of-00006.bin",
328
+ "layers.38.mlp.down_proj.weight": "pytorch_model-00006-of-00006.bin",
329
+ "layers.38.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
330
+ "layers.38.mlp.up_proj.weight": "pytorch_model-00006-of-00006.bin",
331
+ "layers.38.post_attention_layernorm.weight": "pytorch_model-00006-of-00006.bin",
332
+ "layers.38.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
333
+ "layers.38.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
334
+ "layers.38.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
335
+ "layers.38.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00006.bin",
336
+ "layers.38.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
337
+ "layers.39.input_layernorm.weight": "pytorch_model-00006-of-00006.bin",
338
+ "layers.39.mlp.down_proj.weight": "pytorch_model-00006-of-00006.bin",
339
+ "layers.39.mlp.gate_proj.weight": "pytorch_model-00006-of-00006.bin",
340
+ "layers.39.mlp.up_proj.weight": "pytorch_model-00006-of-00006.bin",
341
+ "layers.39.post_attention_layernorm.weight": "pytorch_model-00006-of-00006.bin",
342
+ "layers.39.self_attn.k_proj.weight": "pytorch_model-00006-of-00006.bin",
343
+ "layers.39.self_attn.o_proj.weight": "pytorch_model-00006-of-00006.bin",
344
+ "layers.39.self_attn.q_proj.weight": "pytorch_model-00006-of-00006.bin",
345
+ "layers.39.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00006.bin",
346
+ "layers.39.self_attn.v_proj.weight": "pytorch_model-00006-of-00006.bin",
347
+ "layers.4.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
348
+ "layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin",
349
+ "layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin",
350
+ "layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin",
351
+ "layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
352
+ "layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
353
+ "layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
354
+ "layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
355
+ "layers.4.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00006.bin",
356
+ "layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
357
+ "layers.5.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
358
+ "layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin",
359
+ "layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin",
360
+ "layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin",
361
+ "layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
362
+ "layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
363
+ "layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
364
+ "layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
365
+ "layers.5.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00006.bin",
366
+ "layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
367
+ "layers.6.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
368
+ "layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin",
369
+ "layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin",
370
+ "layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin",
371
+ "layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
372
+ "layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
373
+ "layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
374
+ "layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
375
+ "layers.6.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00006.bin",
376
+ "layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
377
+ "layers.7.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
378
+ "layers.7.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
379
+ "layers.7.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
380
+ "layers.7.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
381
+ "layers.7.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
382
+ "layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
383
+ "layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
384
+ "layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
385
+ "layers.7.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00006.bin",
386
+ "layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
387
+ "layers.8.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
388
+ "layers.8.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
389
+ "layers.8.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
390
+ "layers.8.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
391
+ "layers.8.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
392
+ "layers.8.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
393
+ "layers.8.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
394
+ "layers.8.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
395
+ "layers.8.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00006.bin",
396
+ "layers.8.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
397
+ "layers.9.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
398
+ "layers.9.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
399
+ "layers.9.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
400
+ "layers.9.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
401
+ "layers.9.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
402
+ "layers.9.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
403
+ "layers.9.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
404
+ "layers.9.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
405
+ "layers.9.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00006.bin",
406
+ "layers.9.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
407
+ "norm.weight": "pytorch_model-00006-of-00006.bin"
408
+ }
409
+ }