yanismiraoui commited on
Commit
4409437
1 Parent(s): f752801

Upload folder using huggingface_hub

Browse files
config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "01-ai/Yi-6B",
3
+ "architectures": [
4
+ "YiForCausalLM"
5
+ ],
6
+ "auto_map": {
7
+ "AutoConfig": "01-ai/Yi-6B--configuration_yi.YiConfig",
8
+ "AutoModel": "01-ai/Yi-6B--modeling_yi.YiModel",
9
+ "AutoModelForCausalLM": "01-ai/Yi-6B--modeling_yi.YiForCausalLM"
10
+ },
11
+ "bos_token_id": 1,
12
+ "eos_token_id": 2,
13
+ "hidden_act": "silu",
14
+ "hidden_size": 4096,
15
+ "initializer_range": 0.02,
16
+ "intermediate_size": 11008,
17
+ "max_position_embeddings": 4096,
18
+ "model_type": "Yi",
19
+ "num_attention_heads": 32,
20
+ "num_hidden_layers": 32,
21
+ "num_key_value_heads": 4,
22
+ "pad_token_id": 0,
23
+ "rms_norm_eps": 1e-05,
24
+ "rope_theta": 5000000.0,
25
+ "tie_word_embeddings": false,
26
+ "torch_dtype": "float32",
27
+ "transformers_version": "4.36.0.dev0",
28
+ "use_cache": true,
29
+ "vocab_size": 64000
30
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "pad_token_id": 0,
6
+ "transformers_version": "4.36.0.dev0"
7
+ }
model-00001-of-00009.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:668333064e45d0ae762655f08a6ab0a50457d3bedb00a11f7017a48a5ea7842a
3
+ size 2944469768
model-00002-of-00009.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:60a9145985b7ea7dc955971208f1ddb35bb4ad06cae2069e05e16ef0be16acc7
3
+ size 2948763840
model-00003-of-00009.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:94715d0bd7430ce945e3270b9e1cdf28d93115544d7f368e73229101a5fda459
3
+ size 2919371112
model-00004-of-00009.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:59c3107132c31d6c4a19fd32a43a70a2494474a2256f831c457ec21839d83289
3
+ size 2948730928
model-00005-of-00009.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8da11d523b46b6fad7a50e02bb4d4148036326414ad06292f505b5924d753774
3
+ size 2948730920
model-00006-of-00009.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b37b5998f2a1a93c301421622f25439ec6867dac9ffa01261922cc689d9a9823
3
+ size 2948763880
model-00007-of-00009.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c76748f09f0b8ed9bb08c59487ff2aa96226f5a12916ee054f27efb7b620dc98
3
+ size 2919371144
model-00008-of-00009.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a6fb797235fce5bcfd0fab9b5fb67d5a229fbbfe0a51e93dcdeecc8ea9663800
3
+ size 2617396808
model-00009-of-00009.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aeb7eee65b53c874c1f0f271594009b527d0293aaf11f3651c4a2c0ee3a3d297
3
+ size 1048576128
model.safetensors.index.json ADDED
@@ -0,0 +1,298 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 24244142080
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "model-00009-of-00009.safetensors",
7
+ "model.embed_tokens.weight": "model-00001-of-00009.safetensors",
8
+ "model.layers.0.ln1.weight": "model-00001-of-00009.safetensors",
9
+ "model.layers.0.ln2.weight": "model-00001-of-00009.safetensors",
10
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00009.safetensors",
11
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00009.safetensors",
12
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00009.safetensors",
13
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00009.safetensors",
14
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00009.safetensors",
15
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00009.safetensors",
16
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00009.safetensors",
17
+ "model.layers.1.ln1.weight": "model-00001-of-00009.safetensors",
18
+ "model.layers.1.ln2.weight": "model-00001-of-00009.safetensors",
19
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00009.safetensors",
20
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00009.safetensors",
21
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00009.safetensors",
22
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00009.safetensors",
23
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00009.safetensors",
24
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00009.safetensors",
25
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00009.safetensors",
26
+ "model.layers.10.ln1.weight": "model-00003-of-00009.safetensors",
27
+ "model.layers.10.ln2.weight": "model-00003-of-00009.safetensors",
28
+ "model.layers.10.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
29
+ "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
30
+ "model.layers.10.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
31
+ "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
32
+ "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
33
+ "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
34
+ "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
35
+ "model.layers.11.ln1.weight": "model-00004-of-00009.safetensors",
36
+ "model.layers.11.ln2.weight": "model-00004-of-00009.safetensors",
37
+ "model.layers.11.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
38
+ "model.layers.11.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
39
+ "model.layers.11.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
40
+ "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
41
+ "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
42
+ "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
43
+ "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
44
+ "model.layers.12.ln1.weight": "model-00004-of-00009.safetensors",
45
+ "model.layers.12.ln2.weight": "model-00004-of-00009.safetensors",
46
+ "model.layers.12.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
47
+ "model.layers.12.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
48
+ "model.layers.12.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
49
+ "model.layers.12.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
50
+ "model.layers.12.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
51
+ "model.layers.12.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
52
+ "model.layers.12.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
53
+ "model.layers.13.ln1.weight": "model-00004-of-00009.safetensors",
54
+ "model.layers.13.ln2.weight": "model-00004-of-00009.safetensors",
55
+ "model.layers.13.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
56
+ "model.layers.13.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
57
+ "model.layers.13.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
58
+ "model.layers.13.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
59
+ "model.layers.13.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
60
+ "model.layers.13.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
61
+ "model.layers.13.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
62
+ "model.layers.14.ln1.weight": "model-00004-of-00009.safetensors",
63
+ "model.layers.14.ln2.weight": "model-00004-of-00009.safetensors",
64
+ "model.layers.14.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
65
+ "model.layers.14.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
66
+ "model.layers.14.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
67
+ "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
68
+ "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
69
+ "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
70
+ "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
71
+ "model.layers.15.ln1.weight": "model-00005-of-00009.safetensors",
72
+ "model.layers.15.ln2.weight": "model-00005-of-00009.safetensors",
73
+ "model.layers.15.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
74
+ "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
75
+ "model.layers.15.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
76
+ "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
77
+ "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
78
+ "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
79
+ "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
80
+ "model.layers.16.ln1.weight": "model-00005-of-00009.safetensors",
81
+ "model.layers.16.ln2.weight": "model-00005-of-00009.safetensors",
82
+ "model.layers.16.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
83
+ "model.layers.16.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
84
+ "model.layers.16.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
85
+ "model.layers.16.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
86
+ "model.layers.16.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
87
+ "model.layers.16.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
88
+ "model.layers.16.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
89
+ "model.layers.17.ln1.weight": "model-00005-of-00009.safetensors",
90
+ "model.layers.17.ln2.weight": "model-00005-of-00009.safetensors",
91
+ "model.layers.17.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
92
+ "model.layers.17.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
93
+ "model.layers.17.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
94
+ "model.layers.17.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
95
+ "model.layers.17.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
96
+ "model.layers.17.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
97
+ "model.layers.17.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
98
+ "model.layers.18.ln1.weight": "model-00005-of-00009.safetensors",
99
+ "model.layers.18.ln2.weight": "model-00005-of-00009.safetensors",
100
+ "model.layers.18.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
101
+ "model.layers.18.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
102
+ "model.layers.18.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
103
+ "model.layers.18.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
104
+ "model.layers.18.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
105
+ "model.layers.18.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
106
+ "model.layers.18.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
107
+ "model.layers.19.ln1.weight": "model-00006-of-00009.safetensors",
108
+ "model.layers.19.ln2.weight": "model-00006-of-00009.safetensors",
109
+ "model.layers.19.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
110
+ "model.layers.19.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
111
+ "model.layers.19.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
112
+ "model.layers.19.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
113
+ "model.layers.19.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
114
+ "model.layers.19.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
115
+ "model.layers.19.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
116
+ "model.layers.2.ln1.weight": "model-00002-of-00009.safetensors",
117
+ "model.layers.2.ln2.weight": "model-00002-of-00009.safetensors",
118
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00009.safetensors",
119
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00009.safetensors",
120
+ "model.layers.2.mlp.up_proj.weight": "model-00002-of-00009.safetensors",
121
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00009.safetensors",
122
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00009.safetensors",
123
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00009.safetensors",
124
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00009.safetensors",
125
+ "model.layers.20.ln1.weight": "model-00006-of-00009.safetensors",
126
+ "model.layers.20.ln2.weight": "model-00006-of-00009.safetensors",
127
+ "model.layers.20.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
128
+ "model.layers.20.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
129
+ "model.layers.20.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
130
+ "model.layers.20.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
131
+ "model.layers.20.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
132
+ "model.layers.20.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
133
+ "model.layers.20.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
134
+ "model.layers.21.ln1.weight": "model-00006-of-00009.safetensors",
135
+ "model.layers.21.ln2.weight": "model-00006-of-00009.safetensors",
136
+ "model.layers.21.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
137
+ "model.layers.21.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
138
+ "model.layers.21.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
139
+ "model.layers.21.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
140
+ "model.layers.21.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
141
+ "model.layers.21.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
142
+ "model.layers.21.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
143
+ "model.layers.22.ln1.weight": "model-00006-of-00009.safetensors",
144
+ "model.layers.22.ln2.weight": "model-00006-of-00009.safetensors",
145
+ "model.layers.22.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
146
+ "model.layers.22.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
147
+ "model.layers.22.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
148
+ "model.layers.22.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
149
+ "model.layers.22.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
150
+ "model.layers.22.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
151
+ "model.layers.22.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
152
+ "model.layers.23.ln1.weight": "model-00006-of-00009.safetensors",
153
+ "model.layers.23.ln2.weight": "model-00006-of-00009.safetensors",
154
+ "model.layers.23.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
155
+ "model.layers.23.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
156
+ "model.layers.23.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
157
+ "model.layers.23.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
158
+ "model.layers.23.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
159
+ "model.layers.23.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
160
+ "model.layers.23.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
161
+ "model.layers.24.ln1.weight": "model-00007-of-00009.safetensors",
162
+ "model.layers.24.ln2.weight": "model-00007-of-00009.safetensors",
163
+ "model.layers.24.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
164
+ "model.layers.24.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
165
+ "model.layers.24.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
166
+ "model.layers.24.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
167
+ "model.layers.24.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
168
+ "model.layers.24.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
169
+ "model.layers.24.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
170
+ "model.layers.25.ln1.weight": "model-00007-of-00009.safetensors",
171
+ "model.layers.25.ln2.weight": "model-00007-of-00009.safetensors",
172
+ "model.layers.25.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
173
+ "model.layers.25.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
174
+ "model.layers.25.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
175
+ "model.layers.25.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
176
+ "model.layers.25.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
177
+ "model.layers.25.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
178
+ "model.layers.25.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
179
+ "model.layers.26.ln1.weight": "model-00007-of-00009.safetensors",
180
+ "model.layers.26.ln2.weight": "model-00007-of-00009.safetensors",
181
+ "model.layers.26.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
182
+ "model.layers.26.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
183
+ "model.layers.26.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
184
+ "model.layers.26.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
185
+ "model.layers.26.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
186
+ "model.layers.26.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
187
+ "model.layers.26.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
188
+ "model.layers.27.ln1.weight": "model-00007-of-00009.safetensors",
189
+ "model.layers.27.ln2.weight": "model-00007-of-00009.safetensors",
190
+ "model.layers.27.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
191
+ "model.layers.27.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
192
+ "model.layers.27.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
193
+ "model.layers.27.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
194
+ "model.layers.27.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
195
+ "model.layers.27.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
196
+ "model.layers.27.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
197
+ "model.layers.28.ln1.weight": "model-00008-of-00009.safetensors",
198
+ "model.layers.28.ln2.weight": "model-00008-of-00009.safetensors",
199
+ "model.layers.28.mlp.down_proj.weight": "model-00008-of-00009.safetensors",
200
+ "model.layers.28.mlp.gate_proj.weight": "model-00008-of-00009.safetensors",
201
+ "model.layers.28.mlp.up_proj.weight": "model-00008-of-00009.safetensors",
202
+ "model.layers.28.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
203
+ "model.layers.28.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
204
+ "model.layers.28.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
205
+ "model.layers.28.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
206
+ "model.layers.29.ln1.weight": "model-00008-of-00009.safetensors",
207
+ "model.layers.29.ln2.weight": "model-00008-of-00009.safetensors",
208
+ "model.layers.29.mlp.down_proj.weight": "model-00008-of-00009.safetensors",
209
+ "model.layers.29.mlp.gate_proj.weight": "model-00008-of-00009.safetensors",
210
+ "model.layers.29.mlp.up_proj.weight": "model-00008-of-00009.safetensors",
211
+ "model.layers.29.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
212
+ "model.layers.29.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
213
+ "model.layers.29.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
214
+ "model.layers.29.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
215
+ "model.layers.3.ln1.weight": "model-00002-of-00009.safetensors",
216
+ "model.layers.3.ln2.weight": "model-00002-of-00009.safetensors",
217
+ "model.layers.3.mlp.down_proj.weight": "model-00002-of-00009.safetensors",
218
+ "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00009.safetensors",
219
+ "model.layers.3.mlp.up_proj.weight": "model-00002-of-00009.safetensors",
220
+ "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
221
+ "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
222
+ "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
223
+ "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00009.safetensors",
224
+ "model.layers.30.ln1.weight": "model-00008-of-00009.safetensors",
225
+ "model.layers.30.ln2.weight": "model-00008-of-00009.safetensors",
226
+ "model.layers.30.mlp.down_proj.weight": "model-00008-of-00009.safetensors",
227
+ "model.layers.30.mlp.gate_proj.weight": "model-00008-of-00009.safetensors",
228
+ "model.layers.30.mlp.up_proj.weight": "model-00008-of-00009.safetensors",
229
+ "model.layers.30.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
230
+ "model.layers.30.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
231
+ "model.layers.30.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
232
+ "model.layers.30.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
233
+ "model.layers.31.ln1.weight": "model-00008-of-00009.safetensors",
234
+ "model.layers.31.ln2.weight": "model-00008-of-00009.safetensors",
235
+ "model.layers.31.mlp.down_proj.weight": "model-00008-of-00009.safetensors",
236
+ "model.layers.31.mlp.gate_proj.weight": "model-00008-of-00009.safetensors",
237
+ "model.layers.31.mlp.up_proj.weight": "model-00008-of-00009.safetensors",
238
+ "model.layers.31.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
239
+ "model.layers.31.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
240
+ "model.layers.31.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
241
+ "model.layers.31.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
242
+ "model.layers.4.ln1.weight": "model-00002-of-00009.safetensors",
243
+ "model.layers.4.ln2.weight": "model-00002-of-00009.safetensors",
244
+ "model.layers.4.mlp.down_proj.weight": "model-00002-of-00009.safetensors",
245
+ "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00009.safetensors",
246
+ "model.layers.4.mlp.up_proj.weight": "model-00002-of-00009.safetensors",
247
+ "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
248
+ "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
249
+ "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
250
+ "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00009.safetensors",
251
+ "model.layers.5.ln1.weight": "model-00002-of-00009.safetensors",
252
+ "model.layers.5.ln2.weight": "model-00002-of-00009.safetensors",
253
+ "model.layers.5.mlp.down_proj.weight": "model-00002-of-00009.safetensors",
254
+ "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00009.safetensors",
255
+ "model.layers.5.mlp.up_proj.weight": "model-00002-of-00009.safetensors",
256
+ "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
257
+ "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
258
+ "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
259
+ "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00009.safetensors",
260
+ "model.layers.6.ln1.weight": "model-00002-of-00009.safetensors",
261
+ "model.layers.6.ln2.weight": "model-00002-of-00009.safetensors",
262
+ "model.layers.6.mlp.down_proj.weight": "model-00002-of-00009.safetensors",
263
+ "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00009.safetensors",
264
+ "model.layers.6.mlp.up_proj.weight": "model-00002-of-00009.safetensors",
265
+ "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
266
+ "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
267
+ "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
268
+ "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00009.safetensors",
269
+ "model.layers.7.ln1.weight": "model-00003-of-00009.safetensors",
270
+ "model.layers.7.ln2.weight": "model-00003-of-00009.safetensors",
271
+ "model.layers.7.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
272
+ "model.layers.7.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
273
+ "model.layers.7.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
274
+ "model.layers.7.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
275
+ "model.layers.7.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
276
+ "model.layers.7.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
277
+ "model.layers.7.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
278
+ "model.layers.8.ln1.weight": "model-00003-of-00009.safetensors",
279
+ "model.layers.8.ln2.weight": "model-00003-of-00009.safetensors",
280
+ "model.layers.8.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
281
+ "model.layers.8.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
282
+ "model.layers.8.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
283
+ "model.layers.8.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
284
+ "model.layers.8.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
285
+ "model.layers.8.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
286
+ "model.layers.8.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
287
+ "model.layers.9.ln1.weight": "model-00003-of-00009.safetensors",
288
+ "model.layers.9.ln2.weight": "model-00003-of-00009.safetensors",
289
+ "model.layers.9.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
290
+ "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
291
+ "model.layers.9.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
292
+ "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
293
+ "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
294
+ "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
295
+ "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
296
+ "model.norm.weight": "model-00008-of-00009.safetensors"
297
+ }
298
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|startoftext|>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|endoftext|>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<unk>",
18
+ "lstrip": false,
19
+ "normalized": true,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<unk>",
25
+ "lstrip": false,
26
+ "normalized": true,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:386c49cf943d71aa110361135338c50e38beeff0a66593480421f37b319e1a39
3
+ size 1033105
tokenizer_config.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<unk>",
7
+ "lstrip": false,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<|startoftext|>",
15
+ "lstrip": false,
16
+ "normalized": true,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "<|endoftext|>",
23
+ "lstrip": false,
24
+ "normalized": true,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ }
29
+ },
30
+ "auto_map": {
31
+ "AutoTokenizer": [
32
+ "01-ai/Yi-6B--tokenization_yi.YiTokenizer",
33
+ null
34
+ ]
35
+ },
36
+ "bos_token": "<|startoftext|>",
37
+ "clean_up_tokenization_spaces": false,
38
+ "eos_token": "<|endoftext|>",
39
+ "model_max_length": 4096,
40
+ "pad_token": "<unk>",
41
+ "sp_model_kwargs": {},
42
+ "tokenizer_class": "YiTokenizer",
43
+ "unk_token": "<unk>"
44
+ }