svjack commited on
Commit
f675c03
1 Parent(s): 2f1d9e4

Upload folder using huggingface_hub

Browse files
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "CohereForAI/aya-23-8B",
3
+ "architectures": [
4
+ "CohereForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 5,
9
+ "eos_token_id": 255001,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 4096,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 14336,
14
+ "layer_norm_eps": 1e-05,
15
+ "logit_scale": 0.0625,
16
+ "max_position_embeddings": 8192,
17
+ "model_type": "cohere",
18
+ "num_attention_heads": 32,
19
+ "num_hidden_layers": 32,
20
+ "num_key_value_heads": 8,
21
+ "pad_token_id": 0,
22
+ "rope_theta": 10000,
23
+ "torch_dtype": "float16",
24
+ "transformers_version": "4.41.1",
25
+ "use_cache": true,
26
+ "use_qk_norm": false,
27
+ "vocab_size": 256000
28
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 5,
4
+ "eos_token_id": 255001,
5
+ "pad_token_id": 0,
6
+ "transformers_version": "4.41.1"
7
+ }
pytorch_model-00001-of-00006.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d4182f28cd91afa5e1cebe35834a2a024ef350281aa2cc1ac63becbefa7afc01
3
+ size 2969590108
pytorch_model-00002-of-00006.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:05b36ef34ef95758ebeeefb1352ed264a47c071a85765b64fc7595c457adb1f8
3
+ size 2936080438
pytorch_model-00003-of-00006.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e41f8524db30b8cb577416bdf43742f7b8c9b6acb04ec40a786a92ae2f5ce764
3
+ size 2936089032
pytorch_model-00004-of-00006.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:216d79080072a474109e30d69a02316e9126bf60bf9e4afb5bcd464c3c08f2b5
3
+ size 2936089032
pytorch_model-00005-of-00006.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:998996531582bec854c344d042f1b6a89de3611bd60ec3f7f56f62205efaed80
3
+ size 2969642450
pytorch_model-00006-of-00006.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:846a531640442894285806cfa3cd54ac0a98ecaee67fd88bd665e0ead2642699
3
+ size 1308664492
pytorch_model.bin.index.json ADDED
@@ -0,0 +1,266 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 16056066048
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "pytorch_model-00001-of-00006.bin",
7
+ "model.embed_tokens.weight": "pytorch_model-00001-of-00006.bin",
8
+ "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
9
+ "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin",
10
+ "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin",
11
+ "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin",
12
+ "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
13
+ "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
14
+ "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
15
+ "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
16
+ "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
17
+ "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin",
18
+ "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin",
19
+ "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin",
20
+ "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
21
+ "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
22
+ "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
23
+ "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
24
+ "model.layers.10.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
25
+ "model.layers.10.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
26
+ "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
27
+ "model.layers.10.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
28
+ "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
29
+ "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
30
+ "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
31
+ "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
32
+ "model.layers.11.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
33
+ "model.layers.11.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
34
+ "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
35
+ "model.layers.11.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
36
+ "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
37
+ "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
38
+ "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
39
+ "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
40
+ "model.layers.12.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
41
+ "model.layers.12.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
42
+ "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
43
+ "model.layers.12.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
44
+ "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
45
+ "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
46
+ "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
47
+ "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
48
+ "model.layers.13.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
49
+ "model.layers.13.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
50
+ "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
51
+ "model.layers.13.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
52
+ "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
53
+ "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
54
+ "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
55
+ "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
56
+ "model.layers.14.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
57
+ "model.layers.14.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
58
+ "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
59
+ "model.layers.14.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
60
+ "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
61
+ "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
62
+ "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
63
+ "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
64
+ "model.layers.15.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
65
+ "model.layers.15.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
66
+ "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
67
+ "model.layers.15.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
68
+ "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
69
+ "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
70
+ "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
71
+ "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
72
+ "model.layers.16.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
73
+ "model.layers.16.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
74
+ "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
75
+ "model.layers.16.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
76
+ "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
77
+ "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
78
+ "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
79
+ "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
80
+ "model.layers.17.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
81
+ "model.layers.17.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
82
+ "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
83
+ "model.layers.17.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
84
+ "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
85
+ "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
86
+ "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
87
+ "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
88
+ "model.layers.18.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
89
+ "model.layers.18.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
90
+ "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
91
+ "model.layers.18.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
92
+ "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
93
+ "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
94
+ "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
95
+ "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
96
+ "model.layers.19.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
97
+ "model.layers.19.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
98
+ "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
99
+ "model.layers.19.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
100
+ "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
101
+ "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
102
+ "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
103
+ "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
104
+ "model.layers.2.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
105
+ "model.layers.2.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
106
+ "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
107
+ "model.layers.2.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
108
+ "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
109
+ "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
110
+ "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
111
+ "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
112
+ "model.layers.20.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
113
+ "model.layers.20.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
114
+ "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
115
+ "model.layers.20.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
116
+ "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
117
+ "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
118
+ "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
119
+ "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
120
+ "model.layers.21.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
121
+ "model.layers.21.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
122
+ "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
123
+ "model.layers.21.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
124
+ "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
125
+ "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
126
+ "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
127
+ "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
128
+ "model.layers.22.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
129
+ "model.layers.22.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
130
+ "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
131
+ "model.layers.22.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
132
+ "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
133
+ "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
134
+ "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
135
+ "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
136
+ "model.layers.23.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
137
+ "model.layers.23.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
138
+ "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
139
+ "model.layers.23.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
140
+ "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
141
+ "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
142
+ "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
143
+ "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
144
+ "model.layers.24.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
145
+ "model.layers.24.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
146
+ "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
147
+ "model.layers.24.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
148
+ "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
149
+ "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
150
+ "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
151
+ "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
152
+ "model.layers.25.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
153
+ "model.layers.25.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
154
+ "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
155
+ "model.layers.25.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
156
+ "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
157
+ "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
158
+ "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
159
+ "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
160
+ "model.layers.26.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
161
+ "model.layers.26.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
162
+ "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
163
+ "model.layers.26.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
164
+ "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
165
+ "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
166
+ "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
167
+ "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
168
+ "model.layers.27.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
169
+ "model.layers.27.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
170
+ "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
171
+ "model.layers.27.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
172
+ "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
173
+ "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
174
+ "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
175
+ "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
176
+ "model.layers.28.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
177
+ "model.layers.28.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
178
+ "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
179
+ "model.layers.28.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
180
+ "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
181
+ "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
182
+ "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
183
+ "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
184
+ "model.layers.29.input_layernorm.weight": "pytorch_model-00006-of-00006.bin",
185
+ "model.layers.29.mlp.down_proj.weight": "pytorch_model-00006-of-00006.bin",
186
+ "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00006-of-00006.bin",
187
+ "model.layers.29.mlp.up_proj.weight": "pytorch_model-00006-of-00006.bin",
188
+ "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00006-of-00006.bin",
189
+ "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00006-of-00006.bin",
190
+ "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00006-of-00006.bin",
191
+ "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00006-of-00006.bin",
192
+ "model.layers.3.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
193
+ "model.layers.3.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
194
+ "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
195
+ "model.layers.3.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
196
+ "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
197
+ "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
198
+ "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
199
+ "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
200
+ "model.layers.30.input_layernorm.weight": "pytorch_model-00006-of-00006.bin",
201
+ "model.layers.30.mlp.down_proj.weight": "pytorch_model-00006-of-00006.bin",
202
+ "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00006-of-00006.bin",
203
+ "model.layers.30.mlp.up_proj.weight": "pytorch_model-00006-of-00006.bin",
204
+ "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00006-of-00006.bin",
205
+ "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00006-of-00006.bin",
206
+ "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00006-of-00006.bin",
207
+ "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00006-of-00006.bin",
208
+ "model.layers.31.input_layernorm.weight": "pytorch_model-00006-of-00006.bin",
209
+ "model.layers.31.mlp.down_proj.weight": "pytorch_model-00006-of-00006.bin",
210
+ "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00006-of-00006.bin",
211
+ "model.layers.31.mlp.up_proj.weight": "pytorch_model-00006-of-00006.bin",
212
+ "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00006-of-00006.bin",
213
+ "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00006-of-00006.bin",
214
+ "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00006-of-00006.bin",
215
+ "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00006-of-00006.bin",
216
+ "model.layers.4.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
217
+ "model.layers.4.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
218
+ "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
219
+ "model.layers.4.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
220
+ "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
221
+ "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
222
+ "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
223
+ "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
224
+ "model.layers.5.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
225
+ "model.layers.5.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
226
+ "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
227
+ "model.layers.5.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
228
+ "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
229
+ "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
230
+ "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
231
+ "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
232
+ "model.layers.6.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
233
+ "model.layers.6.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
234
+ "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
235
+ "model.layers.6.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
236
+ "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
237
+ "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
238
+ "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
239
+ "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
240
+ "model.layers.7.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
241
+ "model.layers.7.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
242
+ "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
243
+ "model.layers.7.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
244
+ "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
245
+ "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
246
+ "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
247
+ "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
248
+ "model.layers.8.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
249
+ "model.layers.8.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
250
+ "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
251
+ "model.layers.8.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
252
+ "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
253
+ "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
254
+ "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
255
+ "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
256
+ "model.layers.9.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
257
+ "model.layers.9.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
258
+ "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
259
+ "model.layers.9.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
260
+ "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
261
+ "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
262
+ "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
263
+ "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
264
+ "model.norm.weight": "pytorch_model-00006-of-00006.bin"
265
+ }
266
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<BOS_TOKEN>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|END_OF_TURN_TOKEN|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<PAD>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c69a7ea6c0927dfac8c349186ebcf0466a4723c21cbdb2e850cf559f0bee92b8
3
+ size 12777433
tokenizer_config.json ADDED
@@ -0,0 +1,319 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": false,
5
+ "added_tokens_decoder": {
6
+ "0": {
7
+ "content": "<PAD>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "1": {
15
+ "content": "<UNK>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "2": {
23
+ "content": "<CLS>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": false,
27
+ "single_word": false,
28
+ "special": true
29
+ },
30
+ "3": {
31
+ "content": "<SEP>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false,
36
+ "special": true
37
+ },
38
+ "4": {
39
+ "content": "<MASK_TOKEN>",
40
+ "lstrip": false,
41
+ "normalized": false,
42
+ "rstrip": false,
43
+ "single_word": false,
44
+ "special": true
45
+ },
46
+ "5": {
47
+ "content": "<BOS_TOKEN>",
48
+ "lstrip": false,
49
+ "normalized": false,
50
+ "rstrip": false,
51
+ "single_word": false,
52
+ "special": true
53
+ },
54
+ "6": {
55
+ "content": "<EOS_TOKEN>",
56
+ "lstrip": false,
57
+ "normalized": false,
58
+ "rstrip": false,
59
+ "single_word": false,
60
+ "special": true
61
+ },
62
+ "7": {
63
+ "content": "<EOP_TOKEN>",
64
+ "lstrip": false,
65
+ "normalized": false,
66
+ "rstrip": false,
67
+ "single_word": false,
68
+ "special": true
69
+ },
70
+ "255000": {
71
+ "content": "<|START_OF_TURN_TOKEN|>",
72
+ "lstrip": false,
73
+ "normalized": false,
74
+ "rstrip": false,
75
+ "single_word": false,
76
+ "special": false
77
+ },
78
+ "255001": {
79
+ "content": "<|END_OF_TURN_TOKEN|>",
80
+ "lstrip": false,
81
+ "normalized": false,
82
+ "rstrip": false,
83
+ "single_word": false,
84
+ "special": true
85
+ },
86
+ "255002": {
87
+ "content": "<|YES_TOKEN|>",
88
+ "lstrip": false,
89
+ "normalized": false,
90
+ "rstrip": false,
91
+ "single_word": false,
92
+ "special": false
93
+ },
94
+ "255003": {
95
+ "content": "<|NO_TOKEN|>",
96
+ "lstrip": false,
97
+ "normalized": false,
98
+ "rstrip": false,
99
+ "single_word": false,
100
+ "special": false
101
+ },
102
+ "255004": {
103
+ "content": "<|GOOD_TOKEN|>",
104
+ "lstrip": false,
105
+ "normalized": false,
106
+ "rstrip": false,
107
+ "single_word": false,
108
+ "special": false
109
+ },
110
+ "255005": {
111
+ "content": "<|BAD_TOKEN|>",
112
+ "lstrip": false,
113
+ "normalized": false,
114
+ "rstrip": false,
115
+ "single_word": false,
116
+ "special": false
117
+ },
118
+ "255006": {
119
+ "content": "<|USER_TOKEN|>",
120
+ "lstrip": false,
121
+ "normalized": false,
122
+ "rstrip": false,
123
+ "single_word": false,
124
+ "special": false
125
+ },
126
+ "255007": {
127
+ "content": "<|CHATBOT_TOKEN|>",
128
+ "lstrip": false,
129
+ "normalized": false,
130
+ "rstrip": false,
131
+ "single_word": false,
132
+ "special": false
133
+ },
134
+ "255008": {
135
+ "content": "<|SYSTEM_TOKEN|>",
136
+ "lstrip": false,
137
+ "normalized": false,
138
+ "rstrip": false,
139
+ "single_word": false,
140
+ "special": false
141
+ },
142
+ "255009": {
143
+ "content": "<|USER_0_TOKEN|>",
144
+ "lstrip": false,
145
+ "normalized": false,
146
+ "rstrip": false,
147
+ "single_word": false,
148
+ "special": false
149
+ },
150
+ "255010": {
151
+ "content": "<|USER_1_TOKEN|>",
152
+ "lstrip": false,
153
+ "normalized": false,
154
+ "rstrip": false,
155
+ "single_word": false,
156
+ "special": false
157
+ },
158
+ "255011": {
159
+ "content": "<|USER_2_TOKEN|>",
160
+ "lstrip": false,
161
+ "normalized": false,
162
+ "rstrip": false,
163
+ "single_word": false,
164
+ "special": false
165
+ },
166
+ "255012": {
167
+ "content": "<|USER_3_TOKEN|>",
168
+ "lstrip": false,
169
+ "normalized": false,
170
+ "rstrip": false,
171
+ "single_word": false,
172
+ "special": false
173
+ },
174
+ "255013": {
175
+ "content": "<|USER_4_TOKEN|>",
176
+ "lstrip": false,
177
+ "normalized": false,
178
+ "rstrip": false,
179
+ "single_word": false,
180
+ "special": false
181
+ },
182
+ "255014": {
183
+ "content": "<|USER_5_TOKEN|>",
184
+ "lstrip": false,
185
+ "normalized": false,
186
+ "rstrip": false,
187
+ "single_word": false,
188
+ "special": false
189
+ },
190
+ "255015": {
191
+ "content": "<|USER_6_TOKEN|>",
192
+ "lstrip": false,
193
+ "normalized": false,
194
+ "rstrip": false,
195
+ "single_word": false,
196
+ "special": false
197
+ },
198
+ "255016": {
199
+ "content": "<|USER_7_TOKEN|>",
200
+ "lstrip": false,
201
+ "normalized": false,
202
+ "rstrip": false,
203
+ "single_word": false,
204
+ "special": false
205
+ },
206
+ "255017": {
207
+ "content": "<|USER_8_TOKEN|>",
208
+ "lstrip": false,
209
+ "normalized": false,
210
+ "rstrip": false,
211
+ "single_word": false,
212
+ "special": false
213
+ },
214
+ "255018": {
215
+ "content": "<|USER_9_TOKEN|>",
216
+ "lstrip": false,
217
+ "normalized": false,
218
+ "rstrip": false,
219
+ "single_word": false,
220
+ "special": false
221
+ },
222
+ "255019": {
223
+ "content": "<|EXTRA_0_TOKEN|>",
224
+ "lstrip": false,
225
+ "normalized": false,
226
+ "rstrip": false,
227
+ "single_word": false,
228
+ "special": false
229
+ },
230
+ "255020": {
231
+ "content": "<|EXTRA_1_TOKEN|>",
232
+ "lstrip": false,
233
+ "normalized": false,
234
+ "rstrip": false,
235
+ "single_word": false,
236
+ "special": false
237
+ },
238
+ "255021": {
239
+ "content": "<|EXTRA_2_TOKEN|>",
240
+ "lstrip": false,
241
+ "normalized": false,
242
+ "rstrip": false,
243
+ "single_word": false,
244
+ "special": false
245
+ },
246
+ "255022": {
247
+ "content": "<|EXTRA_3_TOKEN|>",
248
+ "lstrip": false,
249
+ "normalized": false,
250
+ "rstrip": false,
251
+ "single_word": false,
252
+ "special": false
253
+ },
254
+ "255023": {
255
+ "content": "<|EXTRA_4_TOKEN|>",
256
+ "lstrip": false,
257
+ "normalized": false,
258
+ "rstrip": false,
259
+ "single_word": false,
260
+ "special": false
261
+ },
262
+ "255024": {
263
+ "content": "<|EXTRA_5_TOKEN|>",
264
+ "lstrip": false,
265
+ "normalized": false,
266
+ "rstrip": false,
267
+ "single_word": false,
268
+ "special": false
269
+ },
270
+ "255025": {
271
+ "content": "<|EXTRA_6_TOKEN|>",
272
+ "lstrip": false,
273
+ "normalized": false,
274
+ "rstrip": false,
275
+ "single_word": false,
276
+ "special": false
277
+ },
278
+ "255026": {
279
+ "content": "<|EXTRA_7_TOKEN|>",
280
+ "lstrip": false,
281
+ "normalized": false,
282
+ "rstrip": false,
283
+ "single_word": false,
284
+ "special": false
285
+ },
286
+ "255027": {
287
+ "content": "<|EXTRA_8_TOKEN|>",
288
+ "lstrip": false,
289
+ "normalized": false,
290
+ "rstrip": false,
291
+ "single_word": false,
292
+ "special": false
293
+ },
294
+ "255028": {
295
+ "content": "<|EXTRA_9_TOKEN|>",
296
+ "lstrip": false,
297
+ "normalized": false,
298
+ "rstrip": false,
299
+ "single_word": false,
300
+ "special": false
301
+ }
302
+ },
303
+ "bos_token": "<BOS_TOKEN>",
304
+ "chat_template": "{% set system_message = 'You are Command-R, a brilliant, sophisticated, AI-assistant trained to assist human users by providing thorough responses. You are trained by Cohere.' %}{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{% if system_message is defined %}{{ '<BOS_TOKEN>' + '<|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|>' + system_message + '<|END_OF_TURN_TOKEN|>' }}{% endif %}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|START_OF_TURN_TOKEN|><|USER_TOKEN|>' + content + '<|END_OF_TURN_TOKEN|><|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>' }}{% elif message['role'] == 'assistant' %}{{ content + '<|END_OF_TURN_TOKEN|>' }}{% endif %}{% endfor %}",
305
+ "clean_up_tokenization_spaces": false,
306
+ "eos_token": "<|END_OF_TURN_TOKEN|>",
307
+ "legacy": true,
308
+ "merges_file": null,
309
+ "model_max_length": 1000000000000000019884624838656,
310
+ "pad_token": "<PAD>",
311
+ "padding_side": "left",
312
+ "sp_model_kwargs": {},
313
+ "spaces_between_special_tokens": false,
314
+ "split_special_tokens": false,
315
+ "tokenizer_class": "CohereTokenizer",
316
+ "unk_token": null,
317
+ "use_default_system_prompt": false,
318
+ "vocab_file": null
319
+ }