JosephusCheung commited on
Commit
811346c
1 Parent(s): c4653e0

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
.ipynb_checkpoints/config-checkpoint.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/notebooks/35b",
3
+ "architectures": [
4
+ "CohereForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "auto_map": {
9
+ "AutoConfig": "configuration_cohere.CohereConfig",
10
+ "AutoModel": "configuration_cohere.CohereModel",
11
+ "AutoModelForCausalLM": "modeling_cohere.CohereForCausalLM"
12
+ },
13
+ "bos_token_id": 5,
14
+ "eos_token_id": 6,
15
+ "hidden_act": "silu",
16
+ "hidden_size": 8192,
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 22528,
19
+ "layer_norm_eps": 1e-05,
20
+ "logit_scale": 0.0625,
21
+ "max_position_embeddings": 150000,
22
+ "model_type": "cohere",
23
+ "num_attention_heads": 64,
24
+ "num_hidden_layers": 40,
25
+ "num_key_value_heads": 64,
26
+ "pad_token_id": 0,
27
+ "pretraining_tp": 1,
28
+ "rms_norm_eps": 1e-05,
29
+ "rope_theta": 8000000.0,
30
+ "torch_dtype": "bfloat16",
31
+ "transformers_version": "4.38.2",
32
+ "use_cache": true,
33
+ "vocab_size": 256000
34
+ }
config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "35b",
3
+ "architectures": [
4
+ "CohereForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "auto_map": {
9
+ "AutoConfig": "configuration_cohere.CohereConfig",
10
+ "AutoModel": "configuration_cohere.CohereModel",
11
+ "AutoModelForCausalLM": "modeling_cohere.CohereForCausalLM"
12
+ },
13
+ "bos_token_id": 5,
14
+ "eos_token_id": 6,
15
+ "hidden_act": "silu",
16
+ "hidden_size": 8192,
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 22528,
19
+ "layer_norm_eps": 1e-05,
20
+ "logit_scale": 0.0625,
21
+ "max_position_embeddings": 8192,
22
+ "model_type": "cohere",
23
+ "num_attention_heads": 64,
24
+ "num_hidden_layers": 40,
25
+ "num_key_value_heads": 64,
26
+ "pad_token_id": 0,
27
+ "pretraining_tp": 1,
28
+ "rms_norm_eps": 1e-05,
29
+ "rope_theta": 8000000.0,
30
+ "torch_dtype": "bfloat16",
31
+ "transformers_version": "4.38.2",
32
+ "use_cache": true,
33
+ "vocab_size": 256000
34
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 5,
4
+ "eos_token_id": 6,
5
+ "pad_token_id": 0,
6
+ "transformers_version": "4.38.2"
7
+ }
model-00001-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5428fa31fd03765d5c0eb14d3680ba058ee1e0eca4b25140092bb9d669914bbf
3
+ size 4731175520
model-00002-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c8d70c9ce69e42faf9616e1bda1448c2766f00fcaa20800d3beda8302cbb8e5c
3
+ size 4932553440
model-00003-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:10f1162a4f10ebf07324293635b6b9ee3509a835dc47a409abd87b92203f4d26
3
+ size 4932553440
model-00004-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d3d16b8c67947bbfbd37c3b235f50337aa4e0b8450a5c1f21d216bb75456e59
3
+ size 4932553440
model-00005-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:120a4429056e6efd04b1d2756b3e625bd829c4b458203d1cbf1e2e8a7b678489
3
+ size 4932553464
model-00006-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:478c89965e4390aa458d52bbef525f95cb69eb277db1f8454ad3b0dbd8b52b7c
3
+ size 4932553464
model-00007-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5d71536b1c2a5c33f27330b19010f7493c1599898207dc57aa1e7e38767a4c2b
3
+ size 4932553464
model-00008-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:57a64b41fcf22f9fd4855f542dac9d99aae242c9ad1245d34d2b71c428fe32aa
3
+ size 4932553464
model-00009-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ad83531189bb6d9456710a903396ec02987be03f6539048b85f1ac25a01dd10
3
+ size 4932553464
model-00010-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b18986af87bed9d98c7b9deff616540b7721c379113668191bf8f848e5a050fc
3
+ size 4932553464
model-00011-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5ac15fdc4368f7a3532b7e114938aa5e8e50db07f01962bc3801240b9939d9c1
3
+ size 4932553464
model-00012-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b9ae9ccf809835bfd3c3466c80b1377da957896b34a7090614a508220bd7c1df
3
+ size 4932553464
model-00013-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b058ba038b230322ef83091c8a91731d384eb6ca11058a9f5df38a7c3da3df83
3
+ size 4932553464
model-00014-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f6db7c3e17ce948ac5202197613ad977a2dd6a8e474e30076f5146571a4a0a4
3
+ size 4932553464
model-00015-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd1fabad5e9533b25b07d107ba37c5f580bc7a8c1871b794baefdae3fa976b76
3
+ size 1107329592
model.safetensors.index.json ADDED
@@ -0,0 +1,329 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 69961662464
4
+ },
5
+ "weight_map": {
6
+ "model.embed_tokens.weight": "model-00001-of-00015.safetensors",
7
+ "model.layers.0.input_layernorm.weight": "model-00002-of-00015.safetensors",
8
+ "model.layers.0.mlp.down_proj.weight": "model-00002-of-00015.safetensors",
9
+ "model.layers.0.mlp.gate_proj.weight": "model-00002-of-00015.safetensors",
10
+ "model.layers.0.mlp.up_proj.weight": "model-00002-of-00015.safetensors",
11
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00015.safetensors",
12
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00015.safetensors",
13
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00015.safetensors",
14
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00015.safetensors",
15
+ "model.layers.1.input_layernorm.weight": "model-00002-of-00015.safetensors",
16
+ "model.layers.1.mlp.down_proj.weight": "model-00002-of-00015.safetensors",
17
+ "model.layers.1.mlp.gate_proj.weight": "model-00002-of-00015.safetensors",
18
+ "model.layers.1.mlp.up_proj.weight": "model-00002-of-00015.safetensors",
19
+ "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00015.safetensors",
20
+ "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00015.safetensors",
21
+ "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00015.safetensors",
22
+ "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00015.safetensors",
23
+ "model.layers.10.input_layernorm.weight": "model-00005-of-00015.safetensors",
24
+ "model.layers.10.mlp.down_proj.weight": "model-00005-of-00015.safetensors",
25
+ "model.layers.10.mlp.gate_proj.weight": "model-00005-of-00015.safetensors",
26
+ "model.layers.10.mlp.up_proj.weight": "model-00005-of-00015.safetensors",
27
+ "model.layers.10.self_attn.k_proj.weight": "model-00005-of-00015.safetensors",
28
+ "model.layers.10.self_attn.o_proj.weight": "model-00005-of-00015.safetensors",
29
+ "model.layers.10.self_attn.q_proj.weight": "model-00005-of-00015.safetensors",
30
+ "model.layers.10.self_attn.v_proj.weight": "model-00005-of-00015.safetensors",
31
+ "model.layers.11.input_layernorm.weight": "model-00005-of-00015.safetensors",
32
+ "model.layers.11.mlp.down_proj.weight": "model-00005-of-00015.safetensors",
33
+ "model.layers.11.mlp.gate_proj.weight": "model-00005-of-00015.safetensors",
34
+ "model.layers.11.mlp.up_proj.weight": "model-00005-of-00015.safetensors",
35
+ "model.layers.11.self_attn.k_proj.weight": "model-00005-of-00015.safetensors",
36
+ "model.layers.11.self_attn.o_proj.weight": "model-00005-of-00015.safetensors",
37
+ "model.layers.11.self_attn.q_proj.weight": "model-00005-of-00015.safetensors",
38
+ "model.layers.11.self_attn.v_proj.weight": "model-00005-of-00015.safetensors",
39
+ "model.layers.12.input_layernorm.weight": "model-00006-of-00015.safetensors",
40
+ "model.layers.12.mlp.down_proj.weight": "model-00006-of-00015.safetensors",
41
+ "model.layers.12.mlp.gate_proj.weight": "model-00006-of-00015.safetensors",
42
+ "model.layers.12.mlp.up_proj.weight": "model-00006-of-00015.safetensors",
43
+ "model.layers.12.self_attn.k_proj.weight": "model-00005-of-00015.safetensors",
44
+ "model.layers.12.self_attn.o_proj.weight": "model-00005-of-00015.safetensors",
45
+ "model.layers.12.self_attn.q_proj.weight": "model-00005-of-00015.safetensors",
46
+ "model.layers.12.self_attn.v_proj.weight": "model-00005-of-00015.safetensors",
47
+ "model.layers.13.input_layernorm.weight": "model-00006-of-00015.safetensors",
48
+ "model.layers.13.mlp.down_proj.weight": "model-00006-of-00015.safetensors",
49
+ "model.layers.13.mlp.gate_proj.weight": "model-00006-of-00015.safetensors",
50
+ "model.layers.13.mlp.up_proj.weight": "model-00006-of-00015.safetensors",
51
+ "model.layers.13.self_attn.k_proj.weight": "model-00006-of-00015.safetensors",
52
+ "model.layers.13.self_attn.o_proj.weight": "model-00006-of-00015.safetensors",
53
+ "model.layers.13.self_attn.q_proj.weight": "model-00006-of-00015.safetensors",
54
+ "model.layers.13.self_attn.v_proj.weight": "model-00006-of-00015.safetensors",
55
+ "model.layers.14.input_layernorm.weight": "model-00006-of-00015.safetensors",
56
+ "model.layers.14.mlp.down_proj.weight": "model-00006-of-00015.safetensors",
57
+ "model.layers.14.mlp.gate_proj.weight": "model-00006-of-00015.safetensors",
58
+ "model.layers.14.mlp.up_proj.weight": "model-00006-of-00015.safetensors",
59
+ "model.layers.14.self_attn.k_proj.weight": "model-00006-of-00015.safetensors",
60
+ "model.layers.14.self_attn.o_proj.weight": "model-00006-of-00015.safetensors",
61
+ "model.layers.14.self_attn.q_proj.weight": "model-00006-of-00015.safetensors",
62
+ "model.layers.14.self_attn.v_proj.weight": "model-00006-of-00015.safetensors",
63
+ "model.layers.15.input_layernorm.weight": "model-00007-of-00015.safetensors",
64
+ "model.layers.15.mlp.down_proj.weight": "model-00007-of-00015.safetensors",
65
+ "model.layers.15.mlp.gate_proj.weight": "model-00007-of-00015.safetensors",
66
+ "model.layers.15.mlp.up_proj.weight": "model-00007-of-00015.safetensors",
67
+ "model.layers.15.self_attn.k_proj.weight": "model-00006-of-00015.safetensors",
68
+ "model.layers.15.self_attn.o_proj.weight": "model-00006-of-00015.safetensors",
69
+ "model.layers.15.self_attn.q_proj.weight": "model-00006-of-00015.safetensors",
70
+ "model.layers.15.self_attn.v_proj.weight": "model-00006-of-00015.safetensors",
71
+ "model.layers.16.input_layernorm.weight": "model-00007-of-00015.safetensors",
72
+ "model.layers.16.mlp.down_proj.weight": "model-00007-of-00015.safetensors",
73
+ "model.layers.16.mlp.gate_proj.weight": "model-00007-of-00015.safetensors",
74
+ "model.layers.16.mlp.up_proj.weight": "model-00007-of-00015.safetensors",
75
+ "model.layers.16.self_attn.k_proj.weight": "model-00007-of-00015.safetensors",
76
+ "model.layers.16.self_attn.o_proj.weight": "model-00007-of-00015.safetensors",
77
+ "model.layers.16.self_attn.q_proj.weight": "model-00007-of-00015.safetensors",
78
+ "model.layers.16.self_attn.v_proj.weight": "model-00007-of-00015.safetensors",
79
+ "model.layers.17.input_layernorm.weight": "model-00007-of-00015.safetensors",
80
+ "model.layers.17.mlp.down_proj.weight": "model-00007-of-00015.safetensors",
81
+ "model.layers.17.mlp.gate_proj.weight": "model-00007-of-00015.safetensors",
82
+ "model.layers.17.mlp.up_proj.weight": "model-00007-of-00015.safetensors",
83
+ "model.layers.17.self_attn.k_proj.weight": "model-00007-of-00015.safetensors",
84
+ "model.layers.17.self_attn.o_proj.weight": "model-00007-of-00015.safetensors",
85
+ "model.layers.17.self_attn.q_proj.weight": "model-00007-of-00015.safetensors",
86
+ "model.layers.17.self_attn.v_proj.weight": "model-00007-of-00015.safetensors",
87
+ "model.layers.18.input_layernorm.weight": "model-00008-of-00015.safetensors",
88
+ "model.layers.18.mlp.down_proj.weight": "model-00008-of-00015.safetensors",
89
+ "model.layers.18.mlp.gate_proj.weight": "model-00008-of-00015.safetensors",
90
+ "model.layers.18.mlp.up_proj.weight": "model-00008-of-00015.safetensors",
91
+ "model.layers.18.self_attn.k_proj.weight": "model-00007-of-00015.safetensors",
92
+ "model.layers.18.self_attn.o_proj.weight": "model-00007-of-00015.safetensors",
93
+ "model.layers.18.self_attn.q_proj.weight": "model-00007-of-00015.safetensors",
94
+ "model.layers.18.self_attn.v_proj.weight": "model-00007-of-00015.safetensors",
95
+ "model.layers.19.input_layernorm.weight": "model-00008-of-00015.safetensors",
96
+ "model.layers.19.mlp.down_proj.weight": "model-00008-of-00015.safetensors",
97
+ "model.layers.19.mlp.gate_proj.weight": "model-00008-of-00015.safetensors",
98
+ "model.layers.19.mlp.up_proj.weight": "model-00008-of-00015.safetensors",
99
+ "model.layers.19.self_attn.k_proj.weight": "model-00008-of-00015.safetensors",
100
+ "model.layers.19.self_attn.o_proj.weight": "model-00008-of-00015.safetensors",
101
+ "model.layers.19.self_attn.q_proj.weight": "model-00008-of-00015.safetensors",
102
+ "model.layers.19.self_attn.v_proj.weight": "model-00008-of-00015.safetensors",
103
+ "model.layers.2.input_layernorm.weight": "model-00002-of-00015.safetensors",
104
+ "model.layers.2.mlp.down_proj.weight": "model-00002-of-00015.safetensors",
105
+ "model.layers.2.mlp.gate_proj.weight": "model-00002-of-00015.safetensors",
106
+ "model.layers.2.mlp.up_proj.weight": "model-00002-of-00015.safetensors",
107
+ "model.layers.2.self_attn.k_proj.weight": "model-00002-of-00015.safetensors",
108
+ "model.layers.2.self_attn.o_proj.weight": "model-00002-of-00015.safetensors",
109
+ "model.layers.2.self_attn.q_proj.weight": "model-00002-of-00015.safetensors",
110
+ "model.layers.2.self_attn.v_proj.weight": "model-00002-of-00015.safetensors",
111
+ "model.layers.20.input_layernorm.weight": "model-00008-of-00015.safetensors",
112
+ "model.layers.20.mlp.down_proj.weight": "model-00008-of-00015.safetensors",
113
+ "model.layers.20.mlp.gate_proj.weight": "model-00008-of-00015.safetensors",
114
+ "model.layers.20.mlp.up_proj.weight": "model-00008-of-00015.safetensors",
115
+ "model.layers.20.self_attn.k_proj.weight": "model-00008-of-00015.safetensors",
116
+ "model.layers.20.self_attn.o_proj.weight": "model-00008-of-00015.safetensors",
117
+ "model.layers.20.self_attn.q_proj.weight": "model-00008-of-00015.safetensors",
118
+ "model.layers.20.self_attn.v_proj.weight": "model-00008-of-00015.safetensors",
119
+ "model.layers.21.input_layernorm.weight": "model-00009-of-00015.safetensors",
120
+ "model.layers.21.mlp.down_proj.weight": "model-00009-of-00015.safetensors",
121
+ "model.layers.21.mlp.gate_proj.weight": "model-00009-of-00015.safetensors",
122
+ "model.layers.21.mlp.up_proj.weight": "model-00009-of-00015.safetensors",
123
+ "model.layers.21.self_attn.k_proj.weight": "model-00008-of-00015.safetensors",
124
+ "model.layers.21.self_attn.o_proj.weight": "model-00008-of-00015.safetensors",
125
+ "model.layers.21.self_attn.q_proj.weight": "model-00008-of-00015.safetensors",
126
+ "model.layers.21.self_attn.v_proj.weight": "model-00008-of-00015.safetensors",
127
+ "model.layers.22.input_layernorm.weight": "model-00009-of-00015.safetensors",
128
+ "model.layers.22.mlp.down_proj.weight": "model-00009-of-00015.safetensors",
129
+ "model.layers.22.mlp.gate_proj.weight": "model-00009-of-00015.safetensors",
130
+ "model.layers.22.mlp.up_proj.weight": "model-00009-of-00015.safetensors",
131
+ "model.layers.22.self_attn.k_proj.weight": "model-00009-of-00015.safetensors",
132
+ "model.layers.22.self_attn.o_proj.weight": "model-00009-of-00015.safetensors",
133
+ "model.layers.22.self_attn.q_proj.weight": "model-00009-of-00015.safetensors",
134
+ "model.layers.22.self_attn.v_proj.weight": "model-00009-of-00015.safetensors",
135
+ "model.layers.23.input_layernorm.weight": "model-00009-of-00015.safetensors",
136
+ "model.layers.23.mlp.down_proj.weight": "model-00009-of-00015.safetensors",
137
+ "model.layers.23.mlp.gate_proj.weight": "model-00009-of-00015.safetensors",
138
+ "model.layers.23.mlp.up_proj.weight": "model-00009-of-00015.safetensors",
139
+ "model.layers.23.self_attn.k_proj.weight": "model-00009-of-00015.safetensors",
140
+ "model.layers.23.self_attn.o_proj.weight": "model-00009-of-00015.safetensors",
141
+ "model.layers.23.self_attn.q_proj.weight": "model-00009-of-00015.safetensors",
142
+ "model.layers.23.self_attn.v_proj.weight": "model-00009-of-00015.safetensors",
143
+ "model.layers.24.input_layernorm.weight": "model-00010-of-00015.safetensors",
144
+ "model.layers.24.mlp.down_proj.weight": "model-00010-of-00015.safetensors",
145
+ "model.layers.24.mlp.gate_proj.weight": "model-00010-of-00015.safetensors",
146
+ "model.layers.24.mlp.up_proj.weight": "model-00010-of-00015.safetensors",
147
+ "model.layers.24.self_attn.k_proj.weight": "model-00009-of-00015.safetensors",
148
+ "model.layers.24.self_attn.o_proj.weight": "model-00009-of-00015.safetensors",
149
+ "model.layers.24.self_attn.q_proj.weight": "model-00009-of-00015.safetensors",
150
+ "model.layers.24.self_attn.v_proj.weight": "model-00009-of-00015.safetensors",
151
+ "model.layers.25.input_layernorm.weight": "model-00010-of-00015.safetensors",
152
+ "model.layers.25.mlp.down_proj.weight": "model-00010-of-00015.safetensors",
153
+ "model.layers.25.mlp.gate_proj.weight": "model-00010-of-00015.safetensors",
154
+ "model.layers.25.mlp.up_proj.weight": "model-00010-of-00015.safetensors",
155
+ "model.layers.25.self_attn.k_proj.weight": "model-00010-of-00015.safetensors",
156
+ "model.layers.25.self_attn.o_proj.weight": "model-00010-of-00015.safetensors",
157
+ "model.layers.25.self_attn.q_proj.weight": "model-00010-of-00015.safetensors",
158
+ "model.layers.25.self_attn.v_proj.weight": "model-00010-of-00015.safetensors",
159
+ "model.layers.26.input_layernorm.weight": "model-00010-of-00015.safetensors",
160
+ "model.layers.26.mlp.down_proj.weight": "model-00010-of-00015.safetensors",
161
+ "model.layers.26.mlp.gate_proj.weight": "model-00010-of-00015.safetensors",
162
+ "model.layers.26.mlp.up_proj.weight": "model-00010-of-00015.safetensors",
163
+ "model.layers.26.self_attn.k_proj.weight": "model-00010-of-00015.safetensors",
164
+ "model.layers.26.self_attn.o_proj.weight": "model-00010-of-00015.safetensors",
165
+ "model.layers.26.self_attn.q_proj.weight": "model-00010-of-00015.safetensors",
166
+ "model.layers.26.self_attn.v_proj.weight": "model-00010-of-00015.safetensors",
167
+ "model.layers.27.input_layernorm.weight": "model-00011-of-00015.safetensors",
168
+ "model.layers.27.mlp.down_proj.weight": "model-00011-of-00015.safetensors",
169
+ "model.layers.27.mlp.gate_proj.weight": "model-00011-of-00015.safetensors",
170
+ "model.layers.27.mlp.up_proj.weight": "model-00011-of-00015.safetensors",
171
+ "model.layers.27.self_attn.k_proj.weight": "model-00010-of-00015.safetensors",
172
+ "model.layers.27.self_attn.o_proj.weight": "model-00010-of-00015.safetensors",
173
+ "model.layers.27.self_attn.q_proj.weight": "model-00010-of-00015.safetensors",
174
+ "model.layers.27.self_attn.v_proj.weight": "model-00010-of-00015.safetensors",
175
+ "model.layers.28.input_layernorm.weight": "model-00011-of-00015.safetensors",
176
+ "model.layers.28.mlp.down_proj.weight": "model-00011-of-00015.safetensors",
177
+ "model.layers.28.mlp.gate_proj.weight": "model-00011-of-00015.safetensors",
178
+ "model.layers.28.mlp.up_proj.weight": "model-00011-of-00015.safetensors",
179
+ "model.layers.28.self_attn.k_proj.weight": "model-00011-of-00015.safetensors",
180
+ "model.layers.28.self_attn.o_proj.weight": "model-00011-of-00015.safetensors",
181
+ "model.layers.28.self_attn.q_proj.weight": "model-00011-of-00015.safetensors",
182
+ "model.layers.28.self_attn.v_proj.weight": "model-00011-of-00015.safetensors",
183
+ "model.layers.29.input_layernorm.weight": "model-00011-of-00015.safetensors",
184
+ "model.layers.29.mlp.down_proj.weight": "model-00011-of-00015.safetensors",
185
+ "model.layers.29.mlp.gate_proj.weight": "model-00011-of-00015.safetensors",
186
+ "model.layers.29.mlp.up_proj.weight": "model-00011-of-00015.safetensors",
187
+ "model.layers.29.self_attn.k_proj.weight": "model-00011-of-00015.safetensors",
188
+ "model.layers.29.self_attn.o_proj.weight": "model-00011-of-00015.safetensors",
189
+ "model.layers.29.self_attn.q_proj.weight": "model-00011-of-00015.safetensors",
190
+ "model.layers.29.self_attn.v_proj.weight": "model-00011-of-00015.safetensors",
191
+ "model.layers.3.input_layernorm.weight": "model-00003-of-00015.safetensors",
192
+ "model.layers.3.mlp.down_proj.weight": "model-00003-of-00015.safetensors",
193
+ "model.layers.3.mlp.gate_proj.weight": "model-00003-of-00015.safetensors",
194
+ "model.layers.3.mlp.up_proj.weight": "model-00003-of-00015.safetensors",
195
+ "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00015.safetensors",
196
+ "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00015.safetensors",
197
+ "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00015.safetensors",
198
+ "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00015.safetensors",
199
+ "model.layers.30.input_layernorm.weight": "model-00012-of-00015.safetensors",
200
+ "model.layers.30.mlp.down_proj.weight": "model-00012-of-00015.safetensors",
201
+ "model.layers.30.mlp.gate_proj.weight": "model-00012-of-00015.safetensors",
202
+ "model.layers.30.mlp.up_proj.weight": "model-00012-of-00015.safetensors",
203
+ "model.layers.30.self_attn.k_proj.weight": "model-00011-of-00015.safetensors",
204
+ "model.layers.30.self_attn.o_proj.weight": "model-00011-of-00015.safetensors",
205
+ "model.layers.30.self_attn.q_proj.weight": "model-00011-of-00015.safetensors",
206
+ "model.layers.30.self_attn.v_proj.weight": "model-00011-of-00015.safetensors",
207
+ "model.layers.31.input_layernorm.weight": "model-00012-of-00015.safetensors",
208
+ "model.layers.31.mlp.down_proj.weight": "model-00012-of-00015.safetensors",
209
+ "model.layers.31.mlp.gate_proj.weight": "model-00012-of-00015.safetensors",
210
+ "model.layers.31.mlp.up_proj.weight": "model-00012-of-00015.safetensors",
211
+ "model.layers.31.self_attn.k_proj.weight": "model-00012-of-00015.safetensors",
212
+ "model.layers.31.self_attn.o_proj.weight": "model-00012-of-00015.safetensors",
213
+ "model.layers.31.self_attn.q_proj.weight": "model-00012-of-00015.safetensors",
214
+ "model.layers.31.self_attn.v_proj.weight": "model-00012-of-00015.safetensors",
215
+ "model.layers.32.input_layernorm.weight": "model-00012-of-00015.safetensors",
216
+ "model.layers.32.mlp.down_proj.weight": "model-00012-of-00015.safetensors",
217
+ "model.layers.32.mlp.gate_proj.weight": "model-00012-of-00015.safetensors",
218
+ "model.layers.32.mlp.up_proj.weight": "model-00012-of-00015.safetensors",
219
+ "model.layers.32.self_attn.k_proj.weight": "model-00012-of-00015.safetensors",
220
+ "model.layers.32.self_attn.o_proj.weight": "model-00012-of-00015.safetensors",
221
+ "model.layers.32.self_attn.q_proj.weight": "model-00012-of-00015.safetensors",
222
+ "model.layers.32.self_attn.v_proj.weight": "model-00012-of-00015.safetensors",
223
+ "model.layers.33.input_layernorm.weight": "model-00013-of-00015.safetensors",
224
+ "model.layers.33.mlp.down_proj.weight": "model-00013-of-00015.safetensors",
225
+ "model.layers.33.mlp.gate_proj.weight": "model-00013-of-00015.safetensors",
226
+ "model.layers.33.mlp.up_proj.weight": "model-00013-of-00015.safetensors",
227
+ "model.layers.33.self_attn.k_proj.weight": "model-00012-of-00015.safetensors",
228
+ "model.layers.33.self_attn.o_proj.weight": "model-00012-of-00015.safetensors",
229
+ "model.layers.33.self_attn.q_proj.weight": "model-00012-of-00015.safetensors",
230
+ "model.layers.33.self_attn.v_proj.weight": "model-00012-of-00015.safetensors",
231
+ "model.layers.34.input_layernorm.weight": "model-00013-of-00015.safetensors",
232
+ "model.layers.34.mlp.down_proj.weight": "model-00013-of-00015.safetensors",
233
+ "model.layers.34.mlp.gate_proj.weight": "model-00013-of-00015.safetensors",
234
+ "model.layers.34.mlp.up_proj.weight": "model-00013-of-00015.safetensors",
235
+ "model.layers.34.self_attn.k_proj.weight": "model-00013-of-00015.safetensors",
236
+ "model.layers.34.self_attn.o_proj.weight": "model-00013-of-00015.safetensors",
237
+ "model.layers.34.self_attn.q_proj.weight": "model-00013-of-00015.safetensors",
238
+ "model.layers.34.self_attn.v_proj.weight": "model-00013-of-00015.safetensors",
239
+ "model.layers.35.input_layernorm.weight": "model-00013-of-00015.safetensors",
240
+ "model.layers.35.mlp.down_proj.weight": "model-00013-of-00015.safetensors",
241
+ "model.layers.35.mlp.gate_proj.weight": "model-00013-of-00015.safetensors",
242
+ "model.layers.35.mlp.up_proj.weight": "model-00013-of-00015.safetensors",
243
+ "model.layers.35.self_attn.k_proj.weight": "model-00013-of-00015.safetensors",
244
+ "model.layers.35.self_attn.o_proj.weight": "model-00013-of-00015.safetensors",
245
+ "model.layers.35.self_attn.q_proj.weight": "model-00013-of-00015.safetensors",
246
+ "model.layers.35.self_attn.v_proj.weight": "model-00013-of-00015.safetensors",
247
+ "model.layers.36.input_layernorm.weight": "model-00014-of-00015.safetensors",
248
+ "model.layers.36.mlp.down_proj.weight": "model-00014-of-00015.safetensors",
249
+ "model.layers.36.mlp.gate_proj.weight": "model-00014-of-00015.safetensors",
250
+ "model.layers.36.mlp.up_proj.weight": "model-00014-of-00015.safetensors",
251
+ "model.layers.36.self_attn.k_proj.weight": "model-00013-of-00015.safetensors",
252
+ "model.layers.36.self_attn.o_proj.weight": "model-00013-of-00015.safetensors",
253
+ "model.layers.36.self_attn.q_proj.weight": "model-00013-of-00015.safetensors",
254
+ "model.layers.36.self_attn.v_proj.weight": "model-00013-of-00015.safetensors",
255
+ "model.layers.37.input_layernorm.weight": "model-00014-of-00015.safetensors",
256
+ "model.layers.37.mlp.down_proj.weight": "model-00014-of-00015.safetensors",
257
+ "model.layers.37.mlp.gate_proj.weight": "model-00014-of-00015.safetensors",
258
+ "model.layers.37.mlp.up_proj.weight": "model-00014-of-00015.safetensors",
259
+ "model.layers.37.self_attn.k_proj.weight": "model-00014-of-00015.safetensors",
260
+ "model.layers.37.self_attn.o_proj.weight": "model-00014-of-00015.safetensors",
261
+ "model.layers.37.self_attn.q_proj.weight": "model-00014-of-00015.safetensors",
262
+ "model.layers.37.self_attn.v_proj.weight": "model-00014-of-00015.safetensors",
263
+ "model.layers.38.input_layernorm.weight": "model-00014-of-00015.safetensors",
264
+ "model.layers.38.mlp.down_proj.weight": "model-00014-of-00015.safetensors",
265
+ "model.layers.38.mlp.gate_proj.weight": "model-00014-of-00015.safetensors",
266
+ "model.layers.38.mlp.up_proj.weight": "model-00014-of-00015.safetensors",
267
+ "model.layers.38.self_attn.k_proj.weight": "model-00014-of-00015.safetensors",
268
+ "model.layers.38.self_attn.o_proj.weight": "model-00014-of-00015.safetensors",
269
+ "model.layers.38.self_attn.q_proj.weight": "model-00014-of-00015.safetensors",
270
+ "model.layers.38.self_attn.v_proj.weight": "model-00014-of-00015.safetensors",
271
+ "model.layers.39.input_layernorm.weight": "model-00015-of-00015.safetensors",
272
+ "model.layers.39.mlp.down_proj.weight": "model-00015-of-00015.safetensors",
273
+ "model.layers.39.mlp.gate_proj.weight": "model-00015-of-00015.safetensors",
274
+ "model.layers.39.mlp.up_proj.weight": "model-00015-of-00015.safetensors",
275
+ "model.layers.39.self_attn.k_proj.weight": "model-00014-of-00015.safetensors",
276
+ "model.layers.39.self_attn.o_proj.weight": "model-00014-of-00015.safetensors",
277
+ "model.layers.39.self_attn.q_proj.weight": "model-00014-of-00015.safetensors",
278
+ "model.layers.39.self_attn.v_proj.weight": "model-00014-of-00015.safetensors",
279
+ "model.layers.4.input_layernorm.weight": "model-00003-of-00015.safetensors",
280
+ "model.layers.4.mlp.down_proj.weight": "model-00003-of-00015.safetensors",
281
+ "model.layers.4.mlp.gate_proj.weight": "model-00003-of-00015.safetensors",
282
+ "model.layers.4.mlp.up_proj.weight": "model-00003-of-00015.safetensors",
283
+ "model.layers.4.self_attn.k_proj.weight": "model-00003-of-00015.safetensors",
284
+ "model.layers.4.self_attn.o_proj.weight": "model-00003-of-00015.safetensors",
285
+ "model.layers.4.self_attn.q_proj.weight": "model-00003-of-00015.safetensors",
286
+ "model.layers.4.self_attn.v_proj.weight": "model-00003-of-00015.safetensors",
287
+ "model.layers.5.input_layernorm.weight": "model-00003-of-00015.safetensors",
288
+ "model.layers.5.mlp.down_proj.weight": "model-00003-of-00015.safetensors",
289
+ "model.layers.5.mlp.gate_proj.weight": "model-00003-of-00015.safetensors",
290
+ "model.layers.5.mlp.up_proj.weight": "model-00003-of-00015.safetensors",
291
+ "model.layers.5.self_attn.k_proj.weight": "model-00003-of-00015.safetensors",
292
+ "model.layers.5.self_attn.o_proj.weight": "model-00003-of-00015.safetensors",
293
+ "model.layers.5.self_attn.q_proj.weight": "model-00003-of-00015.safetensors",
294
+ "model.layers.5.self_attn.v_proj.weight": "model-00003-of-00015.safetensors",
295
+ "model.layers.6.input_layernorm.weight": "model-00004-of-00015.safetensors",
296
+ "model.layers.6.mlp.down_proj.weight": "model-00004-of-00015.safetensors",
297
+ "model.layers.6.mlp.gate_proj.weight": "model-00004-of-00015.safetensors",
298
+ "model.layers.6.mlp.up_proj.weight": "model-00004-of-00015.safetensors",
299
+ "model.layers.6.self_attn.k_proj.weight": "model-00003-of-00015.safetensors",
300
+ "model.layers.6.self_attn.o_proj.weight": "model-00003-of-00015.safetensors",
301
+ "model.layers.6.self_attn.q_proj.weight": "model-00003-of-00015.safetensors",
302
+ "model.layers.6.self_attn.v_proj.weight": "model-00003-of-00015.safetensors",
303
+ "model.layers.7.input_layernorm.weight": "model-00004-of-00015.safetensors",
304
+ "model.layers.7.mlp.down_proj.weight": "model-00004-of-00015.safetensors",
305
+ "model.layers.7.mlp.gate_proj.weight": "model-00004-of-00015.safetensors",
306
+ "model.layers.7.mlp.up_proj.weight": "model-00004-of-00015.safetensors",
307
+ "model.layers.7.self_attn.k_proj.weight": "model-00004-of-00015.safetensors",
308
+ "model.layers.7.self_attn.o_proj.weight": "model-00004-of-00015.safetensors",
309
+ "model.layers.7.self_attn.q_proj.weight": "model-00004-of-00015.safetensors",
310
+ "model.layers.7.self_attn.v_proj.weight": "model-00004-of-00015.safetensors",
311
+ "model.layers.8.input_layernorm.weight": "model-00004-of-00015.safetensors",
312
+ "model.layers.8.mlp.down_proj.weight": "model-00004-of-00015.safetensors",
313
+ "model.layers.8.mlp.gate_proj.weight": "model-00004-of-00015.safetensors",
314
+ "model.layers.8.mlp.up_proj.weight": "model-00004-of-00015.safetensors",
315
+ "model.layers.8.self_attn.k_proj.weight": "model-00004-of-00015.safetensors",
316
+ "model.layers.8.self_attn.o_proj.weight": "model-00004-of-00015.safetensors",
317
+ "model.layers.8.self_attn.q_proj.weight": "model-00004-of-00015.safetensors",
318
+ "model.layers.8.self_attn.v_proj.weight": "model-00004-of-00015.safetensors",
319
+ "model.layers.9.input_layernorm.weight": "model-00005-of-00015.safetensors",
320
+ "model.layers.9.mlp.down_proj.weight": "model-00005-of-00015.safetensors",
321
+ "model.layers.9.mlp.gate_proj.weight": "model-00005-of-00015.safetensors",
322
+ "model.layers.9.mlp.up_proj.weight": "model-00005-of-00015.safetensors",
323
+ "model.layers.9.self_attn.k_proj.weight": "model-00004-of-00015.safetensors",
324
+ "model.layers.9.self_attn.o_proj.weight": "model-00004-of-00015.safetensors",
325
+ "model.layers.9.self_attn.q_proj.weight": "model-00004-of-00015.safetensors",
326
+ "model.layers.9.self_attn.v_proj.weight": "model-00004-of-00015.safetensors",
327
+ "model.norm.weight": "model-00015-of-00015.safetensors"
328
+ }
329
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
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 sha256:3ec24d1fe80ac960489b2004b7399ea561799de2fae774bd5a9234c13e6a0726
3
+ size 12777306
tokenizer_config.json ADDED
@@ -0,0 +1,314 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<PAD>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<UNK>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "<CLS>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "3": {
30
+ "content": "<SEP>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "4": {
38
+ "content": "<MASK_TOKEN>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "5": {
46
+ "content": "<s>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "6": {
54
+ "content": "</s>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "7": {
62
+ "content": "<EOP_TOKEN>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "255000": {
70
+ "content": "<|im_start|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": false
76
+ },
77
+ "255001": {
78
+ "content": "<|im_end|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": false
84
+ },
85
+ "255002": {
86
+ "content": "<|YES_TOKEN|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": false
92
+ },
93
+ "255003": {
94
+ "content": "<|NO_TOKEN|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": false
100
+ },
101
+ "255004": {
102
+ "content": "<|GOOD_TOKEN|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": false
108
+ },
109
+ "255005": {
110
+ "content": "<|BAD_TOKEN|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": false
116
+ },
117
+ "255006": {
118
+ "content": "<|USER_TOKEN|>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "255007": {
126
+ "content": "<|CHATBOT_TOKEN|>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "255008": {
134
+ "content": "<|SYSTEM_TOKEN|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "255009": {
142
+ "content": "<|USER_0_TOKEN|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "255010": {
150
+ "content": "<|USER_1_TOKEN|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "255011": {
158
+ "content": "<|USER_2_TOKEN|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "255012": {
166
+ "content": "<|USER_3_TOKEN|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "255013": {
174
+ "content": "<|USER_4_TOKEN|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": false
180
+ },
181
+ "255014": {
182
+ "content": "<|USER_5_TOKEN|>",
183
+ "lstrip": false,
184
+ "normalized": false,
185
+ "rstrip": false,
186
+ "single_word": false,
187
+ "special": false
188
+ },
189
+ "255015": {
190
+ "content": "<|USER_6_TOKEN|>",
191
+ "lstrip": false,
192
+ "normalized": false,
193
+ "rstrip": false,
194
+ "single_word": false,
195
+ "special": false
196
+ },
197
+ "255016": {
198
+ "content": "<|USER_7_TOKEN|>",
199
+ "lstrip": false,
200
+ "normalized": false,
201
+ "rstrip": false,
202
+ "single_word": false,
203
+ "special": false
204
+ },
205
+ "255017": {
206
+ "content": "<|USER_8_TOKEN|>",
207
+ "lstrip": false,
208
+ "normalized": false,
209
+ "rstrip": false,
210
+ "single_word": false,
211
+ "special": false
212
+ },
213
+ "255018": {
214
+ "content": "<|USER_9_TOKEN|>",
215
+ "lstrip": false,
216
+ "normalized": false,
217
+ "rstrip": false,
218
+ "single_word": false,
219
+ "special": false
220
+ },
221
+ "255019": {
222
+ "content": "<|EXTRA_0_TOKEN|>",
223
+ "lstrip": false,
224
+ "normalized": false,
225
+ "rstrip": false,
226
+ "single_word": false,
227
+ "special": false
228
+ },
229
+ "255020": {
230
+ "content": "<|EXTRA_1_TOKEN|>",
231
+ "lstrip": false,
232
+ "normalized": false,
233
+ "rstrip": false,
234
+ "single_word": false,
235
+ "special": false
236
+ },
237
+ "255021": {
238
+ "content": "<|EXTRA_2_TOKEN|>",
239
+ "lstrip": false,
240
+ "normalized": false,
241
+ "rstrip": false,
242
+ "single_word": false,
243
+ "special": false
244
+ },
245
+ "255022": {
246
+ "content": "<|EXTRA_3_TOKEN|>",
247
+ "lstrip": false,
248
+ "normalized": false,
249
+ "rstrip": false,
250
+ "single_word": false,
251
+ "special": false
252
+ },
253
+ "255023": {
254
+ "content": "<|EXTRA_4_TOKEN|>",
255
+ "lstrip": false,
256
+ "normalized": false,
257
+ "rstrip": false,
258
+ "single_word": false,
259
+ "special": false
260
+ },
261
+ "255024": {
262
+ "content": "<|EXTRA_5_TOKEN|>",
263
+ "lstrip": false,
264
+ "normalized": false,
265
+ "rstrip": false,
266
+ "single_word": false,
267
+ "special": false
268
+ },
269
+ "255025": {
270
+ "content": "<|EXTRA_6_TOKEN|>",
271
+ "lstrip": false,
272
+ "normalized": false,
273
+ "rstrip": false,
274
+ "single_word": false,
275
+ "special": false
276
+ },
277
+ "255026": {
278
+ "content": "<|EXTRA_7_TOKEN|>",
279
+ "lstrip": false,
280
+ "normalized": false,
281
+ "rstrip": false,
282
+ "single_word": false,
283
+ "special": false
284
+ },
285
+ "255027": {
286
+ "content": "<|EXTRA_8_TOKEN|>",
287
+ "lstrip": false,
288
+ "normalized": false,
289
+ "rstrip": false,
290
+ "single_word": false,
291
+ "special": false
292
+ },
293
+ "255028": {
294
+ "content": "<|EXTRA_9_TOKEN|>",
295
+ "lstrip": false,
296
+ "normalized": false,
297
+ "rstrip": false,
298
+ "single_word": false,
299
+ "special": false
300
+ }
301
+ },
302
+ "bos_token": "<s>",
303
+ "clean_up_tokenization_spaces": false,
304
+ "eos_token": "</s>",
305
+ "chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}",
306
+ "legacy": true,
307
+ "model_max_length": 1000000000000000019884624838656,
308
+ "pad_token": "<PAD>",
309
+ "sp_model_kwargs": {},
310
+ "spaces_between_special_tokens": false,
311
+ "tokenizer_class": "LlamaTokenizer",
312
+ "unk_token": null,
313
+ "use_default_system_prompt": false
314
+ }