zoeywin sequelbox commited on
Commit
1c37006
β€’
1 Parent(s): 1ba2484

Upload folder using huggingface_hub (#1)

Browse files

- a56ddae0c11b717be3336eb980fafc69bf7108d77490865cde067975c953a376 (ce8b5ce9d3b46ea8babf4977f842dd4e3f43fdac)
- d83ac217244425cf243b67b36ea1d6a9d04f88f3b67fcc367d136588b2636de9 (aee3e24ede28fe7a5a8afef797f7b82b3aea7f57)
- eac6c4e4f6c797db353429d7be4befb18748b9017690bf43a214130516d71e6f (b32df86b144360409b58e8cf43d3b1fa09898df4)
- ac1e44890754f8e9f7a1238249f1059007a2b5cea808509ed7c4df96c9ed22ed (34c253ba7291aa7508ae8c87c421b91829a37204)
- 2747e3ff8e0ab0f285689ef439cd10da35ca462f311b70184c8fc091fb7d2fca (79f13f3ea4cb2addfcbad8e6a39f352a9fa88e2d)
- e47a0fad4756647ef4e95a58d632359fdeded5c8bf9bc9bcfc810b7a8a76296a (2b20b4a08eb0371df5ad4f175f5637106e66083a)
- 6a54cad2f4f525b678685951033835a84f6b9d5117e041c15b1abf83f316ed7a (a1616e23acfbc3abebf336b4be1d0f1f16a84d99)
- ae59ebcd51906136fc741a9fcc18ddc66a7a80ca65429a74afbc54165d50d71b (b60628c54259235b8ef278bfb57a7542f3a3aa3a)
- 6d9ec3fde950ed804780b040fe9704e6db99945d433b54b37768fe486376f1bb (b9c073e473a559209423dcf033750c35411981c7)
- c34b01b1c05b9deef85883e46d8a75f456a1f37b3aa6c1934f6c80021333a3ff (344ff0b9c0ea1ebcc68afd5ae9c40ab27fc879d2)
- 0890cef4171a15f470865acd344a67f8f1c46ec6d6fc0bda1ffdb47561df76b7 (ba757e33dadee10ddcbb6678b1005d5b01c9c980)
- 89322c10607a8ac0d6cb3d25f890bcc33805cbf7df224ebc1c87160f06e77936 (b6e1258a8101ef5f0e2b93eed25a0ff6a6ac1c9a)
- fireplace-13b 1.0 (4c62bc48ecc59aed9038aae8f20076c059d2c900)


Co-authored-by: scott <sequelbox@users.noreply.huggingface.co>

config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "ValiantLabs/Fireplace-13b",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 1,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 5120,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 13824,
14
+ "max_position_embeddings": 16384,
15
+ "model_type": "llama",
16
+ "num_attention_heads": 40,
17
+ "num_hidden_layers": 40,
18
+ "num_key_value_heads": 40,
19
+ "pretraining_tp": 1,
20
+ "rms_norm_eps": 1e-05,
21
+ "rope_scaling": null,
22
+ "rope_theta": 1000000,
23
+ "tie_word_embeddings": false,
24
+ "torch_dtype": "float32",
25
+ "transformers_version": "4.36.2",
26
+ "use_cache": true,
27
+ "vocab_size": 32016
28
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "transformers_version": "4.36.2"
6
+ }
model-00001-of-00011.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c7ec70b6f8ab4a6a7b458961023af957beb19a676648076b1bd07ba956f3a201
3
+ size 4881575536
model-00002-of-00011.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b3678b125d5f3077a4dce0ae3c760e26bff2c830ce340e530fa6551779d8434
3
+ size 4970418112
model-00003-of-00011.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cfd086d24373a1e419b90b72d0c43b1a70005cbcdf8ccb9c0a980429ab78ab2b
3
+ size 4970418120
model-00004-of-00011.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d8e76854902ea1c22feb4c06971da01dd8f0ccec119a3877aec0b93f86f651c1
3
+ size 4970418144
model-00005-of-00011.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f0a4becfaf4d3d729b75a2aa6fc8ed6104c6e7921a81a1f81f99907fea18b04
3
+ size 4970418144
model-00006-of-00011.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7583391979299ea23498a3152b92a241b16fdc97945724643eceb29925552688
3
+ size 4792119040
model-00007-of-00011.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e4fb9b67ee3c2cc9c54317c0a350d15d3847b6aa659d917d06009f45f2d9a318
3
+ size 4792160232
model-00008-of-00011.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0f4515966c8ac9f3b587921df80c57df71f75fa7bfbfea6120a11625f6929fde
3
+ size 4792160224
model-00009-of-00011.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:404ac08869a828501d24a7459ec622be1f13407418e03eeedb472e917f9c2224
3
+ size 4970418144
model-00010-of-00011.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2dcd06c9714464f8766ab89912f87868c4a01844cc26a82c1f8116ac2824ce65
3
+ size 4970418144
model-00011-of-00011.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d9878c5bff699108585b0466e188ef60d9f886c862cfe24f1dd31941be84710
3
+ size 2983630864
model.safetensors.index.json ADDED
@@ -0,0 +1,370 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 52064112640
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "model-00011-of-00011.safetensors",
7
+ "model.embed_tokens.weight": "model-00001-of-00011.safetensors",
8
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00011.safetensors",
9
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00011.safetensors",
10
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00011.safetensors",
11
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00011.safetensors",
12
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00011.safetensors",
13
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00011.safetensors",
14
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00011.safetensors",
15
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00011.safetensors",
16
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00011.safetensors",
17
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00011.safetensors",
18
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00011.safetensors",
19
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00011.safetensors",
20
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00011.safetensors",
21
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00011.safetensors",
22
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00011.safetensors",
23
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00011.safetensors",
24
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00011.safetensors",
25
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00011.safetensors",
26
+ "model.layers.10.input_layernorm.weight": "model-00003-of-00011.safetensors",
27
+ "model.layers.10.mlp.down_proj.weight": "model-00003-of-00011.safetensors",
28
+ "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00011.safetensors",
29
+ "model.layers.10.mlp.up_proj.weight": "model-00003-of-00011.safetensors",
30
+ "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00011.safetensors",
31
+ "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00011.safetensors",
32
+ "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00011.safetensors",
33
+ "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00011.safetensors",
34
+ "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00011.safetensors",
35
+ "model.layers.11.input_layernorm.weight": "model-00004-of-00011.safetensors",
36
+ "model.layers.11.mlp.down_proj.weight": "model-00004-of-00011.safetensors",
37
+ "model.layers.11.mlp.gate_proj.weight": "model-00004-of-00011.safetensors",
38
+ "model.layers.11.mlp.up_proj.weight": "model-00004-of-00011.safetensors",
39
+ "model.layers.11.post_attention_layernorm.weight": "model-00004-of-00011.safetensors",
40
+ "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00011.safetensors",
41
+ "model.layers.11.self_attn.o_proj.weight": "model-00004-of-00011.safetensors",
42
+ "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00011.safetensors",
43
+ "model.layers.11.self_attn.v_proj.weight": "model-00004-of-00011.safetensors",
44
+ "model.layers.12.input_layernorm.weight": "model-00004-of-00011.safetensors",
45
+ "model.layers.12.mlp.down_proj.weight": "model-00004-of-00011.safetensors",
46
+ "model.layers.12.mlp.gate_proj.weight": "model-00004-of-00011.safetensors",
47
+ "model.layers.12.mlp.up_proj.weight": "model-00004-of-00011.safetensors",
48
+ "model.layers.12.post_attention_layernorm.weight": "model-00004-of-00011.safetensors",
49
+ "model.layers.12.self_attn.k_proj.weight": "model-00004-of-00011.safetensors",
50
+ "model.layers.12.self_attn.o_proj.weight": "model-00004-of-00011.safetensors",
51
+ "model.layers.12.self_attn.q_proj.weight": "model-00004-of-00011.safetensors",
52
+ "model.layers.12.self_attn.v_proj.weight": "model-00004-of-00011.safetensors",
53
+ "model.layers.13.input_layernorm.weight": "model-00004-of-00011.safetensors",
54
+ "model.layers.13.mlp.down_proj.weight": "model-00004-of-00011.safetensors",
55
+ "model.layers.13.mlp.gate_proj.weight": "model-00004-of-00011.safetensors",
56
+ "model.layers.13.mlp.up_proj.weight": "model-00004-of-00011.safetensors",
57
+ "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00011.safetensors",
58
+ "model.layers.13.self_attn.k_proj.weight": "model-00004-of-00011.safetensors",
59
+ "model.layers.13.self_attn.o_proj.weight": "model-00004-of-00011.safetensors",
60
+ "model.layers.13.self_attn.q_proj.weight": "model-00004-of-00011.safetensors",
61
+ "model.layers.13.self_attn.v_proj.weight": "model-00004-of-00011.safetensors",
62
+ "model.layers.14.input_layernorm.weight": "model-00004-of-00011.safetensors",
63
+ "model.layers.14.mlp.down_proj.weight": "model-00004-of-00011.safetensors",
64
+ "model.layers.14.mlp.gate_proj.weight": "model-00004-of-00011.safetensors",
65
+ "model.layers.14.mlp.up_proj.weight": "model-00004-of-00011.safetensors",
66
+ "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00011.safetensors",
67
+ "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00011.safetensors",
68
+ "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00011.safetensors",
69
+ "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00011.safetensors",
70
+ "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00011.safetensors",
71
+ "model.layers.15.input_layernorm.weight": "model-00005-of-00011.safetensors",
72
+ "model.layers.15.mlp.down_proj.weight": "model-00005-of-00011.safetensors",
73
+ "model.layers.15.mlp.gate_proj.weight": "model-00005-of-00011.safetensors",
74
+ "model.layers.15.mlp.up_proj.weight": "model-00005-of-00011.safetensors",
75
+ "model.layers.15.post_attention_layernorm.weight": "model-00005-of-00011.safetensors",
76
+ "model.layers.15.self_attn.k_proj.weight": "model-00005-of-00011.safetensors",
77
+ "model.layers.15.self_attn.o_proj.weight": "model-00005-of-00011.safetensors",
78
+ "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00011.safetensors",
79
+ "model.layers.15.self_attn.v_proj.weight": "model-00005-of-00011.safetensors",
80
+ "model.layers.16.input_layernorm.weight": "model-00005-of-00011.safetensors",
81
+ "model.layers.16.mlp.down_proj.weight": "model-00005-of-00011.safetensors",
82
+ "model.layers.16.mlp.gate_proj.weight": "model-00005-of-00011.safetensors",
83
+ "model.layers.16.mlp.up_proj.weight": "model-00005-of-00011.safetensors",
84
+ "model.layers.16.post_attention_layernorm.weight": "model-00005-of-00011.safetensors",
85
+ "model.layers.16.self_attn.k_proj.weight": "model-00005-of-00011.safetensors",
86
+ "model.layers.16.self_attn.o_proj.weight": "model-00005-of-00011.safetensors",
87
+ "model.layers.16.self_attn.q_proj.weight": "model-00005-of-00011.safetensors",
88
+ "model.layers.16.self_attn.v_proj.weight": "model-00005-of-00011.safetensors",
89
+ "model.layers.17.input_layernorm.weight": "model-00005-of-00011.safetensors",
90
+ "model.layers.17.mlp.down_proj.weight": "model-00005-of-00011.safetensors",
91
+ "model.layers.17.mlp.gate_proj.weight": "model-00005-of-00011.safetensors",
92
+ "model.layers.17.mlp.up_proj.weight": "model-00005-of-00011.safetensors",
93
+ "model.layers.17.post_attention_layernorm.weight": "model-00005-of-00011.safetensors",
94
+ "model.layers.17.self_attn.k_proj.weight": "model-00005-of-00011.safetensors",
95
+ "model.layers.17.self_attn.o_proj.weight": "model-00005-of-00011.safetensors",
96
+ "model.layers.17.self_attn.q_proj.weight": "model-00005-of-00011.safetensors",
97
+ "model.layers.17.self_attn.v_proj.weight": "model-00005-of-00011.safetensors",
98
+ "model.layers.18.input_layernorm.weight": "model-00005-of-00011.safetensors",
99
+ "model.layers.18.mlp.down_proj.weight": "model-00005-of-00011.safetensors",
100
+ "model.layers.18.mlp.gate_proj.weight": "model-00005-of-00011.safetensors",
101
+ "model.layers.18.mlp.up_proj.weight": "model-00005-of-00011.safetensors",
102
+ "model.layers.18.post_attention_layernorm.weight": "model-00005-of-00011.safetensors",
103
+ "model.layers.18.self_attn.k_proj.weight": "model-00005-of-00011.safetensors",
104
+ "model.layers.18.self_attn.o_proj.weight": "model-00005-of-00011.safetensors",
105
+ "model.layers.18.self_attn.q_proj.weight": "model-00005-of-00011.safetensors",
106
+ "model.layers.18.self_attn.v_proj.weight": "model-00005-of-00011.safetensors",
107
+ "model.layers.19.input_layernorm.weight": "model-00006-of-00011.safetensors",
108
+ "model.layers.19.mlp.down_proj.weight": "model-00006-of-00011.safetensors",
109
+ "model.layers.19.mlp.gate_proj.weight": "model-00006-of-00011.safetensors",
110
+ "model.layers.19.mlp.up_proj.weight": "model-00006-of-00011.safetensors",
111
+ "model.layers.19.post_attention_layernorm.weight": "model-00006-of-00011.safetensors",
112
+ "model.layers.19.self_attn.k_proj.weight": "model-00006-of-00011.safetensors",
113
+ "model.layers.19.self_attn.o_proj.weight": "model-00006-of-00011.safetensors",
114
+ "model.layers.19.self_attn.q_proj.weight": "model-00006-of-00011.safetensors",
115
+ "model.layers.19.self_attn.v_proj.weight": "model-00006-of-00011.safetensors",
116
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00011.safetensors",
117
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00011.safetensors",
118
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00011.safetensors",
119
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00011.safetensors",
120
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00011.safetensors",
121
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00011.safetensors",
122
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00011.safetensors",
123
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00011.safetensors",
124
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00011.safetensors",
125
+ "model.layers.20.input_layernorm.weight": "model-00006-of-00011.safetensors",
126
+ "model.layers.20.mlp.down_proj.weight": "model-00006-of-00011.safetensors",
127
+ "model.layers.20.mlp.gate_proj.weight": "model-00006-of-00011.safetensors",
128
+ "model.layers.20.mlp.up_proj.weight": "model-00006-of-00011.safetensors",
129
+ "model.layers.20.post_attention_layernorm.weight": "model-00006-of-00011.safetensors",
130
+ "model.layers.20.self_attn.k_proj.weight": "model-00006-of-00011.safetensors",
131
+ "model.layers.20.self_attn.o_proj.weight": "model-00006-of-00011.safetensors",
132
+ "model.layers.20.self_attn.q_proj.weight": "model-00006-of-00011.safetensors",
133
+ "model.layers.20.self_attn.v_proj.weight": "model-00006-of-00011.safetensors",
134
+ "model.layers.21.input_layernorm.weight": "model-00006-of-00011.safetensors",
135
+ "model.layers.21.mlp.down_proj.weight": "model-00006-of-00011.safetensors",
136
+ "model.layers.21.mlp.gate_proj.weight": "model-00006-of-00011.safetensors",
137
+ "model.layers.21.mlp.up_proj.weight": "model-00006-of-00011.safetensors",
138
+ "model.layers.21.post_attention_layernorm.weight": "model-00006-of-00011.safetensors",
139
+ "model.layers.21.self_attn.k_proj.weight": "model-00006-of-00011.safetensors",
140
+ "model.layers.21.self_attn.o_proj.weight": "model-00006-of-00011.safetensors",
141
+ "model.layers.21.self_attn.q_proj.weight": "model-00006-of-00011.safetensors",
142
+ "model.layers.21.self_attn.v_proj.weight": "model-00006-of-00011.safetensors",
143
+ "model.layers.22.input_layernorm.weight": "model-00007-of-00011.safetensors",
144
+ "model.layers.22.mlp.down_proj.weight": "model-00007-of-00011.safetensors",
145
+ "model.layers.22.mlp.gate_proj.weight": "model-00006-of-00011.safetensors",
146
+ "model.layers.22.mlp.up_proj.weight": "model-00006-of-00011.safetensors",
147
+ "model.layers.22.post_attention_layernorm.weight": "model-00007-of-00011.safetensors",
148
+ "model.layers.22.self_attn.k_proj.weight": "model-00006-of-00011.safetensors",
149
+ "model.layers.22.self_attn.o_proj.weight": "model-00006-of-00011.safetensors",
150
+ "model.layers.22.self_attn.q_proj.weight": "model-00006-of-00011.safetensors",
151
+ "model.layers.22.self_attn.v_proj.weight": "model-00006-of-00011.safetensors",
152
+ "model.layers.23.input_layernorm.weight": "model-00007-of-00011.safetensors",
153
+ "model.layers.23.mlp.down_proj.weight": "model-00007-of-00011.safetensors",
154
+ "model.layers.23.mlp.gate_proj.weight": "model-00007-of-00011.safetensors",
155
+ "model.layers.23.mlp.up_proj.weight": "model-00007-of-00011.safetensors",
156
+ "model.layers.23.post_attention_layernorm.weight": "model-00007-of-00011.safetensors",
157
+ "model.layers.23.self_attn.k_proj.weight": "model-00007-of-00011.safetensors",
158
+ "model.layers.23.self_attn.o_proj.weight": "model-00007-of-00011.safetensors",
159
+ "model.layers.23.self_attn.q_proj.weight": "model-00007-of-00011.safetensors",
160
+ "model.layers.23.self_attn.v_proj.weight": "model-00007-of-00011.safetensors",
161
+ "model.layers.24.input_layernorm.weight": "model-00007-of-00011.safetensors",
162
+ "model.layers.24.mlp.down_proj.weight": "model-00007-of-00011.safetensors",
163
+ "model.layers.24.mlp.gate_proj.weight": "model-00007-of-00011.safetensors",
164
+ "model.layers.24.mlp.up_proj.weight": "model-00007-of-00011.safetensors",
165
+ "model.layers.24.post_attention_layernorm.weight": "model-00007-of-00011.safetensors",
166
+ "model.layers.24.self_attn.k_proj.weight": "model-00007-of-00011.safetensors",
167
+ "model.layers.24.self_attn.o_proj.weight": "model-00007-of-00011.safetensors",
168
+ "model.layers.24.self_attn.q_proj.weight": "model-00007-of-00011.safetensors",
169
+ "model.layers.24.self_attn.v_proj.weight": "model-00007-of-00011.safetensors",
170
+ "model.layers.25.input_layernorm.weight": "model-00007-of-00011.safetensors",
171
+ "model.layers.25.mlp.down_proj.weight": "model-00007-of-00011.safetensors",
172
+ "model.layers.25.mlp.gate_proj.weight": "model-00007-of-00011.safetensors",
173
+ "model.layers.25.mlp.up_proj.weight": "model-00007-of-00011.safetensors",
174
+ "model.layers.25.post_attention_layernorm.weight": "model-00007-of-00011.safetensors",
175
+ "model.layers.25.self_attn.k_proj.weight": "model-00007-of-00011.safetensors",
176
+ "model.layers.25.self_attn.o_proj.weight": "model-00007-of-00011.safetensors",
177
+ "model.layers.25.self_attn.q_proj.weight": "model-00007-of-00011.safetensors",
178
+ "model.layers.25.self_attn.v_proj.weight": "model-00007-of-00011.safetensors",
179
+ "model.layers.26.input_layernorm.weight": "model-00008-of-00011.safetensors",
180
+ "model.layers.26.mlp.down_proj.weight": "model-00008-of-00011.safetensors",
181
+ "model.layers.26.mlp.gate_proj.weight": "model-00007-of-00011.safetensors",
182
+ "model.layers.26.mlp.up_proj.weight": "model-00008-of-00011.safetensors",
183
+ "model.layers.26.post_attention_layernorm.weight": "model-00008-of-00011.safetensors",
184
+ "model.layers.26.self_attn.k_proj.weight": "model-00007-of-00011.safetensors",
185
+ "model.layers.26.self_attn.o_proj.weight": "model-00007-of-00011.safetensors",
186
+ "model.layers.26.self_attn.q_proj.weight": "model-00007-of-00011.safetensors",
187
+ "model.layers.26.self_attn.v_proj.weight": "model-00007-of-00011.safetensors",
188
+ "model.layers.27.input_layernorm.weight": "model-00008-of-00011.safetensors",
189
+ "model.layers.27.mlp.down_proj.weight": "model-00008-of-00011.safetensors",
190
+ "model.layers.27.mlp.gate_proj.weight": "model-00008-of-00011.safetensors",
191
+ "model.layers.27.mlp.up_proj.weight": "model-00008-of-00011.safetensors",
192
+ "model.layers.27.post_attention_layernorm.weight": "model-00008-of-00011.safetensors",
193
+ "model.layers.27.self_attn.k_proj.weight": "model-00008-of-00011.safetensors",
194
+ "model.layers.27.self_attn.o_proj.weight": "model-00008-of-00011.safetensors",
195
+ "model.layers.27.self_attn.q_proj.weight": "model-00008-of-00011.safetensors",
196
+ "model.layers.27.self_attn.v_proj.weight": "model-00008-of-00011.safetensors",
197
+ "model.layers.28.input_layernorm.weight": "model-00008-of-00011.safetensors",
198
+ "model.layers.28.mlp.down_proj.weight": "model-00008-of-00011.safetensors",
199
+ "model.layers.28.mlp.gate_proj.weight": "model-00008-of-00011.safetensors",
200
+ "model.layers.28.mlp.up_proj.weight": "model-00008-of-00011.safetensors",
201
+ "model.layers.28.post_attention_layernorm.weight": "model-00008-of-00011.safetensors",
202
+ "model.layers.28.self_attn.k_proj.weight": "model-00008-of-00011.safetensors",
203
+ "model.layers.28.self_attn.o_proj.weight": "model-00008-of-00011.safetensors",
204
+ "model.layers.28.self_attn.q_proj.weight": "model-00008-of-00011.safetensors",
205
+ "model.layers.28.self_attn.v_proj.weight": "model-00008-of-00011.safetensors",
206
+ "model.layers.29.input_layernorm.weight": "model-00008-of-00011.safetensors",
207
+ "model.layers.29.mlp.down_proj.weight": "model-00008-of-00011.safetensors",
208
+ "model.layers.29.mlp.gate_proj.weight": "model-00008-of-00011.safetensors",
209
+ "model.layers.29.mlp.up_proj.weight": "model-00008-of-00011.safetensors",
210
+ "model.layers.29.post_attention_layernorm.weight": "model-00008-of-00011.safetensors",
211
+ "model.layers.29.self_attn.k_proj.weight": "model-00008-of-00011.safetensors",
212
+ "model.layers.29.self_attn.o_proj.weight": "model-00008-of-00011.safetensors",
213
+ "model.layers.29.self_attn.q_proj.weight": "model-00008-of-00011.safetensors",
214
+ "model.layers.29.self_attn.v_proj.weight": "model-00008-of-00011.safetensors",
215
+ "model.layers.3.input_layernorm.weight": "model-00002-of-00011.safetensors",
216
+ "model.layers.3.mlp.down_proj.weight": "model-00002-of-00011.safetensors",
217
+ "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00011.safetensors",
218
+ "model.layers.3.mlp.up_proj.weight": "model-00002-of-00011.safetensors",
219
+ "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00011.safetensors",
220
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00011.safetensors",
221
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00011.safetensors",
222
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00011.safetensors",
223
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00011.safetensors",
224
+ "model.layers.30.input_layernorm.weight": "model-00009-of-00011.safetensors",
225
+ "model.layers.30.mlp.down_proj.weight": "model-00009-of-00011.safetensors",
226
+ "model.layers.30.mlp.gate_proj.weight": "model-00009-of-00011.safetensors",
227
+ "model.layers.30.mlp.up_proj.weight": "model-00009-of-00011.safetensors",
228
+ "model.layers.30.post_attention_layernorm.weight": "model-00009-of-00011.safetensors",
229
+ "model.layers.30.self_attn.k_proj.weight": "model-00008-of-00011.safetensors",
230
+ "model.layers.30.self_attn.o_proj.weight": "model-00008-of-00011.safetensors",
231
+ "model.layers.30.self_attn.q_proj.weight": "model-00008-of-00011.safetensors",
232
+ "model.layers.30.self_attn.v_proj.weight": "model-00008-of-00011.safetensors",
233
+ "model.layers.31.input_layernorm.weight": "model-00009-of-00011.safetensors",
234
+ "model.layers.31.mlp.down_proj.weight": "model-00009-of-00011.safetensors",
235
+ "model.layers.31.mlp.gate_proj.weight": "model-00009-of-00011.safetensors",
236
+ "model.layers.31.mlp.up_proj.weight": "model-00009-of-00011.safetensors",
237
+ "model.layers.31.post_attention_layernorm.weight": "model-00009-of-00011.safetensors",
238
+ "model.layers.31.self_attn.k_proj.weight": "model-00009-of-00011.safetensors",
239
+ "model.layers.31.self_attn.o_proj.weight": "model-00009-of-00011.safetensors",
240
+ "model.layers.31.self_attn.q_proj.weight": "model-00009-of-00011.safetensors",
241
+ "model.layers.31.self_attn.v_proj.weight": "model-00009-of-00011.safetensors",
242
+ "model.layers.32.input_layernorm.weight": "model-00009-of-00011.safetensors",
243
+ "model.layers.32.mlp.down_proj.weight": "model-00009-of-00011.safetensors",
244
+ "model.layers.32.mlp.gate_proj.weight": "model-00009-of-00011.safetensors",
245
+ "model.layers.32.mlp.up_proj.weight": "model-00009-of-00011.safetensors",
246
+ "model.layers.32.post_attention_layernorm.weight": "model-00009-of-00011.safetensors",
247
+ "model.layers.32.self_attn.k_proj.weight": "model-00009-of-00011.safetensors",
248
+ "model.layers.32.self_attn.o_proj.weight": "model-00009-of-00011.safetensors",
249
+ "model.layers.32.self_attn.q_proj.weight": "model-00009-of-00011.safetensors",
250
+ "model.layers.32.self_attn.v_proj.weight": "model-00009-of-00011.safetensors",
251
+ "model.layers.33.input_layernorm.weight": "model-00009-of-00011.safetensors",
252
+ "model.layers.33.mlp.down_proj.weight": "model-00009-of-00011.safetensors",
253
+ "model.layers.33.mlp.gate_proj.weight": "model-00009-of-00011.safetensors",
254
+ "model.layers.33.mlp.up_proj.weight": "model-00009-of-00011.safetensors",
255
+ "model.layers.33.post_attention_layernorm.weight": "model-00009-of-00011.safetensors",
256
+ "model.layers.33.self_attn.k_proj.weight": "model-00009-of-00011.safetensors",
257
+ "model.layers.33.self_attn.o_proj.weight": "model-00009-of-00011.safetensors",
258
+ "model.layers.33.self_attn.q_proj.weight": "model-00009-of-00011.safetensors",
259
+ "model.layers.33.self_attn.v_proj.weight": "model-00009-of-00011.safetensors",
260
+ "model.layers.34.input_layernorm.weight": "model-00010-of-00011.safetensors",
261
+ "model.layers.34.mlp.down_proj.weight": "model-00010-of-00011.safetensors",
262
+ "model.layers.34.mlp.gate_proj.weight": "model-00010-of-00011.safetensors",
263
+ "model.layers.34.mlp.up_proj.weight": "model-00010-of-00011.safetensors",
264
+ "model.layers.34.post_attention_layernorm.weight": "model-00010-of-00011.safetensors",
265
+ "model.layers.34.self_attn.k_proj.weight": "model-00009-of-00011.safetensors",
266
+ "model.layers.34.self_attn.o_proj.weight": "model-00010-of-00011.safetensors",
267
+ "model.layers.34.self_attn.q_proj.weight": "model-00009-of-00011.safetensors",
268
+ "model.layers.34.self_attn.v_proj.weight": "model-00009-of-00011.safetensors",
269
+ "model.layers.35.input_layernorm.weight": "model-00010-of-00011.safetensors",
270
+ "model.layers.35.mlp.down_proj.weight": "model-00010-of-00011.safetensors",
271
+ "model.layers.35.mlp.gate_proj.weight": "model-00010-of-00011.safetensors",
272
+ "model.layers.35.mlp.up_proj.weight": "model-00010-of-00011.safetensors",
273
+ "model.layers.35.post_attention_layernorm.weight": "model-00010-of-00011.safetensors",
274
+ "model.layers.35.self_attn.k_proj.weight": "model-00010-of-00011.safetensors",
275
+ "model.layers.35.self_attn.o_proj.weight": "model-00010-of-00011.safetensors",
276
+ "model.layers.35.self_attn.q_proj.weight": "model-00010-of-00011.safetensors",
277
+ "model.layers.35.self_attn.v_proj.weight": "model-00010-of-00011.safetensors",
278
+ "model.layers.36.input_layernorm.weight": "model-00010-of-00011.safetensors",
279
+ "model.layers.36.mlp.down_proj.weight": "model-00010-of-00011.safetensors",
280
+ "model.layers.36.mlp.gate_proj.weight": "model-00010-of-00011.safetensors",
281
+ "model.layers.36.mlp.up_proj.weight": "model-00010-of-00011.safetensors",
282
+ "model.layers.36.post_attention_layernorm.weight": "model-00010-of-00011.safetensors",
283
+ "model.layers.36.self_attn.k_proj.weight": "model-00010-of-00011.safetensors",
284
+ "model.layers.36.self_attn.o_proj.weight": "model-00010-of-00011.safetensors",
285
+ "model.layers.36.self_attn.q_proj.weight": "model-00010-of-00011.safetensors",
286
+ "model.layers.36.self_attn.v_proj.weight": "model-00010-of-00011.safetensors",
287
+ "model.layers.37.input_layernorm.weight": "model-00010-of-00011.safetensors",
288
+ "model.layers.37.mlp.down_proj.weight": "model-00010-of-00011.safetensors",
289
+ "model.layers.37.mlp.gate_proj.weight": "model-00010-of-00011.safetensors",
290
+ "model.layers.37.mlp.up_proj.weight": "model-00010-of-00011.safetensors",
291
+ "model.layers.37.post_attention_layernorm.weight": "model-00010-of-00011.safetensors",
292
+ "model.layers.37.self_attn.k_proj.weight": "model-00010-of-00011.safetensors",
293
+ "model.layers.37.self_attn.o_proj.weight": "model-00010-of-00011.safetensors",
294
+ "model.layers.37.self_attn.q_proj.weight": "model-00010-of-00011.safetensors",
295
+ "model.layers.37.self_attn.v_proj.weight": "model-00010-of-00011.safetensors",
296
+ "model.layers.38.input_layernorm.weight": "model-00011-of-00011.safetensors",
297
+ "model.layers.38.mlp.down_proj.weight": "model-00011-of-00011.safetensors",
298
+ "model.layers.38.mlp.gate_proj.weight": "model-00011-of-00011.safetensors",
299
+ "model.layers.38.mlp.up_proj.weight": "model-00011-of-00011.safetensors",
300
+ "model.layers.38.post_attention_layernorm.weight": "model-00011-of-00011.safetensors",
301
+ "model.layers.38.self_attn.k_proj.weight": "model-00010-of-00011.safetensors",
302
+ "model.layers.38.self_attn.o_proj.weight": "model-00011-of-00011.safetensors",
303
+ "model.layers.38.self_attn.q_proj.weight": "model-00010-of-00011.safetensors",
304
+ "model.layers.38.self_attn.v_proj.weight": "model-00011-of-00011.safetensors",
305
+ "model.layers.39.input_layernorm.weight": "model-00011-of-00011.safetensors",
306
+ "model.layers.39.mlp.down_proj.weight": "model-00011-of-00011.safetensors",
307
+ "model.layers.39.mlp.gate_proj.weight": "model-00011-of-00011.safetensors",
308
+ "model.layers.39.mlp.up_proj.weight": "model-00011-of-00011.safetensors",
309
+ "model.layers.39.post_attention_layernorm.weight": "model-00011-of-00011.safetensors",
310
+ "model.layers.39.self_attn.k_proj.weight": "model-00011-of-00011.safetensors",
311
+ "model.layers.39.self_attn.o_proj.weight": "model-00011-of-00011.safetensors",
312
+ "model.layers.39.self_attn.q_proj.weight": "model-00011-of-00011.safetensors",
313
+ "model.layers.39.self_attn.v_proj.weight": "model-00011-of-00011.safetensors",
314
+ "model.layers.4.input_layernorm.weight": "model-00002-of-00011.safetensors",
315
+ "model.layers.4.mlp.down_proj.weight": "model-00002-of-00011.safetensors",
316
+ "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00011.safetensors",
317
+ "model.layers.4.mlp.up_proj.weight": "model-00002-of-00011.safetensors",
318
+ "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00011.safetensors",
319
+ "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00011.safetensors",
320
+ "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00011.safetensors",
321
+ "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00011.safetensors",
322
+ "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00011.safetensors",
323
+ "model.layers.5.input_layernorm.weight": "model-00002-of-00011.safetensors",
324
+ "model.layers.5.mlp.down_proj.weight": "model-00002-of-00011.safetensors",
325
+ "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00011.safetensors",
326
+ "model.layers.5.mlp.up_proj.weight": "model-00002-of-00011.safetensors",
327
+ "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00011.safetensors",
328
+ "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00011.safetensors",
329
+ "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00011.safetensors",
330
+ "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00011.safetensors",
331
+ "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00011.safetensors",
332
+ "model.layers.6.input_layernorm.weight": "model-00002-of-00011.safetensors",
333
+ "model.layers.6.mlp.down_proj.weight": "model-00002-of-00011.safetensors",
334
+ "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00011.safetensors",
335
+ "model.layers.6.mlp.up_proj.weight": "model-00002-of-00011.safetensors",
336
+ "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00011.safetensors",
337
+ "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00011.safetensors",
338
+ "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00011.safetensors",
339
+ "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00011.safetensors",
340
+ "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00011.safetensors",
341
+ "model.layers.7.input_layernorm.weight": "model-00003-of-00011.safetensors",
342
+ "model.layers.7.mlp.down_proj.weight": "model-00003-of-00011.safetensors",
343
+ "model.layers.7.mlp.gate_proj.weight": "model-00003-of-00011.safetensors",
344
+ "model.layers.7.mlp.up_proj.weight": "model-00003-of-00011.safetensors",
345
+ "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00011.safetensors",
346
+ "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00011.safetensors",
347
+ "model.layers.7.self_attn.o_proj.weight": "model-00003-of-00011.safetensors",
348
+ "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00011.safetensors",
349
+ "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00011.safetensors",
350
+ "model.layers.8.input_layernorm.weight": "model-00003-of-00011.safetensors",
351
+ "model.layers.8.mlp.down_proj.weight": "model-00003-of-00011.safetensors",
352
+ "model.layers.8.mlp.gate_proj.weight": "model-00003-of-00011.safetensors",
353
+ "model.layers.8.mlp.up_proj.weight": "model-00003-of-00011.safetensors",
354
+ "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00011.safetensors",
355
+ "model.layers.8.self_attn.k_proj.weight": "model-00003-of-00011.safetensors",
356
+ "model.layers.8.self_attn.o_proj.weight": "model-00003-of-00011.safetensors",
357
+ "model.layers.8.self_attn.q_proj.weight": "model-00003-of-00011.safetensors",
358
+ "model.layers.8.self_attn.v_proj.weight": "model-00003-of-00011.safetensors",
359
+ "model.layers.9.input_layernorm.weight": "model-00003-of-00011.safetensors",
360
+ "model.layers.9.mlp.down_proj.weight": "model-00003-of-00011.safetensors",
361
+ "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00011.safetensors",
362
+ "model.layers.9.mlp.up_proj.weight": "model-00003-of-00011.safetensors",
363
+ "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00011.safetensors",
364
+ "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00011.safetensors",
365
+ "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00011.safetensors",
366
+ "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00011.safetensors",
367
+ "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00011.safetensors",
368
+ "model.norm.weight": "model-00011-of-00011.safetensors"
369
+ }
370
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "▁<PRE>",
4
+ "▁<MID>",
5
+ "▁<SUF>",
6
+ "▁<EOT>"
7
+ ],
8
+ "bos_token": {
9
+ "content": "<s>",
10
+ "lstrip": false,
11
+ "normalized": false,
12
+ "rstrip": false,
13
+ "single_word": false
14
+ },
15
+ "eos_token": {
16
+ "content": "</s>",
17
+ "lstrip": false,
18
+ "normalized": false,
19
+ "rstrip": false,
20
+ "single_word": false
21
+ },
22
+ "pad_token": "</s>",
23
+ "unk_token": {
24
+ "content": "<unk>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,83 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<unk>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "32007": {
30
+ "content": "▁<PRE>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "32008": {
38
+ "content": "▁<SUF>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "32009": {
46
+ "content": "▁<MID>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "32010": {
54
+ "content": "▁<EOT>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ }
61
+ },
62
+ "additional_special_tokens": [
63
+ "▁<PRE>",
64
+ "▁<MID>",
65
+ "▁<SUF>",
66
+ "▁<EOT>"
67
+ ],
68
+ "bos_token": "<s>",
69
+ "clean_up_tokenization_spaces": false,
70
+ "eos_token": "</s>",
71
+ "eot_token": "▁<EOT>",
72
+ "fill_token": "<FILL_ME>",
73
+ "legacy": null,
74
+ "middle_token": "▁<MID>",
75
+ "model_max_length": 1000000000000000019884624838656,
76
+ "pad_token": "</s>",
77
+ "prefix_token": "▁<PRE>",
78
+ "sp_model_kwargs": {},
79
+ "suffix_token": "▁<SUF>",
80
+ "tokenizer_class": "LlamaTokenizer",
81
+ "unk_token": "<unk>",
82
+ "use_default_system_prompt": false
83
+ }