lanczos commited on
Commit
a6094d6
·
verified ·
1 Parent(s): 2296aac

Upload folder using huggingface_hub

Browse files
config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "fla-hub/gla-7B-mistral-20B",
3
+ "architectures": [
4
+ "GLAForCausalLM"
5
+ ],
6
+ "attn": null,
7
+ "attn_mode": "chunk",
8
+ "bos_token_id": 1,
9
+ "clamp_min": null,
10
+ "conv_size": 4,
11
+ "elementwise_affine": true,
12
+ "eos_token_id": 2,
13
+ "expand_k": 1,
14
+ "expand_v": 1,
15
+ "feature_map": "relu",
16
+ "fuse_cross_entropy": true,
17
+ "fuse_norm": true,
18
+ "hidden_act": "swish",
19
+ "hidden_ratio": 4,
20
+ "hidden_size": 4096,
21
+ "initializer_range": 0.02,
22
+ "intermediate_size": 14336,
23
+ "max_position_embeddings": 32768,
24
+ "model_type": "gla",
25
+ "norm_eps": 1e-05,
26
+ "num_heads": 32,
27
+ "num_hidden_layers": 32,
28
+ "num_kv_heads": 8,
29
+ "share_conv_kernel": true,
30
+ "tie_word_embeddings": false,
31
+ "torch_dtype": "float32",
32
+ "transformers_version": "4.48.1",
33
+ "use_cache": false,
34
+ "use_gk": true,
35
+ "use_gv": false,
36
+ "use_output_gate": false,
37
+ "use_short_conv": false,
38
+ "vocab_size": 32000
39
+ }
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": "4.48.1"
6
+ }
pytorch_model-00001-of-00006.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c90f40499e36f2c9594e2937c7a57800e31f5dc6a4d2daa2e97b400c4480e2e
3
+ size 4989225442
pytorch_model-00002-of-00006.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:451accefffd2b4d62f63b4e90213db4ec392f2572d5b0c80e7e3dafd98a0ef37
3
+ size 4900812318
pytorch_model-00003-of-00006.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cb85c69ca416c3bc8214d0e8a5b332f0eed7887fcae4deb52d64d89edfd11e01
3
+ size 4766945404
pytorch_model-00004-of-00006.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:11e82ca468a24c049716e2475f3593c91d1c7d4727a615b554dbd8c300d70c3a
3
+ size 4833685608
pytorch_model-00005-of-00006.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:76f2610803f4bb7ad7edadf480d2bd761b4d9f2f8ed026bb3afdb2c965783792
3
+ size 4766945404
pytorch_model-00006-of-00006.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f6922cc31dbe30c3bf20d6c16bf3450ecfcdb8a5d864b4f4589524c45e1310f4
3
+ size 4720087458
pytorch_model.bin.index.json ADDED
@@ -0,0 +1,394 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 28977561600
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "pytorch_model-00006-of-00006.bin",
7
+ "model.embeddings.weight": "pytorch_model-00001-of-00006.bin",
8
+ "model.layers.0.attn.g_norm.weight": "pytorch_model-00001-of-00006.bin",
9
+ "model.layers.0.attn.gk_proj.0.weight": "pytorch_model-00001-of-00006.bin",
10
+ "model.layers.0.attn.gk_proj.1.bias": "pytorch_model-00001-of-00006.bin",
11
+ "model.layers.0.attn.gk_proj.1.weight": "pytorch_model-00001-of-00006.bin",
12
+ "model.layers.0.attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
13
+ "model.layers.0.attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
14
+ "model.layers.0.attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
15
+ "model.layers.0.attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
16
+ "model.layers.0.attn_norm.weight": "pytorch_model-00001-of-00006.bin",
17
+ "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin",
18
+ "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin",
19
+ "model.layers.0.mlp_norm.weight": "pytorch_model-00001-of-00006.bin",
20
+ "model.layers.1.attn.g_norm.weight": "pytorch_model-00001-of-00006.bin",
21
+ "model.layers.1.attn.gk_proj.0.weight": "pytorch_model-00001-of-00006.bin",
22
+ "model.layers.1.attn.gk_proj.1.bias": "pytorch_model-00001-of-00006.bin",
23
+ "model.layers.1.attn.gk_proj.1.weight": "pytorch_model-00001-of-00006.bin",
24
+ "model.layers.1.attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
25
+ "model.layers.1.attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
26
+ "model.layers.1.attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
27
+ "model.layers.1.attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
28
+ "model.layers.1.attn_norm.weight": "pytorch_model-00001-of-00006.bin",
29
+ "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin",
30
+ "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin",
31
+ "model.layers.1.mlp_norm.weight": "pytorch_model-00001-of-00006.bin",
32
+ "model.layers.10.attn.g_norm.weight": "pytorch_model-00002-of-00006.bin",
33
+ "model.layers.10.attn.gk_proj.0.weight": "pytorch_model-00002-of-00006.bin",
34
+ "model.layers.10.attn.gk_proj.1.bias": "pytorch_model-00002-of-00006.bin",
35
+ "model.layers.10.attn.gk_proj.1.weight": "pytorch_model-00002-of-00006.bin",
36
+ "model.layers.10.attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
37
+ "model.layers.10.attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
38
+ "model.layers.10.attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
39
+ "model.layers.10.attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
40
+ "model.layers.10.attn_norm.weight": "pytorch_model-00002-of-00006.bin",
41
+ "model.layers.10.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
42
+ "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
43
+ "model.layers.10.mlp_norm.weight": "pytorch_model-00002-of-00006.bin",
44
+ "model.layers.11.attn.g_norm.weight": "pytorch_model-00003-of-00006.bin",
45
+ "model.layers.11.attn.gk_proj.0.weight": "pytorch_model-00003-of-00006.bin",
46
+ "model.layers.11.attn.gk_proj.1.bias": "pytorch_model-00003-of-00006.bin",
47
+ "model.layers.11.attn.gk_proj.1.weight": "pytorch_model-00003-of-00006.bin",
48
+ "model.layers.11.attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
49
+ "model.layers.11.attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
50
+ "model.layers.11.attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
51
+ "model.layers.11.attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
52
+ "model.layers.11.attn_norm.weight": "pytorch_model-00003-of-00006.bin",
53
+ "model.layers.11.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
54
+ "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
55
+ "model.layers.11.mlp_norm.weight": "pytorch_model-00003-of-00006.bin",
56
+ "model.layers.12.attn.g_norm.weight": "pytorch_model-00003-of-00006.bin",
57
+ "model.layers.12.attn.gk_proj.0.weight": "pytorch_model-00003-of-00006.bin",
58
+ "model.layers.12.attn.gk_proj.1.bias": "pytorch_model-00003-of-00006.bin",
59
+ "model.layers.12.attn.gk_proj.1.weight": "pytorch_model-00003-of-00006.bin",
60
+ "model.layers.12.attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
61
+ "model.layers.12.attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
62
+ "model.layers.12.attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
63
+ "model.layers.12.attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
64
+ "model.layers.12.attn_norm.weight": "pytorch_model-00003-of-00006.bin",
65
+ "model.layers.12.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
66
+ "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
67
+ "model.layers.12.mlp_norm.weight": "pytorch_model-00003-of-00006.bin",
68
+ "model.layers.13.attn.g_norm.weight": "pytorch_model-00003-of-00006.bin",
69
+ "model.layers.13.attn.gk_proj.0.weight": "pytorch_model-00003-of-00006.bin",
70
+ "model.layers.13.attn.gk_proj.1.bias": "pytorch_model-00003-of-00006.bin",
71
+ "model.layers.13.attn.gk_proj.1.weight": "pytorch_model-00003-of-00006.bin",
72
+ "model.layers.13.attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
73
+ "model.layers.13.attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
74
+ "model.layers.13.attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
75
+ "model.layers.13.attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
76
+ "model.layers.13.attn_norm.weight": "pytorch_model-00003-of-00006.bin",
77
+ "model.layers.13.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
78
+ "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
79
+ "model.layers.13.mlp_norm.weight": "pytorch_model-00003-of-00006.bin",
80
+ "model.layers.14.attn.g_norm.weight": "pytorch_model-00003-of-00006.bin",
81
+ "model.layers.14.attn.gk_proj.0.weight": "pytorch_model-00003-of-00006.bin",
82
+ "model.layers.14.attn.gk_proj.1.bias": "pytorch_model-00003-of-00006.bin",
83
+ "model.layers.14.attn.gk_proj.1.weight": "pytorch_model-00003-of-00006.bin",
84
+ "model.layers.14.attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
85
+ "model.layers.14.attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
86
+ "model.layers.14.attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
87
+ "model.layers.14.attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
88
+ "model.layers.14.attn_norm.weight": "pytorch_model-00003-of-00006.bin",
89
+ "model.layers.14.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
90
+ "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
91
+ "model.layers.14.mlp_norm.weight": "pytorch_model-00003-of-00006.bin",
92
+ "model.layers.15.attn.g_norm.weight": "pytorch_model-00003-of-00006.bin",
93
+ "model.layers.15.attn.gk_proj.0.weight": "pytorch_model-00003-of-00006.bin",
94
+ "model.layers.15.attn.gk_proj.1.bias": "pytorch_model-00003-of-00006.bin",
95
+ "model.layers.15.attn.gk_proj.1.weight": "pytorch_model-00003-of-00006.bin",
96
+ "model.layers.15.attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
97
+ "model.layers.15.attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
98
+ "model.layers.15.attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
99
+ "model.layers.15.attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
100
+ "model.layers.15.attn_norm.weight": "pytorch_model-00003-of-00006.bin",
101
+ "model.layers.15.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
102
+ "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
103
+ "model.layers.15.mlp_norm.weight": "pytorch_model-00003-of-00006.bin",
104
+ "model.layers.16.attn.g_norm.weight": "pytorch_model-00003-of-00006.bin",
105
+ "model.layers.16.attn.gk_proj.0.weight": "pytorch_model-00003-of-00006.bin",
106
+ "model.layers.16.attn.gk_proj.1.bias": "pytorch_model-00003-of-00006.bin",
107
+ "model.layers.16.attn.gk_proj.1.weight": "pytorch_model-00003-of-00006.bin",
108
+ "model.layers.16.attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
109
+ "model.layers.16.attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
110
+ "model.layers.16.attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
111
+ "model.layers.16.attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
112
+ "model.layers.16.attn_norm.weight": "pytorch_model-00003-of-00006.bin",
113
+ "model.layers.16.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
114
+ "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
115
+ "model.layers.16.mlp_norm.weight": "pytorch_model-00003-of-00006.bin",
116
+ "model.layers.17.attn.g_norm.weight": "pytorch_model-00004-of-00006.bin",
117
+ "model.layers.17.attn.gk_proj.0.weight": "pytorch_model-00004-of-00006.bin",
118
+ "model.layers.17.attn.gk_proj.1.bias": "pytorch_model-00004-of-00006.bin",
119
+ "model.layers.17.attn.gk_proj.1.weight": "pytorch_model-00004-of-00006.bin",
120
+ "model.layers.17.attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
121
+ "model.layers.17.attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
122
+ "model.layers.17.attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
123
+ "model.layers.17.attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
124
+ "model.layers.17.attn_norm.weight": "pytorch_model-00004-of-00006.bin",
125
+ "model.layers.17.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
126
+ "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
127
+ "model.layers.17.mlp_norm.weight": "pytorch_model-00004-of-00006.bin",
128
+ "model.layers.18.attn.g_norm.weight": "pytorch_model-00004-of-00006.bin",
129
+ "model.layers.18.attn.gk_proj.0.weight": "pytorch_model-00004-of-00006.bin",
130
+ "model.layers.18.attn.gk_proj.1.bias": "pytorch_model-00004-of-00006.bin",
131
+ "model.layers.18.attn.gk_proj.1.weight": "pytorch_model-00004-of-00006.bin",
132
+ "model.layers.18.attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
133
+ "model.layers.18.attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
134
+ "model.layers.18.attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
135
+ "model.layers.18.attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
136
+ "model.layers.18.attn_norm.weight": "pytorch_model-00004-of-00006.bin",
137
+ "model.layers.18.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
138
+ "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
139
+ "model.layers.18.mlp_norm.weight": "pytorch_model-00004-of-00006.bin",
140
+ "model.layers.19.attn.g_norm.weight": "pytorch_model-00004-of-00006.bin",
141
+ "model.layers.19.attn.gk_proj.0.weight": "pytorch_model-00004-of-00006.bin",
142
+ "model.layers.19.attn.gk_proj.1.bias": "pytorch_model-00004-of-00006.bin",
143
+ "model.layers.19.attn.gk_proj.1.weight": "pytorch_model-00004-of-00006.bin",
144
+ "model.layers.19.attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
145
+ "model.layers.19.attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
146
+ "model.layers.19.attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
147
+ "model.layers.19.attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
148
+ "model.layers.19.attn_norm.weight": "pytorch_model-00004-of-00006.bin",
149
+ "model.layers.19.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
150
+ "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
151
+ "model.layers.19.mlp_norm.weight": "pytorch_model-00004-of-00006.bin",
152
+ "model.layers.2.attn.g_norm.weight": "pytorch_model-00001-of-00006.bin",
153
+ "model.layers.2.attn.gk_proj.0.weight": "pytorch_model-00001-of-00006.bin",
154
+ "model.layers.2.attn.gk_proj.1.bias": "pytorch_model-00001-of-00006.bin",
155
+ "model.layers.2.attn.gk_proj.1.weight": "pytorch_model-00001-of-00006.bin",
156
+ "model.layers.2.attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
157
+ "model.layers.2.attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
158
+ "model.layers.2.attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
159
+ "model.layers.2.attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
160
+ "model.layers.2.attn_norm.weight": "pytorch_model-00001-of-00006.bin",
161
+ "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin",
162
+ "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin",
163
+ "model.layers.2.mlp_norm.weight": "pytorch_model-00001-of-00006.bin",
164
+ "model.layers.20.attn.g_norm.weight": "pytorch_model-00004-of-00006.bin",
165
+ "model.layers.20.attn.gk_proj.0.weight": "pytorch_model-00004-of-00006.bin",
166
+ "model.layers.20.attn.gk_proj.1.bias": "pytorch_model-00004-of-00006.bin",
167
+ "model.layers.20.attn.gk_proj.1.weight": "pytorch_model-00004-of-00006.bin",
168
+ "model.layers.20.attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
169
+ "model.layers.20.attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
170
+ "model.layers.20.attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
171
+ "model.layers.20.attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
172
+ "model.layers.20.attn_norm.weight": "pytorch_model-00004-of-00006.bin",
173
+ "model.layers.20.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
174
+ "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
175
+ "model.layers.20.mlp_norm.weight": "pytorch_model-00004-of-00006.bin",
176
+ "model.layers.21.attn.g_norm.weight": "pytorch_model-00004-of-00006.bin",
177
+ "model.layers.21.attn.gk_proj.0.weight": "pytorch_model-00004-of-00006.bin",
178
+ "model.layers.21.attn.gk_proj.1.bias": "pytorch_model-00004-of-00006.bin",
179
+ "model.layers.21.attn.gk_proj.1.weight": "pytorch_model-00004-of-00006.bin",
180
+ "model.layers.21.attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
181
+ "model.layers.21.attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
182
+ "model.layers.21.attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
183
+ "model.layers.21.attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
184
+ "model.layers.21.attn_norm.weight": "pytorch_model-00004-of-00006.bin",
185
+ "model.layers.21.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
186
+ "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
187
+ "model.layers.21.mlp_norm.weight": "pytorch_model-00004-of-00006.bin",
188
+ "model.layers.22.attn.g_norm.weight": "pytorch_model-00005-of-00006.bin",
189
+ "model.layers.22.attn.gk_proj.0.weight": "pytorch_model-00005-of-00006.bin",
190
+ "model.layers.22.attn.gk_proj.1.bias": "pytorch_model-00005-of-00006.bin",
191
+ "model.layers.22.attn.gk_proj.1.weight": "pytorch_model-00005-of-00006.bin",
192
+ "model.layers.22.attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
193
+ "model.layers.22.attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
194
+ "model.layers.22.attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
195
+ "model.layers.22.attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
196
+ "model.layers.22.attn_norm.weight": "pytorch_model-00005-of-00006.bin",
197
+ "model.layers.22.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
198
+ "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
199
+ "model.layers.22.mlp_norm.weight": "pytorch_model-00005-of-00006.bin",
200
+ "model.layers.23.attn.g_norm.weight": "pytorch_model-00005-of-00006.bin",
201
+ "model.layers.23.attn.gk_proj.0.weight": "pytorch_model-00005-of-00006.bin",
202
+ "model.layers.23.attn.gk_proj.1.bias": "pytorch_model-00005-of-00006.bin",
203
+ "model.layers.23.attn.gk_proj.1.weight": "pytorch_model-00005-of-00006.bin",
204
+ "model.layers.23.attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
205
+ "model.layers.23.attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
206
+ "model.layers.23.attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
207
+ "model.layers.23.attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
208
+ "model.layers.23.attn_norm.weight": "pytorch_model-00005-of-00006.bin",
209
+ "model.layers.23.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
210
+ "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
211
+ "model.layers.23.mlp_norm.weight": "pytorch_model-00005-of-00006.bin",
212
+ "model.layers.24.attn.g_norm.weight": "pytorch_model-00005-of-00006.bin",
213
+ "model.layers.24.attn.gk_proj.0.weight": "pytorch_model-00005-of-00006.bin",
214
+ "model.layers.24.attn.gk_proj.1.bias": "pytorch_model-00005-of-00006.bin",
215
+ "model.layers.24.attn.gk_proj.1.weight": "pytorch_model-00005-of-00006.bin",
216
+ "model.layers.24.attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
217
+ "model.layers.24.attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
218
+ "model.layers.24.attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
219
+ "model.layers.24.attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
220
+ "model.layers.24.attn_norm.weight": "pytorch_model-00005-of-00006.bin",
221
+ "model.layers.24.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
222
+ "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
223
+ "model.layers.24.mlp_norm.weight": "pytorch_model-00005-of-00006.bin",
224
+ "model.layers.25.attn.g_norm.weight": "pytorch_model-00005-of-00006.bin",
225
+ "model.layers.25.attn.gk_proj.0.weight": "pytorch_model-00005-of-00006.bin",
226
+ "model.layers.25.attn.gk_proj.1.bias": "pytorch_model-00005-of-00006.bin",
227
+ "model.layers.25.attn.gk_proj.1.weight": "pytorch_model-00005-of-00006.bin",
228
+ "model.layers.25.attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
229
+ "model.layers.25.attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
230
+ "model.layers.25.attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
231
+ "model.layers.25.attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
232
+ "model.layers.25.attn_norm.weight": "pytorch_model-00005-of-00006.bin",
233
+ "model.layers.25.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
234
+ "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
235
+ "model.layers.25.mlp_norm.weight": "pytorch_model-00005-of-00006.bin",
236
+ "model.layers.26.attn.g_norm.weight": "pytorch_model-00005-of-00006.bin",
237
+ "model.layers.26.attn.gk_proj.0.weight": "pytorch_model-00005-of-00006.bin",
238
+ "model.layers.26.attn.gk_proj.1.bias": "pytorch_model-00005-of-00006.bin",
239
+ "model.layers.26.attn.gk_proj.1.weight": "pytorch_model-00005-of-00006.bin",
240
+ "model.layers.26.attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
241
+ "model.layers.26.attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
242
+ "model.layers.26.attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
243
+ "model.layers.26.attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
244
+ "model.layers.26.attn_norm.weight": "pytorch_model-00005-of-00006.bin",
245
+ "model.layers.26.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
246
+ "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
247
+ "model.layers.26.mlp_norm.weight": "pytorch_model-00005-of-00006.bin",
248
+ "model.layers.27.attn.g_norm.weight": "pytorch_model-00005-of-00006.bin",
249
+ "model.layers.27.attn.gk_proj.0.weight": "pytorch_model-00005-of-00006.bin",
250
+ "model.layers.27.attn.gk_proj.1.bias": "pytorch_model-00005-of-00006.bin",
251
+ "model.layers.27.attn.gk_proj.1.weight": "pytorch_model-00005-of-00006.bin",
252
+ "model.layers.27.attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
253
+ "model.layers.27.attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
254
+ "model.layers.27.attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
255
+ "model.layers.27.attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
256
+ "model.layers.27.attn_norm.weight": "pytorch_model-00005-of-00006.bin",
257
+ "model.layers.27.mlp.down_proj.weight": "pytorch_model-00006-of-00006.bin",
258
+ "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00006-of-00006.bin",
259
+ "model.layers.27.mlp_norm.weight": "pytorch_model-00005-of-00006.bin",
260
+ "model.layers.28.attn.g_norm.weight": "pytorch_model-00006-of-00006.bin",
261
+ "model.layers.28.attn.gk_proj.0.weight": "pytorch_model-00006-of-00006.bin",
262
+ "model.layers.28.attn.gk_proj.1.bias": "pytorch_model-00006-of-00006.bin",
263
+ "model.layers.28.attn.gk_proj.1.weight": "pytorch_model-00006-of-00006.bin",
264
+ "model.layers.28.attn.k_proj.weight": "pytorch_model-00006-of-00006.bin",
265
+ "model.layers.28.attn.o_proj.weight": "pytorch_model-00006-of-00006.bin",
266
+ "model.layers.28.attn.q_proj.weight": "pytorch_model-00006-of-00006.bin",
267
+ "model.layers.28.attn.v_proj.weight": "pytorch_model-00006-of-00006.bin",
268
+ "model.layers.28.attn_norm.weight": "pytorch_model-00006-of-00006.bin",
269
+ "model.layers.28.mlp.down_proj.weight": "pytorch_model-00006-of-00006.bin",
270
+ "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00006-of-00006.bin",
271
+ "model.layers.28.mlp_norm.weight": "pytorch_model-00006-of-00006.bin",
272
+ "model.layers.29.attn.g_norm.weight": "pytorch_model-00006-of-00006.bin",
273
+ "model.layers.29.attn.gk_proj.0.weight": "pytorch_model-00006-of-00006.bin",
274
+ "model.layers.29.attn.gk_proj.1.bias": "pytorch_model-00006-of-00006.bin",
275
+ "model.layers.29.attn.gk_proj.1.weight": "pytorch_model-00006-of-00006.bin",
276
+ "model.layers.29.attn.k_proj.weight": "pytorch_model-00006-of-00006.bin",
277
+ "model.layers.29.attn.o_proj.weight": "pytorch_model-00006-of-00006.bin",
278
+ "model.layers.29.attn.q_proj.weight": "pytorch_model-00006-of-00006.bin",
279
+ "model.layers.29.attn.v_proj.weight": "pytorch_model-00006-of-00006.bin",
280
+ "model.layers.29.attn_norm.weight": "pytorch_model-00006-of-00006.bin",
281
+ "model.layers.29.mlp.down_proj.weight": "pytorch_model-00006-of-00006.bin",
282
+ "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00006-of-00006.bin",
283
+ "model.layers.29.mlp_norm.weight": "pytorch_model-00006-of-00006.bin",
284
+ "model.layers.3.attn.g_norm.weight": "pytorch_model-00001-of-00006.bin",
285
+ "model.layers.3.attn.gk_proj.0.weight": "pytorch_model-00001-of-00006.bin",
286
+ "model.layers.3.attn.gk_proj.1.bias": "pytorch_model-00001-of-00006.bin",
287
+ "model.layers.3.attn.gk_proj.1.weight": "pytorch_model-00001-of-00006.bin",
288
+ "model.layers.3.attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
289
+ "model.layers.3.attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
290
+ "model.layers.3.attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
291
+ "model.layers.3.attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
292
+ "model.layers.3.attn_norm.weight": "pytorch_model-00001-of-00006.bin",
293
+ "model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin",
294
+ "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin",
295
+ "model.layers.3.mlp_norm.weight": "pytorch_model-00001-of-00006.bin",
296
+ "model.layers.30.attn.g_norm.weight": "pytorch_model-00006-of-00006.bin",
297
+ "model.layers.30.attn.gk_proj.0.weight": "pytorch_model-00006-of-00006.bin",
298
+ "model.layers.30.attn.gk_proj.1.bias": "pytorch_model-00006-of-00006.bin",
299
+ "model.layers.30.attn.gk_proj.1.weight": "pytorch_model-00006-of-00006.bin",
300
+ "model.layers.30.attn.k_proj.weight": "pytorch_model-00006-of-00006.bin",
301
+ "model.layers.30.attn.o_proj.weight": "pytorch_model-00006-of-00006.bin",
302
+ "model.layers.30.attn.q_proj.weight": "pytorch_model-00006-of-00006.bin",
303
+ "model.layers.30.attn.v_proj.weight": "pytorch_model-00006-of-00006.bin",
304
+ "model.layers.30.attn_norm.weight": "pytorch_model-00006-of-00006.bin",
305
+ "model.layers.30.mlp.down_proj.weight": "pytorch_model-00006-of-00006.bin",
306
+ "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00006-of-00006.bin",
307
+ "model.layers.30.mlp_norm.weight": "pytorch_model-00006-of-00006.bin",
308
+ "model.layers.31.attn.g_norm.weight": "pytorch_model-00006-of-00006.bin",
309
+ "model.layers.31.attn.gk_proj.0.weight": "pytorch_model-00006-of-00006.bin",
310
+ "model.layers.31.attn.gk_proj.1.bias": "pytorch_model-00006-of-00006.bin",
311
+ "model.layers.31.attn.gk_proj.1.weight": "pytorch_model-00006-of-00006.bin",
312
+ "model.layers.31.attn.k_proj.weight": "pytorch_model-00006-of-00006.bin",
313
+ "model.layers.31.attn.o_proj.weight": "pytorch_model-00006-of-00006.bin",
314
+ "model.layers.31.attn.q_proj.weight": "pytorch_model-00006-of-00006.bin",
315
+ "model.layers.31.attn.v_proj.weight": "pytorch_model-00006-of-00006.bin",
316
+ "model.layers.31.attn_norm.weight": "pytorch_model-00006-of-00006.bin",
317
+ "model.layers.31.mlp.down_proj.weight": "pytorch_model-00006-of-00006.bin",
318
+ "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00006-of-00006.bin",
319
+ "model.layers.31.mlp_norm.weight": "pytorch_model-00006-of-00006.bin",
320
+ "model.layers.4.attn.g_norm.weight": "pytorch_model-00001-of-00006.bin",
321
+ "model.layers.4.attn.gk_proj.0.weight": "pytorch_model-00001-of-00006.bin",
322
+ "model.layers.4.attn.gk_proj.1.bias": "pytorch_model-00001-of-00006.bin",
323
+ "model.layers.4.attn.gk_proj.1.weight": "pytorch_model-00001-of-00006.bin",
324
+ "model.layers.4.attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
325
+ "model.layers.4.attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
326
+ "model.layers.4.attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
327
+ "model.layers.4.attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
328
+ "model.layers.4.attn_norm.weight": "pytorch_model-00001-of-00006.bin",
329
+ "model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin",
330
+ "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin",
331
+ "model.layers.4.mlp_norm.weight": "pytorch_model-00001-of-00006.bin",
332
+ "model.layers.5.attn.g_norm.weight": "pytorch_model-00002-of-00006.bin",
333
+ "model.layers.5.attn.gk_proj.0.weight": "pytorch_model-00001-of-00006.bin",
334
+ "model.layers.5.attn.gk_proj.1.bias": "pytorch_model-00001-of-00006.bin",
335
+ "model.layers.5.attn.gk_proj.1.weight": "pytorch_model-00001-of-00006.bin",
336
+ "model.layers.5.attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
337
+ "model.layers.5.attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
338
+ "model.layers.5.attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
339
+ "model.layers.5.attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
340
+ "model.layers.5.attn_norm.weight": "pytorch_model-00001-of-00006.bin",
341
+ "model.layers.5.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
342
+ "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
343
+ "model.layers.5.mlp_norm.weight": "pytorch_model-00002-of-00006.bin",
344
+ "model.layers.6.attn.g_norm.weight": "pytorch_model-00002-of-00006.bin",
345
+ "model.layers.6.attn.gk_proj.0.weight": "pytorch_model-00002-of-00006.bin",
346
+ "model.layers.6.attn.gk_proj.1.bias": "pytorch_model-00002-of-00006.bin",
347
+ "model.layers.6.attn.gk_proj.1.weight": "pytorch_model-00002-of-00006.bin",
348
+ "model.layers.6.attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
349
+ "model.layers.6.attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
350
+ "model.layers.6.attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
351
+ "model.layers.6.attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
352
+ "model.layers.6.attn_norm.weight": "pytorch_model-00002-of-00006.bin",
353
+ "model.layers.6.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
354
+ "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
355
+ "model.layers.6.mlp_norm.weight": "pytorch_model-00002-of-00006.bin",
356
+ "model.layers.7.attn.g_norm.weight": "pytorch_model-00002-of-00006.bin",
357
+ "model.layers.7.attn.gk_proj.0.weight": "pytorch_model-00002-of-00006.bin",
358
+ "model.layers.7.attn.gk_proj.1.bias": "pytorch_model-00002-of-00006.bin",
359
+ "model.layers.7.attn.gk_proj.1.weight": "pytorch_model-00002-of-00006.bin",
360
+ "model.layers.7.attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
361
+ "model.layers.7.attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
362
+ "model.layers.7.attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
363
+ "model.layers.7.attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
364
+ "model.layers.7.attn_norm.weight": "pytorch_model-00002-of-00006.bin",
365
+ "model.layers.7.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
366
+ "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
367
+ "model.layers.7.mlp_norm.weight": "pytorch_model-00002-of-00006.bin",
368
+ "model.layers.8.attn.g_norm.weight": "pytorch_model-00002-of-00006.bin",
369
+ "model.layers.8.attn.gk_proj.0.weight": "pytorch_model-00002-of-00006.bin",
370
+ "model.layers.8.attn.gk_proj.1.bias": "pytorch_model-00002-of-00006.bin",
371
+ "model.layers.8.attn.gk_proj.1.weight": "pytorch_model-00002-of-00006.bin",
372
+ "model.layers.8.attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
373
+ "model.layers.8.attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
374
+ "model.layers.8.attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
375
+ "model.layers.8.attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
376
+ "model.layers.8.attn_norm.weight": "pytorch_model-00002-of-00006.bin",
377
+ "model.layers.8.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
378
+ "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
379
+ "model.layers.8.mlp_norm.weight": "pytorch_model-00002-of-00006.bin",
380
+ "model.layers.9.attn.g_norm.weight": "pytorch_model-00002-of-00006.bin",
381
+ "model.layers.9.attn.gk_proj.0.weight": "pytorch_model-00002-of-00006.bin",
382
+ "model.layers.9.attn.gk_proj.1.bias": "pytorch_model-00002-of-00006.bin",
383
+ "model.layers.9.attn.gk_proj.1.weight": "pytorch_model-00002-of-00006.bin",
384
+ "model.layers.9.attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
385
+ "model.layers.9.attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
386
+ "model.layers.9.attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
387
+ "model.layers.9.attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
388
+ "model.layers.9.attn_norm.weight": "pytorch_model-00002-of-00006.bin",
389
+ "model.layers.9.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
390
+ "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
391
+ "model.layers.9.mlp_norm.weight": "pytorch_model-00002-of-00006.bin",
392
+ "model.norm.weight": "pytorch_model-00006-of-00006.bin"
393
+ }
394
+ }
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
+ "unk_token": {
17
+ "content": "<unk>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
3
+ size 493443
tokenizer_config.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": null,
5
+ "added_tokens_decoder": {
6
+ "0": {
7
+ "content": "<unk>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "1": {
15
+ "content": "<s>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "2": {
23
+ "content": "</s>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": false,
27
+ "single_word": false,
28
+ "special": true
29
+ }
30
+ },
31
+ "additional_special_tokens": [],
32
+ "bos_token": "<s>",
33
+ "clean_up_tokenization_spaces": false,
34
+ "eos_token": "</s>",
35
+ "extra_special_tokens": {},
36
+ "legacy": false,
37
+ "model_max_length": 1000000000000000019884624838656,
38
+ "pad_token": null,
39
+ "sp_model_kwargs": {},
40
+ "spaces_between_special_tokens": false,
41
+ "tokenizer_class": "LlamaTokenizer",
42
+ "unk_token": "<unk>",
43
+ "use_default_system_prompt": false
44
+ }