yzhangcs commited on
Commit
671ae86
1 Parent(s): fbd04f2

Upload GSAForCausalLM

Browse files
config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "fla-hub/gsa-2.7B-100B",
3
+ "architectures": [
4
+ "GSAForCausalLM"
5
+ ],
6
+ "bos_token_id": 1,
7
+ "clamp_max": null,
8
+ "clamp_min": null,
9
+ "conv_size": 4,
10
+ "elementwise_affine": false,
11
+ "eos_token_id": 2,
12
+ "expand_k": 1,
13
+ "expand_v": 1,
14
+ "feature_map": "swish",
15
+ "fuse_cross_entropy": true,
16
+ "fuse_norm": true,
17
+ "gate_logit_normalizer": 8,
18
+ "gate_low_rank_dim": null,
19
+ "hidden_act": "swish",
20
+ "hidden_ratio": 4,
21
+ "hidden_size": 2560,
22
+ "initializer_range": 0.02,
23
+ "intermediate_size": null,
24
+ "max_position_embeddings": 2048,
25
+ "model_type": "gsa",
26
+ "norm_eps": 1e-06,
27
+ "norm_first": true,
28
+ "num_heads": 5,
29
+ "num_hidden_layers": 32,
30
+ "num_kv_heads": null,
31
+ "num_slots": 64,
32
+ "pad_token_id": 2,
33
+ "share_conv_kernel": true,
34
+ "tie_word_embeddings": false,
35
+ "torch_dtype": "bfloat16",
36
+ "transformers_version": "4.40.2",
37
+ "use_cache": true,
38
+ "use_norm": true,
39
+ "use_output_gate": false,
40
+ "use_rope": false,
41
+ "use_short_conv": false,
42
+ "vocab_size": 32000
43
+ }
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": "4.40.2"
6
+ }
model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:10a81e67b41435a90b9559f03a44622ea57bba7b538be85a68dcc04c83a1bfc8
3
+ size 4997462776
model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:62fea47173b0014dfe79328d71ea851f1d49f5c90d538e79a9056f41a0fcfb42
3
+ size 458118984
model.safetensors.index.json ADDED
@@ -0,0 +1,298 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 5455549440
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "model-00002-of-00002.safetensors",
7
+ "model.embeddings.weight": "model-00001-of-00002.safetensors",
8
+ "model.layers.0.attn.f_proj.weight": "model-00001-of-00002.safetensors",
9
+ "model.layers.0.attn.k_proj.weight": "model-00001-of-00002.safetensors",
10
+ "model.layers.0.attn.norm.weight": "model-00001-of-00002.safetensors",
11
+ "model.layers.0.attn.o_proj.weight": "model-00001-of-00002.safetensors",
12
+ "model.layers.0.attn.q_proj.weight": "model-00001-of-00002.safetensors",
13
+ "model.layers.0.attn.v_proj.weight": "model-00001-of-00002.safetensors",
14
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
15
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
16
+ "model.layers.0.mlp.norm.weight": "model-00001-of-00002.safetensors",
17
+ "model.layers.1.attn.f_proj.weight": "model-00001-of-00002.safetensors",
18
+ "model.layers.1.attn.k_proj.weight": "model-00001-of-00002.safetensors",
19
+ "model.layers.1.attn.norm.weight": "model-00001-of-00002.safetensors",
20
+ "model.layers.1.attn.o_proj.weight": "model-00001-of-00002.safetensors",
21
+ "model.layers.1.attn.q_proj.weight": "model-00001-of-00002.safetensors",
22
+ "model.layers.1.attn.v_proj.weight": "model-00001-of-00002.safetensors",
23
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
24
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
25
+ "model.layers.1.mlp.norm.weight": "model-00001-of-00002.safetensors",
26
+ "model.layers.10.attn.f_proj.weight": "model-00001-of-00002.safetensors",
27
+ "model.layers.10.attn.k_proj.weight": "model-00001-of-00002.safetensors",
28
+ "model.layers.10.attn.norm.weight": "model-00001-of-00002.safetensors",
29
+ "model.layers.10.attn.o_proj.weight": "model-00001-of-00002.safetensors",
30
+ "model.layers.10.attn.q_proj.weight": "model-00001-of-00002.safetensors",
31
+ "model.layers.10.attn.v_proj.weight": "model-00001-of-00002.safetensors",
32
+ "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
33
+ "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
34
+ "model.layers.10.mlp.norm.weight": "model-00001-of-00002.safetensors",
35
+ "model.layers.11.attn.f_proj.weight": "model-00001-of-00002.safetensors",
36
+ "model.layers.11.attn.k_proj.weight": "model-00001-of-00002.safetensors",
37
+ "model.layers.11.attn.norm.weight": "model-00001-of-00002.safetensors",
38
+ "model.layers.11.attn.o_proj.weight": "model-00001-of-00002.safetensors",
39
+ "model.layers.11.attn.q_proj.weight": "model-00001-of-00002.safetensors",
40
+ "model.layers.11.attn.v_proj.weight": "model-00001-of-00002.safetensors",
41
+ "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
42
+ "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
43
+ "model.layers.11.mlp.norm.weight": "model-00001-of-00002.safetensors",
44
+ "model.layers.12.attn.f_proj.weight": "model-00001-of-00002.safetensors",
45
+ "model.layers.12.attn.k_proj.weight": "model-00001-of-00002.safetensors",
46
+ "model.layers.12.attn.norm.weight": "model-00001-of-00002.safetensors",
47
+ "model.layers.12.attn.o_proj.weight": "model-00001-of-00002.safetensors",
48
+ "model.layers.12.attn.q_proj.weight": "model-00001-of-00002.safetensors",
49
+ "model.layers.12.attn.v_proj.weight": "model-00001-of-00002.safetensors",
50
+ "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
51
+ "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
52
+ "model.layers.12.mlp.norm.weight": "model-00001-of-00002.safetensors",
53
+ "model.layers.13.attn.f_proj.weight": "model-00001-of-00002.safetensors",
54
+ "model.layers.13.attn.k_proj.weight": "model-00001-of-00002.safetensors",
55
+ "model.layers.13.attn.norm.weight": "model-00001-of-00002.safetensors",
56
+ "model.layers.13.attn.o_proj.weight": "model-00001-of-00002.safetensors",
57
+ "model.layers.13.attn.q_proj.weight": "model-00001-of-00002.safetensors",
58
+ "model.layers.13.attn.v_proj.weight": "model-00001-of-00002.safetensors",
59
+ "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
60
+ "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
61
+ "model.layers.13.mlp.norm.weight": "model-00001-of-00002.safetensors",
62
+ "model.layers.14.attn.f_proj.weight": "model-00001-of-00002.safetensors",
63
+ "model.layers.14.attn.k_proj.weight": "model-00001-of-00002.safetensors",
64
+ "model.layers.14.attn.norm.weight": "model-00001-of-00002.safetensors",
65
+ "model.layers.14.attn.o_proj.weight": "model-00001-of-00002.safetensors",
66
+ "model.layers.14.attn.q_proj.weight": "model-00001-of-00002.safetensors",
67
+ "model.layers.14.attn.v_proj.weight": "model-00001-of-00002.safetensors",
68
+ "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
69
+ "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
70
+ "model.layers.14.mlp.norm.weight": "model-00001-of-00002.safetensors",
71
+ "model.layers.15.attn.f_proj.weight": "model-00001-of-00002.safetensors",
72
+ "model.layers.15.attn.k_proj.weight": "model-00001-of-00002.safetensors",
73
+ "model.layers.15.attn.norm.weight": "model-00001-of-00002.safetensors",
74
+ "model.layers.15.attn.o_proj.weight": "model-00001-of-00002.safetensors",
75
+ "model.layers.15.attn.q_proj.weight": "model-00001-of-00002.safetensors",
76
+ "model.layers.15.attn.v_proj.weight": "model-00001-of-00002.safetensors",
77
+ "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
78
+ "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
79
+ "model.layers.15.mlp.norm.weight": "model-00001-of-00002.safetensors",
80
+ "model.layers.16.attn.f_proj.weight": "model-00001-of-00002.safetensors",
81
+ "model.layers.16.attn.k_proj.weight": "model-00001-of-00002.safetensors",
82
+ "model.layers.16.attn.norm.weight": "model-00001-of-00002.safetensors",
83
+ "model.layers.16.attn.o_proj.weight": "model-00001-of-00002.safetensors",
84
+ "model.layers.16.attn.q_proj.weight": "model-00001-of-00002.safetensors",
85
+ "model.layers.16.attn.v_proj.weight": "model-00001-of-00002.safetensors",
86
+ "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
87
+ "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
88
+ "model.layers.16.mlp.norm.weight": "model-00001-of-00002.safetensors",
89
+ "model.layers.17.attn.f_proj.weight": "model-00001-of-00002.safetensors",
90
+ "model.layers.17.attn.k_proj.weight": "model-00001-of-00002.safetensors",
91
+ "model.layers.17.attn.norm.weight": "model-00001-of-00002.safetensors",
92
+ "model.layers.17.attn.o_proj.weight": "model-00001-of-00002.safetensors",
93
+ "model.layers.17.attn.q_proj.weight": "model-00001-of-00002.safetensors",
94
+ "model.layers.17.attn.v_proj.weight": "model-00001-of-00002.safetensors",
95
+ "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
96
+ "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
97
+ "model.layers.17.mlp.norm.weight": "model-00001-of-00002.safetensors",
98
+ "model.layers.18.attn.f_proj.weight": "model-00001-of-00002.safetensors",
99
+ "model.layers.18.attn.k_proj.weight": "model-00001-of-00002.safetensors",
100
+ "model.layers.18.attn.norm.weight": "model-00001-of-00002.safetensors",
101
+ "model.layers.18.attn.o_proj.weight": "model-00001-of-00002.safetensors",
102
+ "model.layers.18.attn.q_proj.weight": "model-00001-of-00002.safetensors",
103
+ "model.layers.18.attn.v_proj.weight": "model-00001-of-00002.safetensors",
104
+ "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
105
+ "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
106
+ "model.layers.18.mlp.norm.weight": "model-00001-of-00002.safetensors",
107
+ "model.layers.19.attn.f_proj.weight": "model-00001-of-00002.safetensors",
108
+ "model.layers.19.attn.k_proj.weight": "model-00001-of-00002.safetensors",
109
+ "model.layers.19.attn.norm.weight": "model-00001-of-00002.safetensors",
110
+ "model.layers.19.attn.o_proj.weight": "model-00001-of-00002.safetensors",
111
+ "model.layers.19.attn.q_proj.weight": "model-00001-of-00002.safetensors",
112
+ "model.layers.19.attn.v_proj.weight": "model-00001-of-00002.safetensors",
113
+ "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
114
+ "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
115
+ "model.layers.19.mlp.norm.weight": "model-00001-of-00002.safetensors",
116
+ "model.layers.2.attn.f_proj.weight": "model-00001-of-00002.safetensors",
117
+ "model.layers.2.attn.k_proj.weight": "model-00001-of-00002.safetensors",
118
+ "model.layers.2.attn.norm.weight": "model-00001-of-00002.safetensors",
119
+ "model.layers.2.attn.o_proj.weight": "model-00001-of-00002.safetensors",
120
+ "model.layers.2.attn.q_proj.weight": "model-00001-of-00002.safetensors",
121
+ "model.layers.2.attn.v_proj.weight": "model-00001-of-00002.safetensors",
122
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
123
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
124
+ "model.layers.2.mlp.norm.weight": "model-00001-of-00002.safetensors",
125
+ "model.layers.20.attn.f_proj.weight": "model-00001-of-00002.safetensors",
126
+ "model.layers.20.attn.k_proj.weight": "model-00001-of-00002.safetensors",
127
+ "model.layers.20.attn.norm.weight": "model-00001-of-00002.safetensors",
128
+ "model.layers.20.attn.o_proj.weight": "model-00001-of-00002.safetensors",
129
+ "model.layers.20.attn.q_proj.weight": "model-00001-of-00002.safetensors",
130
+ "model.layers.20.attn.v_proj.weight": "model-00001-of-00002.safetensors",
131
+ "model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
132
+ "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
133
+ "model.layers.20.mlp.norm.weight": "model-00001-of-00002.safetensors",
134
+ "model.layers.21.attn.f_proj.weight": "model-00001-of-00002.safetensors",
135
+ "model.layers.21.attn.k_proj.weight": "model-00001-of-00002.safetensors",
136
+ "model.layers.21.attn.norm.weight": "model-00001-of-00002.safetensors",
137
+ "model.layers.21.attn.o_proj.weight": "model-00001-of-00002.safetensors",
138
+ "model.layers.21.attn.q_proj.weight": "model-00001-of-00002.safetensors",
139
+ "model.layers.21.attn.v_proj.weight": "model-00001-of-00002.safetensors",
140
+ "model.layers.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
141
+ "model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
142
+ "model.layers.21.mlp.norm.weight": "model-00001-of-00002.safetensors",
143
+ "model.layers.22.attn.f_proj.weight": "model-00001-of-00002.safetensors",
144
+ "model.layers.22.attn.k_proj.weight": "model-00001-of-00002.safetensors",
145
+ "model.layers.22.attn.norm.weight": "model-00001-of-00002.safetensors",
146
+ "model.layers.22.attn.o_proj.weight": "model-00001-of-00002.safetensors",
147
+ "model.layers.22.attn.q_proj.weight": "model-00001-of-00002.safetensors",
148
+ "model.layers.22.attn.v_proj.weight": "model-00001-of-00002.safetensors",
149
+ "model.layers.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
150
+ "model.layers.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
151
+ "model.layers.22.mlp.norm.weight": "model-00001-of-00002.safetensors",
152
+ "model.layers.23.attn.f_proj.weight": "model-00001-of-00002.safetensors",
153
+ "model.layers.23.attn.k_proj.weight": "model-00001-of-00002.safetensors",
154
+ "model.layers.23.attn.norm.weight": "model-00001-of-00002.safetensors",
155
+ "model.layers.23.attn.o_proj.weight": "model-00001-of-00002.safetensors",
156
+ "model.layers.23.attn.q_proj.weight": "model-00001-of-00002.safetensors",
157
+ "model.layers.23.attn.v_proj.weight": "model-00001-of-00002.safetensors",
158
+ "model.layers.23.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
159
+ "model.layers.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
160
+ "model.layers.23.mlp.norm.weight": "model-00001-of-00002.safetensors",
161
+ "model.layers.24.attn.f_proj.weight": "model-00001-of-00002.safetensors",
162
+ "model.layers.24.attn.k_proj.weight": "model-00001-of-00002.safetensors",
163
+ "model.layers.24.attn.norm.weight": "model-00001-of-00002.safetensors",
164
+ "model.layers.24.attn.o_proj.weight": "model-00001-of-00002.safetensors",
165
+ "model.layers.24.attn.q_proj.weight": "model-00001-of-00002.safetensors",
166
+ "model.layers.24.attn.v_proj.weight": "model-00001-of-00002.safetensors",
167
+ "model.layers.24.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
168
+ "model.layers.24.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
169
+ "model.layers.24.mlp.norm.weight": "model-00001-of-00002.safetensors",
170
+ "model.layers.25.attn.f_proj.weight": "model-00001-of-00002.safetensors",
171
+ "model.layers.25.attn.k_proj.weight": "model-00001-of-00002.safetensors",
172
+ "model.layers.25.attn.norm.weight": "model-00001-of-00002.safetensors",
173
+ "model.layers.25.attn.o_proj.weight": "model-00001-of-00002.safetensors",
174
+ "model.layers.25.attn.q_proj.weight": "model-00001-of-00002.safetensors",
175
+ "model.layers.25.attn.v_proj.weight": "model-00001-of-00002.safetensors",
176
+ "model.layers.25.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
177
+ "model.layers.25.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
178
+ "model.layers.25.mlp.norm.weight": "model-00001-of-00002.safetensors",
179
+ "model.layers.26.attn.f_proj.weight": "model-00001-of-00002.safetensors",
180
+ "model.layers.26.attn.k_proj.weight": "model-00001-of-00002.safetensors",
181
+ "model.layers.26.attn.norm.weight": "model-00001-of-00002.safetensors",
182
+ "model.layers.26.attn.o_proj.weight": "model-00001-of-00002.safetensors",
183
+ "model.layers.26.attn.q_proj.weight": "model-00001-of-00002.safetensors",
184
+ "model.layers.26.attn.v_proj.weight": "model-00001-of-00002.safetensors",
185
+ "model.layers.26.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
186
+ "model.layers.26.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
187
+ "model.layers.26.mlp.norm.weight": "model-00001-of-00002.safetensors",
188
+ "model.layers.27.attn.f_proj.weight": "model-00001-of-00002.safetensors",
189
+ "model.layers.27.attn.k_proj.weight": "model-00001-of-00002.safetensors",
190
+ "model.layers.27.attn.norm.weight": "model-00001-of-00002.safetensors",
191
+ "model.layers.27.attn.o_proj.weight": "model-00001-of-00002.safetensors",
192
+ "model.layers.27.attn.q_proj.weight": "model-00001-of-00002.safetensors",
193
+ "model.layers.27.attn.v_proj.weight": "model-00001-of-00002.safetensors",
194
+ "model.layers.27.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
195
+ "model.layers.27.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
196
+ "model.layers.27.mlp.norm.weight": "model-00001-of-00002.safetensors",
197
+ "model.layers.28.attn.f_proj.weight": "model-00001-of-00002.safetensors",
198
+ "model.layers.28.attn.k_proj.weight": "model-00001-of-00002.safetensors",
199
+ "model.layers.28.attn.norm.weight": "model-00001-of-00002.safetensors",
200
+ "model.layers.28.attn.o_proj.weight": "model-00001-of-00002.safetensors",
201
+ "model.layers.28.attn.q_proj.weight": "model-00001-of-00002.safetensors",
202
+ "model.layers.28.attn.v_proj.weight": "model-00001-of-00002.safetensors",
203
+ "model.layers.28.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
204
+ "model.layers.28.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
205
+ "model.layers.28.mlp.norm.weight": "model-00001-of-00002.safetensors",
206
+ "model.layers.29.attn.f_proj.weight": "model-00001-of-00002.safetensors",
207
+ "model.layers.29.attn.k_proj.weight": "model-00001-of-00002.safetensors",
208
+ "model.layers.29.attn.norm.weight": "model-00001-of-00002.safetensors",
209
+ "model.layers.29.attn.o_proj.weight": "model-00001-of-00002.safetensors",
210
+ "model.layers.29.attn.q_proj.weight": "model-00001-of-00002.safetensors",
211
+ "model.layers.29.attn.v_proj.weight": "model-00001-of-00002.safetensors",
212
+ "model.layers.29.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
213
+ "model.layers.29.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
214
+ "model.layers.29.mlp.norm.weight": "model-00001-of-00002.safetensors",
215
+ "model.layers.3.attn.f_proj.weight": "model-00001-of-00002.safetensors",
216
+ "model.layers.3.attn.k_proj.weight": "model-00001-of-00002.safetensors",
217
+ "model.layers.3.attn.norm.weight": "model-00001-of-00002.safetensors",
218
+ "model.layers.3.attn.o_proj.weight": "model-00001-of-00002.safetensors",
219
+ "model.layers.3.attn.q_proj.weight": "model-00001-of-00002.safetensors",
220
+ "model.layers.3.attn.v_proj.weight": "model-00001-of-00002.safetensors",
221
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
222
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
223
+ "model.layers.3.mlp.norm.weight": "model-00001-of-00002.safetensors",
224
+ "model.layers.30.attn.f_proj.weight": "model-00002-of-00002.safetensors",
225
+ "model.layers.30.attn.k_proj.weight": "model-00001-of-00002.safetensors",
226
+ "model.layers.30.attn.norm.weight": "model-00001-of-00002.safetensors",
227
+ "model.layers.30.attn.o_proj.weight": "model-00002-of-00002.safetensors",
228
+ "model.layers.30.attn.q_proj.weight": "model-00001-of-00002.safetensors",
229
+ "model.layers.30.attn.v_proj.weight": "model-00002-of-00002.safetensors",
230
+ "model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
231
+ "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
232
+ "model.layers.30.mlp.norm.weight": "model-00002-of-00002.safetensors",
233
+ "model.layers.31.attn.f_proj.weight": "model-00002-of-00002.safetensors",
234
+ "model.layers.31.attn.k_proj.weight": "model-00002-of-00002.safetensors",
235
+ "model.layers.31.attn.norm.weight": "model-00002-of-00002.safetensors",
236
+ "model.layers.31.attn.o_proj.weight": "model-00002-of-00002.safetensors",
237
+ "model.layers.31.attn.q_proj.weight": "model-00002-of-00002.safetensors",
238
+ "model.layers.31.attn.v_proj.weight": "model-00002-of-00002.safetensors",
239
+ "model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
240
+ "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
241
+ "model.layers.31.mlp.norm.weight": "model-00002-of-00002.safetensors",
242
+ "model.layers.4.attn.f_proj.weight": "model-00001-of-00002.safetensors",
243
+ "model.layers.4.attn.k_proj.weight": "model-00001-of-00002.safetensors",
244
+ "model.layers.4.attn.norm.weight": "model-00001-of-00002.safetensors",
245
+ "model.layers.4.attn.o_proj.weight": "model-00001-of-00002.safetensors",
246
+ "model.layers.4.attn.q_proj.weight": "model-00001-of-00002.safetensors",
247
+ "model.layers.4.attn.v_proj.weight": "model-00001-of-00002.safetensors",
248
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
249
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
250
+ "model.layers.4.mlp.norm.weight": "model-00001-of-00002.safetensors",
251
+ "model.layers.5.attn.f_proj.weight": "model-00001-of-00002.safetensors",
252
+ "model.layers.5.attn.k_proj.weight": "model-00001-of-00002.safetensors",
253
+ "model.layers.5.attn.norm.weight": "model-00001-of-00002.safetensors",
254
+ "model.layers.5.attn.o_proj.weight": "model-00001-of-00002.safetensors",
255
+ "model.layers.5.attn.q_proj.weight": "model-00001-of-00002.safetensors",
256
+ "model.layers.5.attn.v_proj.weight": "model-00001-of-00002.safetensors",
257
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
258
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
259
+ "model.layers.5.mlp.norm.weight": "model-00001-of-00002.safetensors",
260
+ "model.layers.6.attn.f_proj.weight": "model-00001-of-00002.safetensors",
261
+ "model.layers.6.attn.k_proj.weight": "model-00001-of-00002.safetensors",
262
+ "model.layers.6.attn.norm.weight": "model-00001-of-00002.safetensors",
263
+ "model.layers.6.attn.o_proj.weight": "model-00001-of-00002.safetensors",
264
+ "model.layers.6.attn.q_proj.weight": "model-00001-of-00002.safetensors",
265
+ "model.layers.6.attn.v_proj.weight": "model-00001-of-00002.safetensors",
266
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
267
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
268
+ "model.layers.6.mlp.norm.weight": "model-00001-of-00002.safetensors",
269
+ "model.layers.7.attn.f_proj.weight": "model-00001-of-00002.safetensors",
270
+ "model.layers.7.attn.k_proj.weight": "model-00001-of-00002.safetensors",
271
+ "model.layers.7.attn.norm.weight": "model-00001-of-00002.safetensors",
272
+ "model.layers.7.attn.o_proj.weight": "model-00001-of-00002.safetensors",
273
+ "model.layers.7.attn.q_proj.weight": "model-00001-of-00002.safetensors",
274
+ "model.layers.7.attn.v_proj.weight": "model-00001-of-00002.safetensors",
275
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
276
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
277
+ "model.layers.7.mlp.norm.weight": "model-00001-of-00002.safetensors",
278
+ "model.layers.8.attn.f_proj.weight": "model-00001-of-00002.safetensors",
279
+ "model.layers.8.attn.k_proj.weight": "model-00001-of-00002.safetensors",
280
+ "model.layers.8.attn.norm.weight": "model-00001-of-00002.safetensors",
281
+ "model.layers.8.attn.o_proj.weight": "model-00001-of-00002.safetensors",
282
+ "model.layers.8.attn.q_proj.weight": "model-00001-of-00002.safetensors",
283
+ "model.layers.8.attn.v_proj.weight": "model-00001-of-00002.safetensors",
284
+ "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
285
+ "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
286
+ "model.layers.8.mlp.norm.weight": "model-00001-of-00002.safetensors",
287
+ "model.layers.9.attn.f_proj.weight": "model-00001-of-00002.safetensors",
288
+ "model.layers.9.attn.k_proj.weight": "model-00001-of-00002.safetensors",
289
+ "model.layers.9.attn.norm.weight": "model-00001-of-00002.safetensors",
290
+ "model.layers.9.attn.o_proj.weight": "model-00001-of-00002.safetensors",
291
+ "model.layers.9.attn.q_proj.weight": "model-00001-of-00002.safetensors",
292
+ "model.layers.9.attn.v_proj.weight": "model-00001-of-00002.safetensors",
293
+ "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
294
+ "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
295
+ "model.layers.9.mlp.norm.weight": "model-00001-of-00002.safetensors",
296
+ "model.norm.weight": "model-00002-of-00002.safetensors"
297
+ }
298
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "</s>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
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.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 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_eos_token": true,
4
+ "add_prefix_space": true,
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
+ "legacy": true,
36
+ "model_max_length": 1000000000000000019884624838656,
37
+ "pad_token": "</s>",
38
+ "sp_model_kwargs": {},
39
+ "spaces_between_special_tokens": false,
40
+ "tokenizer_class": "LlamaTokenizer",
41
+ "unk_token": "<unk>",
42
+ "use_default_system_prompt": false
43
+ }