张瀚灵
commited on
Commit
·
12d5e7e
1
Parent(s):
1e76ed1
init commit
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- added_tokens.json +40 -0
- merges.txt +0 -0
- mlc-chat-config.json +364 -0
- ndarray-cache.json +0 -0
- params_shard_0.bin +3 -0
- params_shard_1.bin +3 -0
- params_shard_10.bin +3 -0
- params_shard_100.bin +3 -0
- params_shard_101.bin +3 -0
- params_shard_102.bin +3 -0
- params_shard_103.bin +3 -0
- params_shard_104.bin +3 -0
- params_shard_105.bin +3 -0
- params_shard_106.bin +3 -0
- params_shard_107.bin +3 -0
- params_shard_108.bin +3 -0
- params_shard_109.bin +3 -0
- params_shard_11.bin +3 -0
- params_shard_110.bin +3 -0
- params_shard_111.bin +3 -0
- params_shard_112.bin +3 -0
- params_shard_113.bin +3 -0
- params_shard_114.bin +3 -0
- params_shard_115.bin +3 -0
- params_shard_116.bin +3 -0
- params_shard_117.bin +3 -0
- params_shard_118.bin +3 -0
- params_shard_12.bin +3 -0
- params_shard_13.bin +3 -0
- params_shard_14.bin +3 -0
- params_shard_15.bin +3 -0
- params_shard_16.bin +3 -0
- params_shard_17.bin +3 -0
- params_shard_18.bin +3 -0
- params_shard_19.bin +3 -0
- params_shard_2.bin +3 -0
- params_shard_20.bin +3 -0
- params_shard_21.bin +3 -0
- params_shard_22.bin +3 -0
- params_shard_23.bin +3 -0
- params_shard_24.bin +3 -0
- params_shard_25.bin +3 -0
- params_shard_26.bin +3 -0
- params_shard_27.bin +3 -0
- params_shard_28.bin +3 -0
- params_shard_29.bin +3 -0
- params_shard_3.bin +3 -0
- params_shard_30.bin +3 -0
- params_shard_31.bin +3 -0
- params_shard_32.bin +3 -0
added_tokens.json
ADDED
|
@@ -0,0 +1,40 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"\t\t": 50294,
|
| 3 |
+
"\t\t\t": 50293,
|
| 4 |
+
"\t\t\t\t": 50292,
|
| 5 |
+
"\t\t\t\t\t": 50291,
|
| 6 |
+
"\t\t\t\t\t\t": 50290,
|
| 7 |
+
"\t\t\t\t\t\t\t": 50289,
|
| 8 |
+
"\t\t\t\t\t\t\t\t": 50288,
|
| 9 |
+
"\t\t\t\t\t\t\t\t\t": 50287,
|
| 10 |
+
" ": 50286,
|
| 11 |
+
" ": 50285,
|
| 12 |
+
" ": 50284,
|
| 13 |
+
" ": 50283,
|
| 14 |
+
" ": 50282,
|
| 15 |
+
" ": 50281,
|
| 16 |
+
" ": 50280,
|
| 17 |
+
" ": 50279,
|
| 18 |
+
" ": 50278,
|
| 19 |
+
" ": 50277,
|
| 20 |
+
" ": 50276,
|
| 21 |
+
" ": 50275,
|
| 22 |
+
" ": 50274,
|
| 23 |
+
" ": 50273,
|
| 24 |
+
" ": 50272,
|
| 25 |
+
" ": 50271,
|
| 26 |
+
" ": 50270,
|
| 27 |
+
" ": 50269,
|
| 28 |
+
" ": 50268,
|
| 29 |
+
" ": 50267,
|
| 30 |
+
" ": 50266,
|
| 31 |
+
" ": 50265,
|
| 32 |
+
" ": 50264,
|
| 33 |
+
" ": 50263,
|
| 34 |
+
" ": 50262,
|
| 35 |
+
" ": 50261,
|
| 36 |
+
" ": 50260,
|
| 37 |
+
" ": 50259,
|
| 38 |
+
" ": 50258,
|
| 39 |
+
" ": 50257
|
| 40 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
mlc-chat-config.json
ADDED
|
@@ -0,0 +1,364 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"version": "0.1.0",
|
| 3 |
+
"model_type": "asvd_phi",
|
| 4 |
+
"quantization": "q0f16",
|
| 5 |
+
"model_config": {
|
| 6 |
+
"vocab_size": 51200,
|
| 7 |
+
"hidden_size": 2560,
|
| 8 |
+
"intermediate_size": 10240,
|
| 9 |
+
"num_hidden_layers": 32,
|
| 10 |
+
"num_attention_heads": 32,
|
| 11 |
+
"layer_norm_eps": 1e-05,
|
| 12 |
+
"position_embedding_base": 10000.0,
|
| 13 |
+
"partial_rotary_factor": 0.4,
|
| 14 |
+
"num_key_value_heads": 32,
|
| 15 |
+
"context_window_size": 2048,
|
| 16 |
+
"prefill_chunk_size": 128,
|
| 17 |
+
"head_dim": 80,
|
| 18 |
+
"truncation_ranks": {
|
| 19 |
+
"model.layers.0.mlp.fc1": [
|
| 20 |
+
1475,
|
| 21 |
+
163
|
| 22 |
+
],
|
| 23 |
+
"model.layers.0.mlp.fc2": [
|
| 24 |
+
1290,
|
| 25 |
+
143
|
| 26 |
+
],
|
| 27 |
+
"model.layers.0.self_attn.dense": [
|
| 28 |
+
922,
|
| 29 |
+
102
|
| 30 |
+
],
|
| 31 |
+
"model.layers.0.self_attn.k_proj": [
|
| 32 |
+
922,
|
| 33 |
+
102
|
| 34 |
+
],
|
| 35 |
+
"model.layers.0.self_attn.q_proj": [
|
| 36 |
+
807,
|
| 37 |
+
89
|
| 38 |
+
],
|
| 39 |
+
"model.layers.1.mlp.fc1": [
|
| 40 |
+
1475,
|
| 41 |
+
163
|
| 42 |
+
],
|
| 43 |
+
"model.layers.1.self_attn.dense": [
|
| 44 |
+
807,
|
| 45 |
+
89
|
| 46 |
+
],
|
| 47 |
+
"model.layers.1.self_attn.k_proj": [
|
| 48 |
+
692,
|
| 49 |
+
76
|
| 50 |
+
],
|
| 51 |
+
"model.layers.1.self_attn.v_proj": [
|
| 52 |
+
576,
|
| 53 |
+
64
|
| 54 |
+
],
|
| 55 |
+
"model.layers.10.self_attn.q_proj": [
|
| 56 |
+
692,
|
| 57 |
+
76
|
| 58 |
+
],
|
| 59 |
+
"model.layers.11.self_attn.dense": [
|
| 60 |
+
461,
|
| 61 |
+
51
|
| 62 |
+
],
|
| 63 |
+
"model.layers.11.self_attn.v_proj": [
|
| 64 |
+
692,
|
| 65 |
+
76
|
| 66 |
+
],
|
| 67 |
+
"model.layers.12.self_attn.dense": [
|
| 68 |
+
1037,
|
| 69 |
+
115
|
| 70 |
+
],
|
| 71 |
+
"model.layers.12.self_attn.q_proj": [
|
| 72 |
+
807,
|
| 73 |
+
89
|
| 74 |
+
],
|
| 75 |
+
"model.layers.12.self_attn.v_proj": [
|
| 76 |
+
922,
|
| 77 |
+
102
|
| 78 |
+
],
|
| 79 |
+
"model.layers.13.self_attn.dense": [
|
| 80 |
+
807,
|
| 81 |
+
89
|
| 82 |
+
],
|
| 83 |
+
"model.layers.13.self_attn.q_proj": [
|
| 84 |
+
576,
|
| 85 |
+
64
|
| 86 |
+
],
|
| 87 |
+
"model.layers.14.self_attn.dense": [
|
| 88 |
+
1037,
|
| 89 |
+
115
|
| 90 |
+
],
|
| 91 |
+
"model.layers.14.self_attn.q_proj": [
|
| 92 |
+
807,
|
| 93 |
+
89
|
| 94 |
+
],
|
| 95 |
+
"model.layers.15.self_attn.dense": [
|
| 96 |
+
1037,
|
| 97 |
+
115
|
| 98 |
+
],
|
| 99 |
+
"model.layers.15.self_attn.q_proj": [
|
| 100 |
+
807,
|
| 101 |
+
89
|
| 102 |
+
],
|
| 103 |
+
"model.layers.16.self_attn.dense": [
|
| 104 |
+
922,
|
| 105 |
+
102
|
| 106 |
+
],
|
| 107 |
+
"model.layers.16.self_attn.k_proj": [
|
| 108 |
+
922,
|
| 109 |
+
102
|
| 110 |
+
],
|
| 111 |
+
"model.layers.17.self_attn.dense": [
|
| 112 |
+
1037,
|
| 113 |
+
115
|
| 114 |
+
],
|
| 115 |
+
"model.layers.17.self_attn.q_proj": [
|
| 116 |
+
807,
|
| 117 |
+
89
|
| 118 |
+
],
|
| 119 |
+
"model.layers.18.self_attn.dense": [
|
| 120 |
+
922,
|
| 121 |
+
102
|
| 122 |
+
],
|
| 123 |
+
"model.layers.19.self_attn.k_proj": [
|
| 124 |
+
922,
|
| 125 |
+
102
|
| 126 |
+
],
|
| 127 |
+
"model.layers.19.self_attn.v_proj": [
|
| 128 |
+
922,
|
| 129 |
+
102
|
| 130 |
+
],
|
| 131 |
+
"model.layers.2.mlp.fc1": [
|
| 132 |
+
1475,
|
| 133 |
+
163
|
| 134 |
+
],
|
| 135 |
+
"model.layers.2.self_attn.dense": [
|
| 136 |
+
807,
|
| 137 |
+
89
|
| 138 |
+
],
|
| 139 |
+
"model.layers.2.self_attn.k_proj": [
|
| 140 |
+
1037,
|
| 141 |
+
115
|
| 142 |
+
],
|
| 143 |
+
"model.layers.2.self_attn.q_proj": [
|
| 144 |
+
461,
|
| 145 |
+
51
|
| 146 |
+
],
|
| 147 |
+
"model.layers.20.self_attn.dense": [
|
| 148 |
+
807,
|
| 149 |
+
89
|
| 150 |
+
],
|
| 151 |
+
"model.layers.20.self_attn.q_proj": [
|
| 152 |
+
1037,
|
| 153 |
+
115
|
| 154 |
+
],
|
| 155 |
+
"model.layers.21.self_attn.dense": [
|
| 156 |
+
692,
|
| 157 |
+
76
|
| 158 |
+
],
|
| 159 |
+
"model.layers.21.self_attn.q_proj": [
|
| 160 |
+
1037,
|
| 161 |
+
115
|
| 162 |
+
],
|
| 163 |
+
"model.layers.22.self_attn.dense": [
|
| 164 |
+
1037,
|
| 165 |
+
115
|
| 166 |
+
],
|
| 167 |
+
"model.layers.22.self_attn.q_proj": [
|
| 168 |
+
807,
|
| 169 |
+
89
|
| 170 |
+
],
|
| 171 |
+
"model.layers.23.self_attn.dense": [
|
| 172 |
+
922,
|
| 173 |
+
102
|
| 174 |
+
],
|
| 175 |
+
"model.layers.23.self_attn.q_proj": [
|
| 176 |
+
922,
|
| 177 |
+
102
|
| 178 |
+
],
|
| 179 |
+
"model.layers.23.self_attn.v_proj": [
|
| 180 |
+
692,
|
| 181 |
+
76
|
| 182 |
+
],
|
| 183 |
+
"model.layers.24.self_attn.dense": [
|
| 184 |
+
461,
|
| 185 |
+
51
|
| 186 |
+
],
|
| 187 |
+
"model.layers.24.self_attn.q_proj": [
|
| 188 |
+
922,
|
| 189 |
+
102
|
| 190 |
+
],
|
| 191 |
+
"model.layers.25.self_attn.k_proj": [
|
| 192 |
+
576,
|
| 193 |
+
64
|
| 194 |
+
],
|
| 195 |
+
"model.layers.26.self_attn.k_proj": [
|
| 196 |
+
922,
|
| 197 |
+
102
|
| 198 |
+
],
|
| 199 |
+
"model.layers.26.self_attn.q_proj": [
|
| 200 |
+
1037,
|
| 201 |
+
115
|
| 202 |
+
],
|
| 203 |
+
"model.layers.27.self_attn.dense": [
|
| 204 |
+
692,
|
| 205 |
+
76
|
| 206 |
+
],
|
| 207 |
+
"model.layers.27.self_attn.k_proj": [
|
| 208 |
+
807,
|
| 209 |
+
89
|
| 210 |
+
],
|
| 211 |
+
"model.layers.28.self_attn.dense": [
|
| 212 |
+
576,
|
| 213 |
+
64
|
| 214 |
+
],
|
| 215 |
+
"model.layers.28.self_attn.q_proj": [
|
| 216 |
+
922,
|
| 217 |
+
102
|
| 218 |
+
],
|
| 219 |
+
"model.layers.29.self_attn.q_proj": [
|
| 220 |
+
922,
|
| 221 |
+
102
|
| 222 |
+
],
|
| 223 |
+
"model.layers.29.self_attn.v_proj": [
|
| 224 |
+
807,
|
| 225 |
+
89
|
| 226 |
+
],
|
| 227 |
+
"model.layers.3.self_attn.dense": [
|
| 228 |
+
922,
|
| 229 |
+
102
|
| 230 |
+
],
|
| 231 |
+
"model.layers.3.self_attn.k_proj": [
|
| 232 |
+
1037,
|
| 233 |
+
115
|
| 234 |
+
],
|
| 235 |
+
"model.layers.30.self_attn.dense": [
|
| 236 |
+
922,
|
| 237 |
+
102
|
| 238 |
+
],
|
| 239 |
+
"model.layers.30.self_attn.q_proj": [
|
| 240 |
+
807,
|
| 241 |
+
89
|
| 242 |
+
],
|
| 243 |
+
"model.layers.31.self_attn.dense": [
|
| 244 |
+
1037,
|
| 245 |
+
115
|
| 246 |
+
],
|
| 247 |
+
"model.layers.31.self_attn.q_proj": [
|
| 248 |
+
1037,
|
| 249 |
+
115
|
| 250 |
+
],
|
| 251 |
+
"model.layers.4.self_attn.dense": [
|
| 252 |
+
807,
|
| 253 |
+
89
|
| 254 |
+
],
|
| 255 |
+
"model.layers.4.self_attn.k_proj": [
|
| 256 |
+
1037,
|
| 257 |
+
115
|
| 258 |
+
],
|
| 259 |
+
"model.layers.4.self_attn.q_proj": [
|
| 260 |
+
692,
|
| 261 |
+
76
|
| 262 |
+
],
|
| 263 |
+
"model.layers.5.self_attn.k_proj": [
|
| 264 |
+
1037,
|
| 265 |
+
115
|
| 266 |
+
],
|
| 267 |
+
"model.layers.5.self_attn.q_proj": [
|
| 268 |
+
807,
|
| 269 |
+
89
|
| 270 |
+
],
|
| 271 |
+
"model.layers.6.self_attn.dense": [
|
| 272 |
+
807,
|
| 273 |
+
89
|
| 274 |
+
],
|
| 275 |
+
"model.layers.6.self_attn.q_proj": [
|
| 276 |
+
922,
|
| 277 |
+
102
|
| 278 |
+
],
|
| 279 |
+
"model.layers.7.self_attn.q_proj": [
|
| 280 |
+
692,
|
| 281 |
+
76
|
| 282 |
+
],
|
| 283 |
+
"model.layers.8.self_attn.dense": [
|
| 284 |
+
1037,
|
| 285 |
+
115
|
| 286 |
+
],
|
| 287 |
+
"model.layers.8.self_attn.k_proj": [
|
| 288 |
+
692,
|
| 289 |
+
76
|
| 290 |
+
],
|
| 291 |
+
"model.layers.8.self_attn.q_proj": [
|
| 292 |
+
1037,
|
| 293 |
+
115
|
| 294 |
+
],
|
| 295 |
+
"model.layers.9.self_attn.dense": [
|
| 296 |
+
692,
|
| 297 |
+
76
|
| 298 |
+
],
|
| 299 |
+
"model.layers.9.self_attn.q_proj": [
|
| 300 |
+
576,
|
| 301 |
+
64
|
| 302 |
+
]
|
| 303 |
+
},
|
| 304 |
+
"tensor_parallel_shards": 1,
|
| 305 |
+
"max_batch_size": 128
|
| 306 |
+
},
|
| 307 |
+
"vocab_size": 51200,
|
| 308 |
+
"context_window_size": 2048,
|
| 309 |
+
"sliding_window_size": -1,
|
| 310 |
+
"prefill_chunk_size": 128,
|
| 311 |
+
"attention_sink_size": -1,
|
| 312 |
+
"tensor_parallel_shards": 1,
|
| 313 |
+
"pipeline_parallel_stages": 1,
|
| 314 |
+
"temperature": 1.0,
|
| 315 |
+
"presence_penalty": 0.0,
|
| 316 |
+
"frequency_penalty": 0.0,
|
| 317 |
+
"repetition_penalty": 1.0,
|
| 318 |
+
"top_p": 1.0,
|
| 319 |
+
"tokenizer_files": [
|
| 320 |
+
"tokenizer.json",
|
| 321 |
+
"vocab.json",
|
| 322 |
+
"merges.txt",
|
| 323 |
+
"added_tokens.json",
|
| 324 |
+
"tokenizer_config.json"
|
| 325 |
+
],
|
| 326 |
+
"tokenizer_info": {
|
| 327 |
+
"token_postproc_method": "byte_level",
|
| 328 |
+
"prepend_space_in_encode": false,
|
| 329 |
+
"strip_space_in_decode": false
|
| 330 |
+
},
|
| 331 |
+
"conv_template": {
|
| 332 |
+
"name": "LM",
|
| 333 |
+
"system_template": "{system_message}",
|
| 334 |
+
"system_message": "",
|
| 335 |
+
"system_prefix_token_ids": [
|
| 336 |
+
1
|
| 337 |
+
],
|
| 338 |
+
"add_role_after_system_message": true,
|
| 339 |
+
"roles": {
|
| 340 |
+
"user": "",
|
| 341 |
+
"assistant": ""
|
| 342 |
+
},
|
| 343 |
+
"role_templates": {
|
| 344 |
+
"user": "{user_message}",
|
| 345 |
+
"assistant": "{assistant_message}",
|
| 346 |
+
"tool": "{tool_message}"
|
| 347 |
+
},
|
| 348 |
+
"messages": [],
|
| 349 |
+
"seps": [
|
| 350 |
+
""
|
| 351 |
+
],
|
| 352 |
+
"role_content_sep": "",
|
| 353 |
+
"role_empty_sep": "",
|
| 354 |
+
"stop_str": [],
|
| 355 |
+
"stop_token_ids": [
|
| 356 |
+
2
|
| 357 |
+
],
|
| 358 |
+
"function_string": "",
|
| 359 |
+
"use_function_calling": false
|
| 360 |
+
},
|
| 361 |
+
"pad_token_id": 0,
|
| 362 |
+
"bos_token_id": 50256,
|
| 363 |
+
"eos_token_id": 50256
|
| 364 |
+
}
|
ndarray-cache.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
params_shard_0.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:76772b626f4941182e17194c49c813293a6c930e99f41c4266bbf320331364bc
|
| 3 |
+
size 262144000
|
params_shard_1.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aeed8f9939e08ec774f4b20528a5dcae4145adcd9d6d733b7eb878593f42558c
|
| 3 |
+
size 52428800
|
params_shard_10.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:16183de51d729da63f07cedf57d7d38447200758e6937fb475b5bf8aec50994f
|
| 3 |
+
size 52428800
|
params_shard_100.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:93fb492e0e0ff5b6bfa72fd65b6664291a8d936555449f209daaa2956ab8df1d
|
| 3 |
+
size 52428800
|
params_shard_101.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d776d394839d5005822818435f05792a5f809831fc313bd90a3aa5d65007b4d7
|
| 3 |
+
size 52428800
|
params_shard_102.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1fa323830a21bc65e1afe9d5cb9b8de9b43f20a5d6bb402bfda45dfa67abfb54
|
| 3 |
+
size 21611520
|
params_shard_103.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9df31839a15b95359b0edaf7824d85b862300279655028d7436081ea7ae45dd9
|
| 3 |
+
size 29501440
|
params_shard_104.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:76a816336979b2eeeac405f248dc84b96758ac26332027fbe5638a9a343097e2
|
| 3 |
+
size 52428800
|
params_shard_105.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:370b614a4beecb577d66804d6f567d002a15de7324a0919969379b56b751b5c4
|
| 3 |
+
size 52428800
|
params_shard_106.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9b84c00a1b1bd7284ce34018fec9ceef136b55ffdf3e6475649a35804718a29b
|
| 3 |
+
size 26920960
|
params_shard_107.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7e8e2f77488a99d3fe64f4bd723974d20f3446daeeaf001b7558ccbf78c22c19
|
| 3 |
+
size 23603200
|
params_shard_108.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f3aeccd2080c6b511a8d0680cd8f001d1fa2a41b034e6119709d50d5b330ed12
|
| 3 |
+
size 52428800
|
params_shard_109.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a25b7b6656cc7f0a209fa03657592e8261f978b0b306fda4df6e4eb250c555e7
|
| 3 |
+
size 52428800
|
params_shard_11.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1c0b18a42582a54820c88cf8e3043793d7dbb4027f7bb3c22cb382533215ba1c
|
| 3 |
+
size 52428800
|
params_shard_110.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3bcd3fb89ff881fb3015441c39abb8c461540ec939a92db1731eecfb02909c58
|
| 3 |
+
size 26260480
|
params_shard_111.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7e79a45e42f03563c4641ff230f59bd2c0fc12386b53d3030b2b6a841ea5aafc
|
| 3 |
+
size 20981760
|
params_shard_112.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:286dd1c2d7d9e153a38cefb894b53902500e015281fb6a0633e279d4472c236d
|
| 3 |
+
size 52428800
|
params_shard_113.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9b5ed4b65683ccdb7889d33db459e0b4d3730a208c89db1ad8341df6291c845e
|
| 3 |
+
size 52428800
|
params_shard_114.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2292240d858315ab0f39e89511d05edcf8d96d516692789a6210a31aee37c417
|
| 3 |
+
size 32814080
|
params_shard_115.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f5f8e1961ad40c75662eb949f40e402f4779728225c1e241dfb68e01b55b36e2
|
| 3 |
+
size 52428800
|
params_shard_116.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1e57b7cbef72448dcc4a0c5d0dd6e6601eb59071537314c8485d1f2920e8e27d
|
| 3 |
+
size 52428800
|
params_shard_117.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:30ade731a0d9a731594b224b362e6e76887a8d04f71cf9997dc5aa40f355d253
|
| 3 |
+
size 32824320
|
params_shard_118.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:376906f61bf403d59b67e033ca11cf41eaa51f93a9917e40fa25c653263484a7
|
| 3 |
+
size 32778240
|
params_shard_12.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8fb8aa4a34ebc1a8bb239ab95baf1c9a99c8086e716ced8969d25966ad1dda15
|
| 3 |
+
size 32819200
|
params_shard_13.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b1dda264a34ba2a65adaca8744b812892498818da9e0b67b61039b73084ff9a1
|
| 3 |
+
size 20981760
|
params_shard_14.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c02ae6e577c9fb237a89852f1caebd1a4e0b2df46c22fb4b647bec411df60002
|
| 3 |
+
size 52428800
|
params_shard_15.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a22bc57bf53f9dadea0bf6b81b1bac140afc6e4a17426f5053c5b1311b25518e
|
| 3 |
+
size 52428800
|
params_shard_16.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4089bfceefa8c4a62127142bb5df044a0ccc583c815639652b9945e25589007b
|
| 3 |
+
size 31508480
|
params_shard_17.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0ffde4961a1fa907fe4995b5ac415087b1d65cbb3cef25102841050bb62f0de3
|
| 3 |
+
size 52428800
|
params_shard_18.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b7dcfc0a1de379ee30df31eeda004bdec8d05529b388bff4165eabab0043c4cd
|
| 3 |
+
size 52428800
|
params_shard_19.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fc76c900df2a7729f968e89390b0db71941c6e580f7d1ccbb5be240fca6859bb
|
| 3 |
+
size 32819200
|
params_shard_2.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:308d082548ba0bac75d949a779225c5aded8cbd091d4f297e7d9e9beb4f01fc2
|
| 3 |
+
size 262144000
|
params_shard_20.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aa5d994175a60d5c9de27963076ec3626f31791e75e5f43adbf9b69091e6243f
|
| 3 |
+
size 52428800
|
params_shard_21.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:46efc839fe87a3cae558933e3046009a90c11da7fc93344b32c58ae5ff0e4556
|
| 3 |
+
size 52428800
|
params_shard_22.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b92df04d07dab90fe0181aa3482e87ee4d5f044eec0eedbc1d51d3a1c31c191d
|
| 3 |
+
size 32814080
|
params_shard_23.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fbee17aef27542ac668cc323759b75c354ae07666b00af7ff23c038870ce9286
|
| 3 |
+
size 28856320
|
params_shard_24.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:691c1b56e352707c351e51119be5278bc38c2d8128fdf4ab2abd7537a7a07c60
|
| 3 |
+
size 52428800
|
params_shard_25.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c36c7522722420bff4c38abcedb95c124b2e6f626f182154809ded56d224901f
|
| 3 |
+
size 52428800
|
params_shard_26.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:056b49043ccc291a16eba0506b5bacf9e4f6e7c64786fd4d58ceccb95f79f15a
|
| 3 |
+
size 24949760
|
params_shard_27.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f806ca92e1cdec9a383caf6e0f1f9d3f08210c12ef1ad4dcb2ef51368ba9195a
|
| 3 |
+
size 22292480
|
params_shard_28.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:061983a4beaf49e6d215c216c6b413ac2171b43790363c5ec7d9b3699b1a2bc3
|
| 3 |
+
size 52428800
|
params_shard_29.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c3a365a5a5fe47a56fb8ff1f2c777fc867ec171f7046087a971893a0ae3186bf
|
| 3 |
+
size 52428800
|
params_shard_3.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:497b234ee8017c00becca5c6871b4fb2ad199a67b554697da8962f6a45fb1ade
|
| 3 |
+
size 30366720
|
params_shard_30.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:27059127c20b97f45c9b4f6f60ad2496a427b13dc93b11c30cadbb5232db6a17
|
| 3 |
+
size 24949760
|
params_shard_31.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6edb4bf3b3be0ff1c41f98f89ebaa26272d7a3d30f7bb9c2987ba49717c1760a
|
| 3 |
+
size 22292480
|
params_shard_32.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ef556acd0cfbf9564f5c50139682b82eeb2040a5a54aed1034383b6c01b719bf
|
| 3 |
+
size 52428800
|