张瀚灵 commited on
Commit ·
fc30cd3
1
Parent(s): 6a5cfa7
init commit
Browse filesThis view is limited to 50 files because it contains too many changes. See raw diff
- mlc-chat-config.json +759 -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_119.bin +3 -0
- params_shard_12.bin +3 -0
- params_shard_120.bin +3 -0
- params_shard_121.bin +3 -0
- params_shard_122.bin +3 -0
- params_shard_123.bin +3 -0
- params_shard_124.bin +3 -0
- params_shard_125.bin +3 -0
- params_shard_126.bin +3 -0
- params_shard_127.bin +3 -0
- params_shard_128.bin +3 -0
- params_shard_129.bin +3 -0
- params_shard_13.bin +3 -0
- params_shard_130.bin +3 -0
- params_shard_131.bin +3 -0
- params_shard_132.bin +3 -0
- params_shard_133.bin +3 -0
- params_shard_134.bin +3 -0
- params_shard_135.bin +3 -0
- params_shard_136.bin +3 -0
- params_shard_137.bin +3 -0
- params_shard_138.bin +3 -0
- params_shard_139.bin +3 -0
- params_shard_14.bin +3 -0
- params_shard_140.bin +3 -0
mlc-chat-config.json
ADDED
|
@@ -0,0 +1,759 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"model_type": "asvd_llama",
|
| 3 |
+
"quantization": "q0f16",
|
| 4 |
+
"model_config": {
|
| 5 |
+
"hidden_size": 4096,
|
| 6 |
+
"intermediate_size": 14336,
|
| 7 |
+
"num_attention_heads": 32,
|
| 8 |
+
"num_hidden_layers": 32,
|
| 9 |
+
"rms_norm_eps": 1e-05,
|
| 10 |
+
"vocab_size": 77209,
|
| 11 |
+
"position_embedding_base": 500000.0,
|
| 12 |
+
"context_window_size": 131072,
|
| 13 |
+
"prefill_chunk_size": 131072,
|
| 14 |
+
"num_key_value_heads": 8,
|
| 15 |
+
"head_dim": 128,
|
| 16 |
+
"tensor_parallel_shards": 1,
|
| 17 |
+
"truncation_ranks": {
|
| 18 |
+
"model.layers.0.mlp.gate_proj": [
|
| 19 |
+
2007,
|
| 20 |
+
222
|
| 21 |
+
],
|
| 22 |
+
"model.layers.0.self_attn.k_proj": [
|
| 23 |
+
74,
|
| 24 |
+
8
|
| 25 |
+
],
|
| 26 |
+
"model.layers.0.self_attn.o_proj": [
|
| 27 |
+
461,
|
| 28 |
+
51
|
| 29 |
+
],
|
| 30 |
+
"model.layers.0.self_attn.q_proj": [
|
| 31 |
+
185,
|
| 32 |
+
20
|
| 33 |
+
],
|
| 34 |
+
"model.layers.0.self_attn.v_proj": [
|
| 35 |
+
405,
|
| 36 |
+
45
|
| 37 |
+
],
|
| 38 |
+
"model.layers.1.mlp.gate_proj": [
|
| 39 |
+
1576,
|
| 40 |
+
175
|
| 41 |
+
],
|
| 42 |
+
"model.layers.1.mlp.up_proj": [
|
| 43 |
+
2007,
|
| 44 |
+
222
|
| 45 |
+
],
|
| 46 |
+
"model.layers.1.self_attn.k_proj": [
|
| 47 |
+
184,
|
| 48 |
+
20
|
| 49 |
+
],
|
| 50 |
+
"model.layers.1.self_attn.o_proj": [
|
| 51 |
+
738,
|
| 52 |
+
81
|
| 53 |
+
],
|
| 54 |
+
"model.layers.1.self_attn.q_proj": [
|
| 55 |
+
185,
|
| 56 |
+
20
|
| 57 |
+
],
|
| 58 |
+
"model.layers.1.self_attn.v_proj": [
|
| 59 |
+
295,
|
| 60 |
+
32
|
| 61 |
+
],
|
| 62 |
+
"model.layers.10.mlp.down_proj": [
|
| 63 |
+
1146,
|
| 64 |
+
127
|
| 65 |
+
],
|
| 66 |
+
"model.layers.10.mlp.gate_proj": [
|
| 67 |
+
1576,
|
| 68 |
+
175
|
| 69 |
+
],
|
| 70 |
+
"model.layers.10.self_attn.k_proj": [
|
| 71 |
+
184,
|
| 72 |
+
20
|
| 73 |
+
],
|
| 74 |
+
"model.layers.10.self_attn.o_proj": [
|
| 75 |
+
461,
|
| 76 |
+
51
|
| 77 |
+
],
|
| 78 |
+
"model.layers.10.self_attn.q_proj": [
|
| 79 |
+
185,
|
| 80 |
+
20
|
| 81 |
+
],
|
| 82 |
+
"model.layers.10.self_attn.v_proj": [
|
| 83 |
+
295,
|
| 84 |
+
32
|
| 85 |
+
],
|
| 86 |
+
"model.layers.11.mlp.down_proj": [
|
| 87 |
+
1576,
|
| 88 |
+
175
|
| 89 |
+
],
|
| 90 |
+
"model.layers.11.self_attn.k_proj": [
|
| 91 |
+
295,
|
| 92 |
+
32
|
| 93 |
+
],
|
| 94 |
+
"model.layers.11.self_attn.o_proj": [
|
| 95 |
+
1014,
|
| 96 |
+
112
|
| 97 |
+
],
|
| 98 |
+
"model.layers.11.self_attn.q_proj": [
|
| 99 |
+
461,
|
| 100 |
+
51
|
| 101 |
+
],
|
| 102 |
+
"model.layers.11.self_attn.v_proj": [
|
| 103 |
+
405,
|
| 104 |
+
45
|
| 105 |
+
],
|
| 106 |
+
"model.layers.12.mlp.down_proj": [
|
| 107 |
+
1576,
|
| 108 |
+
175
|
| 109 |
+
],
|
| 110 |
+
"model.layers.12.mlp.gate_proj": [
|
| 111 |
+
1146,
|
| 112 |
+
127
|
| 113 |
+
],
|
| 114 |
+
"model.layers.12.self_attn.k_proj": [
|
| 115 |
+
184,
|
| 116 |
+
20
|
| 117 |
+
],
|
| 118 |
+
"model.layers.12.self_attn.o_proj": [
|
| 119 |
+
1014,
|
| 120 |
+
112
|
| 121 |
+
],
|
| 122 |
+
"model.layers.12.self_attn.q_proj": [
|
| 123 |
+
461,
|
| 124 |
+
51
|
| 125 |
+
],
|
| 126 |
+
"model.layers.12.self_attn.v_proj": [
|
| 127 |
+
516,
|
| 128 |
+
57
|
| 129 |
+
],
|
| 130 |
+
"model.layers.13.mlp.gate_proj": [
|
| 131 |
+
1146,
|
| 132 |
+
127
|
| 133 |
+
],
|
| 134 |
+
"model.layers.13.mlp.up_proj": [
|
| 135 |
+
2437,
|
| 136 |
+
270
|
| 137 |
+
],
|
| 138 |
+
"model.layers.13.self_attn.o_proj": [
|
| 139 |
+
461,
|
| 140 |
+
51
|
| 141 |
+
],
|
| 142 |
+
"model.layers.13.self_attn.q_proj": [
|
| 143 |
+
461,
|
| 144 |
+
51
|
| 145 |
+
],
|
| 146 |
+
"model.layers.13.self_attn.v_proj": [
|
| 147 |
+
184,
|
| 148 |
+
20
|
| 149 |
+
],
|
| 150 |
+
"model.layers.14.mlp.gate_proj": [
|
| 151 |
+
717,
|
| 152 |
+
79
|
| 153 |
+
],
|
| 154 |
+
"model.layers.14.self_attn.k_proj": [
|
| 155 |
+
516,
|
| 156 |
+
57
|
| 157 |
+
],
|
| 158 |
+
"model.layers.14.self_attn.o_proj": [
|
| 159 |
+
738,
|
| 160 |
+
81
|
| 161 |
+
],
|
| 162 |
+
"model.layers.14.self_attn.q_proj": [
|
| 163 |
+
461,
|
| 164 |
+
51
|
| 165 |
+
],
|
| 166 |
+
"model.layers.14.self_attn.v_proj": [
|
| 167 |
+
295,
|
| 168 |
+
32
|
| 169 |
+
],
|
| 170 |
+
"model.layers.15.mlp.gate_proj": [
|
| 171 |
+
1146,
|
| 172 |
+
127
|
| 173 |
+
],
|
| 174 |
+
"model.layers.15.mlp.up_proj": [
|
| 175 |
+
1146,
|
| 176 |
+
127
|
| 177 |
+
],
|
| 178 |
+
"model.layers.15.self_attn.o_proj": [
|
| 179 |
+
1014,
|
| 180 |
+
112
|
| 181 |
+
],
|
| 182 |
+
"model.layers.15.self_attn.q_proj": [
|
| 183 |
+
461,
|
| 184 |
+
51
|
| 185 |
+
],
|
| 186 |
+
"model.layers.16.mlp.gate_proj": [
|
| 187 |
+
1576,
|
| 188 |
+
175
|
| 189 |
+
],
|
| 190 |
+
"model.layers.16.mlp.up_proj": [
|
| 191 |
+
1576,
|
| 192 |
+
175
|
| 193 |
+
],
|
| 194 |
+
"model.layers.16.self_attn.k_proj": [
|
| 195 |
+
184,
|
| 196 |
+
20
|
| 197 |
+
],
|
| 198 |
+
"model.layers.16.self_attn.o_proj": [
|
| 199 |
+
1014,
|
| 200 |
+
112
|
| 201 |
+
],
|
| 202 |
+
"model.layers.16.self_attn.q_proj": [
|
| 203 |
+
185,
|
| 204 |
+
20
|
| 205 |
+
],
|
| 206 |
+
"model.layers.17.mlp.gate_proj": [
|
| 207 |
+
1576,
|
| 208 |
+
175
|
| 209 |
+
],
|
| 210 |
+
"model.layers.17.mlp.up_proj": [
|
| 211 |
+
1576,
|
| 212 |
+
175
|
| 213 |
+
],
|
| 214 |
+
"model.layers.17.self_attn.k_proj": [
|
| 215 |
+
74,
|
| 216 |
+
8
|
| 217 |
+
],
|
| 218 |
+
"model.layers.17.self_attn.o_proj": [
|
| 219 |
+
738,
|
| 220 |
+
81
|
| 221 |
+
],
|
| 222 |
+
"model.layers.17.self_attn.q_proj": [
|
| 223 |
+
185,
|
| 224 |
+
20
|
| 225 |
+
],
|
| 226 |
+
"model.layers.18.mlp.gate_proj": [
|
| 227 |
+
1576,
|
| 228 |
+
175
|
| 229 |
+
],
|
| 230 |
+
"model.layers.18.mlp.up_proj": [
|
| 231 |
+
1576,
|
| 232 |
+
175
|
| 233 |
+
],
|
| 234 |
+
"model.layers.18.self_attn.k_proj": [
|
| 235 |
+
184,
|
| 236 |
+
20
|
| 237 |
+
],
|
| 238 |
+
"model.layers.18.self_attn.o_proj": [
|
| 239 |
+
461,
|
| 240 |
+
51
|
| 241 |
+
],
|
| 242 |
+
"model.layers.18.self_attn.q_proj": [
|
| 243 |
+
185,
|
| 244 |
+
20
|
| 245 |
+
],
|
| 246 |
+
"model.layers.18.self_attn.v_proj": [
|
| 247 |
+
295,
|
| 248 |
+
32
|
| 249 |
+
],
|
| 250 |
+
"model.layers.19.mlp.gate_proj": [
|
| 251 |
+
2007,
|
| 252 |
+
222
|
| 253 |
+
],
|
| 254 |
+
"model.layers.19.mlp.up_proj": [
|
| 255 |
+
1576,
|
| 256 |
+
175
|
| 257 |
+
],
|
| 258 |
+
"model.layers.19.self_attn.k_proj": [
|
| 259 |
+
74,
|
| 260 |
+
8
|
| 261 |
+
],
|
| 262 |
+
"model.layers.19.self_attn.o_proj": [
|
| 263 |
+
185,
|
| 264 |
+
20
|
| 265 |
+
],
|
| 266 |
+
"model.layers.19.self_attn.q_proj": [
|
| 267 |
+
185,
|
| 268 |
+
20
|
| 269 |
+
],
|
| 270 |
+
"model.layers.19.self_attn.v_proj": [
|
| 271 |
+
74,
|
| 272 |
+
8
|
| 273 |
+
],
|
| 274 |
+
"model.layers.2.self_attn.k_proj": [
|
| 275 |
+
184,
|
| 276 |
+
20
|
| 277 |
+
],
|
| 278 |
+
"model.layers.2.self_attn.o_proj": [
|
| 279 |
+
461,
|
| 280 |
+
51
|
| 281 |
+
],
|
| 282 |
+
"model.layers.2.self_attn.q_proj": [
|
| 283 |
+
185,
|
| 284 |
+
20
|
| 285 |
+
],
|
| 286 |
+
"model.layers.20.mlp.gate_proj": [
|
| 287 |
+
2007,
|
| 288 |
+
222
|
| 289 |
+
],
|
| 290 |
+
"model.layers.20.mlp.up_proj": [
|
| 291 |
+
2007,
|
| 292 |
+
222
|
| 293 |
+
],
|
| 294 |
+
"model.layers.20.self_attn.k_proj": [
|
| 295 |
+
74,
|
| 296 |
+
8
|
| 297 |
+
],
|
| 298 |
+
"model.layers.20.self_attn.o_proj": [
|
| 299 |
+
185,
|
| 300 |
+
20
|
| 301 |
+
],
|
| 302 |
+
"model.layers.20.self_attn.q_proj": [
|
| 303 |
+
185,
|
| 304 |
+
20
|
| 305 |
+
],
|
| 306 |
+
"model.layers.20.self_attn.v_proj": [
|
| 307 |
+
74,
|
| 308 |
+
8
|
| 309 |
+
],
|
| 310 |
+
"model.layers.21.mlp.gate_proj": [
|
| 311 |
+
2007,
|
| 312 |
+
222
|
| 313 |
+
],
|
| 314 |
+
"model.layers.21.mlp.up_proj": [
|
| 315 |
+
1576,
|
| 316 |
+
175
|
| 317 |
+
],
|
| 318 |
+
"model.layers.21.self_attn.k_proj": [
|
| 319 |
+
184,
|
| 320 |
+
20
|
| 321 |
+
],
|
| 322 |
+
"model.layers.21.self_attn.o_proj": [
|
| 323 |
+
461,
|
| 324 |
+
51
|
| 325 |
+
],
|
| 326 |
+
"model.layers.21.self_attn.q_proj": [
|
| 327 |
+
185,
|
| 328 |
+
20
|
| 329 |
+
],
|
| 330 |
+
"model.layers.21.self_attn.v_proj": [
|
| 331 |
+
295,
|
| 332 |
+
32
|
| 333 |
+
],
|
| 334 |
+
"model.layers.22.mlp.gate_proj": [
|
| 335 |
+
1576,
|
| 336 |
+
175
|
| 337 |
+
],
|
| 338 |
+
"model.layers.22.mlp.up_proj": [
|
| 339 |
+
1576,
|
| 340 |
+
175
|
| 341 |
+
],
|
| 342 |
+
"model.layers.22.self_attn.k_proj": [
|
| 343 |
+
74,
|
| 344 |
+
8
|
| 345 |
+
],
|
| 346 |
+
"model.layers.22.self_attn.o_proj": [
|
| 347 |
+
461,
|
| 348 |
+
51
|
| 349 |
+
],
|
| 350 |
+
"model.layers.22.self_attn.q_proj": [
|
| 351 |
+
185,
|
| 352 |
+
20
|
| 353 |
+
],
|
| 354 |
+
"model.layers.22.self_attn.v_proj": [
|
| 355 |
+
295,
|
| 356 |
+
32
|
| 357 |
+
],
|
| 358 |
+
"model.layers.23.mlp.down_proj": [
|
| 359 |
+
2437,
|
| 360 |
+
270
|
| 361 |
+
],
|
| 362 |
+
"model.layers.23.mlp.gate_proj": [
|
| 363 |
+
1576,
|
| 364 |
+
175
|
| 365 |
+
],
|
| 366 |
+
"model.layers.23.mlp.up_proj": [
|
| 367 |
+
1146,
|
| 368 |
+
127
|
| 369 |
+
],
|
| 370 |
+
"model.layers.23.self_attn.k_proj": [
|
| 371 |
+
74,
|
| 372 |
+
8
|
| 373 |
+
],
|
| 374 |
+
"model.layers.23.self_attn.o_proj": [
|
| 375 |
+
185,
|
| 376 |
+
20
|
| 377 |
+
],
|
| 378 |
+
"model.layers.23.self_attn.q_proj": [
|
| 379 |
+
185,
|
| 380 |
+
20
|
| 381 |
+
],
|
| 382 |
+
"model.layers.23.self_attn.v_proj": [
|
| 383 |
+
184,
|
| 384 |
+
20
|
| 385 |
+
],
|
| 386 |
+
"model.layers.24.mlp.down_proj": [
|
| 387 |
+
1576,
|
| 388 |
+
175
|
| 389 |
+
],
|
| 390 |
+
"model.layers.24.mlp.gate_proj": [
|
| 391 |
+
1576,
|
| 392 |
+
175
|
| 393 |
+
],
|
| 394 |
+
"model.layers.24.mlp.up_proj": [
|
| 395 |
+
1576,
|
| 396 |
+
175
|
| 397 |
+
],
|
| 398 |
+
"model.layers.24.self_attn.k_proj": [
|
| 399 |
+
74,
|
| 400 |
+
8
|
| 401 |
+
],
|
| 402 |
+
"model.layers.24.self_attn.o_proj": [
|
| 403 |
+
185,
|
| 404 |
+
20
|
| 405 |
+
],
|
| 406 |
+
"model.layers.24.self_attn.q_proj": [
|
| 407 |
+
185,
|
| 408 |
+
20
|
| 409 |
+
],
|
| 410 |
+
"model.layers.24.self_attn.v_proj": [
|
| 411 |
+
74,
|
| 412 |
+
8
|
| 413 |
+
],
|
| 414 |
+
"model.layers.25.mlp.down_proj": [
|
| 415 |
+
2437,
|
| 416 |
+
270
|
| 417 |
+
],
|
| 418 |
+
"model.layers.25.mlp.gate_proj": [
|
| 419 |
+
1576,
|
| 420 |
+
175
|
| 421 |
+
],
|
| 422 |
+
"model.layers.25.mlp.up_proj": [
|
| 423 |
+
1576,
|
| 424 |
+
175
|
| 425 |
+
],
|
| 426 |
+
"model.layers.25.self_attn.k_proj": [
|
| 427 |
+
74,
|
| 428 |
+
8
|
| 429 |
+
],
|
| 430 |
+
"model.layers.25.self_attn.o_proj": [
|
| 431 |
+
185,
|
| 432 |
+
20
|
| 433 |
+
],
|
| 434 |
+
"model.layers.25.self_attn.q_proj": [
|
| 435 |
+
185,
|
| 436 |
+
20
|
| 437 |
+
],
|
| 438 |
+
"model.layers.25.self_attn.v_proj": [
|
| 439 |
+
184,
|
| 440 |
+
20
|
| 441 |
+
],
|
| 442 |
+
"model.layers.26.mlp.down_proj": [
|
| 443 |
+
1146,
|
| 444 |
+
127
|
| 445 |
+
],
|
| 446 |
+
"model.layers.26.mlp.gate_proj": [
|
| 447 |
+
1146,
|
| 448 |
+
127
|
| 449 |
+
],
|
| 450 |
+
"model.layers.26.mlp.up_proj": [
|
| 451 |
+
1146,
|
| 452 |
+
127
|
| 453 |
+
],
|
| 454 |
+
"model.layers.26.self_attn.k_proj": [
|
| 455 |
+
74,
|
| 456 |
+
8
|
| 457 |
+
],
|
| 458 |
+
"model.layers.26.self_attn.o_proj": [
|
| 459 |
+
185,
|
| 460 |
+
20
|
| 461 |
+
],
|
| 462 |
+
"model.layers.26.self_attn.q_proj": [
|
| 463 |
+
185,
|
| 464 |
+
20
|
| 465 |
+
],
|
| 466 |
+
"model.layers.26.self_attn.v_proj": [
|
| 467 |
+
74,
|
| 468 |
+
8
|
| 469 |
+
],
|
| 470 |
+
"model.layers.27.mlp.down_proj": [
|
| 471 |
+
1146,
|
| 472 |
+
127
|
| 473 |
+
],
|
| 474 |
+
"model.layers.27.mlp.gate_proj": [
|
| 475 |
+
1146,
|
| 476 |
+
127
|
| 477 |
+
],
|
| 478 |
+
"model.layers.27.mlp.up_proj": [
|
| 479 |
+
1146,
|
| 480 |
+
127
|
| 481 |
+
],
|
| 482 |
+
"model.layers.27.self_attn.k_proj": [
|
| 483 |
+
184,
|
| 484 |
+
20
|
| 485 |
+
],
|
| 486 |
+
"model.layers.27.self_attn.o_proj": [
|
| 487 |
+
461,
|
| 488 |
+
51
|
| 489 |
+
],
|
| 490 |
+
"model.layers.27.self_attn.q_proj": [
|
| 491 |
+
185,
|
| 492 |
+
20
|
| 493 |
+
],
|
| 494 |
+
"model.layers.27.self_attn.v_proj": [
|
| 495 |
+
184,
|
| 496 |
+
20
|
| 497 |
+
],
|
| 498 |
+
"model.layers.28.mlp.down_proj": [
|
| 499 |
+
1146,
|
| 500 |
+
127
|
| 501 |
+
],
|
| 502 |
+
"model.layers.28.mlp.gate_proj": [
|
| 503 |
+
1146,
|
| 504 |
+
127
|
| 505 |
+
],
|
| 506 |
+
"model.layers.28.mlp.up_proj": [
|
| 507 |
+
1146,
|
| 508 |
+
127
|
| 509 |
+
],
|
| 510 |
+
"model.layers.28.self_attn.k_proj": [
|
| 511 |
+
184,
|
| 512 |
+
20
|
| 513 |
+
],
|
| 514 |
+
"model.layers.28.self_attn.o_proj": [
|
| 515 |
+
461,
|
| 516 |
+
51
|
| 517 |
+
],
|
| 518 |
+
"model.layers.28.self_attn.q_proj": [
|
| 519 |
+
185,
|
| 520 |
+
20
|
| 521 |
+
],
|
| 522 |
+
"model.layers.28.self_attn.v_proj": [
|
| 523 |
+
405,
|
| 524 |
+
45
|
| 525 |
+
],
|
| 526 |
+
"model.layers.29.mlp.down_proj": [
|
| 527 |
+
1146,
|
| 528 |
+
127
|
| 529 |
+
],
|
| 530 |
+
"model.layers.29.mlp.gate_proj": [
|
| 531 |
+
1576,
|
| 532 |
+
175
|
| 533 |
+
],
|
| 534 |
+
"model.layers.29.mlp.up_proj": [
|
| 535 |
+
287,
|
| 536 |
+
31
|
| 537 |
+
],
|
| 538 |
+
"model.layers.29.self_attn.k_proj": [
|
| 539 |
+
295,
|
| 540 |
+
32
|
| 541 |
+
],
|
| 542 |
+
"model.layers.29.self_attn.o_proj": [
|
| 543 |
+
461,
|
| 544 |
+
51
|
| 545 |
+
],
|
| 546 |
+
"model.layers.29.self_attn.q_proj": [
|
| 547 |
+
185,
|
| 548 |
+
20
|
| 549 |
+
],
|
| 550 |
+
"model.layers.29.self_attn.v_proj": [
|
| 551 |
+
184,
|
| 552 |
+
20
|
| 553 |
+
],
|
| 554 |
+
"model.layers.3.mlp.gate_proj": [
|
| 555 |
+
2007,
|
| 556 |
+
222
|
| 557 |
+
],
|
| 558 |
+
"model.layers.3.self_attn.k_proj": [
|
| 559 |
+
516,
|
| 560 |
+
57
|
| 561 |
+
],
|
| 562 |
+
"model.layers.3.self_attn.o_proj": [
|
| 563 |
+
1014,
|
| 564 |
+
112
|
| 565 |
+
],
|
| 566 |
+
"model.layers.3.self_attn.q_proj": [
|
| 567 |
+
185,
|
| 568 |
+
20
|
| 569 |
+
],
|
| 570 |
+
"model.layers.30.mlp.down_proj": [
|
| 571 |
+
2007,
|
| 572 |
+
222
|
| 573 |
+
],
|
| 574 |
+
"model.layers.30.mlp.gate_proj": [
|
| 575 |
+
1576,
|
| 576 |
+
175
|
| 577 |
+
],
|
| 578 |
+
"model.layers.30.self_attn.k_proj": [
|
| 579 |
+
184,
|
| 580 |
+
20
|
| 581 |
+
],
|
| 582 |
+
"model.layers.30.self_attn.o_proj": [
|
| 583 |
+
461,
|
| 584 |
+
51
|
| 585 |
+
],
|
| 586 |
+
"model.layers.30.self_attn.q_proj": [
|
| 587 |
+
185,
|
| 588 |
+
20
|
| 589 |
+
],
|
| 590 |
+
"model.layers.30.self_attn.v_proj": [
|
| 591 |
+
405,
|
| 592 |
+
45
|
| 593 |
+
],
|
| 594 |
+
"model.layers.31.mlp.down_proj": [
|
| 595 |
+
1576,
|
| 596 |
+
175
|
| 597 |
+
],
|
| 598 |
+
"model.layers.31.mlp.gate_proj": [
|
| 599 |
+
1576,
|
| 600 |
+
175
|
| 601 |
+
],
|
| 602 |
+
"model.layers.31.self_attn.k_proj": [
|
| 603 |
+
184,
|
| 604 |
+
20
|
| 605 |
+
],
|
| 606 |
+
"model.layers.31.self_attn.o_proj": [
|
| 607 |
+
461,
|
| 608 |
+
51
|
| 609 |
+
],
|
| 610 |
+
"model.layers.31.self_attn.q_proj": [
|
| 611 |
+
185,
|
| 612 |
+
20
|
| 613 |
+
],
|
| 614 |
+
"model.layers.4.self_attn.k_proj": [
|
| 615 |
+
184,
|
| 616 |
+
20
|
| 617 |
+
],
|
| 618 |
+
"model.layers.4.self_attn.o_proj": [
|
| 619 |
+
738,
|
| 620 |
+
81
|
| 621 |
+
],
|
| 622 |
+
"model.layers.4.self_attn.q_proj": [
|
| 623 |
+
185,
|
| 624 |
+
20
|
| 625 |
+
],
|
| 626 |
+
"model.layers.5.mlp.down_proj": [
|
| 627 |
+
1576,
|
| 628 |
+
175
|
| 629 |
+
],
|
| 630 |
+
"model.layers.5.mlp.up_proj": [
|
| 631 |
+
2007,
|
| 632 |
+
222
|
| 633 |
+
],
|
| 634 |
+
"model.layers.5.self_attn.k_proj": [
|
| 635 |
+
295,
|
| 636 |
+
32
|
| 637 |
+
],
|
| 638 |
+
"model.layers.5.self_attn.o_proj": [
|
| 639 |
+
461,
|
| 640 |
+
51
|
| 641 |
+
],
|
| 642 |
+
"model.layers.5.self_attn.q_proj": [
|
| 643 |
+
185,
|
| 644 |
+
20
|
| 645 |
+
],
|
| 646 |
+
"model.layers.5.self_attn.v_proj": [
|
| 647 |
+
184,
|
| 648 |
+
20
|
| 649 |
+
],
|
| 650 |
+
"model.layers.6.self_attn.k_proj": [
|
| 651 |
+
74,
|
| 652 |
+
8
|
| 653 |
+
],
|
| 654 |
+
"model.layers.6.self_attn.o_proj": [
|
| 655 |
+
1014,
|
| 656 |
+
112
|
| 657 |
+
],
|
| 658 |
+
"model.layers.6.self_attn.q_proj": [
|
| 659 |
+
185,
|
| 660 |
+
20
|
| 661 |
+
],
|
| 662 |
+
"model.layers.6.self_attn.v_proj": [
|
| 663 |
+
516,
|
| 664 |
+
57
|
| 665 |
+
],
|
| 666 |
+
"model.layers.7.self_attn.o_proj": [
|
| 667 |
+
1014,
|
| 668 |
+
112
|
| 669 |
+
],
|
| 670 |
+
"model.layers.7.self_attn.q_proj": [
|
| 671 |
+
461,
|
| 672 |
+
51
|
| 673 |
+
],
|
| 674 |
+
"model.layers.7.self_attn.v_proj": [
|
| 675 |
+
405,
|
| 676 |
+
45
|
| 677 |
+
],
|
| 678 |
+
"model.layers.8.mlp.down_proj": [
|
| 679 |
+
717,
|
| 680 |
+
79
|
| 681 |
+
],
|
| 682 |
+
"model.layers.8.mlp.gate_proj": [
|
| 683 |
+
717,
|
| 684 |
+
79
|
| 685 |
+
],
|
| 686 |
+
"model.layers.8.mlp.up_proj": [
|
| 687 |
+
1146,
|
| 688 |
+
127
|
| 689 |
+
],
|
| 690 |
+
"model.layers.8.self_attn.k_proj": [
|
| 691 |
+
74,
|
| 692 |
+
8
|
| 693 |
+
],
|
| 694 |
+
"model.layers.8.self_attn.o_proj": [
|
| 695 |
+
185,
|
| 696 |
+
20
|
| 697 |
+
],
|
| 698 |
+
"model.layers.8.self_attn.q_proj": [
|
| 699 |
+
185,
|
| 700 |
+
20
|
| 701 |
+
],
|
| 702 |
+
"model.layers.8.self_attn.v_proj": [
|
| 703 |
+
74,
|
| 704 |
+
8
|
| 705 |
+
],
|
| 706 |
+
"model.layers.9.mlp.down_proj": [
|
| 707 |
+
2007,
|
| 708 |
+
222
|
| 709 |
+
],
|
| 710 |
+
"model.layers.9.mlp.up_proj": [
|
| 711 |
+
2007,
|
| 712 |
+
222
|
| 713 |
+
],
|
| 714 |
+
"model.layers.9.self_attn.k_proj": [
|
| 715 |
+
184,
|
| 716 |
+
20
|
| 717 |
+
],
|
| 718 |
+
"model.layers.9.self_attn.o_proj": [
|
| 719 |
+
461,
|
| 720 |
+
51
|
| 721 |
+
],
|
| 722 |
+
"model.layers.9.self_attn.q_proj": [
|
| 723 |
+
461,
|
| 724 |
+
51
|
| 725 |
+
],
|
| 726 |
+
"model.layers.9.self_attn.v_proj": [
|
| 727 |
+
516,
|
| 728 |
+
57
|
| 729 |
+
]
|
| 730 |
+
},
|
| 731 |
+
"max_batch_size": 1
|
| 732 |
+
},
|
| 733 |
+
"vocab_size": 77209,
|
| 734 |
+
"context_window_size": 131072,
|
| 735 |
+
"sliding_window_size": -1,
|
| 736 |
+
"prefill_chunk_size": 131072,
|
| 737 |
+
"attention_sink_size": -1,
|
| 738 |
+
"tensor_parallel_shards": 1,
|
| 739 |
+
"max_batch_size": 80,
|
| 740 |
+
"mean_gen_len": 128,
|
| 741 |
+
"max_gen_len": 512,
|
| 742 |
+
"shift_fill_factor": 0.3,
|
| 743 |
+
"temperature": 0.6,
|
| 744 |
+
"repetition_penalty": 1.0,
|
| 745 |
+
"top_p": 0.9,
|
| 746 |
+
"conv_template": "LM",
|
| 747 |
+
"pad_token_id": 0,
|
| 748 |
+
"bos_token_id": 128000,
|
| 749 |
+
"eos_token_id": [
|
| 750 |
+
128001,
|
| 751 |
+
128008,
|
| 752 |
+
128009
|
| 753 |
+
],
|
| 754 |
+
"tokenizer_files": [
|
| 755 |
+
"tokenizer.json",
|
| 756 |
+
"tokenizer_config.json"
|
| 757 |
+
],
|
| 758 |
+
"version": "0.1.0"
|
| 759 |
+
}
|
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 sha256:65d3233e5b85aaca723a8057cd5c20c6a080300145407df23119ab197343a3cb
|
| 3 |
+
size 632496128
|
params_shard_1.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:71ad79ed5e8349e6d35cdb53e00d20c76dd7ab1d3252293ebcda4ccaae118a1f
|
| 3 |
+
size 117440512
|
params_shard_10.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ea01e3daa14023bccacec456da4fe7166622a0f240e3d1be087e57d01597dbaf
|
| 3 |
+
size 45187072
|
params_shard_100.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d439ac469adc2a0f52cba572006d29df63387d7f76f35686b16c589c872d1fdf
|
| 3 |
+
size 33112064
|
params_shard_101.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3dda676a8d317caa73347836420b1e9ff92c51a462a7dfd071acc139943dd7c8
|
| 3 |
+
size 32858112
|
params_shard_102.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:57fdc8b316712f8b703d938cef56d9b794ab2c95d0ce91aea28a4fde26266f27
|
| 3 |
+
size 45187072
|
params_shard_103.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ef2183235ce1c921b5597dc15a2fb65fedf7a7ad4cb92ff6d9f96d1369ab9729
|
| 3 |
+
size 26466304
|
params_shard_104.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7ac83b75ed0a02322431eefaed728c79a1a28b4371189ddc602a547f541f4fd1
|
| 3 |
+
size 117440512
|
params_shard_105.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c30c426bedc25d5288f7d2800c91aaafcb584963b074d95f5d7b181703c9a6ab
|
| 3 |
+
size 31545344
|
params_shard_106.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fd72d5f62129201a651a227ec6187a0b1f205c017b7fba22d7abb42e6aae0e64
|
| 3 |
+
size 45187072
|
params_shard_107.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:66e949ddcf31509f9eb6d6fac9c8b04750cff629c2292dd380af077012e687a5
|
| 3 |
+
size 117440512
|
params_shard_108.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e99ce5815e7258bc824dfe3f29fad7b80291d960f33856506085570772dbb90d
|
| 3 |
+
size 117440512
|
params_shard_109.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:73440539c0aaa3277b459ee85b37606769748c42b682ebda60720d9b2750eea8
|
| 3 |
+
size 31942656
|
params_shard_11.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:286b53e709d41d0116ec802081f682e4a5b53c7cb4f2ea287d5d9681d669cbcc
|
| 3 |
+
size 31027200
|
params_shard_110.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6a70f6f03667808e6a3c2cb1b55fe114dc9be40b91701bd6f1a89ea5746a304e
|
| 3 |
+
size 22228992
|
params_shard_111.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fe53099ccb172a305fa1bca72cd6cf7e6a43249853c5f8e6ff4f74f82b576ca5
|
| 3 |
+
size 45187072
|
params_shard_112.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:def4dbda87d6c59c94d7b67e6b0be4b16843bfe5da55f233d65abcac979c7848
|
| 3 |
+
size 32858112
|
params_shard_113.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c49fd14708fec6c77ce8ec97880b9be754b3734b2a990ffacfb3d665edd26bfb
|
| 3 |
+
size 117440512
|
params_shard_114.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:81100f4a872e26a77bfff715ebff2c7e0be63d1772ede331999ee6f229e0d056
|
| 3 |
+
size 33439744
|
params_shard_115.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fa8255e795473e2b6fc69ee7a72ca6b54de56c8c166468f43b84ec452f7a66db
|
| 3 |
+
size 30099456
|
params_shard_116.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7e086f74692dfa8217f6f924001ced29f7a3250bf5da84b5cc5ec0a59ec1653a
|
| 3 |
+
size 117440512
|
params_shard_117.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:04a3efccc410f6a398273538e59cb89e4e6a2b5a9c5d5d5f6f6b80c208d3af32
|
| 3 |
+
size 32858112
|
params_shard_118.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:deeddc3d8682f723e5a027c5799d6c9066f58efca0f653325eef491e7c88dfd0
|
| 3 |
+
size 69873664
|
params_shard_119.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:97666ea506d8356f816eef34c4b8ae83f0d43aa58ea302e86398e8de7725a01f
|
| 3 |
+
size 19963904
|
params_shard_12.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5ffa4f110581d43f49750c4432eb027ecafd98ca6f7e64c8c9e201eb422d25d4
|
| 3 |
+
size 45187072
|
params_shard_120.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f3b8eda758b330c817ff3cb3621da7d196024b4c5bec1ac53f0744f13fe537a2
|
| 3 |
+
size 28733440
|
params_shard_121.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ec5261e30244b55835f92b13ba9fddde15b8041a443863cc50a212c4661485b2
|
| 3 |
+
size 33122304
|
params_shard_122.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2ee7689a755ce25b029a42efc4a1d48827bf62fa4266a56dbee79bd515e0587e
|
| 3 |
+
size 117440512
|
params_shard_123.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b3fd01eed5f5a52263d4c6f25201a21e1264b1d410c37e46f57c62a232ddacdf
|
| 3 |
+
size 117440512
|
params_shard_124.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:df80d5e00232afc5c78117c7610db276fb25db6a111776187cc66ec4c22582f2
|
| 3 |
+
size 117440512
|
params_shard_125.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5d3d26c03213aa0666dccbf9217b7c601fe9b30fae28408d2011e506eff5392e
|
| 3 |
+
size 32299008
|
params_shard_126.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7396186ecd5c8d394e78b65f09ba97cebaec824d4d4617fd27481cfb8524b052
|
| 3 |
+
size 117440512
|
params_shard_127.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:264898b13aa03ff3d10d8008458cebee115e24a8ca04160b0401b0dc6d17714d
|
| 3 |
+
size 57544704
|
params_shard_128.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cd6b3e3910aeeb37e401de92395ea1fd40e4d086c350c44c117c44304bd614b0
|
| 3 |
+
size 117440512
|
params_shard_129.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1dfe4af4aa0f67a51b5b55c118ced79f05df19aa422a32aae1c68d850dd2dcd4
|
| 3 |
+
size 33030144
|
params_shard_13.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d1bf797cc78e289638733397129c737f447aae0c6192e2643cc6446bc9a19fee
|
| 3 |
+
size 32272384
|
params_shard_130.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:29a26991ddf66237510378aa015b608a5fec74be52cd6b05789e1b26f31527a4
|
| 3 |
+
size 27674624
|
params_shard_131.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:62210b28af08648f273fb5790944b78185fb263cf8fc9d999f6a29df04f0b264
|
| 3 |
+
size 117440512
|
params_shard_132.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:674702c498130c4a565635a3c7af830c666581f72bcd90d1c34610e10f298c84
|
| 3 |
+
size 117440512
|
params_shard_133.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6874d939b77589c7aff53e8de02b2ad79c50a4c388b4694d55417d1ccbccec16
|
| 3 |
+
size 117440512
|
params_shard_134.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:19f18c658b512ecea52ba1cf91a0b0e140c63112fc639714d441c09caec66b37
|
| 3 |
+
size 27271168
|
params_shard_135.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:19dc723fc396bf87cacacc6189eb0781033bee7ece9393bc564b5f89f7beaa54
|
| 3 |
+
size 45187072
|
params_shard_136.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7265fb9280268170062b39bc0154662e2ac7e48cbea731851ee3f7e19874b99d
|
| 3 |
+
size 117440512
|
params_shard_137.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dddfec9a7cf205e4c249484030008ec265f90ad2a97a7d29b052a277c327beb7
|
| 3 |
+
size 57544704
|
params_shard_138.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2701cbc2dddb976dba62deb8af03aa405e85ac473ef82805f9ea6d11f7f27dac
|
| 3 |
+
size 27758592
|
params_shard_139.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a138ee7c8feefe6690bd3e6f890b4fe730783c06c604c3b3be16140874bfe7e4
|
| 3 |
+
size 32176128
|
params_shard_14.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:809eb55a1f07debe1c603e2ad9b3f2d45d43a35bfbf58cb7506b1fe24e272592
|
| 3 |
+
size 25337856
|
params_shard_140.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0531ac9e5af64e9a3657bc995292c238e13edd1bb580611acb3d6b924d9666ab
|
| 3 |
+
size 117440512
|