model.safetensors.index.json
| 1 | { |
| 2 | "metadata": { |
| 3 | "format": "pt" |
| 4 | }, |
| 5 | "weight_map": { |
| 6 | "thinker.audio_tower.conv2d1.bias": "model-00001-of-00002.safetensors", |
| 7 | "thinker.audio_tower.conv2d1.weight": "model-00001-of-00002.safetensors", |
| 8 | "thinker.audio_tower.conv2d2.bias": "model-00001-of-00002.safetensors", |
| 9 | "thinker.audio_tower.conv2d2.weight": "model-00001-of-00002.safetensors", |
| 10 | "thinker.audio_tower.conv2d3.bias": "model-00001-of-00002.safetensors", |
| 11 | "thinker.audio_tower.conv2d3.weight": "model-00001-of-00002.safetensors", |
| 12 | "thinker.audio_tower.conv_out.weight": "model-00001-of-00002.safetensors", |
| 13 | "thinker.audio_tower.layers.0.fc1.bias": "model-00001-of-00002.safetensors", |
| 14 | "thinker.audio_tower.layers.0.fc1.weight": "model-00001-of-00002.safetensors", |
| 15 | "thinker.audio_tower.layers.0.fc2.bias": "model-00001-of-00002.safetensors", |
| 16 | "thinker.audio_tower.layers.0.fc2.weight": "model-00001-of-00002.safetensors", |
| 17 | "thinker.audio_tower.layers.0.final_layer_norm.bias": "model-00001-of-00002.safetensors", |
| 18 | "thinker.audio_tower.layers.0.final_layer_norm.weight": "model-00001-of-00002.safetensors", |
| 19 | "thinker.audio_tower.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", |
| 20 | "thinker.audio_tower.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", |
| 21 | "thinker.audio_tower.layers.0.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", |
| 22 | "thinker.audio_tower.layers.0.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", |
| 23 | "thinker.audio_tower.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", |
| 24 | "thinker.audio_tower.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", |
| 25 | "thinker.audio_tower.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", |
| 26 | "thinker.audio_tower.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", |
| 27 | "thinker.audio_tower.layers.0.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors", |
| 28 | "thinker.audio_tower.layers.0.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors", |
| 29 | "thinker.audio_tower.layers.1.fc1.bias": "model-00001-of-00002.safetensors", |
| 30 | "thinker.audio_tower.layers.1.fc1.weight": "model-00001-of-00002.safetensors", |
| 31 | "thinker.audio_tower.layers.1.fc2.bias": "model-00001-of-00002.safetensors", |
| 32 | "thinker.audio_tower.layers.1.fc2.weight": "model-00001-of-00002.safetensors", |
| 33 | "thinker.audio_tower.layers.1.final_layer_norm.bias": "model-00001-of-00002.safetensors", |
| 34 | "thinker.audio_tower.layers.1.final_layer_norm.weight": "model-00001-of-00002.safetensors", |
| 35 | "thinker.audio_tower.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", |
| 36 | "thinker.audio_tower.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", |
| 37 | "thinker.audio_tower.layers.1.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", |
| 38 | "thinker.audio_tower.layers.1.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", |
| 39 | "thinker.audio_tower.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", |
| 40 | "thinker.audio_tower.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", |
| 41 | "thinker.audio_tower.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", |
| 42 | "thinker.audio_tower.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", |
| 43 | "thinker.audio_tower.layers.1.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors", |
| 44 | "thinker.audio_tower.layers.1.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors", |
| 45 | "thinker.audio_tower.layers.10.fc1.bias": "model-00001-of-00002.safetensors", |
| 46 | "thinker.audio_tower.layers.10.fc1.weight": "model-00001-of-00002.safetensors", |
| 47 | "thinker.audio_tower.layers.10.fc2.bias": "model-00001-of-00002.safetensors", |
| 48 | "thinker.audio_tower.layers.10.fc2.weight": "model-00001-of-00002.safetensors", |
| 49 | "thinker.audio_tower.layers.10.final_layer_norm.bias": "model-00001-of-00002.safetensors", |
| 50 | "thinker.audio_tower.layers.10.final_layer_norm.weight": "model-00001-of-00002.safetensors", |
| 51 | "thinker.audio_tower.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", |
| 52 | "thinker.audio_tower.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", |
| 53 | "thinker.audio_tower.layers.10.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", |
| 54 | "thinker.audio_tower.layers.10.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", |
| 55 | "thinker.audio_tower.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", |
| 56 | "thinker.audio_tower.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", |
| 57 | "thinker.audio_tower.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", |
| 58 | "thinker.audio_tower.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", |
| 59 | "thinker.audio_tower.layers.10.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors", |
| 60 | "thinker.audio_tower.layers.10.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors", |
| 61 | "thinker.audio_tower.layers.11.fc1.bias": "model-00001-of-00002.safetensors", |
| 62 | "thinker.audio_tower.layers.11.fc1.weight": "model-00001-of-00002.safetensors", |
| 63 | "thinker.audio_tower.layers.11.fc2.bias": "model-00001-of-00002.safetensors", |
| 64 | "thinker.audio_tower.layers.11.fc2.weight": "model-00001-of-00002.safetensors", |
| 65 | "thinker.audio_tower.layers.11.final_layer_norm.bias": "model-00001-of-00002.safetensors", |
| 66 | "thinker.audio_tower.layers.11.final_layer_norm.weight": "model-00001-of-00002.safetensors", |
| 67 | "thinker.audio_tower.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", |
| 68 | "thinker.audio_tower.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", |
| 69 | "thinker.audio_tower.layers.11.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", |
| 70 | "thinker.audio_tower.layers.11.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", |
| 71 | "thinker.audio_tower.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", |
| 72 | "thinker.audio_tower.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", |
| 73 | "thinker.audio_tower.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", |
| 74 | "thinker.audio_tower.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", |
| 75 | "thinker.audio_tower.layers.11.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors", |
| 76 | "thinker.audio_tower.layers.11.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors", |
| 77 | "thinker.audio_tower.layers.12.fc1.bias": "model-00001-of-00002.safetensors", |
| 78 | "thinker.audio_tower.layers.12.fc1.weight": "model-00001-of-00002.safetensors", |
| 79 | "thinker.audio_tower.layers.12.fc2.bias": "model-00001-of-00002.safetensors", |
| 80 | "thinker.audio_tower.layers.12.fc2.weight": "model-00001-of-00002.safetensors", |
| 81 | "thinker.audio_tower.layers.12.final_layer_norm.bias": "model-00001-of-00002.safetensors", |
| 82 | "thinker.audio_tower.layers.12.final_layer_norm.weight": "model-00001-of-00002.safetensors", |
| 83 | "thinker.audio_tower.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", |
| 84 | "thinker.audio_tower.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", |
| 85 | "thinker.audio_tower.layers.12.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", |
| 86 | "thinker.audio_tower.layers.12.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", |
| 87 | "thinker.audio_tower.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", |
| 88 | "thinker.audio_tower.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", |
| 89 | "thinker.audio_tower.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", |
| 90 | "thinker.audio_tower.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", |
| 91 | "thinker.audio_tower.layers.12.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors", |
| 92 | "thinker.audio_tower.layers.12.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors", |
| 93 | "thinker.audio_tower.layers.13.fc1.bias": "model-00001-of-00002.safetensors", |
| 94 | "thinker.audio_tower.layers.13.fc1.weight": "model-00001-of-00002.safetensors", |
| 95 | "thinker.audio_tower.layers.13.fc2.bias": "model-00001-of-00002.safetensors", |
| 96 | "thinker.audio_tower.layers.13.fc2.weight": "model-00001-of-00002.safetensors", |
| 97 | "thinker.audio_tower.layers.13.final_layer_norm.bias": "model-00001-of-00002.safetensors", |
| 98 | "thinker.audio_tower.layers.13.final_layer_norm.weight": "model-00001-of-00002.safetensors", |
| 99 | "thinker.audio_tower.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", |
| 100 | "thinker.audio_tower.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", |
| 101 | "thinker.audio_tower.layers.13.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", |
| 102 | "thinker.audio_tower.layers.13.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", |
| 103 | "thinker.audio_tower.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", |
| 104 | "thinker.audio_tower.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", |
| 105 | "thinker.audio_tower.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", |
| 106 | "thinker.audio_tower.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", |
| 107 | "thinker.audio_tower.layers.13.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors", |
| 108 | "thinker.audio_tower.layers.13.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors", |
| 109 | "thinker.audio_tower.layers.14.fc1.bias": "model-00001-of-00002.safetensors", |
| 110 | "thinker.audio_tower.layers.14.fc1.weight": "model-00001-of-00002.safetensors", |
| 111 | "thinker.audio_tower.layers.14.fc2.bias": "model-00001-of-00002.safetensors", |
| 112 | "thinker.audio_tower.layers.14.fc2.weight": "model-00001-of-00002.safetensors", |
| 113 | "thinker.audio_tower.layers.14.final_layer_norm.bias": "model-00001-of-00002.safetensors", |
| 114 | "thinker.audio_tower.layers.14.final_layer_norm.weight": "model-00001-of-00002.safetensors", |
| 115 | "thinker.audio_tower.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", |
| 116 | "thinker.audio_tower.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", |
| 117 | "thinker.audio_tower.layers.14.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", |
| 118 | "thinker.audio_tower.layers.14.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", |
| 119 | "thinker.audio_tower.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", |
| 120 | "thinker.audio_tower.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", |
| 121 | "thinker.audio_tower.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", |
| 122 | "thinker.audio_tower.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", |
| 123 | "thinker.audio_tower.layers.14.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors", |
| 124 | "thinker.audio_tower.layers.14.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors", |
| 125 | "thinker.audio_tower.layers.15.fc1.bias": "model-00001-of-00002.safetensors", |
| 126 | "thinker.audio_tower.layers.15.fc1.weight": "model-00001-of-00002.safetensors", |
| 127 | "thinker.audio_tower.layers.15.fc2.bias": "model-00001-of-00002.safetensors", |
| 128 | "thinker.audio_tower.layers.15.fc2.weight": "model-00001-of-00002.safetensors", |
| 129 | "thinker.audio_tower.layers.15.final_layer_norm.bias": "model-00001-of-00002.safetensors", |
| 130 | "thinker.audio_tower.layers.15.final_layer_norm.weight": "model-00001-of-00002.safetensors", |
| 131 | "thinker.audio_tower.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", |
| 132 | "thinker.audio_tower.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", |
| 133 | "thinker.audio_tower.layers.15.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", |
| 134 | "thinker.audio_tower.layers.15.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", |
| 135 | "thinker.audio_tower.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", |
| 136 | "thinker.audio_tower.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", |
| 137 | "thinker.audio_tower.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", |
| 138 | "thinker.audio_tower.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", |
| 139 | "thinker.audio_tower.layers.15.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors", |
| 140 | "thinker.audio_tower.layers.15.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors", |
| 141 | "thinker.audio_tower.layers.16.fc1.bias": "model-00001-of-00002.safetensors", |
| 142 | "thinker.audio_tower.layers.16.fc1.weight": "model-00001-of-00002.safetensors", |
| 143 | "thinker.audio_tower.layers.16.fc2.bias": "model-00001-of-00002.safetensors", |
| 144 | "thinker.audio_tower.layers.16.fc2.weight": "model-00001-of-00002.safetensors", |
| 145 | "thinker.audio_tower.layers.16.final_layer_norm.bias": "model-00001-of-00002.safetensors", |
| 146 | "thinker.audio_tower.layers.16.final_layer_norm.weight": "model-00001-of-00002.safetensors", |
| 147 | "thinker.audio_tower.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", |
| 148 | "thinker.audio_tower.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", |
| 149 | "thinker.audio_tower.layers.16.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", |
| 150 | "thinker.audio_tower.layers.16.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", |
| 151 | "thinker.audio_tower.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", |
| 152 | "thinker.audio_tower.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", |
| 153 | "thinker.audio_tower.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", |
| 154 | "thinker.audio_tower.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", |
| 155 | "thinker.audio_tower.layers.16.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors", |
| 156 | "thinker.audio_tower.layers.16.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors", |
| 157 | "thinker.audio_tower.layers.17.fc1.bias": "model-00001-of-00002.safetensors", |
| 158 | "thinker.audio_tower.layers.17.fc1.weight": "model-00001-of-00002.safetensors", |
| 159 | "thinker.audio_tower.layers.17.fc2.bias": "model-00001-of-00002.safetensors", |
| 160 | "thinker.audio_tower.layers.17.fc2.weight": "model-00001-of-00002.safetensors", |
| 161 | "thinker.audio_tower.layers.17.final_layer_norm.bias": "model-00001-of-00002.safetensors", |
| 162 | "thinker.audio_tower.layers.17.final_layer_norm.weight": "model-00001-of-00002.safetensors", |
| 163 | "thinker.audio_tower.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", |
| 164 | "thinker.audio_tower.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", |
| 165 | "thinker.audio_tower.layers.17.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", |
| 166 | "thinker.audio_tower.layers.17.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", |
| 167 | "thinker.audio_tower.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", |
| 168 | "thinker.audio_tower.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", |
| 169 | "thinker.audio_tower.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", |
| 170 | "thinker.audio_tower.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", |
| 171 | "thinker.audio_tower.layers.17.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors", |
| 172 | "thinker.audio_tower.layers.17.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors", |
| 173 | "thinker.audio_tower.layers.18.fc1.bias": "model-00001-of-00002.safetensors", |
| 174 | "thinker.audio_tower.layers.18.fc1.weight": "model-00001-of-00002.safetensors", |
| 175 | "thinker.audio_tower.layers.18.fc2.bias": "model-00001-of-00002.safetensors", |
| 176 | "thinker.audio_tower.layers.18.fc2.weight": "model-00001-of-00002.safetensors", |
| 177 | "thinker.audio_tower.layers.18.final_layer_norm.bias": "model-00001-of-00002.safetensors", |
| 178 | "thinker.audio_tower.layers.18.final_layer_norm.weight": "model-00001-of-00002.safetensors", |
| 179 | "thinker.audio_tower.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", |
| 180 | "thinker.audio_tower.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", |
| 181 | "thinker.audio_tower.layers.18.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", |
| 182 | "thinker.audio_tower.layers.18.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", |
| 183 | "thinker.audio_tower.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", |
| 184 | "thinker.audio_tower.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", |
| 185 | "thinker.audio_tower.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", |
| 186 | "thinker.audio_tower.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", |
| 187 | "thinker.audio_tower.layers.18.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors", |
| 188 | "thinker.audio_tower.layers.18.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors", |
| 189 | "thinker.audio_tower.layers.19.fc1.bias": "model-00001-of-00002.safetensors", |
| 190 | "thinker.audio_tower.layers.19.fc1.weight": "model-00001-of-00002.safetensors", |
| 191 | "thinker.audio_tower.layers.19.fc2.bias": "model-00001-of-00002.safetensors", |
| 192 | "thinker.audio_tower.layers.19.fc2.weight": "model-00001-of-00002.safetensors", |
| 193 | "thinker.audio_tower.layers.19.final_layer_norm.bias": "model-00001-of-00002.safetensors", |
| 194 | "thinker.audio_tower.layers.19.final_layer_norm.weight": "model-00001-of-00002.safetensors", |
| 195 | "thinker.audio_tower.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", |
| 196 | "thinker.audio_tower.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", |
| 197 | "thinker.audio_tower.layers.19.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", |
| 198 | "thinker.audio_tower.layers.19.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", |
| 199 | "thinker.audio_tower.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", |
| 200 | "thinker.audio_tower.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", |
| 201 | "thinker.audio_tower.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", |
| 202 | "thinker.audio_tower.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", |
| 203 | "thinker.audio_tower.layers.19.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors", |
| 204 | "thinker.audio_tower.layers.19.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors", |
| 205 | "thinker.audio_tower.layers.2.fc1.bias": "model-00001-of-00002.safetensors", |
| 206 | "thinker.audio_tower.layers.2.fc1.weight": "model-00001-of-00002.safetensors", |
| 207 | "thinker.audio_tower.layers.2.fc2.bias": "model-00001-of-00002.safetensors", |
| 208 | "thinker.audio_tower.layers.2.fc2.weight": "model-00001-of-00002.safetensors", |
| 209 | "thinker.audio_tower.layers.2.final_layer_norm.bias": "model-00001-of-00002.safetensors", |
| 210 | "thinker.audio_tower.layers.2.final_layer_norm.weight": "model-00001-of-00002.safetensors", |
| 211 | "thinker.audio_tower.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", |
| 212 | "thinker.audio_tower.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", |
| 213 | "thinker.audio_tower.layers.2.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", |
| 214 | "thinker.audio_tower.layers.2.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", |
| 215 | "thinker.audio_tower.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", |
| 216 | "thinker.audio_tower.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", |
| 217 | "thinker.audio_tower.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", |
| 218 | "thinker.audio_tower.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", |
| 219 | "thinker.audio_tower.layers.2.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors", |
| 220 | "thinker.audio_tower.layers.2.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors", |
| 221 | "thinker.audio_tower.layers.20.fc1.bias": "model-00001-of-00002.safetensors", |
| 222 | "thinker.audio_tower.layers.20.fc1.weight": "model-00001-of-00002.safetensors", |
| 223 | "thinker.audio_tower.layers.20.fc2.bias": "model-00001-of-00002.safetensors", |
| 224 | "thinker.audio_tower.layers.20.fc2.weight": "model-00001-of-00002.safetensors", |
| 225 | "thinker.audio_tower.layers.20.final_layer_norm.bias": "model-00001-of-00002.safetensors", |
| 226 | "thinker.audio_tower.layers.20.final_layer_norm.weight": "model-00001-of-00002.safetensors", |
| 227 | "thinker.audio_tower.layers.20.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", |
| 228 | "thinker.audio_tower.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", |
| 229 | "thinker.audio_tower.layers.20.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", |
| 230 | "thinker.audio_tower.layers.20.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", |
| 231 | "thinker.audio_tower.layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", |
| 232 | "thinker.audio_tower.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", |
| 233 | "thinker.audio_tower.layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", |
| 234 | "thinker.audio_tower.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", |
| 235 | "thinker.audio_tower.layers.20.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors", |
| 236 | "thinker.audio_tower.layers.20.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors", |
| 237 | "thinker.audio_tower.layers.21.fc1.bias": "model-00001-of-00002.safetensors", |
| 238 | "thinker.audio_tower.layers.21.fc1.weight": "model-00001-of-00002.safetensors", |
| 239 | "thinker.audio_tower.layers.21.fc2.bias": "model-00001-of-00002.safetensors", |
| 240 | "thinker.audio_tower.layers.21.fc2.weight": "model-00001-of-00002.safetensors", |
| 241 | "thinker.audio_tower.layers.21.final_layer_norm.bias": "model-00001-of-00002.safetensors", |
| 242 | "thinker.audio_tower.layers.21.final_layer_norm.weight": "model-00001-of-00002.safetensors", |
| 243 | "thinker.audio_tower.layers.21.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", |
| 244 | "thinker.audio_tower.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", |
| 245 | "thinker.audio_tower.layers.21.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", |
| 246 | "thinker.audio_tower.layers.21.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", |
| 247 | "thinker.audio_tower.layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", |
| 248 | "thinker.audio_tower.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", |
| 249 | "thinker.audio_tower.layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", |
| 250 | "thinker.audio_tower.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", |
| 251 | "thinker.audio_tower.layers.21.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors", |
| 252 | "thinker.audio_tower.layers.21.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors", |
| 253 | "thinker.audio_tower.layers.22.fc1.bias": "model-00001-of-00002.safetensors", |
| 254 | "thinker.audio_tower.layers.22.fc1.weight": "model-00001-of-00002.safetensors", |
| 255 | "thinker.audio_tower.layers.22.fc2.bias": "model-00001-of-00002.safetensors", |
| 256 | "thinker.audio_tower.layers.22.fc2.weight": "model-00001-of-00002.safetensors", |
| 257 | "thinker.audio_tower.layers.22.final_layer_norm.bias": "model-00001-of-00002.safetensors", |
| 258 | "thinker.audio_tower.layers.22.final_layer_norm.weight": "model-00001-of-00002.safetensors", |
| 259 | "thinker.audio_tower.layers.22.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", |
| 260 | "thinker.audio_tower.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", |
| 261 | "thinker.audio_tower.layers.22.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", |
| 262 | "thinker.audio_tower.layers.22.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", |
| 263 | "thinker.audio_tower.layers.22.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", |
| 264 | "thinker.audio_tower.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", |
| 265 | "thinker.audio_tower.layers.22.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", |
| 266 | "thinker.audio_tower.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", |
| 267 | "thinker.audio_tower.layers.22.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors", |
| 268 | "thinker.audio_tower.layers.22.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors", |
| 269 | "thinker.audio_tower.layers.23.fc1.bias": "model-00001-of-00002.safetensors", |
| 270 | "thinker.audio_tower.layers.23.fc1.weight": "model-00001-of-00002.safetensors", |
| 271 | "thinker.audio_tower.layers.23.fc2.bias": "model-00001-of-00002.safetensors", |
| 272 | "thinker.audio_tower.layers.23.fc2.weight": "model-00001-of-00002.safetensors", |
| 273 | "thinker.audio_tower.layers.23.final_layer_norm.bias": "model-00001-of-00002.safetensors", |
| 274 | "thinker.audio_tower.layers.23.final_layer_norm.weight": "model-00001-of-00002.safetensors", |
| 275 | "thinker.audio_tower.layers.23.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", |
| 276 | "thinker.audio_tower.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", |
| 277 | "thinker.audio_tower.layers.23.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", |
| 278 | "thinker.audio_tower.layers.23.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", |
| 279 | "thinker.audio_tower.layers.23.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", |
| 280 | "thinker.audio_tower.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", |
| 281 | "thinker.audio_tower.layers.23.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", |
| 282 | "thinker.audio_tower.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", |
| 283 | "thinker.audio_tower.layers.23.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors", |
| 284 | "thinker.audio_tower.layers.23.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors", |
| 285 | "thinker.audio_tower.layers.3.fc1.bias": "model-00001-of-00002.safetensors", |
| 286 | "thinker.audio_tower.layers.3.fc1.weight": "model-00001-of-00002.safetensors", |
| 287 | "thinker.audio_tower.layers.3.fc2.bias": "model-00001-of-00002.safetensors", |
| 288 | "thinker.audio_tower.layers.3.fc2.weight": "model-00001-of-00002.safetensors", |
| 289 | "thinker.audio_tower.layers.3.final_layer_norm.bias": "model-00001-of-00002.safetensors", |
| 290 | "thinker.audio_tower.layers.3.final_layer_norm.weight": "model-00001-of-00002.safetensors", |
| 291 | "thinker.audio_tower.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", |
| 292 | "thinker.audio_tower.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", |
| 293 | "thinker.audio_tower.layers.3.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", |
| 294 | "thinker.audio_tower.layers.3.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", |
| 295 | "thinker.audio_tower.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", |
| 296 | "thinker.audio_tower.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", |
| 297 | "thinker.audio_tower.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", |
| 298 | "thinker.audio_tower.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", |
| 299 | "thinker.audio_tower.layers.3.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors", |
| 300 | "thinker.audio_tower.layers.3.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors", |
| 301 | "thinker.audio_tower.layers.4.fc1.bias": "model-00001-of-00002.safetensors", |
| 302 | "thinker.audio_tower.layers.4.fc1.weight": "model-00001-of-00002.safetensors", |
| 303 | "thinker.audio_tower.layers.4.fc2.bias": "model-00001-of-00002.safetensors", |
| 304 | "thinker.audio_tower.layers.4.fc2.weight": "model-00001-of-00002.safetensors", |
| 305 | "thinker.audio_tower.layers.4.final_layer_norm.bias": "model-00001-of-00002.safetensors", |
| 306 | "thinker.audio_tower.layers.4.final_layer_norm.weight": "model-00001-of-00002.safetensors", |
| 307 | "thinker.audio_tower.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", |
| 308 | "thinker.audio_tower.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", |
| 309 | "thinker.audio_tower.layers.4.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", |
| 310 | "thinker.audio_tower.layers.4.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", |
| 311 | "thinker.audio_tower.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", |
| 312 | "thinker.audio_tower.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", |
| 313 | "thinker.audio_tower.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", |
| 314 | "thinker.audio_tower.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", |
| 315 | "thinker.audio_tower.layers.4.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors", |
| 316 | "thinker.audio_tower.layers.4.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors", |
| 317 | "thinker.audio_tower.layers.5.fc1.bias": "model-00001-of-00002.safetensors", |
| 318 | "thinker.audio_tower.layers.5.fc1.weight": "model-00001-of-00002.safetensors", |
| 319 | "thinker.audio_tower.layers.5.fc2.bias": "model-00001-of-00002.safetensors", |
| 320 | "thinker.audio_tower.layers.5.fc2.weight": "model-00001-of-00002.safetensors", |
| 321 | "thinker.audio_tower.layers.5.final_layer_norm.bias": "model-00001-of-00002.safetensors", |
| 322 | "thinker.audio_tower.layers.5.final_layer_norm.weight": "model-00001-of-00002.safetensors", |
| 323 | "thinker.audio_tower.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", |
| 324 | "thinker.audio_tower.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", |
| 325 | "thinker.audio_tower.layers.5.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", |
| 326 | "thinker.audio_tower.layers.5.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", |
| 327 | "thinker.audio_tower.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", |
| 328 | "thinker.audio_tower.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", |
| 329 | "thinker.audio_tower.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", |
| 330 | "thinker.audio_tower.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", |
| 331 | "thinker.audio_tower.layers.5.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors", |
| 332 | "thinker.audio_tower.layers.5.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors", |
| 333 | "thinker.audio_tower.layers.6.fc1.bias": "model-00001-of-00002.safetensors", |
| 334 | "thinker.audio_tower.layers.6.fc1.weight": "model-00001-of-00002.safetensors", |
| 335 | "thinker.audio_tower.layers.6.fc2.bias": "model-00001-of-00002.safetensors", |
| 336 | "thinker.audio_tower.layers.6.fc2.weight": "model-00001-of-00002.safetensors", |
| 337 | "thinker.audio_tower.layers.6.final_layer_norm.bias": "model-00001-of-00002.safetensors", |
| 338 | "thinker.audio_tower.layers.6.final_layer_norm.weight": "model-00001-of-00002.safetensors", |
| 339 | "thinker.audio_tower.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", |
| 340 | "thinker.audio_tower.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", |
| 341 | "thinker.audio_tower.layers.6.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", |
| 342 | "thinker.audio_tower.layers.6.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", |
| 343 | "thinker.audio_tower.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", |
| 344 | "thinker.audio_tower.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", |
| 345 | "thinker.audio_tower.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", |
| 346 | "thinker.audio_tower.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", |
| 347 | "thinker.audio_tower.layers.6.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors", |
| 348 | "thinker.audio_tower.layers.6.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors", |
| 349 | "thinker.audio_tower.layers.7.fc1.bias": "model-00001-of-00002.safetensors", |
| 350 | "thinker.audio_tower.layers.7.fc1.weight": "model-00001-of-00002.safetensors", |
| 351 | "thinker.audio_tower.layers.7.fc2.bias": "model-00001-of-00002.safetensors", |
| 352 | "thinker.audio_tower.layers.7.fc2.weight": "model-00001-of-00002.safetensors", |
| 353 | "thinker.audio_tower.layers.7.final_layer_norm.bias": "model-00001-of-00002.safetensors", |
| 354 | "thinker.audio_tower.layers.7.final_layer_norm.weight": "model-00001-of-00002.safetensors", |
| 355 | "thinker.audio_tower.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", |
| 356 | "thinker.audio_tower.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", |
| 357 | "thinker.audio_tower.layers.7.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", |
| 358 | "thinker.audio_tower.layers.7.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", |
| 359 | "thinker.audio_tower.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", |
| 360 | "thinker.audio_tower.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", |
| 361 | "thinker.audio_tower.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", |
| 362 | "thinker.audio_tower.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", |
| 363 | "thinker.audio_tower.layers.7.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors", |
| 364 | "thinker.audio_tower.layers.7.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors", |
| 365 | "thinker.audio_tower.layers.8.fc1.bias": "model-00001-of-00002.safetensors", |
| 366 | "thinker.audio_tower.layers.8.fc1.weight": "model-00001-of-00002.safetensors", |
| 367 | "thinker.audio_tower.layers.8.fc2.bias": "model-00001-of-00002.safetensors", |
| 368 | "thinker.audio_tower.layers.8.fc2.weight": "model-00001-of-00002.safetensors", |
| 369 | "thinker.audio_tower.layers.8.final_layer_norm.bias": "model-00001-of-00002.safetensors", |
| 370 | "thinker.audio_tower.layers.8.final_layer_norm.weight": "model-00001-of-00002.safetensors", |
| 371 | "thinker.audio_tower.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", |
| 372 | "thinker.audio_tower.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", |
| 373 | "thinker.audio_tower.layers.8.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", |
| 374 | "thinker.audio_tower.layers.8.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", |
| 375 | "thinker.audio_tower.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", |
| 376 | "thinker.audio_tower.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", |
| 377 | "thinker.audio_tower.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", |
| 378 | "thinker.audio_tower.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", |
| 379 | "thinker.audio_tower.layers.8.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors", |
| 380 | "thinker.audio_tower.layers.8.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors", |
| 381 | "thinker.audio_tower.layers.9.fc1.bias": "model-00001-of-00002.safetensors", |
| 382 | "thinker.audio_tower.layers.9.fc1.weight": "model-00001-of-00002.safetensors", |
| 383 | "thinker.audio_tower.layers.9.fc2.bias": "model-00001-of-00002.safetensors", |
| 384 | "thinker.audio_tower.layers.9.fc2.weight": "model-00001-of-00002.safetensors", |
| 385 | "thinker.audio_tower.layers.9.final_layer_norm.bias": "model-00001-of-00002.safetensors", |
| 386 | "thinker.audio_tower.layers.9.final_layer_norm.weight": "model-00001-of-00002.safetensors", |
| 387 | "thinker.audio_tower.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", |
| 388 | "thinker.audio_tower.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", |
| 389 | "thinker.audio_tower.layers.9.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", |
| 390 | "thinker.audio_tower.layers.9.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", |
| 391 | "thinker.audio_tower.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", |
| 392 | "thinker.audio_tower.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", |
| 393 | "thinker.audio_tower.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", |
| 394 | "thinker.audio_tower.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", |
| 395 | "thinker.audio_tower.layers.9.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors", |
| 396 | "thinker.audio_tower.layers.9.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors", |
| 397 | "thinker.audio_tower.ln_post.bias": "model-00001-of-00002.safetensors", |
| 398 | "thinker.audio_tower.ln_post.weight": "model-00001-of-00002.safetensors", |
| 399 | "thinker.audio_tower.proj1.bias": "model-00001-of-00002.safetensors", |
| 400 | "thinker.audio_tower.proj1.weight": "model-00001-of-00002.safetensors", |
| 401 | "thinker.audio_tower.proj2.bias": "model-00001-of-00002.safetensors", |
| 402 | "thinker.audio_tower.proj2.weight": "model-00001-of-00002.safetensors", |
| 403 | "thinker.lm_head.weight": "model-00001-of-00002.safetensors", |
| 404 | "thinker.model.embed_tokens.weight": "model-00001-of-00002.safetensors", |
| 405 | "thinker.model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors", |
| 406 | "thinker.model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors", |
| 407 | "thinker.model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", |
| 408 | "thinker.model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors", |
| 409 | "thinker.model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", |
| 410 | "thinker.model.layers.0.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", |
| 411 | "thinker.model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", |
| 412 | "thinker.model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", |
| 413 | "thinker.model.layers.0.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", |
| 414 | "thinker.model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", |
| 415 | "thinker.model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", |
| 416 | "thinker.model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors", |
| 417 | "thinker.model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors", |
| 418 | "thinker.model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", |
| 419 | "thinker.model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors", |
| 420 | "thinker.model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", |
| 421 | "thinker.model.layers.1.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", |
| 422 | "thinker.model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", |
| 423 | "thinker.model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", |
| 424 | "thinker.model.layers.1.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", |
| 425 | "thinker.model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", |
| 426 | "thinker.model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", |
| 427 | "thinker.model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors", |
| 428 | "thinker.model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors", |
| 429 | "thinker.model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", |
| 430 | "thinker.model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors", |
| 431 | "thinker.model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", |
| 432 | "thinker.model.layers.10.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", |
| 433 | "thinker.model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", |
| 434 | "thinker.model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", |
| 435 | "thinker.model.layers.10.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", |
| 436 | "thinker.model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", |
| 437 | "thinker.model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", |
| 438 | "thinker.model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors", |
| 439 | "thinker.model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors", |
| 440 | "thinker.model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", |
| 441 | "thinker.model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors", |
| 442 | "thinker.model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", |
| 443 | "thinker.model.layers.11.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", |
| 444 | "thinker.model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", |
| 445 | "thinker.model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", |
| 446 | "thinker.model.layers.11.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", |
| 447 | "thinker.model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", |
| 448 | "thinker.model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", |
| 449 | "thinker.model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors", |
| 450 | "thinker.model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors", |
| 451 | "thinker.model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", |
| 452 | "thinker.model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors", |
| 453 | "thinker.model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", |
| 454 | "thinker.model.layers.12.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", |
| 455 | "thinker.model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", |
| 456 | "thinker.model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", |
| 457 | "thinker.model.layers.12.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", |
| 458 | "thinker.model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", |
| 459 | "thinker.model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", |
| 460 | "thinker.model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors", |
| 461 | "thinker.model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors", |
| 462 | "thinker.model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", |
| 463 | "thinker.model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors", |
| 464 | "thinker.model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", |
| 465 | "thinker.model.layers.13.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", |
| 466 | "thinker.model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", |
| 467 | "thinker.model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", |
| 468 | "thinker.model.layers.13.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", |
| 469 | "thinker.model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", |
| 470 | "thinker.model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", |
| 471 | "thinker.model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors", |
| 472 | "thinker.model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors", |
| 473 | "thinker.model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", |
| 474 | "thinker.model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors", |
| 475 | "thinker.model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", |
| 476 | "thinker.model.layers.14.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", |
| 477 | "thinker.model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", |
| 478 | "thinker.model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", |
| 479 | "thinker.model.layers.14.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", |
| 480 | "thinker.model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", |
| 481 | "thinker.model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", |
| 482 | "thinker.model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors", |
| 483 | "thinker.model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors", |
| 484 | "thinker.model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", |
| 485 | "thinker.model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors", |
| 486 | "thinker.model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", |
| 487 | "thinker.model.layers.15.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", |
| 488 | "thinker.model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", |
| 489 | "thinker.model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", |
| 490 | "thinker.model.layers.15.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", |
| 491 | "thinker.model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", |
| 492 | "thinker.model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", |
| 493 | "thinker.model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors", |
| 494 | "thinker.model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors", |
| 495 | "thinker.model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", |
| 496 | "thinker.model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors", |
| 497 | "thinker.model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", |
| 498 | "thinker.model.layers.16.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", |
| 499 | "thinker.model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", |
| 500 | "thinker.model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", |
| 501 | "thinker.model.layers.16.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", |
| 502 | "thinker.model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", |
| 503 | "thinker.model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", |
| 504 | "thinker.model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors", |
| 505 | "thinker.model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors", |
| 506 | "thinker.model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", |
| 507 | "thinker.model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors", |
| 508 | "thinker.model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", |
| 509 | "thinker.model.layers.17.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", |
| 510 | "thinker.model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", |
| 511 | "thinker.model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", |
| 512 | "thinker.model.layers.17.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", |
| 513 | "thinker.model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", |
| 514 | "thinker.model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", |
| 515 | "thinker.model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors", |
| 516 | "thinker.model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors", |
| 517 | "thinker.model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", |
| 518 | "thinker.model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors", |
| 519 | "thinker.model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", |
| 520 | "thinker.model.layers.18.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", |
| 521 | "thinker.model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", |
| 522 | "thinker.model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", |
| 523 | "thinker.model.layers.18.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", |
| 524 | "thinker.model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", |
| 525 | "thinker.model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", |
| 526 | "thinker.model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors", |
| 527 | "thinker.model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors", |
| 528 | "thinker.model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", |
| 529 | "thinker.model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors", |
| 530 | "thinker.model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", |
| 531 | "thinker.model.layers.19.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", |
| 532 | "thinker.model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", |
| 533 | "thinker.model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", |
| 534 | "thinker.model.layers.19.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", |
| 535 | "thinker.model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", |
| 536 | "thinker.model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", |
| 537 | "thinker.model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors", |
| 538 | "thinker.model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors", |
| 539 | "thinker.model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", |
| 540 | "thinker.model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors", |
| 541 | "thinker.model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", |
| 542 | "thinker.model.layers.2.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", |
| 543 | "thinker.model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", |
| 544 | "thinker.model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", |
| 545 | "thinker.model.layers.2.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", |
| 546 | "thinker.model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", |
| 547 | "thinker.model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", |
| 548 | "thinker.model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors", |
| 549 | "thinker.model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors", |
| 550 | "thinker.model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", |
| 551 | "thinker.model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors", |
| 552 | "thinker.model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", |
| 553 | "thinker.model.layers.20.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", |
| 554 | "thinker.model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", |
| 555 | "thinker.model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", |
| 556 | "thinker.model.layers.20.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", |
| 557 | "thinker.model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", |
| 558 | "thinker.model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", |
| 559 | "thinker.model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors", |
| 560 | "thinker.model.layers.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors", |
| 561 | "thinker.model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", |
| 562 | "thinker.model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors", |
| 563 | "thinker.model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", |
| 564 | "thinker.model.layers.21.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", |
| 565 | "thinker.model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", |
| 566 | "thinker.model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", |
| 567 | "thinker.model.layers.21.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", |
| 568 | "thinker.model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", |
| 569 | "thinker.model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", |
| 570 | "thinker.model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors", |
| 571 | "thinker.model.layers.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors", |
| 572 | "thinker.model.layers.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", |
| 573 | "thinker.model.layers.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors", |
| 574 | "thinker.model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", |
| 575 | "thinker.model.layers.22.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", |
| 576 | "thinker.model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", |
| 577 | "thinker.model.layers.22.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", |
| 578 | "thinker.model.layers.22.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", |
| 579 | "thinker.model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", |
| 580 | "thinker.model.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", |
| 581 | "thinker.model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors", |
| 582 | "thinker.model.layers.23.mlp.down_proj.weight": "model-00001-of-00002.safetensors", |
| 583 | "thinker.model.layers.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", |
| 584 | "thinker.model.layers.23.mlp.up_proj.weight": "model-00001-of-00002.safetensors", |
| 585 | "thinker.model.layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", |
| 586 | "thinker.model.layers.23.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", |
| 587 | "thinker.model.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", |
| 588 | "thinker.model.layers.23.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", |
| 589 | "thinker.model.layers.23.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", |
| 590 | "thinker.model.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", |
| 591 | "thinker.model.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", |
| 592 | "thinker.model.layers.24.input_layernorm.weight": "model-00001-of-00002.safetensors", |
| 593 | "thinker.model.layers.24.mlp.down_proj.weight": "model-00001-of-00002.safetensors", |
| 594 | "thinker.model.layers.24.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", |
| 595 | "thinker.model.layers.24.mlp.up_proj.weight": "model-00001-of-00002.safetensors", |
| 596 | "thinker.model.layers.24.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", |
| 597 | "thinker.model.layers.24.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", |
| 598 | "thinker.model.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", |
| 599 | "thinker.model.layers.24.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", |
| 600 | "thinker.model.layers.24.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", |
| 601 | "thinker.model.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", |
| 602 | "thinker.model.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", |
| 603 | "thinker.model.layers.25.input_layernorm.weight": "model-00001-of-00002.safetensors", |
| 604 | "thinker.model.layers.25.mlp.down_proj.weight": "model-00001-of-00002.safetensors", |
| 605 | "thinker.model.layers.25.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", |
| 606 | "thinker.model.layers.25.mlp.up_proj.weight": "model-00001-of-00002.safetensors", |
| 607 | "thinker.model.layers.25.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", |
| 608 | "thinker.model.layers.25.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", |
| 609 | "thinker.model.layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", |
| 610 | "thinker.model.layers.25.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", |
| 611 | "thinker.model.layers.25.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", |
| 612 | "thinker.model.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", |
| 613 | "thinker.model.layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", |
| 614 | "thinker.model.layers.26.input_layernorm.weight": "model-00001-of-00002.safetensors", |
| 615 | "thinker.model.layers.26.mlp.down_proj.weight": "model-00001-of-00002.safetensors", |
| 616 | "thinker.model.layers.26.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", |
| 617 | "thinker.model.layers.26.mlp.up_proj.weight": "model-00001-of-00002.safetensors", |
| 618 | "thinker.model.layers.26.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", |
| 619 | "thinker.model.layers.26.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", |
| 620 | "thinker.model.layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", |
| 621 | "thinker.model.layers.26.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", |
| 622 | "thinker.model.layers.26.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", |
| 623 | "thinker.model.layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", |
| 624 | "thinker.model.layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", |
| 625 | "thinker.model.layers.27.input_layernorm.weight": "model-00001-of-00002.safetensors", |
| 626 | "thinker.model.layers.27.mlp.down_proj.weight": "model-00001-of-00002.safetensors", |
| 627 | "thinker.model.layers.27.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", |
| 628 | "thinker.model.layers.27.mlp.up_proj.weight": "model-00001-of-00002.safetensors", |
| 629 | "thinker.model.layers.27.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", |
| 630 | "thinker.model.layers.27.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", |
| 631 | "thinker.model.layers.27.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", |
| 632 | "thinker.model.layers.27.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", |
| 633 | "thinker.model.layers.27.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", |
| 634 | "thinker.model.layers.27.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", |
| 635 | "thinker.model.layers.27.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", |
| 636 | "thinker.model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors", |
| 637 | "thinker.model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors", |
| 638 | "thinker.model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", |
| 639 | "thinker.model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors", |
| 640 | "thinker.model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", |
| 641 | "thinker.model.layers.3.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", |
| 642 | "thinker.model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", |
| 643 | "thinker.model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", |
| 644 | "thinker.model.layers.3.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", |
| 645 | "thinker.model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", |
| 646 | "thinker.model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", |
| 647 | "thinker.model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors", |
| 648 | "thinker.model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors", |
| 649 | "thinker.model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", |
| 650 | "thinker.model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors", |
| 651 | "thinker.model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", |
| 652 | "thinker.model.layers.4.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", |
| 653 | "thinker.model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", |
| 654 | "thinker.model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", |
| 655 | "thinker.model.layers.4.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", |
| 656 | "thinker.model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", |
| 657 | "thinker.model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", |
| 658 | "thinker.model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors", |
| 659 | "thinker.model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors", |
| 660 | "thinker.model.layers.5.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", |
| 661 | "thinker.model.layers.5.mlp.up_proj.weight": "model-00002-of-00002.safetensors", |
| 662 | "thinker.model.layers.5.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", |
| 663 | "thinker.model.layers.5.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", |
| 664 | "thinker.model.layers.5.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", |
| 665 | "thinker.model.layers.5.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", |
| 666 | "thinker.model.layers.5.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", |
| 667 | "thinker.model.layers.5.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", |
| 668 | "thinker.model.layers.5.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", |
| 669 | "thinker.model.layers.6.input_layernorm.weight": "model-00002-of-00002.safetensors", |
| 670 | "thinker.model.layers.6.mlp.down_proj.weight": "model-00002-of-00002.safetensors", |
| 671 | "thinker.model.layers.6.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", |
| 672 | "thinker.model.layers.6.mlp.up_proj.weight": "model-00002-of-00002.safetensors", |
| 673 | "thinker.model.layers.6.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", |
| 674 | "thinker.model.layers.6.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", |
| 675 | "thinker.model.layers.6.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", |
| 676 | "thinker.model.layers.6.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", |
| 677 | "thinker.model.layers.6.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", |
| 678 | "thinker.model.layers.6.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", |
| 679 | "thinker.model.layers.6.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", |
| 680 | "thinker.model.layers.7.input_layernorm.weight": "model-00002-of-00002.safetensors", |
| 681 | "thinker.model.layers.7.mlp.down_proj.weight": "model-00002-of-00002.safetensors", |
| 682 | "thinker.model.layers.7.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", |
| 683 | "thinker.model.layers.7.mlp.up_proj.weight": "model-00002-of-00002.safetensors", |
| 684 | "thinker.model.layers.7.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", |
| 685 | "thinker.model.layers.7.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", |
| 686 | "thinker.model.layers.7.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", |
| 687 | "thinker.model.layers.7.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", |
| 688 | "thinker.model.layers.7.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", |
| 689 | "thinker.model.layers.7.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", |
| 690 | "thinker.model.layers.7.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", |
| 691 | "thinker.model.layers.8.input_layernorm.weight": "model-00002-of-00002.safetensors", |
| 692 | "thinker.model.layers.8.mlp.down_proj.weight": "model-00002-of-00002.safetensors", |
| 693 | "thinker.model.layers.8.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", |
| 694 | "thinker.model.layers.8.mlp.up_proj.weight": "model-00002-of-00002.safetensors", |
| 695 | "thinker.model.layers.8.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", |
| 696 | "thinker.model.layers.8.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", |
| 697 | "thinker.model.layers.8.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", |
| 698 | "thinker.model.layers.8.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", |
| 699 | "thinker.model.layers.8.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", |
| 700 | "thinker.model.layers.8.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", |
| 701 | "thinker.model.layers.8.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", |
| 702 | "thinker.model.layers.9.input_layernorm.weight": "model-00002-of-00002.safetensors", |
| 703 | "thinker.model.layers.9.mlp.down_proj.weight": "model-00002-of-00002.safetensors", |
| 704 | "thinker.model.layers.9.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", |
| 705 | "thinker.model.layers.9.mlp.up_proj.weight": "model-00002-of-00002.safetensors", |
| 706 | "thinker.model.layers.9.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", |
| 707 | "thinker.model.layers.9.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", |
| 708 | "thinker.model.layers.9.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", |
| 709 | "thinker.model.layers.9.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", |
| 710 | "thinker.model.layers.9.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", |
| 711 | "thinker.model.layers.9.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", |
| 712 | "thinker.model.layers.9.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", |
| 713 | "thinker.model.norm.weight": "model-00002-of-00002.safetensors" |
| 714 | } |
| 715 | } |