llama_model_loader: - tensor 0: token_embd.weight q4_0 [ 4096, 32000, 1, 1 ] llama_model_loader: - tensor 1: output_norm.weight f32 [ 4096, 1, 1, 1 ] llama_model_loader: - tensor 2: output.weight q6_K [ 4096, 32000, 1, 1 ] llama_model_loader: - tensor 3: blk.0.attn_norm.weight f32 [ 4096, 1, 1, 1 ] llama_model_loader: - tensor 4: blk.0.attn_q.weight q4_0 [ 4096, 4096, 1, 1 ] llama_model_loader: - tensor 5: blk.0.attn_k.weight q8_0 [ 4096, 1024, 1, 1 ] llama_model_loader: - tensor 6: blk.0.attn_v.weight q8_0 [ 4096, 1024, 1, 1 ] llama_model_loader: - tensor 7: blk.0.attn_output.weight q4_0 [ 4096, 4096, 1, 1 ] llama_model_loader: - tensor 8: blk.0.ffn_gate_inp.weight f16 [ 4096, 8, 1, 1 ] llama_model_loader: - tensor 9: blk.0.ffn_norm.weight f32 [ 4096, 1, 1, 1 ] llama_model_loader: - tensor 10: blk.1.attn_norm.weight f32 [ 4096, 1, 1, 1 ] llama_model_loader: - tensor 11: blk.1.attn_q.weight q4_0 [ 4096, 4096, 1, 1 ] llama_model_loader: - tensor 12: blk.1.attn_k.weight q8_0 [ 4096, 1024, 1, 1 ] llama_model_loader: - tensor 13: blk.1.attn_v.weight q8_0 [ 4096, 1024, 1, 1 ] llama_model_loader: - tensor 14: blk.1.attn_output.weight q4_0 [ 4096, 4096, 1, 1 ] llama_model_loader: - tensor 15: blk.1.ffn_gate_inp.weight f16 [ 4096, 8, 1, 1 ] llama_model_loader: - tensor 16: blk.1.ffn_norm.weight f32 [ 4096, 1, 1, 1 ] llama_model_loader: - tensor 17: blk.2.attn_norm.weight f32 [ 4096, 1, 1, 1 ] llama_model_loader: - tensor 18: blk.2.attn_q.weight q4_0 [ 4096, 4096, 1, 1 ] llama_model_loader: - tensor 19: blk.2.attn_k.weight q8_0 [ 4096, 1024, 1, 1 ] llama_model_loader: - tensor 20: blk.2.attn_v.weight q8_0 [ 4096, 1024, 1, 1 ] llama_model_loader: - tensor 21: blk.2.attn_output.weight q4_0 [ 4096, 4096, 1, 1 ] llama_model_loader: - tensor 22: blk.2.ffn_gate_inp.weight f16 [ 4096, 8, 1, 1 ] llama_model_loader: - tensor 23: blk.2.ffn_norm.weight f32 [ 4096, 1, 1, 1 ] llama_model_loader: - tensor 24: blk.3.attn_norm.weight f32 [ 4096, 1, 1, 1 ] llama_model_loader: - tensor 25: blk.3.attn_q.weight q4_0 [ 4096, 4096, 1, 1 ] llama_model_loader: - tensor 26: blk.3.attn_k.weight q8_0 [ 4096, 1024, 1, 1 ] llama_model_loader: - tensor 27: blk.3.attn_v.weight q8_0 [ 4096, 1024, 1, 1 ] llama_model_loader: - tensor 28: blk.3.attn_output.weight q4_0 [ 4096, 4096, 1, 1 ] llama_model_loader: - tensor 29: blk.3.ffn_gate_inp.weight f16 [ 4096, 8, 1, 1 ] llama_model_loader: - tensor 30: blk.3.ffn_norm.weight f32 [ 4096, 1, 1, 1 ] llama_model_loader: - tensor 31: blk.4.attn_norm.weight f32 [ 4096, 1, 1, 1 ] llama_model_loader: - tensor 32: blk.4.attn_q.weight q4_0 [ 4096, 4096, 1, 1 ] llama_model_loader: - tensor 33: blk.4.attn_k.weight q8_0 [ 4096, 1024, 1, 1 ] llama_model_loader: - tensor 34: blk.4.attn_v.weight q8_0 [ 4096, 1024, 1, 1 ] llama_model_loader: - tensor 35: blk.4.attn_output.weight q4_0 [ 4096, 4096, 1, 1 ] llama_model_loader: - tensor 36: blk.4.ffn_gate_inp.weight f16 [ 4096, 8, 1, 1 ] llama_model_loader: - tensor 37: blk.4.ffn_norm.weight f32 [ 4096, 1, 1, 1 ] llama_model_loader: - tensor 38: blk.5.attn_norm.weight f32 [ 4096, 1, 1, 1 ] llama_model_loader: - tensor 39: blk.5.attn_q.weight q4_0 [ 4096, 4096, 1, 1 ] llama_model_loader: - tensor 40: blk.5.attn_k.weight q8_0 [ 4096, 1024, 1, 1 ] llama_model_loader: - tensor 41: blk.5.attn_v.weight q8_0 [ 4096, 1024, 1, 1 ] llama_model_loader: - tensor 42: blk.5.attn_output.weight q4_0 [ 4096, 4096, 1, 1 ] llama_model_loader: - tensor 43: blk.5.ffn_gate_inp.weight f16 [ 4096, 8, 1, 1 ] llama_model_loader: - tensor 44: blk.5.ffn_norm.weight f32 [ 4096, 1, 1, 1 ] llama_model_loader: - tensor 45: blk.6.attn_norm.weight f32 [ 4096, 1, 1, 1 ] llama_model_loader: - tensor 46: blk.6.attn_q.weight q4_0 [ 4096, 4096, 1, 1 ] llama_model_loader: - tensor 47: blk.6.attn_k.weight q8_0 [ 4096, 1024, 1, 1 ] llama_model_loader: - tensor 48: blk.6.attn_v.weight q8_0 [ 4096, 1024, 1, 1 ] llama_model_loader: - tensor 49: blk.6.attn_output.weight q4_0 [ 4096, 4096, 1, 1 ] llama_model_loader: - tensor 50: blk.6.ffn_gate_inp.weight f16 [ 4096, 8, 1, 1 ] llama_model_loader: - tensor 51: blk.6.ffn_norm.weight f32 [ 4096, 1, 1, 1 ] llama_model_loader: - tensor 52: blk.7.attn_norm.weight f32 [ 4096, 1, 1, 1 ] llama_model_loader: - tensor 53: blk.7.attn_q.weight q4_0 [ 4096, 4096, 1, 1 ] llama_model_loader: - tensor 54: blk.7.attn_k.weight q8_0 [ 4096, 1024, 1, 1 ] llama_model_loader: - tensor 55: blk.7.attn_v.weight q8_0 [ 4096, 1024, 1, 1 ] llama_model_loader: - tensor 56: blk.7.attn_output.weight q4_0 [ 4096, 4096, 1, 1 ] llama_model_loader: - tensor 57: blk.7.ffn_gate_inp.weight f16 [ 4096, 8, 1, 1 ] llama_model_loader: - tensor 58: blk.7.ffn_norm.weight f32 [ 4096, 1, 1, 1 ] llama_model_loader: - tensor 59: blk.8.attn_norm.weight f32 [ 4096, 1, 1, 1 ] llama_model_loader: - tensor 60: blk.8.attn_q.weight q4_0 [ 4096, 4096, 1, 1 ] llama_model_loader: - tensor 61: blk.8.attn_k.weight q8_0 [ 4096, 1024, 1, 1 ] llama_model_loader: - tensor 62: blk.8.attn_v.weight q8_0 [ 4096, 1024, 1, 1 ] llama_model_loader: - tensor 63: blk.8.attn_output.weight q4_0 [ 4096, 4096, 1, 1 ] llama_model_loader: - tensor 64: blk.8.ffn_gate_inp.weight f16 [ 4096, 8, 1, 1 ] llama_model_loader: - tensor 65: blk.8.ffn_norm.weight f32 [ 4096, 1, 1, 1 ] llama_model_loader: - tensor 66: blk.9.attn_norm.weight f32 [ 4096, 1, 1, 1 ] llama_model_loader: - tensor 67: blk.9.attn_q.weight q4_0 [ 4096, 4096, 1, 1 ] llama_model_loader: - tensor 68: blk.9.attn_k.weight q8_0 [ 4096, 1024, 1, 1 ] llama_model_loader: - tensor 69: blk.9.attn_v.weight q8_0 [ 4096, 1024, 1, 1 ] llama_model_loader: - tensor 70: blk.9.attn_output.weight q4_0 [ 4096, 4096, 1, 1 ] llama_model_loader: - tensor 71: blk.9.ffn_gate_inp.weight f16 [ 4096, 8, 1, 1 ] llama_model_loader: - tensor 72: blk.9.ffn_norm.weight f32 [ 4096, 1, 1, 1 ] llama_model_loader: - tensor 73: blk.10.attn_norm.weight f32 [ 4096, 1, 1, 1 ] llama_model_loader: - tensor 74: blk.10.attn_q.weight q4_0 [ 4096, 4096, 1, 1 ] llama_model_loader: - tensor 75: blk.10.attn_k.weight q8_0 [ 4096, 1024, 1, 1 ] llama_model_loader: - tensor 76: blk.10.attn_v.weight q8_0 [ 4096, 1024, 1, 1 ] llama_model_loader: - tensor 77: blk.10.attn_output.weight q4_0 [ 4096, 4096, 1, 1 ] llama_model_loader: - tensor 78: blk.10.ffn_gate_inp.weight f16 [ 4096, 8, 1, 1 ] llama_model_loader: - tensor 79: blk.10.ffn_norm.weight f32 [ 4096, 1, 1, 1 ] llama_model_loader: - tensor 80: blk.11.attn_norm.weight f32 [ 4096, 1, 1, 1 ] llama_model_loader: - tensor 81: blk.11.attn_q.weight q4_0 [ 4096, 4096, 1, 1 ] llama_model_loader: - tensor 82: blk.11.attn_k.weight q8_0 [ 4096, 1024, 1, 1 ] llama_model_loader: - tensor 83: blk.11.attn_v.weight q8_0 [ 4096, 1024, 1, 1 ] llama_model_loader: - tensor 84: blk.11.attn_output.weight q4_0 [ 4096, 4096, 1, 1 ] llama_model_loader: - tensor 85: blk.11.ffn_gate_inp.weight f16 [ 4096, 8, 1, 1 ] llama_model_loader: - tensor 86: blk.11.ffn_norm.weight f32 [ 4096, 1, 1, 1 ] llama_model_loader: - tensor 87: blk.12.attn_norm.weight f32 [ 4096, 1, 1, 1 ] llama_model_loader: - tensor 88: blk.12.attn_q.weight q4_0 [ 4096, 4096, 1, 1 ] llama_model_loader: - tensor 89: blk.12.attn_k.weight q8_0 [ 4096, 1024, 1, 1 ] llama_model_loader: - tensor 90: blk.12.attn_v.weight q8_0 [ 4096, 1024, 1, 1 ] llama_model_loader: - tensor 91: blk.12.attn_output.weight q4_0 [ 4096, 4096, 1, 1 ] llama_model_loader: - tensor 92: blk.12.ffn_gate_inp.weight f16 [ 4096, 8, 1, 1 ] llama_model_loader: - tensor 93: blk.12.ffn_norm.weight f32 [ 4096, 1, 1, 1 ] llama_model_loader: - tensor 94: blk.13.attn_norm.weight f32 [ 4096, 1, 1, 1 ] llama_model_loader: - tensor 95: blk.13.attn_q.weight q4_0 [ 4096, 4096, 1, 1 ] llama_model_loader: - tensor 96: blk.13.attn_k.weight q8_0 [ 4096, 1024, 1, 1 ] llama_model_loader: - tensor 97: blk.13.attn_v.weight q8_0 [ 4096, 1024, 1, 1 ] llama_model_loader: - tensor 98: blk.13.attn_output.weight q4_0 [ 4096, 4096, 1, 1 ] llama_model_loader: - tensor 99: blk.13.ffn_gate_inp.weight f16 [ 4096, 8, 1, 1 ] llama_model_loader: - tensor 100: blk.13.ffn_norm.weight f32 [ 4096, 1, 1, 1 ] llama_model_loader: - tensor 101: blk.14.attn_norm.weight f32 [ 4096, 1, 1, 1 ] llama_model_loader: - tensor 102: blk.14.attn_q.weight q4_0 [ 4096, 4096, 1, 1 ] llama_model_loader: - tensor 103: blk.14.attn_k.weight q8_0 [ 4096, 1024, 1, 1 ] llama_model_loader: - tensor 104: blk.14.attn_v.weight q8_0 [ 4096, 1024, 1, 1 ] llama_model_loader: - tensor 105: blk.14.attn_output.weight q4_0 [ 4096, 4096, 1, 1 ] llama_model_loader: - tensor 106: blk.14.ffn_gate_inp.weight f16 [ 4096, 8, 1, 1 ] llama_model_loader: - tensor 107: blk.14.ffn_norm.weight f32 [ 4096, 1, 1, 1 ] llama_model_loader: - tensor 108: blk.15.attn_norm.weight f32 [ 4096, 1, 1, 1 ] llama_model_loader: - tensor 109: blk.15.attn_q.weight q4_0 [ 4096, 4096, 1, 1 ] llama_model_loader: - tensor 110: blk.15.attn_k.weight q8_0 [ 4096, 1024, 1, 1 ] llama_model_loader: - tensor 111: blk.15.attn_v.weight q8_0 [ 4096, 1024, 1, 1 ] llama_model_loader: - tensor 112: blk.15.attn_output.weight q4_0 [ 4096, 4096, 1, 1 ] llama_model_loader: - tensor 113: blk.15.ffn_gate_inp.weight f16 [ 4096, 8, 1, 1 ] llama_model_loader: - tensor 114: blk.15.ffn_norm.weight f32 [ 4096, 1, 1, 1 ] llama_model_loader: - tensor 115: blk.16.attn_norm.weight f32 [ 4096, 1, 1, 1 ] llama_model_loader: - tensor 116: blk.16.attn_q.weight q4_0 [ 4096, 4096, 1, 1 ] llama_model_loader: - tensor 117: blk.16.attn_k.weight q8_0 [ 4096, 1024, 1, 1 ] llama_model_loader: - tensor 118: blk.16.attn_v.weight q8_0 [ 4096, 1024, 1, 1 ] llama_model_loader: - tensor 119: blk.16.attn_output.weight q4_0 [ 4096, 4096, 1, 1 ] llama_model_loader: - tensor 120: blk.16.ffn_gate_inp.weight f16 [ 4096, 8, 1, 1 ] llama_model_loader: - tensor 121: blk.16.ffn_norm.weight f32 [ 4096, 1, 1, 1 ] llama_model_loader: - tensor 122: blk.17.attn_norm.weight f32 [ 4096, 1, 1, 1 ] llama_model_loader: - tensor 123: blk.17.attn_q.weight q4_0 [ 4096, 4096, 1, 1 ] llama_model_loader: - tensor 124: blk.17.attn_k.weight q8_0 [ 4096, 1024, 1, 1 ] llama_model_loader: - tensor 125: blk.17.attn_v.weight q8_0 [ 4096, 1024, 1, 1 ] llama_model_loader: - tensor 126: blk.17.attn_output.weight q4_0 [ 4096, 4096, 1, 1 ] llama_model_loader: - tensor 127: blk.17.ffn_gate_inp.weight f16 [ 4096, 8, 1, 1 ] llama_model_loader: - tensor 128: blk.17.ffn_norm.weight f32 [ 4096, 1, 1, 1 ] llama_model_loader: - tensor 129: blk.18.attn_norm.weight f32 [ 4096, 1, 1, 1 ] llama_model_loader: - tensor 130: blk.18.attn_q.weight q4_0 [ 4096, 4096, 1, 1 ] llama_model_loader: - tensor 131: blk.18.attn_k.weight q8_0 [ 4096, 1024, 1, 1 ] llama_model_loader: - tensor 132: blk.18.attn_v.weight q8_0 [ 4096, 1024, 1, 1 ] llama_model_loader: - tensor 133: blk.18.attn_output.weight q4_0 [ 4096, 4096, 1, 1 ] llama_model_loader: - tensor 134: blk.18.ffn_gate_inp.weight f16 [ 4096, 8, 1, 1 ] llama_model_loader: - tensor 135: blk.18.ffn_norm.weight f32 [ 4096, 1, 1, 1 ] llama_model_loader: - tensor 136: blk.19.attn_norm.weight f32 [ 4096, 1, 1, 1 ] llama_model_loader: - tensor 137: blk.19.attn_q.weight q4_0 [ 4096, 4096, 1, 1 ] llama_model_loader: - tensor 138: blk.19.attn_k.weight q8_0 [ 4096, 1024, 1, 1 ] llama_model_loader: - tensor 139: blk.19.attn_v.weight q8_0 [ 4096, 1024, 1, 1 ] llama_model_loader: - tensor 140: blk.19.attn_output.weight q4_0 [ 4096, 4096, 1, 1 ] llama_model_loader: - tensor 141: blk.19.ffn_gate_inp.weight f16 [ 4096, 8, 1, 1 ] llama_model_loader: - tensor 142: blk.19.ffn_norm.weight f32 [ 4096, 1, 1, 1 ] llama_model_loader: - tensor 143: blk.20.attn_norm.weight f32 [ 4096, 1, 1, 1 ] llama_model_loader: - tensor 144: blk.20.attn_q.weight q4_0 [ 4096, 4096, 1, 1 ] llama_model_loader: - tensor 145: blk.20.attn_k.weight q8_0 [ 4096, 1024, 1, 1 ] llama_model_loader: - tensor 146: blk.20.attn_v.weight q8_0 [ 4096, 1024, 1, 1 ] llama_model_loader: - tensor 147: blk.20.attn_output.weight q4_0 [ 4096, 4096, 1, 1 ] llama_model_loader: - tensor 148: blk.20.ffn_gate_inp.weight f16 [ 4096, 8, 1, 1 ] llama_model_loader: - tensor 149: blk.20.ffn_norm.weight f32 [ 4096, 1, 1, 1 ] llama_model_loader: - tensor 150: blk.21.attn_norm.weight f32 [ 4096, 1, 1, 1 ] llama_model_loader: - tensor 151: blk.21.attn_q.weight q4_0 [ 4096, 4096, 1, 1 ] llama_model_loader: - tensor 152: blk.21.attn_k.weight q8_0 [ 4096, 1024, 1, 1 ] llama_model_loader: - tensor 153: blk.21.attn_v.weight q8_0 [ 4096, 1024, 1, 1 ] llama_model_loader: - tensor 154: blk.21.attn_output.weight q4_0 [ 4096, 4096, 1, 1 ] llama_model_loader: - tensor 155: blk.21.ffn_gate_inp.weight f16 [ 4096, 8, 1, 1 ] llama_model_loader: - tensor 156: blk.21.ffn_norm.weight f32 [ 4096, 1, 1, 1 ] llama_model_loader: - tensor 157: blk.22.attn_norm.weight f32 [ 4096, 1, 1, 1 ] llama_model_loader: - tensor 158: blk.22.attn_q.weight q4_0 [ 4096, 4096, 1, 1 ] llama_model_loader: - tensor 159: blk.22.attn_k.weight q8_0 [ 4096, 1024, 1, 1 ] llama_model_loader: - tensor 160: blk.22.attn_v.weight q8_0 [ 4096, 1024, 1, 1 ] llama_model_loader: - tensor 161: blk.22.attn_output.weight q4_0 [ 4096, 4096, 1, 1 ] llama_model_loader: - tensor 162: blk.22.ffn_gate_inp.weight f16 [ 4096, 8, 1, 1 ] llama_model_loader: - tensor 163: blk.22.ffn_norm.weight f32 [ 4096, 1, 1, 1 ] llama_model_loader: - tensor 164: blk.23.attn_norm.weight f32 [ 4096, 1, 1, 1 ] llama_model_loader: - tensor 165: blk.23.attn_q.weight q4_0 [ 4096, 4096, 1, 1 ] llama_model_loader: - tensor 166: blk.23.attn_k.weight q8_0 [ 4096, 1024, 1, 1 ] llama_model_loader: - tensor 167: blk.23.attn_v.weight q8_0 [ 4096, 1024, 1, 1 ] llama_model_loader: - tensor 168: blk.23.attn_output.weight q4_0 [ 4096, 4096, 1, 1 ] llama_model_loader: - tensor 169: blk.23.ffn_gate_inp.weight f16 [ 4096, 8, 1, 1 ] llama_model_loader: - tensor 170: blk.23.ffn_norm.weight f32 [ 4096, 1, 1, 1 ] llama_model_loader: - tensor 171: blk.24.attn_norm.weight f32 [ 4096, 1, 1, 1 ] llama_model_loader: - tensor 172: blk.24.attn_q.weight q4_0 [ 4096, 4096, 1, 1 ] llama_model_loader: - tensor 173: blk.24.attn_k.weight q8_0 [ 4096, 1024, 1, 1 ] llama_model_loader: - tensor 174: blk.24.attn_v.weight q8_0 [ 4096, 1024, 1, 1 ] llama_model_loader: - tensor 175: blk.24.attn_output.weight q4_0 [ 4096, 4096, 1, 1 ] llama_model_loader: - tensor 176: blk.24.ffn_gate_inp.weight f16 [ 4096, 8, 1, 1 ] llama_model_loader: - tensor 177: blk.24.ffn_norm.weight f32 [ 4096, 1, 1, 1 ] llama_model_loader: - tensor 178: blk.25.attn_norm.weight f32 [ 4096, 1, 1, 1 ] llama_model_loader: - tensor 179: blk.25.attn_q.weight q4_0 [ 4096, 4096, 1, 1 ] llama_model_loader: - tensor 180: blk.25.attn_k.weight q8_0 [ 4096, 1024, 1, 1 ] llama_model_loader: - tensor 181: blk.25.attn_v.weight q8_0 [ 4096, 1024, 1, 1 ] llama_model_loader: - tensor 182: blk.25.attn_output.weight q4_0 [ 4096, 4096, 1, 1 ] llama_model_loader: - tensor 183: blk.25.ffn_gate_inp.weight f16 [ 4096, 8, 1, 1 ] llama_model_loader: - tensor 184: blk.25.ffn_norm.weight f32 [ 4096, 1, 1, 1 ] llama_model_loader: - tensor 185: blk.26.attn_norm.weight f32 [ 4096, 1, 1, 1 ] llama_model_loader: - tensor 186: blk.26.attn_q.weight q4_0 [ 4096, 4096, 1, 1 ] llama_model_loader: - tensor 187: blk.26.attn_k.weight q8_0 [ 4096, 1024, 1, 1 ] llama_model_loader: - tensor 188: blk.26.attn_v.weight q8_0 [ 4096, 1024, 1, 1 ] llama_model_loader: - tensor 189: blk.26.attn_output.weight q4_0 [ 4096, 4096, 1, 1 ] llama_model_loader: - tensor 190: blk.26.ffn_gate_inp.weight f16 [ 4096, 8, 1, 1 ] llama_model_loader: - tensor 191: blk.26.ffn_norm.weight f32 [ 4096, 1, 1, 1 ] llama_model_loader: - tensor 192: blk.27.attn_norm.weight f32 [ 4096, 1, 1, 1 ] llama_model_loader: - tensor 193: blk.27.attn_q.weight q4_0 [ 4096, 4096, 1, 1 ] llama_model_loader: - tensor 194: blk.27.attn_k.weight q8_0 [ 4096, 1024, 1, 1 ] llama_model_loader: - tensor 195: blk.27.attn_v.weight q8_0 [ 4096, 1024, 1, 1 ] llama_model_loader: - tensor 196: blk.27.attn_output.weight q4_0 [ 4096, 4096, 1, 1 ] llama_model_loader: - tensor 197: blk.27.ffn_gate_inp.weight f16 [ 4096, 8, 1, 1 ] llama_model_loader: - tensor 198: blk.27.ffn_norm.weight f32 [ 4096, 1, 1, 1 ] llama_model_loader: - tensor 199: blk.28.attn_norm.weight f32 [ 4096, 1, 1, 1 ] llama_model_loader: - tensor 200: blk.28.attn_q.weight q4_0 [ 4096, 4096, 1, 1 ] llama_model_loader: - tensor 201: blk.28.attn_k.weight q8_0 [ 4096, 1024, 1, 1 ] llama_model_loader: - tensor 202: blk.28.attn_v.weight q8_0 [ 4096, 1024, 1, 1 ] llama_model_loader: - tensor 203: blk.28.attn_output.weight q4_0 [ 4096, 4096, 1, 1 ] llama_model_loader: - tensor 204: blk.28.ffn_gate_inp.weight f16 [ 4096, 8, 1, 1 ] llama_model_loader: - tensor 205: blk.28.ffn_norm.weight f32 [ 4096, 1, 1, 1 ] llama_model_loader: - tensor 206: blk.29.attn_norm.weight f32 [ 4096, 1, 1, 1 ] llama_model_loader: - tensor 207: blk.29.attn_q.weight q4_0 [ 4096, 4096, 1, 1 ] llama_model_loader: - tensor 208: blk.29.attn_k.weight q8_0 [ 4096, 1024, 1, 1 ] llama_model_loader: - tensor 209: blk.29.attn_v.weight q8_0 [ 4096, 1024, 1, 1 ] llama_model_loader: - tensor 210: blk.29.attn_output.weight q4_0 [ 4096, 4096, 1, 1 ] llama_model_loader: - tensor 211: blk.29.ffn_gate_inp.weight f16 [ 4096, 8, 1, 1 ] llama_model_loader: - tensor 212: blk.29.ffn_norm.weight f32 [ 4096, 1, 1, 1 ] llama_model_loader: - tensor 213: blk.30.attn_norm.weight f32 [ 4096, 1, 1, 1 ] llama_model_loader: - tensor 214: blk.30.attn_q.weight q4_0 [ 4096, 4096, 1, 1 ] llama_model_loader: - tensor 215: blk.30.attn_k.weight q8_0 [ 4096, 1024, 1, 1 ] llama_model_loader: - tensor 216: blk.30.attn_v.weight q8_0 [ 4096, 1024, 1, 1 ] llama_model_loader: - tensor 217: blk.30.attn_output.weight q4_0 [ 4096, 4096, 1, 1 ] llama_model_loader: - tensor 218: blk.30.ffn_gate_inp.weight f16 [ 4096, 8, 1, 1 ] llama_model_loader: - tensor 219: blk.30.ffn_norm.weight f32 [ 4096, 1, 1, 1 ] llama_model_loader: - tensor 220: blk.31.attn_norm.weight f32 [ 4096, 1, 1, 1 ] llama_model_loader: - tensor 221: blk.31.attn_q.weight q4_0 [ 4096, 4096, 1, 1 ] llama_model_loader: - tensor 222: blk.31.attn_k.weight q8_0 [ 4096, 1024, 1, 1 ] llama_model_loader: - tensor 223: blk.31.attn_v.weight q8_0 [ 4096, 1024, 1, 1 ] llama_model_loader: - tensor 224: blk.31.attn_output.weight q4_0 [ 4096, 4096, 1, 1 ] llama_model_loader: - tensor 225: blk.31.ffn_gate_inp.weight f16 [ 4096, 8, 1, 1 ] llama_model_loader: - tensor 226: blk.31.ffn_norm.weight f32 [ 4096, 1, 1, 1 ] llama_model_loader: - tensor 227: blk.0.ffn_gate.0.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 228: blk.0.ffn_gate.1.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 229: blk.0.ffn_gate.2.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 230: blk.0.ffn_gate.3.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 231: blk.0.ffn_gate.4.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 232: blk.0.ffn_gate.5.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 233: blk.0.ffn_gate.6.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 234: blk.0.ffn_gate.7.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 235: blk.0.ffn_down.0.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 236: blk.0.ffn_down.1.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 237: blk.0.ffn_down.2.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 238: blk.0.ffn_down.3.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 239: blk.0.ffn_down.4.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 240: blk.0.ffn_down.5.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 241: blk.0.ffn_down.6.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 242: blk.0.ffn_down.7.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 243: blk.0.ffn_up.0.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 244: blk.0.ffn_up.1.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 245: blk.0.ffn_up.2.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 246: blk.0.ffn_up.3.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 247: blk.0.ffn_up.4.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 248: blk.0.ffn_up.5.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 249: blk.0.ffn_up.6.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 250: blk.0.ffn_up.7.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 251: blk.1.ffn_gate.0.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 252: blk.1.ffn_gate.1.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 253: blk.1.ffn_gate.2.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 254: blk.1.ffn_gate.3.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 255: blk.1.ffn_gate.4.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 256: blk.1.ffn_gate.5.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 257: blk.1.ffn_gate.6.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 258: blk.1.ffn_gate.7.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 259: blk.1.ffn_down.0.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 260: blk.1.ffn_down.1.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 261: blk.1.ffn_down.2.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 262: blk.1.ffn_down.3.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 263: blk.1.ffn_down.4.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 264: blk.1.ffn_down.5.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 265: blk.1.ffn_down.6.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 266: blk.1.ffn_down.7.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 267: blk.1.ffn_up.0.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 268: blk.1.ffn_up.1.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 269: blk.1.ffn_up.2.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 270: blk.1.ffn_up.3.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 271: blk.1.ffn_up.4.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 272: blk.1.ffn_up.5.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 273: blk.1.ffn_up.6.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 274: blk.1.ffn_up.7.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 275: blk.2.ffn_gate.0.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 276: blk.2.ffn_gate.1.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 277: blk.2.ffn_gate.2.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 278: blk.2.ffn_gate.3.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 279: blk.2.ffn_gate.4.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 280: blk.2.ffn_gate.5.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 281: blk.2.ffn_gate.6.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 282: blk.2.ffn_gate.7.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 283: blk.2.ffn_down.0.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 284: blk.2.ffn_down.1.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 285: blk.2.ffn_down.2.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 286: blk.2.ffn_down.3.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 287: blk.2.ffn_down.4.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 288: blk.2.ffn_down.5.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 289: blk.2.ffn_down.6.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 290: blk.2.ffn_down.7.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 291: blk.2.ffn_up.0.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 292: blk.2.ffn_up.1.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 293: blk.2.ffn_up.2.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 294: blk.2.ffn_up.3.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 295: blk.2.ffn_up.4.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 296: blk.2.ffn_up.5.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 297: blk.2.ffn_up.6.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 298: blk.2.ffn_up.7.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 299: blk.3.ffn_gate.0.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 300: blk.3.ffn_gate.1.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 301: blk.3.ffn_gate.2.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 302: blk.3.ffn_gate.3.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 303: blk.3.ffn_gate.4.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 304: blk.3.ffn_gate.5.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 305: blk.3.ffn_gate.6.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 306: blk.3.ffn_gate.7.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 307: blk.3.ffn_down.0.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 308: blk.3.ffn_down.1.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 309: blk.3.ffn_down.2.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 310: blk.3.ffn_down.3.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 311: blk.3.ffn_down.4.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 312: blk.3.ffn_down.5.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 313: blk.3.ffn_down.6.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 314: blk.3.ffn_down.7.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 315: blk.3.ffn_up.0.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 316: blk.3.ffn_up.1.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 317: blk.3.ffn_up.2.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 318: blk.3.ffn_up.3.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 319: blk.3.ffn_up.4.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 320: blk.3.ffn_up.5.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 321: blk.3.ffn_up.6.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 322: blk.3.ffn_up.7.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 323: blk.4.ffn_gate.0.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 324: blk.4.ffn_gate.1.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 325: blk.4.ffn_gate.2.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 326: blk.4.ffn_gate.3.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 327: blk.4.ffn_gate.4.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 328: blk.4.ffn_gate.5.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 329: blk.4.ffn_gate.6.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 330: blk.4.ffn_gate.7.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 331: blk.4.ffn_down.0.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 332: blk.4.ffn_down.1.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 333: blk.4.ffn_down.2.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 334: blk.4.ffn_down.3.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 335: blk.4.ffn_down.4.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 336: blk.4.ffn_down.5.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 337: blk.4.ffn_down.6.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 338: blk.4.ffn_down.7.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 339: blk.4.ffn_up.0.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 340: blk.4.ffn_up.1.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 341: blk.4.ffn_up.2.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 342: blk.4.ffn_up.3.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 343: blk.4.ffn_up.4.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 344: blk.4.ffn_up.5.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 345: blk.4.ffn_up.6.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 346: blk.4.ffn_up.7.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 347: blk.5.ffn_gate.0.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 348: blk.5.ffn_gate.1.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 349: blk.5.ffn_gate.2.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 350: blk.5.ffn_gate.3.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 351: blk.5.ffn_gate.4.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 352: blk.5.ffn_gate.5.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 353: blk.5.ffn_gate.6.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 354: blk.5.ffn_gate.7.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 355: blk.5.ffn_down.0.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 356: blk.5.ffn_down.1.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 357: blk.5.ffn_down.2.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 358: blk.5.ffn_down.3.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 359: blk.5.ffn_down.4.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 360: blk.5.ffn_down.5.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 361: blk.5.ffn_down.6.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 362: blk.5.ffn_down.7.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 363: blk.5.ffn_up.0.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 364: blk.5.ffn_up.1.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 365: blk.5.ffn_up.2.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 366: blk.5.ffn_up.3.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 367: blk.5.ffn_up.4.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 368: blk.5.ffn_up.5.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 369: blk.5.ffn_up.6.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 370: blk.5.ffn_up.7.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 371: blk.6.ffn_gate.0.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 372: blk.6.ffn_gate.1.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 373: blk.6.ffn_gate.2.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 374: blk.6.ffn_gate.3.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 375: blk.6.ffn_gate.4.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 376: blk.6.ffn_gate.5.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 377: blk.6.ffn_gate.6.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 378: blk.6.ffn_gate.7.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 379: blk.6.ffn_down.0.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 380: blk.6.ffn_down.1.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 381: blk.6.ffn_down.2.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 382: blk.6.ffn_down.3.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 383: blk.6.ffn_down.4.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 384: blk.6.ffn_down.5.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 385: blk.6.ffn_down.6.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 386: blk.6.ffn_down.7.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 387: blk.6.ffn_up.0.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 388: blk.6.ffn_up.1.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 389: blk.6.ffn_up.2.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 390: blk.6.ffn_up.3.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 391: blk.6.ffn_up.4.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 392: blk.6.ffn_up.5.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 393: blk.6.ffn_up.6.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 394: blk.6.ffn_up.7.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 395: blk.7.ffn_gate.0.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 396: blk.7.ffn_gate.1.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 397: blk.7.ffn_gate.2.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 398: blk.7.ffn_gate.3.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 399: blk.7.ffn_gate.4.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 400: blk.7.ffn_gate.5.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 401: blk.7.ffn_gate.6.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 402: blk.7.ffn_gate.7.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 403: blk.7.ffn_down.0.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 404: blk.7.ffn_down.1.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 405: blk.7.ffn_down.2.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 406: blk.7.ffn_down.3.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 407: blk.7.ffn_down.4.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 408: blk.7.ffn_down.5.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 409: blk.7.ffn_down.6.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 410: blk.7.ffn_down.7.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 411: blk.7.ffn_up.0.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 412: blk.7.ffn_up.1.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 413: blk.7.ffn_up.2.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 414: blk.7.ffn_up.3.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 415: blk.7.ffn_up.4.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 416: blk.7.ffn_up.5.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 417: blk.7.ffn_up.6.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 418: blk.7.ffn_up.7.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 419: blk.8.ffn_gate.0.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 420: blk.8.ffn_gate.1.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 421: blk.8.ffn_gate.2.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 422: blk.8.ffn_gate.3.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 423: blk.8.ffn_gate.4.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 424: blk.8.ffn_gate.5.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 425: blk.8.ffn_gate.6.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 426: blk.8.ffn_gate.7.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 427: blk.8.ffn_down.0.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 428: blk.8.ffn_down.1.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 429: blk.8.ffn_down.2.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 430: blk.8.ffn_down.3.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 431: blk.8.ffn_down.4.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 432: blk.8.ffn_down.5.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 433: blk.8.ffn_down.6.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 434: blk.8.ffn_down.7.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 435: blk.8.ffn_up.0.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 436: blk.8.ffn_up.1.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 437: blk.8.ffn_up.2.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 438: blk.8.ffn_up.3.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 439: blk.8.ffn_up.4.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 440: blk.8.ffn_up.5.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 441: blk.8.ffn_up.6.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 442: blk.8.ffn_up.7.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 443: blk.9.ffn_gate.0.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 444: blk.9.ffn_gate.1.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 445: blk.9.ffn_gate.2.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 446: blk.9.ffn_gate.3.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 447: blk.9.ffn_gate.4.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 448: blk.9.ffn_gate.5.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 449: blk.9.ffn_gate.6.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 450: blk.9.ffn_gate.7.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 451: blk.9.ffn_down.0.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 452: blk.9.ffn_down.1.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 453: blk.9.ffn_down.2.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 454: blk.9.ffn_down.3.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 455: blk.9.ffn_down.4.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 456: blk.9.ffn_down.5.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 457: blk.9.ffn_down.6.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 458: blk.9.ffn_down.7.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 459: blk.9.ffn_up.0.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 460: blk.9.ffn_up.1.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 461: blk.9.ffn_up.2.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 462: blk.9.ffn_up.3.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 463: blk.9.ffn_up.4.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 464: blk.9.ffn_up.5.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 465: blk.9.ffn_up.6.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 466: blk.9.ffn_up.7.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 467: blk.10.ffn_gate.0.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 468: blk.10.ffn_gate.1.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 469: blk.10.ffn_gate.2.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 470: blk.10.ffn_gate.3.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 471: blk.10.ffn_gate.4.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 472: blk.10.ffn_gate.5.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 473: blk.10.ffn_gate.6.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 474: blk.10.ffn_gate.7.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 475: blk.10.ffn_down.0.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 476: blk.10.ffn_down.1.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 477: blk.10.ffn_down.2.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 478: blk.10.ffn_down.3.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 479: blk.10.ffn_down.4.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 480: blk.10.ffn_down.5.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 481: blk.10.ffn_down.6.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 482: blk.10.ffn_down.7.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 483: blk.10.ffn_up.0.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 484: blk.10.ffn_up.1.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 485: blk.10.ffn_up.2.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 486: blk.10.ffn_up.3.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 487: blk.10.ffn_up.4.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 488: blk.10.ffn_up.5.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 489: blk.10.ffn_up.6.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 490: blk.10.ffn_up.7.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 491: blk.11.ffn_gate.0.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 492: blk.11.ffn_gate.1.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 493: blk.11.ffn_gate.2.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 494: blk.11.ffn_gate.3.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 495: blk.11.ffn_gate.4.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 496: blk.11.ffn_gate.5.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 497: blk.11.ffn_gate.6.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 498: blk.11.ffn_gate.7.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 499: blk.11.ffn_down.0.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 500: blk.11.ffn_down.1.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 501: blk.11.ffn_down.2.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 502: blk.11.ffn_down.3.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 503: blk.11.ffn_down.4.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 504: blk.11.ffn_down.5.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 505: blk.11.ffn_down.6.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 506: blk.11.ffn_down.7.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 507: blk.11.ffn_up.0.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 508: blk.11.ffn_up.1.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 509: blk.11.ffn_up.2.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 510: blk.11.ffn_up.3.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 511: blk.11.ffn_up.4.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 512: blk.11.ffn_up.5.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 513: blk.11.ffn_up.6.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 514: blk.11.ffn_up.7.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 515: blk.12.ffn_gate.0.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 516: blk.12.ffn_gate.1.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 517: blk.12.ffn_gate.2.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 518: blk.12.ffn_gate.3.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 519: blk.12.ffn_gate.4.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 520: blk.12.ffn_gate.5.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 521: blk.12.ffn_gate.6.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 522: blk.12.ffn_gate.7.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 523: blk.12.ffn_down.0.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 524: blk.12.ffn_down.1.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 525: blk.12.ffn_down.2.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 526: blk.12.ffn_down.3.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 527: blk.12.ffn_down.4.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 528: blk.12.ffn_down.5.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 529: blk.12.ffn_down.6.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 530: blk.12.ffn_down.7.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 531: blk.12.ffn_up.0.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 532: blk.12.ffn_up.1.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 533: blk.12.ffn_up.2.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 534: blk.12.ffn_up.3.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 535: blk.12.ffn_up.4.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 536: blk.12.ffn_up.5.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 537: blk.12.ffn_up.6.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 538: blk.12.ffn_up.7.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 539: blk.13.ffn_gate.0.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 540: blk.13.ffn_gate.1.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 541: blk.13.ffn_gate.2.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 542: blk.13.ffn_gate.3.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 543: blk.13.ffn_gate.4.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 544: blk.13.ffn_gate.5.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 545: blk.13.ffn_gate.6.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 546: blk.13.ffn_gate.7.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 547: blk.13.ffn_down.0.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 548: blk.13.ffn_down.1.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 549: blk.13.ffn_down.2.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 550: blk.13.ffn_down.3.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 551: blk.13.ffn_down.4.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 552: blk.13.ffn_down.5.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 553: blk.13.ffn_down.6.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 554: blk.13.ffn_down.7.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 555: blk.13.ffn_up.0.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 556: blk.13.ffn_up.1.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 557: blk.13.ffn_up.2.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 558: blk.13.ffn_up.3.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 559: blk.13.ffn_up.4.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 560: blk.13.ffn_up.5.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 561: blk.13.ffn_up.6.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 562: blk.13.ffn_up.7.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 563: blk.14.ffn_gate.0.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 564: blk.14.ffn_gate.1.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 565: blk.14.ffn_gate.2.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 566: blk.14.ffn_gate.3.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 567: blk.14.ffn_gate.4.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 568: blk.14.ffn_gate.5.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 569: blk.14.ffn_gate.6.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 570: blk.14.ffn_gate.7.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 571: blk.14.ffn_down.0.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 572: blk.14.ffn_down.1.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 573: blk.14.ffn_down.2.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 574: blk.14.ffn_down.3.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 575: blk.14.ffn_down.4.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 576: blk.14.ffn_down.5.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 577: blk.14.ffn_down.6.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 578: blk.14.ffn_down.7.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 579: blk.14.ffn_up.0.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 580: blk.14.ffn_up.1.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 581: blk.14.ffn_up.2.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 582: blk.14.ffn_up.3.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 583: blk.14.ffn_up.4.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 584: blk.14.ffn_up.5.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 585: blk.14.ffn_up.6.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 586: blk.14.ffn_up.7.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 587: blk.15.ffn_gate.0.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 588: blk.15.ffn_gate.1.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 589: blk.15.ffn_gate.2.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 590: blk.15.ffn_gate.3.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 591: blk.15.ffn_gate.4.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 592: blk.15.ffn_gate.5.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 593: blk.15.ffn_gate.6.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 594: blk.15.ffn_gate.7.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 595: blk.15.ffn_down.0.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 596: blk.15.ffn_down.1.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 597: blk.15.ffn_down.2.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 598: blk.15.ffn_down.3.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 599: blk.15.ffn_down.4.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 600: blk.15.ffn_down.5.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 601: blk.15.ffn_down.6.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 602: blk.15.ffn_down.7.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 603: blk.15.ffn_up.0.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 604: blk.15.ffn_up.1.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 605: blk.15.ffn_up.2.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 606: blk.15.ffn_up.3.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 607: blk.15.ffn_up.4.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 608: blk.15.ffn_up.5.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 609: blk.15.ffn_up.6.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 610: blk.15.ffn_up.7.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 611: blk.16.ffn_gate.0.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 612: blk.16.ffn_gate.1.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 613: blk.16.ffn_gate.2.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 614: blk.16.ffn_gate.3.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 615: blk.16.ffn_gate.4.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 616: blk.16.ffn_gate.5.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 617: blk.16.ffn_gate.6.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 618: blk.16.ffn_gate.7.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 619: blk.16.ffn_down.0.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 620: blk.16.ffn_down.1.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 621: blk.16.ffn_down.2.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 622: blk.16.ffn_down.3.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 623: blk.16.ffn_down.4.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 624: blk.16.ffn_down.5.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 625: blk.16.ffn_down.6.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 626: blk.16.ffn_down.7.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 627: blk.16.ffn_up.0.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 628: blk.16.ffn_up.1.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 629: blk.16.ffn_up.2.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 630: blk.16.ffn_up.3.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 631: blk.16.ffn_up.4.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 632: blk.16.ffn_up.5.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 633: blk.16.ffn_up.6.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 634: blk.16.ffn_up.7.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 635: blk.17.ffn_gate.0.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 636: blk.17.ffn_gate.1.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 637: blk.17.ffn_gate.2.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 638: blk.17.ffn_gate.3.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 639: blk.17.ffn_gate.4.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 640: blk.17.ffn_gate.5.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 641: blk.17.ffn_gate.6.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 642: blk.17.ffn_gate.7.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 643: blk.17.ffn_down.0.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 644: blk.17.ffn_down.1.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 645: blk.17.ffn_down.2.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 646: blk.17.ffn_down.3.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 647: blk.17.ffn_down.4.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 648: blk.17.ffn_down.5.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 649: blk.17.ffn_down.6.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 650: blk.17.ffn_down.7.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 651: blk.17.ffn_up.0.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 652: blk.17.ffn_up.1.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 653: blk.17.ffn_up.2.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 654: blk.17.ffn_up.3.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 655: blk.17.ffn_up.4.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 656: blk.17.ffn_up.5.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 657: blk.17.ffn_up.6.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 658: blk.17.ffn_up.7.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 659: blk.18.ffn_gate.0.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 660: blk.18.ffn_gate.1.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 661: blk.18.ffn_gate.2.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 662: blk.18.ffn_gate.3.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 663: blk.18.ffn_gate.4.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 664: blk.18.ffn_gate.5.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 665: blk.18.ffn_gate.6.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 666: blk.18.ffn_gate.7.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 667: blk.18.ffn_down.0.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 668: blk.18.ffn_down.1.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 669: blk.18.ffn_down.2.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 670: blk.18.ffn_down.3.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 671: blk.18.ffn_down.4.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 672: blk.18.ffn_down.5.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 673: blk.18.ffn_down.6.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 674: blk.18.ffn_down.7.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 675: blk.18.ffn_up.0.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 676: blk.18.ffn_up.1.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 677: blk.18.ffn_up.2.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 678: blk.18.ffn_up.3.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 679: blk.18.ffn_up.4.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 680: blk.18.ffn_up.5.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 681: blk.18.ffn_up.6.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 682: blk.18.ffn_up.7.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 683: blk.19.ffn_gate.0.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 684: blk.19.ffn_gate.1.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 685: blk.19.ffn_gate.2.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 686: blk.19.ffn_gate.3.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 687: blk.19.ffn_gate.4.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 688: blk.19.ffn_gate.5.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 689: blk.19.ffn_gate.6.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 690: blk.19.ffn_gate.7.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 691: blk.19.ffn_down.0.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 692: blk.19.ffn_down.1.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 693: blk.19.ffn_down.2.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 694: blk.19.ffn_down.3.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 695: blk.19.ffn_down.4.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 696: blk.19.ffn_down.5.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 697: blk.19.ffn_down.6.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 698: blk.19.ffn_down.7.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 699: blk.19.ffn_up.0.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 700: blk.19.ffn_up.1.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 701: blk.19.ffn_up.2.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 702: blk.19.ffn_up.3.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 703: blk.19.ffn_up.4.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 704: blk.19.ffn_up.5.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 705: blk.19.ffn_up.6.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 706: blk.19.ffn_up.7.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 707: blk.20.ffn_gate.0.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 708: blk.20.ffn_gate.1.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 709: blk.20.ffn_gate.2.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 710: blk.20.ffn_gate.3.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 711: blk.20.ffn_gate.4.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 712: blk.20.ffn_gate.5.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 713: blk.20.ffn_gate.6.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 714: blk.20.ffn_gate.7.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 715: blk.20.ffn_down.0.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 716: blk.20.ffn_down.1.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 717: blk.20.ffn_down.2.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 718: blk.20.ffn_down.3.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 719: blk.20.ffn_down.4.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 720: blk.20.ffn_down.5.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 721: blk.20.ffn_down.6.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 722: blk.20.ffn_down.7.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 723: blk.20.ffn_up.0.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 724: blk.20.ffn_up.1.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 725: blk.20.ffn_up.2.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 726: blk.20.ffn_up.3.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 727: blk.20.ffn_up.4.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 728: blk.20.ffn_up.5.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 729: blk.20.ffn_up.6.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 730: blk.20.ffn_up.7.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 731: blk.21.ffn_gate.0.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 732: blk.21.ffn_gate.1.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 733: blk.21.ffn_gate.2.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 734: blk.21.ffn_gate.3.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 735: blk.21.ffn_gate.4.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 736: blk.21.ffn_gate.5.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 737: blk.21.ffn_gate.6.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 738: blk.21.ffn_gate.7.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 739: blk.21.ffn_down.0.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 740: blk.21.ffn_down.1.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 741: blk.21.ffn_down.2.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 742: blk.21.ffn_down.3.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 743: blk.21.ffn_down.4.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 744: blk.21.ffn_down.5.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 745: blk.21.ffn_down.6.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 746: blk.21.ffn_down.7.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 747: blk.21.ffn_up.0.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 748: blk.21.ffn_up.1.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 749: blk.21.ffn_up.2.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 750: blk.21.ffn_up.3.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 751: blk.21.ffn_up.4.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 752: blk.21.ffn_up.5.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 753: blk.21.ffn_up.6.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 754: blk.21.ffn_up.7.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 755: blk.22.ffn_gate.0.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 756: blk.22.ffn_gate.1.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 757: blk.22.ffn_gate.2.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 758: blk.22.ffn_gate.3.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 759: blk.22.ffn_gate.4.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 760: blk.22.ffn_gate.5.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 761: blk.22.ffn_gate.6.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 762: blk.22.ffn_gate.7.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 763: blk.22.ffn_down.0.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 764: blk.22.ffn_down.1.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 765: blk.22.ffn_down.2.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 766: blk.22.ffn_down.3.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 767: blk.22.ffn_down.4.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 768: blk.22.ffn_down.5.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 769: blk.22.ffn_down.6.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 770: blk.22.ffn_down.7.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 771: blk.22.ffn_up.0.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 772: blk.22.ffn_up.1.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 773: blk.22.ffn_up.2.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 774: blk.22.ffn_up.3.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 775: blk.22.ffn_up.4.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 776: blk.22.ffn_up.5.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 777: blk.22.ffn_up.6.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 778: blk.22.ffn_up.7.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 779: blk.23.ffn_gate.0.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 780: blk.23.ffn_gate.1.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 781: blk.23.ffn_gate.2.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 782: blk.23.ffn_gate.3.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 783: blk.23.ffn_gate.4.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 784: blk.23.ffn_gate.5.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 785: blk.23.ffn_gate.6.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 786: blk.23.ffn_gate.7.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 787: blk.23.ffn_down.0.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 788: blk.23.ffn_down.1.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 789: blk.23.ffn_down.2.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 790: blk.23.ffn_down.3.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 791: blk.23.ffn_down.4.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 792: blk.23.ffn_down.5.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 793: blk.23.ffn_down.6.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 794: blk.23.ffn_down.7.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 795: blk.23.ffn_up.0.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 796: blk.23.ffn_up.1.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 797: blk.23.ffn_up.2.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 798: blk.23.ffn_up.3.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 799: blk.23.ffn_up.4.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 800: blk.23.ffn_up.5.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 801: blk.23.ffn_up.6.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 802: blk.23.ffn_up.7.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 803: blk.24.ffn_gate.0.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 804: blk.24.ffn_gate.1.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 805: blk.24.ffn_gate.2.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 806: blk.24.ffn_gate.3.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 807: blk.24.ffn_gate.4.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 808: blk.24.ffn_gate.5.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 809: blk.24.ffn_gate.6.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 810: blk.24.ffn_gate.7.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 811: blk.24.ffn_down.0.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 812: blk.24.ffn_down.1.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 813: blk.24.ffn_down.2.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 814: blk.24.ffn_down.3.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 815: blk.24.ffn_down.4.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 816: blk.24.ffn_down.5.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 817: blk.24.ffn_down.6.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 818: blk.24.ffn_down.7.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 819: blk.24.ffn_up.0.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 820: blk.24.ffn_up.1.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 821: blk.24.ffn_up.2.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 822: blk.24.ffn_up.3.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 823: blk.24.ffn_up.4.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 824: blk.24.ffn_up.5.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 825: blk.24.ffn_up.6.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 826: blk.24.ffn_up.7.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 827: blk.25.ffn_gate.0.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 828: blk.25.ffn_gate.1.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 829: blk.25.ffn_gate.2.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 830: blk.25.ffn_gate.3.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 831: blk.25.ffn_gate.4.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 832: blk.25.ffn_gate.5.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 833: blk.25.ffn_gate.6.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 834: blk.25.ffn_gate.7.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 835: blk.25.ffn_down.0.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 836: blk.25.ffn_down.1.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 837: blk.25.ffn_down.2.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 838: blk.25.ffn_down.3.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 839: blk.25.ffn_down.4.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 840: blk.25.ffn_down.5.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 841: blk.25.ffn_down.6.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 842: blk.25.ffn_down.7.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 843: blk.25.ffn_up.0.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 844: blk.25.ffn_up.1.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 845: blk.25.ffn_up.2.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 846: blk.25.ffn_up.3.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 847: blk.25.ffn_up.4.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 848: blk.25.ffn_up.5.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 849: blk.25.ffn_up.6.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 850: blk.25.ffn_up.7.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 851: blk.26.ffn_gate.0.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 852: blk.26.ffn_gate.1.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 853: blk.26.ffn_gate.2.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 854: blk.26.ffn_gate.3.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 855: blk.26.ffn_gate.4.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 856: blk.26.ffn_gate.5.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 857: blk.26.ffn_gate.6.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 858: blk.26.ffn_gate.7.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 859: blk.26.ffn_down.0.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 860: blk.26.ffn_down.1.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 861: blk.26.ffn_down.2.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 862: blk.26.ffn_down.3.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 863: blk.26.ffn_down.4.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 864: blk.26.ffn_down.5.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 865: blk.26.ffn_down.6.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 866: blk.26.ffn_down.7.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 867: blk.26.ffn_up.0.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 868: blk.26.ffn_up.1.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 869: blk.26.ffn_up.2.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 870: blk.26.ffn_up.3.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 871: blk.26.ffn_up.4.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 872: blk.26.ffn_up.5.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 873: blk.26.ffn_up.6.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 874: blk.26.ffn_up.7.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 875: blk.27.ffn_gate.0.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 876: blk.27.ffn_gate.1.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 877: blk.27.ffn_gate.2.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 878: blk.27.ffn_gate.3.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 879: blk.27.ffn_gate.4.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 880: blk.27.ffn_gate.5.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 881: blk.27.ffn_gate.6.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 882: blk.27.ffn_gate.7.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 883: blk.27.ffn_down.0.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 884: blk.27.ffn_down.1.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 885: blk.27.ffn_down.2.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 886: blk.27.ffn_down.3.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 887: blk.27.ffn_down.4.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 888: blk.27.ffn_down.5.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 889: blk.27.ffn_down.6.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 890: blk.27.ffn_down.7.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 891: blk.27.ffn_up.0.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 892: blk.27.ffn_up.1.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 893: blk.27.ffn_up.2.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 894: blk.27.ffn_up.3.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 895: blk.27.ffn_up.4.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 896: blk.27.ffn_up.5.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 897: blk.27.ffn_up.6.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 898: blk.27.ffn_up.7.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 899: blk.28.ffn_gate.0.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 900: blk.28.ffn_gate.1.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 901: blk.28.ffn_gate.2.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 902: blk.28.ffn_gate.3.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 903: blk.28.ffn_gate.4.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 904: blk.28.ffn_gate.5.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 905: blk.28.ffn_gate.6.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 906: blk.28.ffn_gate.7.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 907: blk.28.ffn_down.0.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 908: blk.28.ffn_down.1.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 909: blk.28.ffn_down.2.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 910: blk.28.ffn_down.3.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 911: blk.28.ffn_down.4.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 912: blk.28.ffn_down.5.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 913: blk.28.ffn_down.6.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 914: blk.28.ffn_down.7.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 915: blk.28.ffn_up.0.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 916: blk.28.ffn_up.1.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 917: blk.28.ffn_up.2.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 918: blk.28.ffn_up.3.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 919: blk.28.ffn_up.4.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 920: blk.28.ffn_up.5.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 921: blk.28.ffn_up.6.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 922: blk.28.ffn_up.7.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 923: blk.29.ffn_gate.0.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 924: blk.29.ffn_gate.1.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 925: blk.29.ffn_gate.2.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 926: blk.29.ffn_gate.3.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 927: blk.29.ffn_gate.4.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 928: blk.29.ffn_gate.5.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 929: blk.29.ffn_gate.6.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 930: blk.29.ffn_gate.7.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 931: blk.29.ffn_down.0.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 932: blk.29.ffn_down.1.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 933: blk.29.ffn_down.2.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 934: blk.29.ffn_down.3.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 935: blk.29.ffn_down.4.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 936: blk.29.ffn_down.5.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 937: blk.29.ffn_down.6.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 938: blk.29.ffn_down.7.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 939: blk.29.ffn_up.0.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 940: blk.29.ffn_up.1.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 941: blk.29.ffn_up.2.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 942: blk.29.ffn_up.3.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 943: blk.29.ffn_up.4.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 944: blk.29.ffn_up.5.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 945: blk.29.ffn_up.6.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 946: blk.29.ffn_up.7.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 947: blk.30.ffn_gate.0.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 948: blk.30.ffn_gate.1.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 949: blk.30.ffn_gate.2.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 950: blk.30.ffn_gate.3.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 951: blk.30.ffn_gate.4.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 952: blk.30.ffn_gate.5.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 953: blk.30.ffn_gate.6.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 954: blk.30.ffn_gate.7.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 955: blk.30.ffn_down.0.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 956: blk.30.ffn_down.1.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 957: blk.30.ffn_down.2.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 958: blk.30.ffn_down.3.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 959: blk.30.ffn_down.4.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 960: blk.30.ffn_down.5.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 961: blk.30.ffn_down.6.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 962: blk.30.ffn_down.7.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 963: blk.30.ffn_up.0.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 964: blk.30.ffn_up.1.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 965: blk.30.ffn_up.2.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 966: blk.30.ffn_up.3.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 967: blk.30.ffn_up.4.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 968: blk.30.ffn_up.5.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 969: blk.30.ffn_up.6.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 970: blk.30.ffn_up.7.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 971: blk.31.ffn_gate.0.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 972: blk.31.ffn_gate.1.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 973: blk.31.ffn_gate.2.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 974: blk.31.ffn_gate.3.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 975: blk.31.ffn_gate.4.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 976: blk.31.ffn_gate.5.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 977: blk.31.ffn_gate.6.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 978: blk.31.ffn_gate.7.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 979: blk.31.ffn_down.0.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 980: blk.31.ffn_down.1.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 981: blk.31.ffn_down.2.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 982: blk.31.ffn_down.3.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 983: blk.31.ffn_down.4.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 984: blk.31.ffn_down.5.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 985: blk.31.ffn_down.6.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 986: blk.31.ffn_down.7.weight q4_0 [ 14336, 4096, 1, 1 ] llama_model_loader: - tensor 987: blk.31.ffn_up.0.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 988: blk.31.ffn_up.1.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 989: blk.31.ffn_up.2.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 990: blk.31.ffn_up.3.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 991: blk.31.ffn_up.4.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 992: blk.31.ffn_up.5.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 993: blk.31.ffn_up.6.weight q4_0 [ 4096, 14336, 1, 1 ] llama_model_loader: - tensor 994: blk.31.ffn_up.7.weight q4_0 [ 4096, 14336, 1, 1 ]