Closed
Description
The error is:
error loading model: invalid character
- the conversion tol gguf was done with recent
convert-refact-hf-to-gguf.py(Oct. 6) - the error occurs with f16 also (not just the Q4_K_M version which is show here), of course that is expected since the error comes from
unicode.h - since the error comes from
unicode.hI presume the bpe commit is what caused this
nain: build = 1343 (c47066d)
main: built with cc (GCC) 13.2.1 20230801 for x86_64-pc-linux-gnu
main: seed = 1333
llama_model_loader: loaded meta data with 19 key-value pairs and 291 tensors from ./refact-1_6B-fim-Q4_K_M.gguf (version GGUF V2 (latest))
llama_model_loader: - tensor 0: token_embd.weight q4_K [ 2048, 49216, 1, 1 ]
llama_model_loader: - tensor 1: blk.0.attn_norm.weight f32 [ 2048, 1, 1, 1 ]
llama_model_loader: - tensor 2: blk.0.attn_output.weight q4_K [ 2048, 2048, 1, 1 ]
llama_model_loader: - tensor 3: blk.0.ffn_norm.weight f32 [ 2048, 1, 1, 1 ]
llama_model_loader: - tensor 4: blk.0.ffn_down.weight q6_K [ 5632, 2048, 1, 1 ]
llama_model_loader: - tensor 5: blk.1.attn_norm.weight f32 [ 2048, 1, 1, 1 ]
llama_model_loader: - tensor 6: blk.1.attn_output.weight q4_K [ 2048, 2048, 1, 1 ]
llama_model_loader: - tensor 7: blk.1.ffn_norm.weight f32 [ 2048, 1, 1, 1 ]
llama_model_loader: - tensor 8: blk.1.ffn_down.weight q6_K [ 5632, 2048, 1, 1 ]
llama_model_loader: - tensor 9: blk.2.attn_norm.weight f32 [ 2048, 1, 1, 1 ]
llama_model_loader: - tensor 10: blk.2.attn_output.weight q4_K [ 2048, 2048, 1, 1 ]
llama_model_loader: - tensor 11: blk.2.ffn_norm.weight f32 [ 2048, 1, 1, 1 ]
llama_model_loader: - tensor 12: blk.2.ffn_down.weight q6_K [ 5632, 2048, 1, 1 ]
llama_model_loader: - tensor 13: blk.3.attn_norm.weight f32 [ 2048, 1, 1, 1 ]
llama_model_loader: - tensor 14: blk.3.attn_output.weight q4_K [ 2048, 2048, 1, 1 ]
llama_model_loader: - tensor 15: blk.3.ffn_norm.weight f32 [ 2048, 1, 1, 1 ]
llama_model_loader: - tensor 16: blk.3.ffn_down.weight q6_K [ 5632, 2048, 1, 1 ]
llama_model_loader: - tensor 17: blk.4.attn_norm.weight f32 [ 2048, 1, 1, 1 ]
llama_model_loader: - tensor 18: blk.4.attn_output.weight q4_K [ 2048, 2048, 1, 1 ]
llama_model_loader: - tensor 19: blk.4.ffn_norm.weight f32 [ 2048, 1, 1, 1 ]
llama_model_loader: - tensor 20: blk.4.ffn_down.weight q4_K [ 5632, 2048, 1, 1 ]
llama_model_loader: - tensor 21: blk.5.attn_norm.weight f32 [ 2048, 1, 1, 1 ]
llama_model_loader: - tensor 22: blk.5.attn_output.weight q4_K [ 2048, 2048, 1, 1 ]
llama_model_loader: - tensor 23: blk.5.ffn_norm.weight f32 [ 2048, 1, 1, 1 ]
llama_model_loader: - tensor 24: blk.5.ffn_down.weight q4_K [ 5632, 2048, 1, 1 ]
llama_model_loader: - tensor 25: blk.6.attn_norm.weight f32 [ 2048, 1, 1, 1 ]
llama_model_loader: - tensor 26: blk.6.attn_output.weight q4_K [ 2048, 2048, 1, 1 ]
llama_model_loader: - tensor 27: blk.6.ffn_norm.weight f32 [ 2048, 1, 1, 1 ]
llama_model_loader: - tensor 28: blk.6.ffn_down.weight q6_K [ 5632, 2048, 1, 1 ]
llama_model_loader: - tensor 29: blk.7.attn_norm.weight f32 [ 2048, 1, 1, 1 ]
llama_model_loader: - tensor 30: blk.7.attn_output.weight q4_K [ 2048, 2048, 1, 1 ]
llama_model_loader: - tensor 31: blk.7.ffn_norm.weight f32 [ 2048, 1, 1, 1 ]
llama_model_loader: - tensor 32: blk.7.ffn_down.weight q4_K [ 5632, 2048, 1, 1 ]
llama_model_loader: - tensor 33: blk.8.attn_norm.weight f32 [ 2048, 1, 1, 1 ]
llama_model_loader: - tensor 34: blk.8.attn_output.weight q4_K [ 2048, 2048, 1, 1 ]
llama_model_loader: - tensor 35: blk.8.ffn_norm.weight f32 [ 2048, 1, 1, 1 ]
llama_model_loader: - tensor 36: blk.8.ffn_down.weight q4_K [ 5632, 2048, 1, 1 ]
llama_model_loader: - tensor 37: blk.9.attn_norm.weight f32 [ 2048, 1, 1, 1 ]
llama_model_loader: - tensor 38: blk.9.attn_output.weight q4_K [ 2048, 2048, 1, 1 ]
llama_model_loader: - tensor 39: blk.9.ffn_norm.weight f32 [ 2048, 1, 1, 1 ]
llama_model_loader: - tensor 40: blk.9.ffn_down.weight q6_K [ 5632, 2048, 1, 1 ]
llama_model_loader: - tensor 41: blk.10.attn_norm.weight f32 [ 2048, 1, 1, 1 ]
llama_model_loader: - tensor 42: blk.10.attn_output.weight q4_K [ 2048, 2048, 1, 1 ]
llama_model_loader: - tensor 43: blk.10.ffn_norm.weight f32 [ 2048, 1, 1, 1 ]
llama_model_loader: - tensor 44: blk.10.ffn_down.weight q4_K [ 5632, 2048, 1, 1 ]
llama_model_loader: - tensor 45: blk.11.attn_norm.weight f32 [ 2048, 1, 1, 1 ]
llama_model_loader: - tensor 46: blk.11.attn_output.weight q4_K [ 2048, 2048, 1, 1 ]
llama_model_loader: - tensor 47: blk.11.ffn_norm.weight f32 [ 2048, 1, 1, 1 ]
llama_model_loader: - tensor 48: blk.11.ffn_down.weight q4_K [ 5632, 2048, 1, 1 ]
llama_model_loader: - tensor 49: blk.12.attn_norm.weight f32 [ 2048, 1, 1, 1 ]
llama_model_loader: - tensor 50: blk.12.attn_output.weight q4_K [ 2048, 2048, 1, 1 ]
llama_model_loader: - tensor 51: blk.12.ffn_norm.weight f32 [ 2048, 1, 1, 1 ]
llama_model_loader: - tensor 52: blk.12.ffn_down.weight q6_K [ 5632, 2048, 1, 1 ]
llama_model_loader: - tensor 53: blk.13.attn_norm.weight f32 [ 2048, 1, 1, 1 ]
llama_model_loader: - tensor 54: blk.13.attn_output.weight q4_K [ 2048, 2048, 1, 1 ]
llama_model_loader: - tensor 55: blk.13.ffn_norm.weight f32 [ 2048, 1, 1, 1 ]
llama_model_loader: - tensor 56: blk.13.ffn_down.weight q4_K [ 5632, 2048, 1, 1 ]
llama_model_loader: - tensor 57: blk.14.attn_norm.weight f32 [ 2048, 1, 1, 1 ]
llama_model_loader: - tensor 58: blk.14.attn_output.weight q4_K [ 2048, 2048, 1, 1 ]
llama_model_loader: - tensor 59: blk.14.ffn_norm.weight f32 [ 2048, 1, 1, 1 ]
llama_model_loader: - tensor 60: blk.14.ffn_down.weight q4_K [ 5632, 2048, 1, 1 ]
llama_model_loader: - tensor 61: blk.15.attn_norm.weight f32 [ 2048, 1, 1, 1 ]
llama_model_loader: - tensor 62: blk.15.attn_output.weight q4_K [ 2048, 2048, 1, 1 ]
llama_model_loader: - tensor 63: blk.15.ffn_norm.weight f32 [ 2048, 1, 1, 1 ]
llama_model_loader: - tensor 64: blk.15.ffn_down.weight q6_K [ 5632, 2048, 1, 1 ]
llama_model_loader: - tensor 65: blk.16.attn_norm.weight f32 [ 2048, 1, 1, 1 ]
llama_model_loader: - tensor 66: blk.16.attn_output.weight q4_K [ 2048, 2048, 1, 1 ]
llama_model_loader: - tensor 67: blk.16.ffn_norm.weight f32 [ 2048, 1, 1, 1 ]
llama_model_loader: - tensor 68: blk.16.ffn_down.weight q4_K [ 5632, 2048, 1, 1 ]
llama_model_loader: - tensor 69: blk.17.attn_norm.weight f32 [ 2048, 1, 1, 1 ]
llama_model_loader: - tensor 70: blk.17.attn_output.weight q4_K [ 2048, 2048, 1, 1 ]
llama_model_loader: - tensor 71: blk.17.ffn_norm.weight f32 [ 2048, 1, 1, 1 ]
llama_model_loader: - tensor 72: blk.17.ffn_down.weight q4_K [ 5632, 2048, 1, 1 ]
llama_model_loader: - tensor 73: blk.18.attn_norm.weight f32 [ 2048, 1, 1, 1 ]
llama_model_loader: - tensor 74: blk.18.attn_output.weight q4_K [ 2048, 2048, 1, 1 ]
llama_model_loader: - tensor 75: blk.18.ffn_norm.weight f32 [ 2048, 1, 1, 1 ]
llama_model_loader: - tensor 76: blk.18.ffn_down.weight q6_K [ 5632, 2048, 1, 1 ]
llama_model_loader: - tensor 77: blk.19.attn_norm.weight f32 [ 2048, 1, 1, 1 ]
llama_model_loader: - tensor 78: blk.19.attn_output.weight q4_K [ 2048, 2048, 1, 1 ]
llama_model_loader: - tensor 79: blk.19.ffn_norm.weight f32 [ 2048, 1, 1, 1 ]
llama_model_loader: - tensor 80: blk.19.ffn_down.weight q4_K [ 5632, 2048, 1, 1 ]
llama_model_loader: - tensor 81: blk.20.attn_norm.weight f32 [ 2048, 1, 1, 1 ]
llama_model_loader: - tensor 82: blk.20.attn_output.weight q4_K [ 2048, 2048, 1, 1 ]
llama_model_loader: - tensor 83: blk.20.ffn_norm.weight f32 [ 2048, 1, 1, 1 ]
llama_model_loader: - tensor 84: blk.20.ffn_down.weight q4_K [ 5632, 2048, 1, 1 ]
llama_model_loader: - tensor 85: blk.21.attn_norm.weight f32 [ 2048, 1, 1, 1 ]
llama_model_loader: - tensor 86: blk.21.attn_output.weight q4_K [ 2048, 2048, 1, 1 ]
llama_model_loader: - tensor 87: blk.21.ffn_norm.weight f32 [ 2048, 1, 1, 1 ]
llama_model_loader: - tensor 88: blk.21.ffn_down.weight q6_K [ 5632, 2048, 1, 1 ]
llama_model_loader: - tensor 89: blk.22.attn_norm.weight f32 [ 2048, 1, 1, 1 ]
llama_model_loader: - tensor 90: blk.22.attn_output.weight q4_K [ 2048, 2048, 1, 1 ]
llama_model_loader: - tensor 91: blk.22.ffn_norm.weight f32 [ 2048, 1, 1, 1 ]
llama_model_loader: - tensor 92: blk.22.ffn_down.weight q4_K [ 5632, 2048, 1, 1 ]
llama_model_loader: - tensor 93: blk.23.attn_norm.weight f32 [ 2048, 1, 1, 1 ]
llama_model_loader: - tensor 94: blk.23.attn_output.weight q4_K [ 2048, 2048, 1, 1 ]
llama_model_loader: - tensor 95: blk.23.ffn_norm.weight f32 [ 2048, 1, 1, 1 ]
llama_model_loader: - tensor 96: blk.23.ffn_down.weight q4_K [ 5632, 2048, 1, 1 ]
llama_model_loader: - tensor 97: blk.24.attn_norm.weight f32 [ 2048, 1, 1, 1 ]
llama_model_loader: - tensor 98: blk.24.attn_output.weight q4_K [ 2048, 2048, 1, 1 ]
llama_model_loader: - tensor 99: blk.24.ffn_norm.weight f32 [ 2048, 1, 1, 1 ]
llama_model_loader: - tensor 100: blk.24.ffn_down.weight q6_K [ 5632, 2048, 1, 1 ]
llama_model_loader: - tensor 101: blk.25.attn_norm.weight f32 [ 2048, 1, 1, 1 ]
llama_model_loader: - tensor 102: blk.25.attn_output.weight q4_K [ 2048, 2048, 1, 1 ]
llama_model_loader: - tensor 103: blk.25.ffn_norm.weight f32 [ 2048, 1, 1, 1 ]
llama_model_loader: - tensor 104: blk.25.ffn_down.weight q4_K [ 5632, 2048, 1, 1 ]
llama_model_loader: - tensor 105: blk.26.attn_norm.weight f32 [ 2048, 1, 1, 1 ]
llama_model_loader: - tensor 106: blk.26.attn_output.weight q4_K [ 2048, 2048, 1, 1 ]
llama_model_loader: - tensor 107: blk.26.ffn_norm.weight f32 [ 2048, 1, 1, 1 ]
llama_model_loader: - tensor 108: blk.26.ffn_down.weight q4_K [ 5632, 2048, 1, 1 ]
llama_model_loader: - tensor 109: blk.27.attn_norm.weight f32 [ 2048, 1, 1, 1 ]
llama_model_loader: - tensor 110: blk.27.attn_output.weight q4_K [ 2048, 2048, 1, 1 ]
llama_model_loader: - tensor 111: blk.27.ffn_norm.weight f32 [ 2048, 1, 1, 1 ]
llama_model_loader: - tensor 112: blk.27.ffn_down.weight q6_K [ 5632, 2048, 1, 1 ]
llama_model_loader: - tensor 113: blk.28.attn_norm.weight f32 [ 2048, 1, 1, 1 ]
llama_model_loader: - tensor 114: blk.28.attn_output.weight q4_K [ 2048, 2048, 1, 1 ]
llama_model_loader: - tensor 115: blk.28.ffn_norm.weight f32 [ 2048, 1, 1, 1 ]
llama_model_loader: - tensor 116: blk.28.ffn_down.weight q6_K [ 5632, 2048, 1, 1 ]
llama_model_loader: - tensor 117: blk.29.attn_norm.weight f32 [ 2048, 1, 1, 1 ]
llama_model_loader: - tensor 118: blk.29.attn_output.weight q4_K [ 2048, 2048, 1, 1 ]
llama_model_loader: - tensor 119: blk.29.ffn_norm.weight f32 [ 2048, 1, 1, 1 ]
llama_model_loader: - tensor 120: blk.29.ffn_down.weight q6_K [ 5632, 2048, 1, 1 ]
llama_model_loader: - tensor 121: blk.30.attn_norm.weight f32 [ 2048, 1, 1, 1 ]
llama_model_loader: - tensor 122: blk.30.attn_output.weight q4_K [ 2048, 2048, 1, 1 ]
llama_model_loader: - tensor 123: blk.30.ffn_norm.weight f32 [ 2048, 1, 1, 1 ]
llama_model_loader: - tensor 124: blk.30.ffn_down.weight q6_K [ 5632, 2048, 1, 1 ]
llama_model_loader: - tensor 125: blk.31.attn_norm.weight f32 [ 2048, 1, 1, 1 ]
llama_model_loader: - tensor 126: blk.31.attn_output.weight q4_K [ 2048, 2048, 1, 1 ]
llama_model_loader: - tensor 127: blk.31.ffn_norm.weight f32 [ 2048, 1, 1, 1 ]
llama_model_loader: - tensor 128: blk.31.ffn_down.weight q6_K [ 5632, 2048, 1, 1 ]
llama_model_loader: - tensor 129: output_norm.weight f32 [ 2048, 1, 1, 1 ]
llama_model_loader: - tensor 130: output.weight q6_K [ 2048, 49216, 1, 1 ]
llama_model_loader: - tensor 131: blk.0.attn_k.weight q4_K [ 2048, 64, 1, 1 ]
llama_model_loader: - tensor 132: blk.0.attn_v.weight q6_K [ 2048, 64, 1, 1 ]
llama_model_loader: - tensor 133: blk.0.attn_q.weight q4_K [ 2048, 2048, 1, 1 ]
llama_model_loader: - tensor 134: blk.0.ffn_gate.weight q4_K [ 2048, 5632, 1, 1 ]
llama_model_loader: - tensor 135: blk.0.ffn_up.weight q4_K [ 2048, 5632, 1, 1 ]
llama_model_loader: - tensor 136: blk.1.attn_k.weight q4_K [ 2048, 64, 1, 1 ]
llama_model_loader: - tensor 137: blk.1.attn_v.weight q6_K [ 2048, 64, 1, 1 ]
llama_model_loader: - tensor 138: blk.1.attn_q.weight q4_K [ 2048, 2048, 1, 1 ]
llama_model_loader: - tensor 139: blk.1.ffn_gate.weight q4_K [ 2048, 5632, 1, 1 ]
llama_model_loader: - tensor 140: blk.1.ffn_up.weight q4_K [ 2048, 5632, 1, 1 ]
llama_model_loader: - tensor 141: blk.2.attn_k.weight q4_K [ 2048, 64, 1, 1 ]
llama_model_loader: - tensor 142: blk.2.attn_v.weight q6_K [ 2048, 64, 1, 1 ]
llama_model_loader: - tensor 143: blk.2.attn_q.weight q4_K [ 2048, 2048, 1, 1 ]
llama_model_loader: - tensor 144: blk.2.ffn_gate.weight q4_K [ 2048, 5632, 1, 1 ]
llama_model_loader: - tensor 145: blk.2.ffn_up.weight q4_K [ 2048, 5632, 1, 1 ]
llama_model_loader: - tensor 146: blk.3.attn_k.weight q4_K [ 2048, 64, 1, 1 ]
llama_model_loader: - tensor 147: blk.3.attn_v.weight q6_K [ 2048, 64, 1, 1 ]
llama_model_loader: - tensor 148: blk.3.attn_q.weight q4_K [ 2048, 2048, 1, 1 ]
llama_model_loader: - tensor 149: blk.3.ffn_gate.weight q4_K [ 2048, 5632, 1, 1 ]
llama_model_loader: - tensor 150: blk.3.ffn_up.weight q4_K [ 2048, 5632, 1, 1 ]
llama_model_loader: - tensor 151: blk.4.attn_k.weight q4_K [ 2048, 64, 1, 1 ]
llama_model_loader: - tensor 152: blk.4.attn_v.weight q4_K [ 2048, 64, 1, 1 ]
llama_model_loader: - tensor 153: blk.4.attn_q.weight q4_K [ 2048, 2048, 1, 1 ]
llama_model_loader: - tensor 154: blk.4.ffn_gate.weight q4_K [ 2048, 5632, 1, 1 ]
llama_model_loader: - tensor 155: blk.4.ffn_up.weight q4_K [ 2048, 5632, 1, 1 ]
llama_model_loader: - tensor 156: blk.5.attn_k.weight q4_K [ 2048, 64, 1, 1 ]
llama_model_loader: - tensor 157: blk.5.attn_v.weight q4_K [ 2048, 64, 1, 1 ]
llama_model_loader: - tensor 158: blk.5.attn_q.weight q4_K [ 2048, 2048, 1, 1 ]
llama_model_loader: - tensor 159: blk.5.ffn_gate.weight q4_K [ 2048, 5632, 1, 1 ]
llama_model_loader: - tensor 160: blk.5.ffn_up.weight q4_K [ 2048, 5632, 1, 1 ]
llama_model_loader: - tensor 161: blk.6.attn_k.weight q4_K [ 2048, 64, 1, 1 ]
llama_model_loader: - tensor 162: blk.6.attn_v.weight q6_K [ 2048, 64, 1, 1 ]
llama_model_loader: - tensor 163: blk.6.attn_q.weight q4_K [ 2048, 2048, 1, 1 ]
llama_model_loader: - tensor 164: blk.6.ffn_gate.weight q4_K [ 2048, 5632, 1, 1 ]
llama_model_loader: - tensor 165: blk.6.ffn_up.weight q4_K [ 2048, 5632, 1, 1 ]
llama_model_loader: - tensor 166: blk.7.attn_k.weight q4_K [ 2048, 64, 1, 1 ]
llama_model_loader: - tensor 167: blk.7.attn_v.weight q4_K [ 2048, 64, 1, 1 ]
llama_model_loader: - tensor 168: blk.7.attn_q.weight q4_K [ 2048, 2048, 1, 1 ]
llama_model_loader: - tensor 169: blk.7.ffn_gate.weight q4_K [ 2048, 5632, 1, 1 ]
llama_model_loader: - tensor 170: blk.7.ffn_up.weight q4_K [ 2048, 5632, 1, 1 ]
llama_model_loader: - tensor 171: blk.8.attn_k.weight q4_K [ 2048, 64, 1, 1 ]
llama_model_loader: - tensor 172: blk.8.attn_v.weight q4_K [ 2048, 64, 1, 1 ]
llama_model_loader: - tensor 173: blk.8.attn_q.weight q4_K [ 2048, 2048, 1, 1 ]
llama_model_loader: - tensor 174: blk.8.ffn_gate.weight q4_K [ 2048, 5632, 1, 1 ]
llama_model_loader: - tensor 175: blk.8.ffn_up.weight q4_K [ 2048, 5632, 1, 1 ]
llama_model_loader: - tensor 176: blk.9.attn_k.weight q4_K [ 2048, 64, 1, 1 ]
llama_model_loader: - tensor 177: blk.9.attn_v.weight q6_K [ 2048, 64, 1, 1 ]
llama_model_loader: - tensor 178: blk.9.attn_q.weight q4_K [ 2048, 2048, 1, 1 ]
llama_model_loader: - tensor 179: blk.9.ffn_gate.weight q4_K [ 2048, 5632, 1, 1 ]
llama_model_loader: - tensor 180: blk.9.ffn_up.weight q4_K [ 2048, 5632, 1, 1 ]
llama_model_loader: - tensor 181: blk.10.attn_k.weight q4_K [ 2048, 64, 1, 1 ]
llama_model_loader: - tensor 182: blk.10.attn_v.weight q4_K [ 2048, 64, 1, 1 ]
llama_model_loader: - tensor 183: blk.10.attn_q.weight q4_K [ 2048, 2048, 1, 1 ]
llama_model_loader: - tensor 184: blk.10.ffn_gate.weight q4_K [ 2048, 5632, 1, 1 ]
llama_model_loader: - tensor 185: blk.10.ffn_up.weight q4_K [ 2048, 5632, 1, 1 ]
llama_model_loader: - tensor 186: blk.11.attn_k.weight q4_K [ 2048, 64, 1, 1 ]
llama_model_loader: - tensor 187: blk.11.attn_v.weight q4_K [ 2048, 64, 1, 1 ]
llama_model_loader: - tensor 188: blk.11.attn_q.weight q4_K [ 2048, 2048, 1, 1 ]
llama_model_loader: - tensor 189: blk.11.ffn_gate.weight q4_K [ 2048, 5632, 1, 1 ]
llama_model_loader: - tensor 190: blk.11.ffn_up.weight q4_K [ 2048, 5632, 1, 1 ]
llama_model_loader: - tensor 191: blk.12.attn_k.weight q4_K [ 2048, 64, 1, 1 ]
llama_model_loader: - tensor 192: blk.12.attn_v.weight q6_K [ 2048, 64, 1, 1 ]
llama_model_loader: - tensor 193: blk.12.attn_q.weight q4_K [ 2048, 2048, 1, 1 ]
llama_model_loader: - tensor 194: blk.12.ffn_gate.weight q4_K [ 2048, 5632, 1, 1 ]
llama_model_loader: - tensor 195: blk.12.ffn_up.weight q4_K [ 2048, 5632, 1, 1 ]
llama_model_loader: - tensor 196: blk.13.attn_k.weight q4_K [ 2048, 64, 1, 1 ]
llama_model_loader: - tensor 197: blk.13.attn_v.weight q4_K [ 2048, 64, 1, 1 ]
llama_model_loader: - tensor 198: blk.13.attn_q.weight q4_K [ 2048, 2048, 1, 1 ]
llama_model_loader: - tensor 199: blk.13.ffn_gate.weight q4_K [ 2048, 5632, 1, 1 ]
llama_model_loader: - tensor 200: blk.13.ffn_up.weight q4_K [ 2048, 5632, 1, 1 ]
llama_model_loader: - tensor 201: blk.14.attn_k.weight q4_K [ 2048, 64, 1, 1 ]
llama_model_loader: - tensor 202: blk.14.attn_v.weight q4_K [ 2048, 64, 1, 1 ]
llama_model_loader: - tensor 203: blk.14.attn_q.weight q4_K [ 2048, 2048, 1, 1 ]
llama_model_loader: - tensor 204: blk.14.ffn_gate.weight q4_K [ 2048, 5632, 1, 1 ]
llama_model_loader: - tensor 205: blk.14.ffn_up.weight q4_K [ 2048, 5632, 1, 1 ]
llama_model_loader: - tensor 206: blk.15.attn_k.weight q4_K [ 2048, 64, 1, 1 ]
llama_model_loader: - tensor 207: blk.15.attn_v.weight q6_K [ 2048, 64, 1, 1 ]
llama_model_loader: - tensor 208: blk.15.attn_q.weight q4_K [ 2048, 2048, 1, 1 ]
llama_model_loader: - tensor 209: blk.15.ffn_gate.weight q4_K [ 2048, 5632, 1, 1 ]
llama_model_loader: - tensor 210: blk.15.ffn_up.weight q4_K [ 2048, 5632, 1, 1 ]
llama_model_loader: - tensor 211: blk.16.attn_k.weight q4_K [ 2048, 64, 1, 1 ]
llama_model_loader: - tensor 212: blk.16.attn_v.weight q4_K [ 2048, 64, 1, 1 ]
llama_model_loader: - tensor 213: blk.16.attn_q.weight q4_K [ 2048, 2048, 1, 1 ]
llama_model_loader: - tensor 214: blk.16.ffn_gate.weight q4_K [ 2048, 5632, 1, 1 ]
llama_model_loader: - tensor 215: blk.16.ffn_up.weight q4_K [ 2048, 5632, 1, 1 ]
llama_model_loader: - tensor 216: blk.17.attn_k.weight q4_K [ 2048, 64, 1, 1 ]
llama_model_loader: - tensor 217: blk.17.attn_v.weight q4_K [ 2048, 64, 1, 1 ]
llama_model_loader: - tensor 218: blk.17.attn_q.weight q4_K [ 2048, 2048, 1, 1 ]
llama_model_loader: - tensor 219: blk.17.ffn_gate.weight q4_K [ 2048, 5632, 1, 1 ]
llama_model_loader: - tensor 220: blk.17.ffn_up.weight q4_K [ 2048, 5632, 1, 1 ]
llama_model_loader: - tensor 221: blk.18.attn_k.weight q4_K [ 2048, 64, 1, 1 ]
llama_model_loader: - tensor 222: blk.18.attn_v.weight q6_K [ 2048, 64, 1, 1 ]
llama_model_loader: - tensor 223: blk.18.attn_q.weight q4_K [ 2048, 2048, 1, 1 ]
llama_model_loader: - tensor 224: blk.18.ffn_gate.weight q4_K [ 2048, 5632, 1, 1 ]
llama_model_loader: - tensor 225: blk.18.ffn_up.weight q4_K [ 2048, 5632, 1, 1 ]
llama_model_loader: - tensor 226: blk.19.attn_k.weight q4_K [ 2048, 64, 1, 1 ]
llama_model_loader: - tensor 227: blk.19.attn_v.weight q4_K [ 2048, 64, 1, 1 ]
llama_model_loader: - tensor 228: blk.19.attn_q.weight q4_K [ 2048, 2048, 1, 1 ]
llama_model_loader: - tensor 229: blk.19.ffn_gate.weight q4_K [ 2048, 5632, 1, 1 ]
llama_model_loader: - tensor 230: blk.19.ffn_up.weight q4_K [ 2048, 5632, 1, 1 ]
llama_model_loader: - tensor 231: blk.20.attn_k.weight q4_K [ 2048, 64, 1, 1 ]
llama_model_loader: - tensor 232: blk.20.attn_v.weight q4_K [ 2048, 64, 1, 1 ]
llama_model_loader: - tensor 233: blk.20.attn_q.weight q4_K [ 2048, 2048, 1, 1 ]
llama_model_loader: - tensor 234: blk.20.ffn_gate.weight q4_K [ 2048, 5632, 1, 1 ]
llama_model_loader: - tensor 235: blk.20.ffn_up.weight q4_K [ 2048, 5632, 1, 1 ]
llama_model_loader: - tensor 236: blk.21.attn_k.weight q4_K [ 2048, 64, 1, 1 ]
llama_model_loader: - tensor 237: blk.21.attn_v.weight q6_K [ 2048, 64, 1, 1 ]
llama_model_loader: - tensor 238: blk.21.attn_q.weight q4_K [ 2048, 2048, 1, 1 ]
llama_model_loader: - tensor 239: blk.21.ffn_gate.weight q4_K [ 2048, 5632, 1, 1 ]
llama_model_loader: - tensor 240: blk.21.ffn_up.weight q4_K [ 2048, 5632, 1, 1 ]
llama_model_loader: - tensor 241: blk.22.attn_k.weight q4_K [ 2048, 64, 1, 1 ]
llama_model_loader: - tensor 242: blk.22.attn_v.weight q4_K [ 2048, 64, 1, 1 ]
llama_model_loader: - tensor 243: blk.22.attn_q.weight q4_K [ 2048, 2048, 1, 1 ]
llama_model_loader: - tensor 244: blk.22.ffn_gate.weight q4_K [ 2048, 5632, 1, 1 ]
llama_model_loader: - tensor 245: blk.22.ffn_up.weight q4_K [ 2048, 5632, 1, 1 ]
llama_model_loader: - tensor 246: blk.23.attn_k.weight q4_K [ 2048, 64, 1, 1 ]
llama_model_loader: - tensor 247: blk.23.attn_v.weight q4_K [ 2048, 64, 1, 1 ]
llama_model_loader: - tensor 248: blk.23.attn_q.weight q4_K [ 2048, 2048, 1, 1 ]
llama_model_loader: - tensor 249: blk.23.ffn_gate.weight q4_K [ 2048, 5632, 1, 1 ]
llama_model_loader: - tensor 250: blk.23.ffn_up.weight q4_K [ 2048, 5632, 1, 1 ]
llama_model_loader: - tensor 251: blk.24.attn_k.weight q4_K [ 2048, 64, 1, 1 ]
llama_model_loader: - tensor 252: blk.24.attn_v.weight q6_K [ 2048, 64, 1, 1 ]
llama_model_loader: - tensor 253: blk.24.attn_q.weight q4_K [ 2048, 2048, 1, 1 ]
llama_model_loader: - tensor 254: blk.24.ffn_gate.weight q4_K [ 2048, 5632, 1, 1 ]
llama_model_loader: - tensor 255: blk.24.ffn_up.weight q4_K [ 2048, 5632, 1, 1 ]
llama_model_loader: - tensor 256: blk.25.attn_k.weight q4_K [ 2048, 64, 1, 1 ]
llama_model_loader: - tensor 257: blk.25.attn_v.weight q4_K [ 2048, 64, 1, 1 ]
llama_model_loader: - tensor 258: blk.25.attn_q.weight q4_K [ 2048, 2048, 1, 1 ]
llama_model_loader: - tensor 259: blk.25.ffn_gate.weight q4_K [ 2048, 5632, 1, 1 ]
llama_model_loader: - tensor 260: blk.25.ffn_up.weight q4_K [ 2048, 5632, 1, 1 ]
llama_model_loader: - tensor 261: blk.26.attn_k.weight q4_K [ 2048, 64, 1, 1 ]
llama_model_loader: - tensor 262: blk.26.attn_v.weight q4_K [ 2048, 64, 1, 1 ]
llama_model_loader: - tensor 263: blk.26.attn_q.weight q4_K [ 2048, 2048, 1, 1 ]
llama_model_loader: - tensor 264: blk.26.ffn_gate.weight q4_K [ 2048, 5632, 1, 1 ]
llama_model_loader: - tensor 265: blk.26.ffn_up.weight q4_K [ 2048, 5632, 1, 1 ]
llama_model_loader: - tensor 266: blk.27.attn_k.weight q4_K [ 2048, 64, 1, 1 ]
llama_model_loader: - tensor 267: blk.27.attn_v.weight q6_K [ 2048, 64, 1, 1 ]
llama_model_loader: - tensor 268: blk.27.attn_q.weight q4_K [ 2048, 2048, 1, 1 ]
llama_model_loader: - tensor 269: blk.27.ffn_gate.weight q4_K [ 2048, 5632, 1, 1 ]
llama_model_loader: - tensor 270: blk.27.ffn_up.weight q4_K [ 2048, 5632, 1, 1 ]
llama_model_loader: - tensor 271: blk.28.attn_k.weight q4_K [ 2048, 64, 1, 1 ]
llama_model_loader: - tensor 272: blk.28.attn_v.weight q6_K [ 2048, 64, 1, 1 ]
llama_model_loader: - tensor 273: blk.28.attn_q.weight q4_K [ 2048, 2048, 1, 1 ]
llama_model_loader: - tensor 274: blk.28.ffn_gate.weight q4_K [ 2048, 5632, 1, 1 ]
llama_model_loader: - tensor 275: blk.28.ffn_up.weight q4_K [ 2048, 5632, 1, 1 ]
llama_model_loader: - tensor 276: blk.29.attn_k.weight q4_K [ 2048, 64, 1, 1 ]
llama_model_loader: - tensor 277: blk.29.attn_v.weight q6_K [ 2048, 64, 1, 1 ]
llama_model_loader: - tensor 278: blk.29.attn_q.weight q4_K [ 2048, 2048, 1, 1 ]
llama_model_loader: - tensor 279: blk.29.ffn_gate.weight q4_K [ 2048, 5632, 1, 1 ]
llama_model_loader: - tensor 280: blk.29.ffn_up.weight q4_K [ 2048, 5632, 1, 1 ]
llama_model_loader: - tensor 281: blk.30.attn_k.weight q4_K [ 2048, 64, 1, 1 ]
llama_model_loader: - tensor 282: blk.30.attn_v.weight q6_K [ 2048, 64, 1, 1 ]
llama_model_loader: - tensor 283: blk.30.attn_q.weight q4_K [ 2048, 2048, 1, 1 ]
llama_model_loader: - tensor 284: blk.30.ffn_gate.weight q4_K [ 2048, 5632, 1, 1 ]
llama_model_loader: - tensor 285: blk.30.ffn_up.weight q4_K [ 2048, 5632, 1, 1 ]
llama_model_loader: - tensor 286: blk.31.attn_k.weight q4_K [ 2048, 64, 1, 1 ]
llama_model_loader: - tensor 287: blk.31.attn_v.weight q6_K [ 2048, 64, 1, 1 ]
llama_model_loader: - tensor 288: blk.31.attn_q.weight q4_K [ 2048, 2048, 1, 1 ]
llama_model_loader: - tensor 289: blk.31.ffn_gate.weight q4_K [ 2048, 5632, 1, 1 ]
llama_model_loader: - tensor 290: blk.31.ffn_up.weight q4_K [ 2048, 5632, 1, 1 ]
llama_model_loader: - kv 0: general.architecture str
llama_model_loader: - kv 1: general.name str
llama_model_loader: - kv 2: refact.context_length u32
llama_model_loader: - kv 3: refact.embedding_length u32
llama_model_loader: - kv 4: refact.feed_forward_length u32
llama_model_loader: - kv 5: refact.block_count u32
llama_model_loader: - kv 6: refact.attention.head_count u32
llama_model_loader: - kv 7: refact.attention.head_count_kv u32
llama_model_loader: - kv 8: refact.attention.layer_norm_rms_epsilon f32
llama_model_loader: - kv 9: general.file_type u32
llama_model_loader: - kv 10: tokenizer.ggml.model str
llama_model_loader: - kv 11: tokenizer.ggml.tokens arr
llama_model_loader: - kv 12: tokenizer.ggml.scores arr
llama_model_loader: - kv 13: tokenizer.ggml.token_type arr
llama_model_loader: - kv 14: tokenizer.ggml.merges arr
llama_model_loader: - kv 15: tokenizer.ggml.bos_token_id u32
llama_model_loader: - kv 16: tokenizer.ggml.eos_token_id u32
llama_model_loader: - kv 17: tokenizer.ggml.unknown_token_id u32
llama_model_loader: - kv 18: general.quantization_version u32
llama_model_loader: - type f32: 65 tensors
llama_model_loader: - type q4_K: 193 tensors
llama_model_loader: - type q6_K: 33 tensors
error loading model: invalid character
llama_load_model_from_file: failed to load model
llama_init_from_gpt_params: error: failed to load model './refact-1_6B-fim-Q4_K_M.gguf'
main: error: unable to load model