Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

model: refact-1_6B-fim unable to load model #3531

Closed
nortekax opened this issue Oct 7, 2023 · 3 comments
Closed

model: refact-1_6B-fim unable to load model #3531

nortekax opened this issue Oct 7, 2023 · 3 comments
Labels
stale

Comments

@nortekax
Copy link

nortekax commented Oct 7, 2023

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.h I 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
@martell
Copy link

martell commented Oct 8, 2023 •
edited
Loading

Hi @nortekax, thanks for reporting this. This is currently being addressed in #3523

@nortekax
Copy link
Author

@martell, your kindness in answering makes a big difference, thank you. It looks like the fix was merged.

@github-actions github-actions bot added the stale label Mar 19, 2024
@github-actions GitHub Actions
Copy link
Contributor

github-actions bot commented Apr 4, 2024

This issue was closed because it has been inactive for 14 days since being marked as stale.

@github-actions github-actions bot closed this as completed Apr 4, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
stale
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
2 participants
@martell @nortekax