search

ggerganov / llama.cpp

LLM inference in C/C++
MIT License
67.22k stars 9.65k forks source link

CausalLM: Llama + vocab.json BPE tokenizer = `error loading model: cannot find tokenizer merges in model file` #3732

Closed TheBloke closed 7 months ago

TheBloke commented 1 year ago

Hi guys

A coupe of new and interesting models dropped today:

These are a merge of Qwen + Llama in Llama architecture, but with a vobab.json + merges.txt GPT2 tokenizer, with a vocab size exceeding 150,000.

I was able to make an FP16 with two extra steps:

This seemed to produce a valid FP16, from which I made quants as normal. For 14B I could only make old-style quants, as many of the tensors are not 256-divisible. For 7B I could make k-quants.

Unfortunately, the resulting files are not usable with llama.cpp, giving this error:

error loading model: cannot find tokenizer merges in model file

llama_load_model_from_file: failed to load model
llama_init_from_gpt_params: error: failed to load model '/workspace/causallm_7b.Q3_K_M.gguf'
main: error: unable to load model

Did I do anything wrong? Or is this a bug?

Full log of attempting to run inference on one of the 7B k-quants:

(pytorch2)  ubuntu@a10:/workspace/git/gguf-llama (master ✘)✭ ᐅ ./main -m /workspace/causallm_7b.Q3_K_M.gguf -p "<|im_start|>system\nYou are a helpful assistant<|im_end|>\n<|im_start|>user\nwrite a story<|im_end|>\n<|im_start|>assistant"
Log start
main: build = 1414 (96981f3)
main: built with cc (Ubuntu 9.4.0-1ubuntu1~20.04.1) 9.4.0 for x86_64-linux-gnu
main: seed  = 1698010184
ggml_init_cublas: found 1 CUDA devices:
  Device 0: NVIDIA A10, compute capability 8.6
llama_model_loader: loaded meta data with 20 key-value pairs and 291 tensors from /workspace/causallm_7b.Q3_K_M.gguf (version unknown)
llama_model_loader: - tensor    0:                token_embd.weight q3_K     [  4096, 151936,     1,     1 ]
llama_model_loader: - tensor    1:              blk.0.attn_q.weight q3_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor    2:              blk.0.attn_k.weight q3_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor    3:              blk.0.attn_v.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor    4:         blk.0.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor    5:            blk.0.ffn_gate.weight q3_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor    6:              blk.0.ffn_up.weight q3_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor    7:            blk.0.ffn_down.weight q5_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor    8:           blk.0.attn_norm.weight f32      [  4096,     1,     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_q.weight q3_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   11:              blk.1.attn_k.weight q3_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   12:              blk.1.attn_v.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   13:         blk.1.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   14:            blk.1.ffn_gate.weight q3_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   15:              blk.1.ffn_up.weight q3_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   16:            blk.1.ffn_down.weight q5_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor   17:           blk.1.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   18:            blk.1.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   19:              blk.2.attn_q.weight q3_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   20:              blk.2.attn_k.weight q3_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   21:              blk.2.attn_v.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   22:         blk.2.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   23:            blk.2.ffn_gate.weight q3_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   24:              blk.2.ffn_up.weight q3_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   25:            blk.2.ffn_down.weight q4_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor   26:           blk.2.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   27:            blk.2.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   28:              blk.3.attn_q.weight q3_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   29:              blk.3.attn_k.weight q3_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   30:              blk.3.attn_v.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   31:         blk.3.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   32:            blk.3.ffn_gate.weight q3_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   33:              blk.3.ffn_up.weight q3_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   34:            blk.3.ffn_down.weight q4_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor   35:           blk.3.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   36:            blk.3.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   37:              blk.4.attn_q.weight q3_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   38:              blk.4.attn_k.weight q3_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   39:              blk.4.attn_v.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   40:         blk.4.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   41:            blk.4.ffn_gate.weight q3_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   42:              blk.4.ffn_up.weight q3_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   43:            blk.4.ffn_down.weight q4_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor   44:           blk.4.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   45:            blk.4.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   46:              blk.5.attn_q.weight q3_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   47:              blk.5.attn_k.weight q3_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   48:              blk.5.attn_v.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   49:         blk.5.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   50:            blk.5.ffn_gate.weight q3_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   51:              blk.5.ffn_up.weight q3_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   52:            blk.5.ffn_down.weight q4_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor   53:           blk.5.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   54:            blk.5.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   55:              blk.6.attn_q.weight q3_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   56:              blk.6.attn_k.weight q3_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   57:              blk.6.attn_v.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   58:         blk.6.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   59:            blk.6.ffn_gate.weight q3_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   60:              blk.6.ffn_up.weight q3_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   61:            blk.6.ffn_down.weight q4_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor   62:           blk.6.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   63:            blk.6.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   64:              blk.7.attn_q.weight q3_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   65:              blk.7.attn_k.weight q3_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   66:              blk.7.attn_v.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   67:         blk.7.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   68:            blk.7.ffn_gate.weight q3_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   69:              blk.7.ffn_up.weight q3_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   70:            blk.7.ffn_down.weight q4_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor   71:           blk.7.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   72:            blk.7.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   73:              blk.8.attn_q.weight q3_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   74:              blk.8.attn_k.weight q3_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   75:              blk.8.attn_v.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   76:         blk.8.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   77:            blk.8.ffn_gate.weight q3_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   78:              blk.8.ffn_up.weight q3_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   79:            blk.8.ffn_down.weight q4_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor   80:           blk.8.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   81:            blk.8.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   82:              blk.9.attn_q.weight q3_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   83:              blk.9.attn_k.weight q3_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   84:              blk.9.attn_v.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   85:         blk.9.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   86:            blk.9.ffn_gate.weight q3_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   87:              blk.9.ffn_up.weight q3_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   88:            blk.9.ffn_down.weight q4_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor   89:           blk.9.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   90:            blk.9.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   91:             blk.10.attn_q.weight q3_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   92:             blk.10.attn_k.weight q3_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   93:             blk.10.attn_v.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   94:        blk.10.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   95:           blk.10.ffn_gate.weight q3_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   96:             blk.10.ffn_up.weight q3_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   97:           blk.10.ffn_down.weight q4_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor   98:          blk.10.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   99:           blk.10.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  100:             blk.11.attn_q.weight q3_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  101:             blk.11.attn_k.weight q3_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  102:             blk.11.attn_v.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  103:        blk.11.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  104:           blk.11.ffn_gate.weight q3_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  105:             blk.11.ffn_up.weight q3_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  106:           blk.11.ffn_down.weight q4_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  107:          blk.11.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  108:           blk.11.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  109:             blk.12.attn_q.weight q3_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  110:             blk.12.attn_k.weight q3_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  111:             blk.12.attn_v.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  112:        blk.12.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  113:           blk.12.ffn_gate.weight q3_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  114:             blk.12.ffn_up.weight q3_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  115:           blk.12.ffn_down.weight q4_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  116:          blk.12.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  117:           blk.12.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  118:             blk.13.attn_q.weight q3_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  119:             blk.13.attn_k.weight q3_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  120:             blk.13.attn_v.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  121:        blk.13.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  122:           blk.13.ffn_gate.weight q3_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  123:             blk.13.ffn_up.weight q3_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  124:           blk.13.ffn_down.weight q4_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  125:          blk.13.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  126:           blk.13.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  127:             blk.14.attn_q.weight q3_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  128:             blk.14.attn_k.weight q3_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  129:             blk.14.attn_v.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  130:        blk.14.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  131:           blk.14.ffn_gate.weight q3_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  132:             blk.14.ffn_up.weight q3_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  133:           blk.14.ffn_down.weight q4_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  134:          blk.14.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  135:           blk.14.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  136:             blk.15.attn_q.weight q3_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  137:             blk.15.attn_k.weight q3_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  138:             blk.15.attn_v.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  139:        blk.15.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  140:           blk.15.ffn_gate.weight q3_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  141:             blk.15.ffn_up.weight q3_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  142:           blk.15.ffn_down.weight q4_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  143:          blk.15.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  144:           blk.15.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  145:             blk.16.attn_q.weight q3_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  146:             blk.16.attn_k.weight q3_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  147:             blk.16.attn_v.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  148:        blk.16.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  149:           blk.16.ffn_gate.weight q3_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  150:             blk.16.ffn_up.weight q3_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  151:           blk.16.ffn_down.weight q4_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  152:          blk.16.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  153:           blk.16.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  154:             blk.17.attn_q.weight q3_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  155:             blk.17.attn_k.weight q3_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  156:             blk.17.attn_v.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  157:        blk.17.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  158:           blk.17.ffn_gate.weight q3_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  159:             blk.17.ffn_up.weight q3_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  160:           blk.17.ffn_down.weight q4_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  161:          blk.17.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  162:           blk.17.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  163:             blk.18.attn_q.weight q3_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  164:             blk.18.attn_k.weight q3_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  165:             blk.18.attn_v.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  166:        blk.18.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  167:           blk.18.ffn_gate.weight q3_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  168:             blk.18.ffn_up.weight q3_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  169:           blk.18.ffn_down.weight q4_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  170:          blk.18.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  171:           blk.18.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  172:             blk.19.attn_q.weight q3_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  173:             blk.19.attn_k.weight q3_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  174:             blk.19.attn_v.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  175:        blk.19.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  176:           blk.19.ffn_gate.weight q3_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  177:             blk.19.ffn_up.weight q3_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  178:           blk.19.ffn_down.weight q4_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  179:          blk.19.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  180:           blk.19.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  181:             blk.20.attn_q.weight q3_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  182:             blk.20.attn_k.weight q3_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  183:             blk.20.attn_v.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  184:        blk.20.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  185:           blk.20.ffn_gate.weight q3_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  186:             blk.20.ffn_up.weight q3_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  187:           blk.20.ffn_down.weight q4_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  188:          blk.20.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  189:           blk.20.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  190:             blk.21.attn_q.weight q3_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  191:             blk.21.attn_k.weight q3_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  192:             blk.21.attn_v.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  193:        blk.21.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  194:           blk.21.ffn_gate.weight q3_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  195:             blk.21.ffn_up.weight q3_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  196:           blk.21.ffn_down.weight q4_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  197:          blk.21.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  198:           blk.21.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  199:             blk.22.attn_q.weight q3_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  200:             blk.22.attn_k.weight q3_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  201:             blk.22.attn_v.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  202:        blk.22.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  203:           blk.22.ffn_gate.weight q3_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  204:             blk.22.ffn_up.weight q3_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  205:           blk.22.ffn_down.weight q4_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  206:          blk.22.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  207:           blk.22.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  208:             blk.23.attn_q.weight q3_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  209:             blk.23.attn_k.weight q3_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  210:             blk.23.attn_v.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  211:        blk.23.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  212:           blk.23.ffn_gate.weight q3_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  213:             blk.23.ffn_up.weight q3_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  214:           blk.23.ffn_down.weight q4_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  215:          blk.23.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  216:           blk.23.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  217:             blk.24.attn_q.weight q3_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  218:             blk.24.attn_k.weight q3_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  219:             blk.24.attn_v.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  220:        blk.24.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  221:           blk.24.ffn_gate.weight q3_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  222:             blk.24.ffn_up.weight q3_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  223:           blk.24.ffn_down.weight q4_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  224:          blk.24.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  225:           blk.24.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  226:             blk.25.attn_q.weight q3_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  227:             blk.25.attn_k.weight q3_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  228:             blk.25.attn_v.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  229:        blk.25.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  230:           blk.25.ffn_gate.weight q3_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  231:             blk.25.ffn_up.weight q3_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  232:           blk.25.ffn_down.weight q4_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  233:          blk.25.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  234:           blk.25.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  235:             blk.26.attn_q.weight q3_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  236:             blk.26.attn_k.weight q3_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  237:             blk.26.attn_v.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  238:        blk.26.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  239:           blk.26.ffn_gate.weight q3_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  240:             blk.26.ffn_up.weight q3_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  241:           blk.26.ffn_down.weight q4_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  242:          blk.26.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  243:           blk.26.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  244:             blk.27.attn_q.weight q3_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  245:             blk.27.attn_k.weight q3_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  246:             blk.27.attn_v.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  247:        blk.27.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  248:           blk.27.ffn_gate.weight q3_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  249:             blk.27.ffn_up.weight q3_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  250:           blk.27.ffn_down.weight q4_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  251:          blk.27.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  252:           blk.27.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  253:             blk.28.attn_q.weight q3_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  254:             blk.28.attn_k.weight q3_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  255:             blk.28.attn_v.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  256:        blk.28.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  257:           blk.28.ffn_gate.weight q3_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  258:             blk.28.ffn_up.weight q3_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  259:           blk.28.ffn_down.weight q4_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  260:          blk.28.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  261:           blk.28.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  262:             blk.29.attn_q.weight q3_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  263:             blk.29.attn_k.weight q3_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  264:             blk.29.attn_v.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  265:        blk.29.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  266:           blk.29.ffn_gate.weight q3_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  267:             blk.29.ffn_up.weight q3_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  268:           blk.29.ffn_down.weight q4_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  269:          blk.29.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  270:           blk.29.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  271:             blk.30.attn_q.weight q3_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  272:             blk.30.attn_k.weight q3_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  273:             blk.30.attn_v.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  274:        blk.30.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  275:           blk.30.ffn_gate.weight q3_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  276:             blk.30.ffn_up.weight q3_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  277:           blk.30.ffn_down.weight q4_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  278:          blk.30.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  279:           blk.30.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  280:             blk.31.attn_q.weight q3_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  281:             blk.31.attn_k.weight q3_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  282:             blk.31.attn_v.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  283:        blk.31.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  284:           blk.31.ffn_gate.weight q3_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  285:             blk.31.ffn_up.weight q3_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  286:           blk.31.ffn_down.weight q4_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  287:          blk.31.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  288:           blk.31.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  289:               output_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  290:                    output.weight q6_K     [  4096, 151936,     1,     1 ]
llama_model_loader: - kv   0:                       general.architecture str
llama_model_loader: - kv   1:                               general.name str
llama_model_loader: - kv   2:                       llama.context_length u32
llama_model_loader: - kv   3:                     llama.embedding_length u32
llama_model_loader: - kv   4:                          llama.block_count u32
llama_model_loader: - kv   5:                  llama.feed_forward_length u32
llama_model_loader: - kv   6:                 llama.rope.dimension_count u32
llama_model_loader: - kv   7:                 llama.attention.head_count u32
llama_model_loader: - kv   8:              llama.attention.head_count_kv u32
llama_model_loader: - kv   9:     llama.attention.layer_norm_rms_epsilon f32
llama_model_loader: - kv  10:                       llama.rope.freq_base f32
llama_model_loader: - kv  11:                          general.file_type u32
llama_model_loader: - kv  12:                       tokenizer.ggml.model str
llama_model_loader: - kv  13:                      tokenizer.ggml.tokens arr
llama_model_loader: - kv  14:                      tokenizer.ggml.scores arr
llama_model_loader: - kv  15:                  tokenizer.ggml.token_type arr
llama_model_loader: - kv  16:                tokenizer.ggml.bos_token_id u32
llama_model_loader: - kv  17:                tokenizer.ggml.eos_token_id u32
llama_model_loader: - kv  18:            tokenizer.ggml.padding_token_id u32
llama_model_loader: - kv  19:               general.quantization_version u32
llama_model_loader: - type  f32:   65 tensors
llama_model_loader: - type q3_K:  129 tensors
llama_model_loader: - type q4_K:   92 tensors
llama_model_loader: - type q5_K:    4 tensors
llama_model_loader: - type q6_K:    1 tensors
error loading model: cannot find tokenizer merges in model file

llama_load_model_from_file: failed to load model
llama_init_from_gpt_params: error: failed to load model '/workspace/causallm_7b.Q3_K_M.gguf'
main: error: unable to load model
goerch commented 1 year ago

Looks like an old style (i.e. using slow tokenizers) model to me.

Edit: funny, didn't find a mention of merges.txt in the repository. What are we fighting against?

KerfuffleV2 commented 1 year ago

@TheBloke Assuming you have merges.txt which looks like:

#version: blah
a b
d ef
etc etc

and a tokenizer.json that lacks a merges section, you can try this little script I made:

import json
with open('tokenizer.json', 'r') as fp:
  tokenizer = json.load(fp)
merges = []
with open('merges.txt', 'r') as mfp:
  firstline = next(mfp).strip()
  if not firstline.startswith('#version:'):
    merges.append(firstline)
  for l in mfp:
    l = l.strip()
    if len(l) > 0:
      merges.append(l)
tokenizer['merges'] = merges
with open('tokenizer.json.new', 'w') as outfp:
  json.dump(tokenizer, outfp, indent = 4)

It'll open tokenizer.json and merges.txt in the current directory, and then add the merges to the stuff in that tokenizer.json. The result will get saved to tokenizer.json.new in the current directory - you can verify if it looks right. The format looks pretty simple at least with the random model I checked. I don't have a way to test it, but I think this should work.

staviq commented 1 year ago

@KerfuffleV2

It works, but the merges.txt for both models looks like it's damaged or incomplete, last line in that file is not a pair.

KerfuffleV2 commented 1 year ago

I don't have a HF account so I can't look at it myself. I guess TB could try just trimming that last line then? Or change if len(l) > 0: to if len(l) > 0 and ' ' in l: to make it just skip lines that don't have at least one space.

From what I recall, before GGUF we didn't even add the merges at all so it'll probably be okay. What are the odds that one merge is the super important one? (With my luck...)

quick edit: Even if it seems to work, probably a bad idea to leave it as is though. I assume that if it doesn't just crash/detect an error then it's going to work like "blah" merges with empty string, which might actually have an effect.

CausalLM commented 1 year ago

The tokenizer is the same as Qwen Models, they use a tiktoken, and this GPT2FastTokenizer is converted from their vocab.

Their CPP tiktoken implement: https://github.com/QwenLM/qwen.cpp/tree/master/tiktoken_cpp

And their tiktoken vocab: https://huggingface.co/Qwen/Qwen-7B/blob/main/qwen.tiktoken

The converted GPT2 style tokenizer from: https://huggingface.co/JosephusCheung/Qwen-LLaMAfied-7B-Chat/tree/main

But I am still confused, what makes it different from those working BPE tokenized models?

KerfuffleV2 commented 1 year ago

But I am still confused, what makes it different from those working BPE tokenized models?

For the purposes of converting to GGUF in BPE mode, the difference is that it (apparently) doesn't have the merges in a tokenizer section in tokenizer.json. We currently only look there and don't consider external sources like merges.txt at all.

Also the original Qwen as far as I know isn't included in the category "already working BPE tokenized models", there are still some issues open requesting Qwen support. So after fixing/working around this issue there definitely may be more to deal with.

KerfuffleV2 commented 1 year ago

Please test #3743 and see if you can create a functional model. You'll need to use --padvocab to add the dummy tokens.

TheBloke commented 1 year ago

Testing now, thanks. Love --padvocab, that's awesome thanks!

TheBloke commented 1 year ago

Working, thank you! Great work.

...........................................................................................
llama_new_context_with_model: n_ctx      = 512
llama_new_context_with_model: freq_base  = 10000.0
llama_new_context_with_model: freq_scale = 1
llama_new_context_with_model: kv self size  =  400.00 MB
llama_new_context_with_model: compute buffer total size = 313.13 MB
llama_new_context_with_model: VRAM scratch buffer: 307.00 MB
llama_new_context_with_model: total VRAM used: 307.00 MB (model: 0.00 MB, context: 307.00 MB)

system_info: n_threads = 15 / 30 | AVX = 1 | AVX2 = 1 | AVX512 = 1 | AVX512_VBMI = 1 | AVX512_VNNI = 1 | FMA = 1 | NEON = 0 | ARM_FMA = 0 | F16C = 1 | FP16_VA = 0 | WASM_SIMD = 0 | BLAS = 1 | SSE3 = 1 | SSSE3 = 1 | VSX = 0 | 
sampling: 
        repeat_last_n = 64, repeat_penalty = 1.100, frequency_penalty = 0.000, presence_penalty = 0.000
        top_k = 40, tfs_z = 1.000, top_p = 0.950, typical_p = 1.000, temp = 0.800
        mirostat = 0, mirostat_lr = 0.100, mirostat_ent = 5.000
generate: n_ctx = 512, n_batch = 512, n_predict = -1, n_keep = 0

<|im_start|>system\nYou are a helpful assistant<|im_end|>\n<|im_start|>user\nWrite a story about llamas<|im_end|>\n<|im_start|>assistant:Once upon a time, in the highlands of South America, there lived a group of llamas. These gentle creatures had thick fur to protect them from the cold mountain winds and were well adapted to life at high altitudes.

The llamas lived on a small farm owned by a kind old man named Pedro. Pedro loved his llamas dearly and took great care of them. He would feed them fresh grass every day, clean their pens, and take good care of their health.

One day, Pedro decided to enter his llamas into a local llama show. He worked hard with his llamas for weeks, training them to walk in formation and perform tricks. Finally, the big day arrived, and the llamas were ready to shine.

The day of the show was bright and sunny. The llamas walked proudly in their colorful blankets, following Pedro as he led them around the ring. The audience watched in awe as the llamas performed their tricks, from weaving in and out between each other to lying down on command.

At the end of the show, Pedro was overjoyed when his llamas were awarded first place. From that day on, Pedro and his llamas became famous throughout the region for their incredible skills and beauty.

Years passed, and Pedro grew older. He knew it was time to pass on his love for llamas to the next generation. So he decided to start a llama sanctuary, where people could come and learn about these amazing creatures.

Pedro's llamas continued to live long and happy lives, teaching others about the importance of caring for animals and preserving their habitats. And Pedro's legacy lived on through the love and care that his llamas brought to everyone who met them.<|endoftext|> [end of text]

re-uploading 14B and 7B quants now

TheBloke commented 1 year ago

7B and 14B quants are tested and re-uploaded

happyme531 commented 1 year ago

Can't use with text generation webui currently. llama-cpp-python may need a upgrade.

...
llama_model_loader: - type  f32:   81 tensors
llama_model_loader: - type q5_1:  281 tensors
llama_model_loader: - type q6_K:    1 tensors
ERROR: byte not found in vocab: '
'
fish: Job 1, 'python server.py --api --listen…' terminated by signal SIGSEGV (Address boundary error)
goerch commented 1 year ago

If this model is to be supported can we have a tokenizer test, please?

ArtyomZemlyak commented 1 year ago

Have error on CUDA GPU:

1
CUDA error 9 at /home/artem/Research/llm/llama/llama.cpp/ggml-cuda.cu:6862: invalid configuration argument
current device: 0

Not when prompt processed, but in first maeeage processing

ArtyomZemlyak commented 1 year ago

CUDA GPU Error Fixed for me: https://github.com/ggerganov/llama.cpp/issues/3740#issuecomment-1783125187

lumiamilk commented 10 months ago

7B and 14B quants are tested and re-uploaded7B 和 14B 量化经过测试并重新上传

Hello, how did you make a 14B gguf file that works properly? I used [python "D:\llama.cpp\convert.py" "D: \14B" - -padvocab], but the converted 14B file could not answer correctly, answer confusion, and output scrambled code. The same thing happens in [CausalLM / 14B-DPO-alpha] and [CausalLM / 8x7B-MoE-test-NOT-MIXTRAL], my system is win11, which runs in cmd.[TheBloke / CausalLM-14B-GGUF] was working normally

github-actions[bot] commented 7 months ago

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