Stuck very long and then got meaningless output when running llama2 inference

darthjaja6 commented 7 months ago

Enviroment: macOS, mac studio 32gb Command:

LLAMA_LOG=1 wasmedge --dir .:. --nn-preload default:GGML:CPU:llama-2-7b-chat.Q5_K_M.gguf wasmedge-ggml-llama-interactive.wasm default

Then I got the log:

....
llama_new_context_with_model: kv self size  =  256.00 MB
llama_new_context_with_model: compute buffer total size =   73.47 MB
llama_new_context_with_model: max tensor size =   102.54 MB
[2023-10-14 18:22:35.415] [info] [WASI-NN] GGML backend: llama_system_info: AVX = 0 | AVX2 = 0 | AVX512 = 0 | AVX512_VBMI = 0 | AVX512_VNNI = 0 | FMA = 0 | NEON = 1 | ARM_FMA = 1 | F16C = 0 | FP16_VA = 1 | WASM_SIMD = 0 | BLAS = 0 | SSE3 = 0 | SSSE3 = 0 | VSX = 0 |

It stuck here for ~ 20 minutes and showed me the log:

llama_print_timings:        load time =  3329.70 ms
llama_print_timings:      sample time =    54.92 ms /   500 runs   (    0.11 ms per token,  9104.65 tokens per second)
llama_print_timings: prompt eval time =  3157.47 ms /    13 tokens (  242.88 ms per token,     4.12 tokens per second)
llama_print_timings:        eval time = 1002320.31 ms /   499 runs   ( 2008.66 ms per token,     0.50 tokens per second)
llama_print_timings:       total time = 1005746.73 ms
Question:

Where I inputed hte question "Who is the president of the United states?" Then I waited for another ~10min and got the output:

[2023-10-14 18:16:30.155] [info] [WASI-NN] GGML backend: llama_get_kv_cache_token_count 512

llama_print_timings:        load time = 1073122.65 ms
llama_print_timings:      sample time =    51.63 ms /   465 runs   (    0.11 ms per token,  9006.22 tokens per second)
llama_print_timings: prompt eval time =  7842.43 ms /    48 tokens (  163.38 ms per token,     6.12 tokens per second)
llama_print_timings:        eval time = 984737.58 ms /   464 runs   ( 2122.28 ms per token,     0.47 tokens per second)
llama_print_timings:       total time = 2057951.73 ms
Answer:
▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅
Question:

Seems to be just an invalid output and then prompted me for another input.

Can someone help?

juntao commented 7 months ago

May I ask the model and year of the mac studio device you are using?

You could try to add LLAMA_N_PREDICT=128 after LLAMA_LOG=1 to limit the length of the response.

darthjaja6 commented 7 months ago

Thanks for the quick response.

The machine is an 2022 model with m1 max. It can run llama.cpp 4q model in gguf formatpretty fast, haven't measured how many tokens per second but inference starts within 5s.

Tried as you suggested and now it shows this for ~5min

llama_new_context_with_model: kv self size  =  256.00 MB
llama_new_context_with_model: compute buffer total size =   73.47 MB
llama_new_context_with_model: max tensor size =   102.54 MB
[2023-10-15 11:39:47.880] [info] [WASI-NN] GGML backend: llama_system_info: AVX = 0 | AVX2 = 0 | AVX512 = 0 | AVX512_VBMI = 0 | AVX512_VNNI = 0 | FMA = 0 | NEON = 1 | ARM_FMA = 1 | F16C = 0 | FP16_VA = 1 | WASM_SIMD = 0 | BLAS = 0 | SSE3 = 0 | SSSE3 = 0 | VSX = 0 | 
[2023-10-15 11:39:47.880] [info] [WASI-NN] GGML backend: set n_predict to 128

Then pops up the question prompt:

llama_print_timings:        load time =  3342.54 ms
llama_print_timings:      sample time =    12.80 ms /   116 runs   (    0.11 ms per token,  9063.21 tokens per second)
llama_print_timings: prompt eval time =  3177.20 ms /    13 tokens (  244.40 ms per token,     4.09 tokens per second)
llama_print_timings:        eval time = 231942.34 ms /   115 runs   ( 2016.89 ms per token,     0.50 tokens per second)
llama_print_timings:       total time = 235307.35 ms
Question:

I input my question and saw this log

Question:
Who is the president of the United States
llama_new_context_with_model: kv self size  =  256.00 MB
llama_new_context_with_model: compute buffer total size =   73.47 MB
llama_new_context_with_model: max tensor size =   102.54 MB
[2023-10-15 11:44:42.533] [info] [WASI-NN] GGML backend: llama_system_info: AVX = 0 | AVX2 = 0 | AVX512 = 0 | AVX512_VBMI = 0 | AVX512_VNNI = 0 | FMA = 0 | NEON = 1 | ARM_FMA = 1 | F16C = 0 | FP16_VA = 1 | WASM_SIMD = 0 | BLAS = 0 | SSE3 = 0 | SSSE3 = 0 | VSX = 0 | 
[2023-10-15 11:44:42.533] [info] [WASI-NN] GGML backend: set n_predict to 128

And then stuck for another ~5min until getting this output:

[2023-10-15 11:47:39.819] [info] [WASI-NN] GGML backend: llama_get_kv_cache_token_count 128

llama_print_timings:        load time = 302639.31 ms
llama_print_timings:      sample time =     9.15 ms /    82 runs   (    0.11 ms per token,  8959.79 tokens per second)
llama_print_timings: prompt eval time =  7821.10 ms /    47 tokens (  166.41 ms per token,     6.01 tokens per second)
llama_print_timings:        eval time = 169449.23 ms /    81 runs   ( 2091.97 ms per token,     0.48 tokens per second)
llama_print_timings:       total time = 472104.35 ms
Answer:
▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅▅
Question:

I'm pretty new to Rust and WASM. Just wonder

if I'm doing it the correct way
is there anything I can do to add some log to know what's going on?
Is there anything in the code that replaces characters of the answer with ▅? I noticed that different generations resulted in different length, it seems to be a replacement by character.

apepkuss commented 7 months ago

@darthjaja6 I verified the wasmedge-ggml-llama-interactive example on my Macbook Pro (2021, Apple M1 Pro, 32GB Memory, macOS Ventura 13.2.1). I put all relevant things below. Hope they can help you.

The version of WasmEdge Runtime and the info of the deployment directory:

  │  ~/.wasmedge  wasmedge --version                                                                            ✔ │ 11:25:28  
wasmedge version 0.13.4

  │  ~/.wasmedge  pwd                                                                                           ✔ │ 11:25:31  
/Users/sam/.wasmedge

  │  ~/.wasmedge  tree .                                                                                        ✔ │ 11:25:35  
.
├── bin
│   ├── wasmedge
│   └── wasmedgec
├── env
├── include
│   └── wasmedge
│       ├── enum.inc
│       ├── enum_configure.h
│       ├── enum_errcode.h
│       ├── enum_types.h
│       ├── int128.h
│       ├── version.h
│       └── wasmedge.h
├── lib
│   ├── libwasmedge.0.0.3.dylib
│   ├── libwasmedge.0.0.3.tbd
│   ├── libwasmedge.0.dylib -> libwasmedge.0.0.3.dylib
│   ├── libwasmedge.0.tbd -> libwasmedge.0.0.3.tbd
│   ├── libwasmedge.dylib -> libwasmedge.0.dylib
│   └── libwasmedge.tbd -> libwasmedge.0.tbd
└── plugin
    ├── ggml-metal.metal
    └── libwasmedgePluginWasiNN.dylib

5 directories, 18 files

The command I used is LLAMA_LOG=1 wasmedge --dir .:. --nn-preload default:GGML:CPU:llama-2-7b-chat.Q5_K_M.gguf wasmedge-ggml-llama-interactive.wasm default.
The statistics of one-turn conversation:

Question:
what's the capital of France?
llama_new_context_with_model: kv self size  =  256.00 MB
llama_new_context_with_model: compute buffer total size =   73.47 MB
llama_new_context_with_model: max tensor size =   102.54 MB
[2023-10-16 11:21:39.282] [info] [WASI-NN] GGML backend: llama_system_info: AVX = 0 | AVX2 = 0 | AVX512 = 0 | AVX512_VBMI = 0 | AVX512_VNNI = 0 | FMA = 0 | NEON = 1 | ARM_FMA = 1 | F16C = 0 | FP16_VA = 1 | WASM_SIMD = 0 | BLAS = 0 | SSE3 = 0 | SSSE3 = 0 | VSX = 0 | 
[2023-10-16 11:21:40.191] [info] [WASI-NN] GGML backend: llama_get_kv_cache_token_count 55

llama_print_timings:        load time = 246485.72 ms
llama_print_timings:      sample time =     1.09 ms /     9 runs   (    0.12 ms per token,  8264.46 tokens per second)
llama_print_timings: prompt eval time =   557.88 ms /    47 tokens (   11.87 ms per token,    84.25 tokens per second)
llama_print_timings:        eval time =   348.64 ms /     8 runs   (   43.58 ms per token,    22.95 tokens per second)
llama_print_timings:       total time = 246836.28 ms
Answer:
The capital of France is Paris.

The entire running log:

LLAMA_LOG=1 wasmedge --dir .:. --nn-preload default:GGML:CPU:llama-2-7b-chat.Q5_K_M.gguf wasmedge-ggml-llama-interactive.wasm default
llama_model_loader: loaded meta data with 19 key-value pairs and 291 tensors from llama-2-7b-chat.Q5_K_M.gguf (version GGUF V2 (latest))
llama_model_loader: - tensor    0:                token_embd.weight q5_K     [  4096, 32000,     1,     1 ]
llama_model_loader: - tensor    1:           blk.0.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor    2:            blk.0.ffn_down.weight q6_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor    3:            blk.0.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor    4:              blk.0.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor    5:            blk.0.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor    6:              blk.0.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor    7:         blk.0.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor    8:              blk.0.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor    9:              blk.0.attn_v.weight q6_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   10:           blk.1.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   11:            blk.1.ffn_down.weight q6_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor   12:            blk.1.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   13:              blk.1.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   14:            blk.1.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   15:              blk.1.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   16:         blk.1.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   17:              blk.1.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   18:              blk.1.attn_v.weight q6_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   19:          blk.10.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   20:           blk.10.ffn_down.weight q6_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor   21:           blk.10.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   22:             blk.10.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   23:           blk.10.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   24:             blk.10.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   25:        blk.10.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   26:             blk.10.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   27:             blk.10.attn_v.weight q6_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   28:          blk.11.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   29:           blk.11.ffn_down.weight q6_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor   30:           blk.11.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   31:             blk.11.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   32:           blk.11.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   33:             blk.11.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   34:        blk.11.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   35:             blk.11.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   36:             blk.11.attn_v.weight q6_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   37:          blk.12.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   38:           blk.12.ffn_down.weight q5_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor   39:           blk.12.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   40:             blk.12.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   41:           blk.12.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   42:             blk.12.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   43:        blk.12.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   44:             blk.12.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   45:             blk.12.attn_v.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   46:          blk.13.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   47:           blk.13.ffn_down.weight q5_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor   48:           blk.13.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   49:             blk.13.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   50:           blk.13.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   51:             blk.13.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   52:        blk.13.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   53:             blk.13.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   54:             blk.13.attn_v.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   55:          blk.14.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   56:           blk.14.ffn_down.weight q6_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor   57:           blk.14.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   58:             blk.14.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   59:           blk.14.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   60:             blk.14.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   61:        blk.14.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   62:             blk.14.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   63:             blk.14.attn_v.weight q6_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   64:          blk.15.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   65:           blk.15.ffn_down.weight q5_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor   66:           blk.15.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   67:             blk.15.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   68:           blk.15.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   69:             blk.15.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   70:        blk.15.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   71:             blk.15.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   72:             blk.15.attn_v.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   73:          blk.16.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   74:           blk.16.ffn_down.weight q5_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor   75:           blk.16.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   76:             blk.16.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   77:           blk.16.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   78:             blk.16.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   79:        blk.16.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   80:             blk.16.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   81:             blk.16.attn_v.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   82:          blk.17.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   83:           blk.17.ffn_down.weight q6_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor   84:           blk.17.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   85:             blk.17.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   86:           blk.17.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   87:             blk.17.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   88:        blk.17.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   89:             blk.17.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   90:             blk.17.attn_v.weight q6_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   91:          blk.18.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   92:           blk.18.ffn_down.weight q5_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor   93:           blk.18.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   94:             blk.18.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   95:           blk.18.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   96:             blk.18.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   97:        blk.18.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   98:             blk.18.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   99:             blk.18.attn_v.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  100:          blk.19.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  101:           blk.19.ffn_down.weight q5_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  102:           blk.19.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  103:             blk.19.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  104:           blk.19.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  105:             blk.19.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  106:        blk.19.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  107:             blk.19.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  108:             blk.19.attn_v.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  109:           blk.2.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  110:            blk.2.ffn_down.weight q6_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  111:            blk.2.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  112:              blk.2.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  113:            blk.2.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  114:              blk.2.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  115:         blk.2.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  116:              blk.2.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  117:              blk.2.attn_v.weight q6_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  118:          blk.20.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  119:           blk.20.ffn_down.weight q5_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  120:           blk.20.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  121:             blk.20.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  122:           blk.20.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  123:             blk.20.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  124:        blk.20.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  125:             blk.20.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  126:             blk.20.attn_v.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  127:          blk.21.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  128:           blk.21.ffn_down.weight q5_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  129:           blk.21.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  130:             blk.21.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  131:           blk.21.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  132:             blk.21.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  133:        blk.21.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  134:             blk.21.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  135:             blk.21.attn_v.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  136:          blk.22.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  137:           blk.22.ffn_down.weight q6_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  138:           blk.22.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  139:             blk.22.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  140:           blk.22.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  141:             blk.22.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  142:        blk.22.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  143:             blk.22.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  144:             blk.22.attn_v.weight q6_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  145:          blk.23.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  146:           blk.23.ffn_down.weight q5_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  147:           blk.23.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  148:             blk.23.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  149:           blk.23.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  150:             blk.23.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  151:        blk.23.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  152:             blk.23.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  153:             blk.23.attn_v.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  154:           blk.3.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  155:            blk.3.ffn_down.weight q5_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  156:            blk.3.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  157:              blk.3.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  158:            blk.3.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  159:              blk.3.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  160:         blk.3.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  161:              blk.3.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  162:              blk.3.attn_v.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  163:           blk.4.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  164:            blk.4.ffn_down.weight q6_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  165:            blk.4.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  166:              blk.4.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  167:            blk.4.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  168:              blk.4.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  169:         blk.4.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  170:              blk.4.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  171:              blk.4.attn_v.weight q6_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  172:           blk.5.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  173:            blk.5.ffn_down.weight q5_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  174:            blk.5.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  175:              blk.5.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  176:            blk.5.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  177:              blk.5.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  178:         blk.5.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  179:              blk.5.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  180:              blk.5.attn_v.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  181:           blk.6.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  182:            blk.6.ffn_down.weight q5_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  183:            blk.6.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  184:              blk.6.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  185:            blk.6.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  186:              blk.6.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  187:         blk.6.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  188:              blk.6.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  189:              blk.6.attn_v.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  190:           blk.7.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  191:            blk.7.ffn_down.weight q6_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  192:            blk.7.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  193:              blk.7.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  194:            blk.7.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  195:              blk.7.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  196:         blk.7.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  197:              blk.7.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  198:              blk.7.attn_v.weight q6_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  199:           blk.8.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  200:            blk.8.ffn_down.weight q5_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  201:            blk.8.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  202:              blk.8.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  203:            blk.8.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  204:              blk.8.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  205:         blk.8.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  206:              blk.8.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  207:              blk.8.attn_v.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  208:           blk.9.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  209:            blk.9.ffn_down.weight q5_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  210:            blk.9.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  211:              blk.9.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  212:            blk.9.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  213:              blk.9.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  214:         blk.9.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  215:              blk.9.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  216:              blk.9.attn_v.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  217:                    output.weight q6_K     [  4096, 32000,     1,     1 ]
llama_model_loader: - tensor  218:          blk.24.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  219:           blk.24.ffn_down.weight q6_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  220:           blk.24.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  221:             blk.24.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  222:           blk.24.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  223:             blk.24.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  224:        blk.24.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  225:             blk.24.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  226:             blk.24.attn_v.weight q6_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  227:          blk.25.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  228:           blk.25.ffn_down.weight q5_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  229:           blk.25.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  230:             blk.25.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  231:           blk.25.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  232:             blk.25.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  233:        blk.25.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  234:             blk.25.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  235:             blk.25.attn_v.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  236:          blk.26.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  237:           blk.26.ffn_down.weight q5_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  238:           blk.26.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  239:             blk.26.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  240:           blk.26.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  241:             blk.26.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  242:        blk.26.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  243:             blk.26.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  244:             blk.26.attn_v.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  245:          blk.27.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  246:           blk.27.ffn_down.weight q6_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  247:           blk.27.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  248:             blk.27.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  249:           blk.27.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  250:             blk.27.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  251:        blk.27.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  252:             blk.27.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  253:             blk.27.attn_v.weight q6_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  254:          blk.28.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  255:           blk.28.ffn_down.weight q6_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  256:           blk.28.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  257:             blk.28.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  258:           blk.28.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  259:             blk.28.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  260:        blk.28.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  261:             blk.28.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  262:             blk.28.attn_v.weight q6_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  263:          blk.29.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  264:           blk.29.ffn_down.weight q6_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  265:           blk.29.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  266:             blk.29.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  267:           blk.29.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  268:             blk.29.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  269:        blk.29.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  270:             blk.29.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  271:             blk.29.attn_v.weight q6_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  272:          blk.30.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  273:           blk.30.ffn_down.weight q6_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  274:           blk.30.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  275:             blk.30.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  276:           blk.30.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  277:             blk.30.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  278:        blk.30.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  279:             blk.30.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  280:             blk.30.attn_v.weight q6_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  281:          blk.31.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  282:           blk.31.ffn_down.weight q6_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  283:           blk.31.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  284:             blk.31.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  285:           blk.31.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  286:             blk.31.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  287:        blk.31.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  288:             blk.31.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  289:             blk.31.attn_v.weight q6_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  290:               output_norm.weight f32      [  4096,     1,     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:                          general.file_type u32     
llama_model_loader: - kv  11:                       tokenizer.ggml.model str     
llama_model_loader: - kv  12:                      tokenizer.ggml.tokens arr     
llama_model_loader: - kv  13:                      tokenizer.ggml.scores arr     
llama_model_loader: - kv  14:                  tokenizer.ggml.token_type 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 q5_K:  193 tensors
llama_model_loader: - type q6_K:   33 tensors
llm_load_print_meta: format         = GGUF V2 (latest)
llm_load_print_meta: arch           = llama
llm_load_print_meta: vocab type     = SPM
llm_load_print_meta: n_vocab        = 32000
llm_load_print_meta: n_merges       = 0
llm_load_print_meta: n_ctx_train    = 4096
llm_load_print_meta: n_ctx          = 512
llm_load_print_meta: n_embd         = 4096
llm_load_print_meta: n_head         = 32
llm_load_print_meta: n_head_kv      = 32
llm_load_print_meta: n_layer        = 32
llm_load_print_meta: n_rot          = 128
llm_load_print_meta: n_gqa          = 1
llm_load_print_meta: f_norm_eps     = 0.0e+00
llm_load_print_meta: f_norm_rms_eps = 1.0e-06
llm_load_print_meta: n_ff           = 11008
llm_load_print_meta: freq_base      = 10000.0
llm_load_print_meta: freq_scale     = 1
llm_load_print_meta: model type     = 7B
llm_load_print_meta: model ftype    = mostly Q5_K - Medium
llm_load_print_meta: model params   = 6.74 B
llm_load_print_meta: model size     = 4.45 GiB (5.68 BPW) 
llm_load_print_meta: general.name   = LLaMA v2
llm_load_print_meta: BOS token = 1 '<s>'
llm_load_print_meta: EOS token = 2 '</s>'
llm_load_print_meta: UNK token = 0 '<unk>'
llm_load_print_meta: LF token  = 13 '<0x0A>'
llm_load_tensors: ggml ctx size =    0.09 MB
llm_load_tensors: mem required  = 4560.96 MB (+  256.00 MB per state)
...................................................................................................
llama_new_context_with_model: kv self size  =  256.00 MB
llama_new_context_with_model: compute buffer total size =   73.47 MB
llama_new_context_with_model: max tensor size =   102.54 MB
[2023-10-16 11:17:33.562] [info] [WASI-NN] GGML backend: llama_system_info: AVX = 0 | AVX2 = 0 | AVX512 = 0 | AVX512_VBMI = 0 | AVX512_VNNI = 0 | FMA = 0 | NEON = 1 | ARM_FMA = 1 | F16C = 0 | FP16_VA = 1 | WASM_SIMD = 0 | BLAS = 0 | SSE3 = 0 | SSSE3 = 0 | VSX = 0 | 
[2023-10-16 11:17:38.799] [info] [WASI-NN] GGML backend: llama_get_kv_cache_token_count 75

llama_print_timings:        load time =  2725.90 ms
llama_print_timings:      sample time =     7.33 ms /    63 runs   (    0.12 ms per token,  8590.13 tokens per second)
llama_print_timings: prompt eval time =  2517.63 ms /    13 tokens (  193.66 ms per token,     5.16 tokens per second)
llama_print_timings:        eval time =  2705.67 ms /    62 runs   (   43.64 ms per token,    22.91 tokens per second)
llama_print_timings:       total time =  5444.28 ms
Question:
what's the capital of France?
llama_new_context_with_model: kv self size  =  256.00 MB
llama_new_context_with_model: compute buffer total size =   73.47 MB
llama_new_context_with_model: max tensor size =   102.54 MB
[2023-10-16 11:21:39.282] [info] [WASI-NN] GGML backend: llama_system_info: AVX = 0 | AVX2 = 0 | AVX512 = 0 | AVX512_VBMI = 0 | AVX512_VNNI = 0 | FMA = 0 | NEON = 1 | ARM_FMA = 1 | F16C = 0 | FP16_VA = 1 | WASM_SIMD = 0 | BLAS = 0 | SSE3 = 0 | SSSE3 = 0 | VSX = 0 | 
[2023-10-16 11:21:40.191] [info] [WASI-NN] GGML backend: llama_get_kv_cache_token_count 55

llama_print_timings:        load time = 246485.72 ms
llama_print_timings:      sample time =     1.09 ms /     9 runs   (    0.12 ms per token,  8264.46 tokens per second)
llama_print_timings: prompt eval time =   557.88 ms /    47 tokens (   11.87 ms per token,    84.25 tokens per second)
llama_print_timings:        eval time =   348.64 ms /     8 runs   (   43.58 ms per token,    22.95 tokens per second)
llama_print_timings:       total time = 246836.28 ms
Answer:
The capital of France is Paris.
Question:
what about Norway?
llama_new_context_with_model: kv self size  =  256.00 MB
llama_new_context_with_model: compute buffer total size =   73.47 MB
llama_new_context_with_model: max tensor size =   102.54 MB
[2023-10-16 11:22:54.002] [info] [WASI-NN] GGML backend: llama_system_info: AVX = 0 | AVX2 = 0 | AVX512 = 0 | AVX512_VBMI = 0 | AVX512_VNNI = 0 | FMA = 0 | NEON = 1 | ARM_FMA = 1 | F16C = 0 | FP16_VA = 1 | WASM_SIMD = 0 | BLAS = 0 | SSE3 = 0 | SSSE3 = 0 | VSX = 0 | 
[2023-10-16 11:22:55.023] [info] [WASI-NN] GGML backend: llama_get_kv_cache_token_count 75

llama_print_timings:        load time = 321275.01 ms
llama_print_timings:      sample time =     1.32 ms /    10 runs   (    0.13 ms per token,  7558.58 tokens per second)
llama_print_timings: prompt eval time =   627.47 ms /    66 tokens (    9.51 ms per token,   105.18 tokens per second)
llama_print_timings:        eval time =   391.16 ms /     9 runs   (   43.46 ms per token,    23.01 tokens per second)
llama_print_timings:       total time = 321668.28 ms
Answer:
The capital of Norway is Oslo.

hydai commented 6 months ago

Hi @darthjaja6 We released 0.13.5 last week and updated the examples. Could you please try again?

On my M2 Max macbook, it has ~40 TPS. Ref: https://github.com/second-state/WasmEdge-WASINN-examples/tree/master/wasmedge-ggml-llama-interactive#performance

hydai commented 6 months ago

This issue is already fixed. If you still have the same problem, feel free to re-open it. Thanks.

second-state / WasmEdge-WASINN-examples

Stuck very long and then got meaningless output when running llama2 inference #51