llama.cpp: Illegal instruction on Android (Honor Magic 5)
Prerequisites
Please answer the following questions for yourself before submitting an issue.
- I am running the latest code. Development is very rapid so there are no tagged versions as of now.
- I carefully followed the README.md.
- I searched using keywords relevant to my issue to make sure that I am creating a new issue that is not already open (or closed).
- I reviewed the Discussions, and have a new bug or useful enhancement to share.
Current Behavior
$ git clone --depth 1 https://github.com/ggerganov/llama.cpp
$ cd llama.cpp
$ mkdir -p build
$ rm -rf build/*
$ cd build
$ cmake .. -DLLAMA_SANITIZE_ADDRESS=ON && cmake --build . --config Debug
-- CMAKE_SYSTEM_PROCESSOR: aarch64
-- ARM detected
-- Configuring done (0.3s)
-- Generating done (0.1s)
-- Build files have been written to: /data/data/com.termux/files/home/llama.cpp/build
[ 1%] Built target BUILD_INFO
[ 2%] Building C object CMakeFiles/ggml.dir/ggml.c.o
/data/data/com.termux/files/home/llama.cpp/ggml.c:2432:5: warning: implicit conversion increases floating-point precision: 'float32_t' (aka 'float') to 'ggml_float' (aka 'double') [-Wdouble-promotion]
2432 | GGML_F16_VEC_REDUCE(sumf, sum);
| ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
/data/data/com.termux/files/home/llama.cpp/ggml.c:1959:41: note: expanded from macro 'GGML_F16_VEC_REDUCE'
1959 | #define GGML_F16_VEC_REDUCE GGML_F32Cx4_REDUCE
| ^
/data/data/com.termux/files/home/llama.cpp/ggml.c:1949:38: note: expanded from macro 'GGML_F32Cx4_REDUCE'
1949 | #define GGML_F32Cx4_REDUCE GGML_F32x4_REDUCE
| ^
/data/data/com.termux/files/home/llama.cpp/ggml.c:1879:11: note: expanded from macro 'GGML_F32x4_REDUCE'
1879 | res = GGML_F32x4_REDUCE_ONE(x[0]); \
| ~ ^~~~~~~~~~~~~~~~~~~~~~~~~~~
/data/data/com.termux/files/home/llama.cpp/ggml.c:1864:34: note: expanded from macro 'GGML_F32x4_REDUCE_ONE'
1864 | #define GGML_F32x4_REDUCE_ONE(x) vaddvq_f32(x)
| ^~~~~~~~~~~~~
/data/data/com.termux/files/home/llama.cpp/ggml.c:3692:9: warning: implicit conversion increases floating-point precision: 'float32_t' (aka 'float') to 'ggml_float' (aka 'double') [-Wdouble-promotion]
3692 | GGML_F16_VEC_REDUCE(sumf[k], sum[k]);
| ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
/data/data/com.termux/files/home/llama.cpp/ggml.c:1959:41: note: expanded from macro 'GGML_F16_VEC_REDUCE'
1959 | #define GGML_F16_VEC_REDUCE GGML_F32Cx4_REDUCE
| ^
/data/data/com.termux/files/home/llama.cpp/ggml.c:1949:38: note: expanded from macro 'GGML_F32Cx4_REDUCE'
1949 | #define GGML_F32Cx4_REDUCE GGML_F32x4_REDUCE
| ^
/data/data/com.termux/files/home/llama.cpp/ggml.c:1879:11: note: expanded from macro 'GGML_F32x4_REDUCE'
1879 | res = GGML_F32x4_REDUCE_ONE(x[0]); \
| ~ ^~~~~~~~~~~~~~~~~~~~~~~~~~~
/data/data/com.termux/files/home/llama.cpp/ggml.c:1864:34: note: expanded from macro 'GGML_F32x4_REDUCE_ONE'
1864 | #define GGML_F32x4_REDUCE_ONE(x) vaddvq_f32(x)
| ^~~~~~~~~~~~~
2 warnings generated.
[ 3%] Building C object CMakeFiles/ggml.dir/ggml-alloc.c.o
[ 4%] Building C object CMakeFiles/ggml.dir/ggml-backend.c.o
[ 5%] Building C object CMakeFiles/ggml.dir/k_quants.c.o
[ 5%] Built target ggml
[ 6%] Linking C static library libggml_static.a
[ 6%] Built target ggml_static
[ 7%] Building CXX object CMakeFiles/llama.dir/llama.cpp.o
[ 8%] Linking CXX static library libllama.a
[ 8%] Built target llama
[ 10%] Building CXX object common/CMakeFiles/common.dir/common.cpp.o
[ 11%] Building CXX object common/CMakeFiles/common.dir/sampling.cpp.o
[ 12%] Building CXX object common/CMakeFiles/common.dir/console.cpp.o
[ 13%] Building CXX object common/CMakeFiles/common.dir/grammar-parser.cpp.o
[ 14%] Building CXX object common/CMakeFiles/common.dir/train.cpp.o
[ 14%] Built target common
[ 15%] Building CXX object tests/CMakeFiles/test-quantize-fns.dir/test-quantize-fns.cpp.o
[ 16%] Linking CXX executable ../bin/test-quantize-fns
[ 16%] Built target test-quantize-fns
[ 17%] Building CXX object tests/CMakeFiles/test-quantize-perf.dir/test-quantize-perf.cpp.o
[ 19%] Linking CXX executable ../bin/test-quantize-perf
[ 19%] Built target test-quantize-perf
[ 20%] Building CXX object tests/CMakeFiles/test-sampling.dir/test-sampling.cpp.o
[ 21%] Linking CXX executable ../bin/test-sampling
[ 21%] Built target test-sampling
[ 22%] Building CXX object tests/CMakeFiles/test-tokenizer-0-llama.dir/test-tokenizer-0-llama.cpp.o
[ 23%] Linking CXX executable ../bin/test-tokenizer-0-llama
[ 23%] Built target test-tokenizer-0-llama
[ 24%] Building CXX object tests/CMakeFiles/test-tokenizer-0-falcon.dir/test-tokenizer-0-falcon.cpp.o
[ 25%] Linking CXX executable ../bin/test-tokenizer-0-falcon
[ 25%] Built target test-tokenizer-0-falcon
[ 26%] Building CXX object tests/CMakeFiles/test-tokenizer-1-llama.dir/test-tokenizer-1-llama.cpp.o
[ 28%] Linking CXX executable ../bin/test-tokenizer-1-llama
[ 28%] Built target test-tokenizer-1-llama
[ 29%] Building CXX object tests/CMakeFiles/test-tokenizer-1-bpe.dir/test-tokenizer-1-bpe.cpp.o
[ 30%] Linking CXX executable ../bin/test-tokenizer-1-bpe
[ 30%] Built target test-tokenizer-1-bpe
[ 31%] Building CXX object tests/CMakeFiles/test-grammar-parser.dir/test-grammar-parser.cpp.o
[ 32%] Linking CXX executable ../bin/test-grammar-parser
[ 32%] Built target test-grammar-parser
[ 33%] Building CXX object tests/CMakeFiles/test-llama-grammar.dir/test-llama-grammar.cpp.o
[ 34%] Linking CXX executable ../bin/test-llama-grammar
[ 34%] Built target test-llama-grammar
[ 35%] Building CXX object tests/CMakeFiles/test-grad0.dir/test-grad0.cpp.o
[ 37%] Linking CXX executable ../bin/test-grad0
[ 37%] Built target test-grad0
[ 38%] Building CXX object tests/CMakeFiles/test-rope.dir/test-rope.cpp.o
[ 39%] Linking CXX executable ../bin/test-rope
[ 39%] Built target test-rope
[ 40%] Building C object tests/CMakeFiles/test-c.dir/test-c.c.o
[ 41%] Linking CXX executable ../bin/test-c
[ 41%] Built target test-c
[ 42%] Building CXX object examples/main/CMakeFiles/main.dir/main.cpp.o
[ 43%] Linking CXX executable ../../bin/main
[ 43%] Built target main
[ 44%] Building CXX object examples/quantize/CMakeFiles/quantize.dir/quantize.cpp.o
[ 46%] Linking CXX executable ../../bin/quantize
[ 46%] Built target quantize
[ 47%] Building CXX object examples/quantize-stats/CMakeFiles/quantize-stats.dir/quantize-stats.cpp.o
[ 48%] Linking CXX executable ../../bin/quantize-stats
[ 48%] Built target quantize-stats
[ 49%] Building CXX object examples/perplexity/CMakeFiles/perplexity.dir/perplexity.cpp.o
[ 50%] Linking CXX executable ../../bin/perplexity
[ 50%] Built target perplexity
[ 51%] Building CXX object examples/embedding/CMakeFiles/embedding.dir/embedding.cpp.o
[ 52%] Linking CXX executable ../../bin/embedding
[ 52%] Built target embedding
[ 53%] Building CXX object examples/save-load-state/CMakeFiles/save-load-state.dir/save-load-state.cpp.o
[ 55%] Linking CXX executable ../../bin/save-load-state
[ 55%] Built target save-load-state
[ 56%] Building CXX object examples/benchmark/CMakeFiles/benchmark.dir/benchmark-matmult.cpp.o
[ 57%] Linking CXX executable ../../bin/benchmark
[ 57%] Built target benchmark
[ 58%] Building CXX object examples/baby-llama/CMakeFiles/baby-llama.dir/baby-llama.cpp.o
[ 59%] Linking CXX executable ../../bin/baby-llama
[ 59%] Built target baby-llama
[ 60%] Building CXX object examples/train-text-from-scratch/CMakeFiles/train-text-from-scratch.dir/train-text-from-scratch.cpp.o
[ 61%] Linking CXX executable ../../bin/train-text-from-scratch
[ 61%] Built target train-text-from-scratch
[ 62%] Building CXX object examples/finetune/CMakeFiles/finetune.dir/finetune.cpp.o
[ 64%] Linking CXX executable ../../bin/finetune
[ 64%] Built target finetune
[ 65%] Building CXX object examples/convert-llama2c-to-ggml/CMakeFiles/convert-llama2c-to-ggml.dir/convert-llama2c-to-ggml.cpp.o
[ 66%] Linking CXX executable ../../bin/convert-llama2c-to-ggml
[ 66%] Built target convert-llama2c-to-ggml
[ 67%] Building CXX object examples/simple/CMakeFiles/simple.dir/simple.cpp.o
[ 68%] Linking CXX executable ../../bin/simple
[ 68%] Built target simple
[ 69%] Building CXX object examples/batched/CMakeFiles/batched.dir/batched.cpp.o
[ 70%] Linking CXX executable ../../bin/batched
[ 70%] Built target batched
[ 71%] Building CXX object examples/batched-bench/CMakeFiles/batched-bench.dir/batched-bench.cpp.o
[ 73%] Linking CXX executable ../../bin/batched-bench
[ 73%] Built target batched-bench
[ 74%] Building CXX object examples/speculative/CMakeFiles/speculative.dir/speculative.cpp.o
[ 75%] Linking CXX executable ../../bin/speculative
[ 75%] Built target speculative
[ 76%] Building CXX object examples/parallel/CMakeFiles/parallel.dir/parallel.cpp.o
[ 77%] Linking CXX executable ../../bin/parallel
[ 77%] Built target parallel
[ 78%] Building CXX object examples/embd-input/CMakeFiles/embdinput.dir/embd-input-lib.cpp.o
[ 79%] Linking CXX static library libembdinput.a
[ 79%] Built target embdinput
[ 80%] Building CXX object examples/embd-input/CMakeFiles/embd-input-test.dir/embd-input-test.cpp.o
[ 82%] Linking CXX executable ../../bin/embd-input-test
[ 82%] Built target embd-input-test
[ 83%] Building CXX object examples/llava/CMakeFiles/clip.dir/clip.cpp.o
[ 84%] Linking CXX static library libclip.a
[ 84%] Built target clip
[ 85%] Building CXX object examples/llava/CMakeFiles/llava.dir/llava.cpp.o
[ 86%] Linking CXX executable ../../bin/llava
[ 86%] Built target llava
[ 87%] Building CXX object examples/llama-bench/CMakeFiles/llama-bench.dir/llama-bench.cpp.o
[ 88%] Linking CXX executable ../../bin/llama-bench
[ 88%] Built target llama-bench
[ 89%] Building CXX object examples/beam-search/CMakeFiles/beam-search.dir/beam-search.cpp.o
[ 91%] Linking CXX executable ../../bin/beam-search
[ 91%] Built target beam-search
[ 92%] Building CXX object examples/server/CMakeFiles/server.dir/server.cpp.o
[ 93%] Linking CXX executable ../../bin/server
[ 93%] Built target server
[ 94%] Building CXX object examples/export-lora/CMakeFiles/export-lora.dir/export-lora.cpp.o
[ 95%] Linking CXX executable ../../bin/export-lora
[ 95%] Built target export-lora
[ 96%] Building CXX object pocs/vdot/CMakeFiles/vdot.dir/vdot.cpp.o
[ 97%] Linking CXX executable ../../bin/vdot
[ 97%] Built target vdot
[ 98%] Building CXX object pocs/vdot/CMakeFiles/q8dot.dir/q8dot.cpp.o
[100%] Linking CXX executable ../../bin/q8dot
[100%] Built target q8dot
$ ./build/bin/main -m /sdcard/Download/llama-2-7b-chat.Q3_K_S.gguf -color -c 2048 --keep 1 -t 3 -b 10 -i -ins
Log start
main: build = 1 (2a4bcba)
main: built with clang version 17.0.2 for aarch64-unknown-linux-android24
main: seed = 1697243692
llama_model_loader: loaded meta data with 19 key-value pairs and 291 tensors from /sdcard/Download/llama-2-7b-chat.Q3_K_S.gguf (version GGUF V2 (latest))
llama_model_loader: - tensor 0: token_embd.weight q3_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 q3_K [ 11008, 4096, 1, 1 ]
llama_model_loader: - tensor 3: blk.0.ffn_gate.weight q3_K [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 4: blk.0.ffn_up.weight q3_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 q3_K [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 7: blk.0.attn_output.weight q3_K [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 8: blk.0.attn_q.weight q3_K [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 9: blk.0.attn_v.weight q3_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 q3_K [ 11008, 4096, 1, 1 ]
llama_model_loader: - tensor 12: blk.1.ffn_gate.weight q3_K [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 13: blk.1.ffn_up.weight q3_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 q3_K [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 16: blk.1.attn_output.weight q3_K [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 17: blk.1.attn_q.weight q3_K [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 18: blk.1.attn_v.weight q3_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 q3_K [ 11008, 4096, 1, 1 ]
llama_model_loader: - tensor 21: blk.10.ffn_gate.weight q3_K [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 22: blk.10.ffn_up.weight q3_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 q3_K [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 25: blk.10.attn_output.weight q3_K [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 26: blk.10.attn_q.weight q3_K [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 27: blk.10.attn_v.weight q3_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 q3_K [ 11008, 4096, 1, 1 ]
llama_model_loader: - tensor 30: blk.11.ffn_gate.weight q3_K [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 31: blk.11.ffn_up.weight q3_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 q3_K [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 34: blk.11.attn_output.weight q3_K [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 35: blk.11.attn_q.weight q3_K [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 36: blk.11.attn_v.weight q3_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 q3_K [ 11008, 4096, 1, 1 ]
llama_model_loader: - tensor 39: blk.12.ffn_gate.weight q3_K [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 40: blk.12.ffn_up.weight q3_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 q3_K [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 43: blk.12.attn_output.weight q3_K [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 44: blk.12.attn_q.weight q3_K [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 45: blk.12.attn_v.weight q3_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 q3_K [ 11008, 4096, 1, 1 ]
llama_model_loader: - tensor 48: blk.13.ffn_gate.weight q3_K [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 49: blk.13.ffn_up.weight q3_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 q3_K [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 52: blk.13.attn_output.weight q3_K [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 53: blk.13.attn_q.weight q3_K [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 54: blk.13.attn_v.weight q3_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 q3_K [ 11008, 4096, 1, 1 ]
llama_model_loader: - tensor 57: blk.14.ffn_gate.weight q3_K [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 58: blk.14.ffn_up.weight q3_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 q3_K [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 61: blk.14.attn_output.weight q3_K [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 62: blk.14.attn_q.weight q3_K [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 63: blk.14.attn_v.weight q3_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 q3_K [ 11008, 4096, 1, 1 ]
llama_model_loader: - tensor 66: blk.15.ffn_gate.weight q3_K [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 67: blk.15.ffn_up.weight q3_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 q3_K [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 70: blk.15.attn_output.weight q3_K [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 71: blk.15.attn_q.weight q3_K [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 72: blk.15.attn_v.weight q3_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 q3_K [ 11008, 4096, 1, 1 ]
llama_model_loader: - tensor 75: blk.16.ffn_gate.weight q3_K [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 76: blk.16.ffn_up.weight q3_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 q3_K [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 79: blk.16.attn_output.weight q3_K [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 80: blk.16.attn_q.weight q3_K [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 81: blk.16.attn_v.weight q3_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 q3_K [ 11008, 4096, 1, 1 ]
llama_model_loader: - tensor 84: blk.17.ffn_gate.weight q3_K [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 85: blk.17.ffn_up.weight q3_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 q3_K [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 88: blk.17.attn_output.weight q3_K [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 89: blk.17.attn_q.weight q3_K [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 90: blk.17.attn_v.weight q3_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 q3_K [ 11008, 4096, 1, 1 ]
llama_model_loader: - tensor 93: blk.18.ffn_gate.weight q3_K [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 94: blk.18.ffn_up.weight q3_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 q3_K [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 97: blk.18.attn_output.weight q3_K [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 98: blk.18.attn_q.weight q3_K [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 99: blk.18.attn_v.weight q3_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 q3_K [ 11008, 4096, 1, 1 ]
llama_model_loader: - tensor 102: blk.19.ffn_gate.weight q3_K [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 103: blk.19.ffn_up.weight q3_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 q3_K [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 106: blk.19.attn_output.weight q3_K [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 107: blk.19.attn_q.weight q3_K [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 108: blk.19.attn_v.weight q3_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 q3_K [ 11008, 4096, 1, 1 ]
llama_model_loader: - tensor 111: blk.2.ffn_gate.weight q3_K [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 112: blk.2.ffn_up.weight q3_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 q3_K [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 115: blk.2.attn_output.weight q3_K [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 116: blk.2.attn_q.weight q3_K [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 117: blk.2.attn_v.weight q3_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 q3_K [ 11008, 4096, 1, 1 ]
llama_model_loader: - tensor 120: blk.20.ffn_gate.weight q3_K [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 121: blk.20.ffn_up.weight q3_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 q3_K [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 124: blk.20.attn_output.weight q3_K [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 125: blk.20.attn_q.weight q3_K [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 126: blk.20.attn_v.weight q3_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 q3_K [ 11008, 4096, 1, 1 ]
llama_model_loader: - tensor 129: blk.21.ffn_gate.weight q3_K [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 130: blk.21.ffn_up.weight q3_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 q3_K [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 133: blk.21.attn_output.weight q3_K [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 134: blk.21.attn_q.weight q3_K [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 135: blk.21.attn_v.weight q3_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 q3_K [ 11008, 4096, 1, 1 ]
llama_model_loader: - tensor 138: blk.22.ffn_gate.weight q3_K [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 139: blk.22.ffn_up.weight q3_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 q3_K [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 142: blk.22.attn_output.weight q3_K [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 143: blk.22.attn_q.weight q3_K [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 144: blk.22.attn_v.weight q3_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 q3_K [ 11008, 4096, 1, 1 ]
llama_model_loader: - tensor 147: blk.23.ffn_gate.weight q3_K [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 148: blk.23.ffn_up.weight q3_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 q3_K [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 151: blk.23.attn_output.weight q3_K [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 152: blk.23.attn_q.weight q3_K [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 153: blk.23.attn_v.weight q3_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 q3_K [ 11008, 4096, 1, 1 ]
llama_model_loader: - tensor 156: blk.3.ffn_gate.weight q3_K [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 157: blk.3.ffn_up.weight q3_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 q3_K [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 160: blk.3.attn_output.weight q3_K [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 161: blk.3.attn_q.weight q3_K [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 162: blk.3.attn_v.weight q3_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 q3_K [ 11008, 4096, 1, 1 ]
llama_model_loader: - tensor 165: blk.4.ffn_gate.weight q3_K [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 166: blk.4.ffn_up.weight q3_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 q3_K [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 169: blk.4.attn_output.weight q3_K [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 170: blk.4.attn_q.weight q3_K [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 171: blk.4.attn_v.weight q3_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 q3_K [ 11008, 4096, 1, 1 ]
llama_model_loader: - tensor 174: blk.5.ffn_gate.weight q3_K [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 175: blk.5.ffn_up.weight q3_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 q3_K [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 178: blk.5.attn_output.weight q3_K [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 179: blk.5.attn_q.weight q3_K [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 180: blk.5.attn_v.weight q3_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 q3_K [ 11008, 4096, 1, 1 ]
llama_model_loader: - tensor 183: blk.6.ffn_gate.weight q3_K [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 184: blk.6.ffn_up.weight q3_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 q3_K [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 187: blk.6.attn_output.weight q3_K [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 188: blk.6.attn_q.weight q3_K [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 189: blk.6.attn_v.weight q3_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 q3_K [ 11008, 4096, 1, 1 ]
llama_model_loader: - tensor 192: blk.7.ffn_gate.weight q3_K [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 193: blk.7.ffn_up.weight q3_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 q3_K [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 196: blk.7.attn_output.weight q3_K [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 197: blk.7.attn_q.weight q3_K [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 198: blk.7.attn_v.weight q3_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 q3_K [ 11008, 4096, 1, 1 ]
llama_model_loader: - tensor 201: blk.8.ffn_gate.weight q3_K [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 202: blk.8.ffn_up.weight q3_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 q3_K [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 205: blk.8.attn_output.weight q3_K [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 206: blk.8.attn_q.weight q3_K [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 207: blk.8.attn_v.weight q3_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 q3_K [ 11008, 4096, 1, 1 ]
llama_model_loader: - tensor 210: blk.9.ffn_gate.weight q3_K [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 211: blk.9.ffn_up.weight q3_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 q3_K [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 214: blk.9.attn_output.weight q3_K [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 215: blk.9.attn_q.weight q3_K [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 216: blk.9.attn_v.weight q3_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 q3_K [ 11008, 4096, 1, 1 ]
llama_model_loader: - tensor 220: blk.24.ffn_gate.weight q3_K [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 221: blk.24.ffn_up.weight q3_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 q3_K [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 224: blk.24.attn_output.weight q3_K [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 225: blk.24.attn_q.weight q3_K [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 226: blk.24.attn_v.weight q3_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 q3_K [ 11008, 4096, 1, 1 ]
llama_model_loader: - tensor 229: blk.25.ffn_gate.weight q3_K [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 230: blk.25.ffn_up.weight q3_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 q3_K [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 233: blk.25.attn_output.weight q3_K [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 234: blk.25.attn_q.weight q3_K [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 235: blk.25.attn_v.weight q3_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 q3_K [ 11008, 4096, 1, 1 ]
llama_model_loader: - tensor 238: blk.26.ffn_gate.weight q3_K [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 239: blk.26.ffn_up.weight q3_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 q3_K [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 242: blk.26.attn_output.weight q3_K [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 243: blk.26.attn_q.weight q3_K [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 244: blk.26.attn_v.weight q3_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 q3_K [ 11008, 4096, 1, 1 ]
llama_model_loader: - tensor 247: blk.27.ffn_gate.weight q3_K [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 248: blk.27.ffn_up.weight q3_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 q3_K [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 251: blk.27.attn_output.weight q3_K [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 252: blk.27.attn_q.weight q3_K [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 253: blk.27.attn_v.weight q3_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 q3_K [ 11008, 4096, 1, 1 ]
llama_model_loader: - tensor 256: blk.28.ffn_gate.weight q3_K [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 257: blk.28.ffn_up.weight q3_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 q3_K [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 260: blk.28.attn_output.weight q3_K [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 261: blk.28.attn_q.weight q3_K [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 262: blk.28.attn_v.weight q3_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 q3_K [ 11008, 4096, 1, 1 ]
llama_model_loader: - tensor 265: blk.29.ffn_gate.weight q3_K [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 266: blk.29.ffn_up.weight q3_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 q3_K [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 269: blk.29.attn_output.weight q3_K [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 270: blk.29.attn_q.weight q3_K [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 271: blk.29.attn_v.weight q3_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 q3_K [ 11008, 4096, 1, 1 ]
llama_model_loader: - tensor 274: blk.30.ffn_gate.weight q3_K [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 275: blk.30.ffn_up.weight q3_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 q3_K [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 278: blk.30.attn_output.weight q3_K [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 279: blk.30.attn_q.weight q3_K [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 280: blk.30.attn_v.weight q3_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 q3_K [ 11008, 4096, 1, 1 ]
llama_model_loader: - tensor 283: blk.31.ffn_gate.weight q3_K [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 284: blk.31.ffn_up.weight q3_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 q3_K [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 287: blk.31.attn_output.weight q3_K [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 288: blk.31.attn_q.weight q3_K [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 289: blk.31.attn_v.weight q3_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 q3_K: 225 tensors
llama_model_loader: - type q6_K: 1 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_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: f_clamp_kqv = 0.0e+00
llm_load_print_meta: f_max_alibi_bias = 0.0e+00
llm_load_print_meta: n_ff = 11008
llm_load_print_meta: freq_base_train = 10000.0
llm_load_print_meta: freq_scale_train = 1
llm_load_print_meta: model type = 7B
llm_load_print_meta: model ftype = mostly Q3_K - Small
llm_load_print_meta: model params = 6.74 B
llm_load_print_meta: model size = 2.75 GiB (3.50 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 = 0.10 MB
llm_load_tensors: mem required = 2811.11 MB
.................................................................................................
llama_new_context_with_model: n_ctx = 2048
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 = 1024.00 MB
llama_new_context_with_model: compute buffer total size = 9.17 MB
Illegal instruction
Environment and Context
Please provide detailed information about your computer setup. This is important in case the issue is not reproducible except for under certain specific conditions.
- Physical (or virtual) hardware you are using, e.g. for Linux:
$ lscpu
Architecture: aarch64
CPU op-mode(s): 32-bit, 64-bit
Byte Order: Little Endian
CPU(s): 8
On-line CPU(s) list: 0-7
Vendor ID: ARM
Model name: Cortex-A510
Model: 1
Thread(s) per core: 1
Core(s) per socket: 3
Socket(s): 1
Stepping: r1p1
Frequency boost: enabled
CPU(s) scaling MHz: 61%
CPU max MHz: 2016.0000
CPU min MHz: 307.2000
BogoMIPS: 38.40
Flags: fp asimd evtstrm aes pmull sha1 sha2 crc32 atomics fphp asimdhp cpuid asimdrdm jscvt fcma lrcpc dcpop sha3 sm3 sm4 asimddp sha512 asimdfhm dit uscat ilrcpc flagm ssbs sb paca pacg dcpodp flagm2 frint i8mm bf16 bti
Model name: Cortex-A715
Model: 0
Thread(s) per core: 1
Core(s) per socket: 2
Socket(s): 1
Stepping: r1p0
CPU(s) scaling MHz: 59%
CPU max MHz: 2803.2000
CPU min MHz: 499.2000
BogoMIPS: 38.40
Flags: fp asimd evtstrm aes pmull sha1 sha2 crc32 atomics fphp asimdhp cpuid asimdrdm jscvt fcma lrcpc dcpop sha3 sm3 sm4 asimddp sha512 asimdfhm dit uscat ilrcpc flagm ssbs sb paca pacg dcpodp flagm2 frint i8mm bf16 bti
Model name: Cortex-A710
Model: 0
Thread(s) per core: 1
Core(s) per socket: 2
Socket(s): 1
Stepping: r2p0
CPU(s) scaling MHz: 59%
CPU max MHz: 2803.2000
CPU min MHz: 499.2000
BogoMIPS: 38.40
Flags: fp asimd evtstrm aes pmull sha1 sha2 crc32 atomics fphp asimdhp cpuid asimdrdm jscvt fcma lrcpc dcpop sha3 sm3 sm4 asimddp sha512 asimdfhm dit uscat ilrcpc flagm ssbs sb paca pacg dcpodp flagm2 frint i8mm bf16 bti
Model name: -
Model: 0
Thread(s) per core: 1
Core(s) per socket: 1
Socket(s): 1
Stepping: 0x1
CPU(s) scaling MHz: 27%
CPU max MHz: 3187.2000
CPU min MHz: 595.2000
Vulnerability Itlb multihit: Not affected
Vulnerability L1tf: Not affected
Vulnerability Mds: Not affected
Vulnerability Meltdown: Not affected
Vulnerability Spec store bypass: Mitigation; Speculative Store Bypass disabled via prctl
Vulnerability Spectre v1: Mitigation; __user pointer sanitization
Vulnerability Spectre v2: Vulnerable: Unprivileged eBPF enabled
Vulnerability Srbds: Not affected
Vulnerability Tsx async abort: Not affected
- Operating System, e.g. for Linux:
$ uname -a
Linux localhost 5.15.41-qki-consolidate-android13-8-g8d73f5ad0193 #1 SMP PREEMPT Tue Dec 27 04:30:59 UTC 2022 aarch64 Android
$ python3 --version
Python 3.11.6
$ make --version
GNU Make 4.4.1
$ cmake --version
cmake version 3.27.7
$ g++ --version
clang version 17.0.2
Target: aarch64-unknown-linux-android24
Thread model: posix
InstalledDir: /data/data/com.termux/files/usr/bin
Failure Information (for bugs)
see above
Steps to Reproduce
see above
Failure Logs
see above
About this issue
- Original URL
- State: closed
- Created 9 months ago
- Comments: 18 (1 by maintainers)
@ElvisClaros Ok, thank you for confirming.
By the way, that’s not complete/correct prompt format, give me a moment and I’ll give you correct arguments for
mainfor ChatML formatAlso, you might want to beta test #3538 because current master branch ignores those ChatML tags ( you can just
git clone --branch specialtokens https://github.com/staviq/llama.cpp.git specialtokensto get that PR in one go )EDIT: Your arguments would be like so
./main -m /data/data/com.termux/files/home/llama.cpp/models/tinyllama-1.1b-chat-v0.3.Q4_0.gguf -e -p "<|im_start|>system\nYou are an AI assistant.Below is an instruction that describes a task. Write a response that appropriately completes the request.<|im_end|>\n" -r "<|im_start|>user\n" --in-prefix "<|im_start|>user\n" --in-suffix "<|im_end|>\n<|im_start|>assistant\n" -r "<|im_end|>\n" --color -c 2048 -ins --temp 0.7 --repeat_penalty 1.1 -t 8 -n -1 -s -1You can save that -p prompt argument to your prompt file and call it with -f, but you have to replace
\nwith newlines and make sure that prompt file ends with a newline too, they seem to be important with ChatML format.You can confirm the prompt format was properly processes by adding
--verbose-prompt, this will print tokenized prompt format in the output after model loads.If everything goes correctly, tokenized prompt should not contain
<|im_start|>or<|im_end|>but an empty string with token number assigned.Please note,
mainin that PR does process special tokens correctly, but they are still shown on the screen during the chat, you can ignore that as long as--verbose-promptshows that prompt format tokenized properly.issue closed
yes this method works and is repeatable with
make -C llama.cpp -j4andllama.cpp/server -m /sdcard/Download/llama-2-7b-chat.Q3_K_S.ggufon the Honor Magic 5. Thank you!