TwinDoc/test-multiple-lora-serving-classification-module-7-rank-8-gguf

Logs

make: Entering directory '/home/jovyan/nas_team/1_user/[email protected]/workspace/serving/multilora/prepare/classification/llama.cpp'
I ccache not found. Consider installing it for faster compilation.
I llama.cpp build info: 
I UNAME_S:   Linux
I UNAME_P:   x86_64
I UNAME_M:   x86_64
I CFLAGS:    -Iggml/include -Iggml/src -Iinclude -Isrc -Icommon -D_XOPEN_SOURCE=600 -D_GNU_SOURCE -DNDEBUG -DGGML_USE_CPU_AARCH64 -DGGML_USE_OPENMP -DGGML_USE_LLAMAFILE -DGGML_USE_AMX  -std=c11   -fPIC -O3 -g -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wshadow -Wstrict-prototypes -Wpointer-arith -Wmissing-prototypes -Werror=implicit-int -Werror=implicit-function-declaration -pthread -march=native -mtune=native -fopenmp -Wdouble-promotion 
I CXXFLAGS:  -std=c++11 -fPIC -O3 -g -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wmissing-declarations -Wmissing-noreturn -pthread -fopenmp  -march=native -mtune=native -Wno-array-bounds -Wno-format-truncation -Wextra-semi -Iggml/include -Iggml/src -Iinclude -Isrc -Icommon -D_XOPEN_SOURCE=600 -D_GNU_SOURCE -DNDEBUG -DGGML_USE_CPU_AARCH64 -DGGML_USE_OPENMP -DGGML_USE_LLAMAFILE -DGGML_USE_AMX 
I NVCCFLAGS: -std=c++11 -O3 -g 
I LDFLAGS:    
I CC:        cc (Ubuntu 9.4.0-1ubuntu1~20.04.2) 9.4.0
I CXX:       c++ (Ubuntu 9.4.0-1ubuntu1~20.04.2) 9.4.0

rm -vrf libllava.a llama-batched llama-batched-bench llama-bench llama-cli llama-convert-llama2c-to-ggml llama-embedding llama-eval-callback llama-export-lora llama-gbnf-validator llama-gguf llama-gguf-hash llama-gguf-split llama-gritlm llama-imatrix llama-infill llama-llava-cli llama-minicpmv-cli llama-lookahead llama-lookup llama-lookup-create llama-lookup-merge llama-lookup-stats llama-parallel llama-passkey llama-perplexity llama-q8dot llama-quantize llama-quantize-stats llama-retrieval llama-save-load-state llama-server llama-simple llama-simple-chat llama-speculative llama-tokenize llama-vdot llama-cvector-generator llama-gen-docs tests/test-c.o libggml.so libggml.a libllama.so libllama.a libcommon.so libcommon.a tests/test-arg-parser tests/test-autorelease tests/test-backend-ops tests/test-chat-template tests/test-double-float tests/test-grammar-integration tests/test-grammar-parser tests/test-json-schema-to-grammar tests/test-llama-grammar tests/test-log tests/test-model-load-cancel tests/test-quantize-fns tests/test-quantize-perf tests/test-rope tests/test-sampling tests/test-tokenizer-0 tests/test-tokenizer-1-bpe tests/test-tokenizer-1-spm
rm -rvf *.a *.dll *.so *.dot
find ggml src common tests examples pocs -type f -name "*.o" -delete
find ggml src common tests examples pocs -type f -name "*.d" -delete
make: Leaving directory '/home/jovyan/nas_team/1_user/[email protected]/workspace/serving/multilora/prepare/classification/llama.cpp'


This will take 3 minutes...
INFO:hf-to-gguf:Loading model: test-multiple-lora-serving-classification-module-7-rank-8-gguf
INFO:gguf.gguf_writer:gguf: This GGUF file is for Little Endian only
INFO:hf-to-gguf:Exporting model...
INFO:hf-to-gguf:rope_freqs.weight,           torch.float32 --> F32, shape = {64}
INFO:hf-to-gguf:gguf: loading model weight map from 'model.safetensors.index.json'
INFO:hf-to-gguf:gguf: loading model part 'model-00001-of-00004.safetensors'
INFO:hf-to-gguf:token_embd.weight,           torch.bfloat16 --> Q8_0, shape = {4096, 128256}
INFO:hf-to-gguf:blk.0.attn_norm.weight,      torch.bfloat16 --> F32, shape = {4096}
INFO:hf-to-gguf:blk.0.ffn_down.weight,       torch.bfloat16 --> Q8_0, shape = {14336, 4096}
INFO:hf-to-gguf:blk.0.ffn_gate.weight,       torch.bfloat16 --> Q8_0, shape = {4096, 14336}
INFO:hf-to-gguf:blk.0.ffn_up.weight,         torch.bfloat16 --> Q8_0, shape = {4096, 14336}
INFO:hf-to-gguf:blk.0.ffn_norm.weight,       torch.bfloat16 --> F32, shape = {4096}
INFO:hf-to-gguf:blk.0.attn_k.weight,         torch.bfloat16 --> Q8_0, shape = {4096, 1024}
INFO:hf-to-gguf:blk.0.attn_output.weight,    torch.bfloat16 --> Q8_0, shape = {4096, 4096}
INFO:hf-to-gguf:blk.0.attn_q.weight,         torch.bfloat16 --> Q8_0, shape = {4096, 4096}
INFO:hf-to-gguf:blk.0.attn_v.weight,         torch.bfloat16 --> Q8_0, shape = {4096, 1024}
INFO:hf-to-gguf:blk.1.attn_norm.weight,      torch.bfloat16 --> F32, shape = {4096}
INFO:hf-to-gguf:blk.1.ffn_down.weight,       torch.bfloat16 --> Q8_0, shape = {14336, 4096}
INFO:hf-to-gguf:blk.1.ffn_gate.weight,       torch.bfloat16 --> Q8_0, shape = {4096, 14336}
INFO:hf-to-gguf:blk.1.ffn_up.weight,         torch.bfloat16 --> Q8_0, shape = {4096, 14336}
INFO:hf-to-gguf:blk.1.ffn_norm.weight,       torch.bfloat16 --> F32, shape = {4096}
INFO:hf-to-gguf:blk.1.attn_k.weight,         torch.bfloat16 --> Q8_0, shape = {4096, 1024}
INFO:hf-to-gguf:blk.1.attn_output.weight,    torch.bfloat16 --> Q8_0, shape = {4096, 4096}
INFO:hf-to-gguf:blk.1.attn_q.weight,         torch.bfloat16 --> Q8_0, shape = {4096, 4096}
INFO:hf-to-gguf:blk.1.attn_v.weight,         torch.bfloat16 --> Q8_0, shape = {4096, 1024}
INFO:hf-to-gguf:blk.2.attn_norm.weight,      torch.bfloat16 --> F32, shape = {4096}
INFO:hf-to-gguf:blk.2.ffn_down.weight,       torch.bfloat16 --> Q8_0, shape = {14336, 4096}
INFO:hf-to-gguf:blk.2.ffn_gate.weight,       torch.bfloat16 --> Q8_0, shape = {4096, 14336}
INFO:hf-to-gguf:blk.2.ffn_up.weight,         torch.bfloat16 --> Q8_0, shape = {4096, 14336}
INFO:hf-to-gguf:blk.2.ffn_norm.weight,       torch.bfloat16 --> F32, shape = {4096}
INFO:hf-to-gguf:blk.2.attn_k.weight,         torch.bfloat16 --> Q8_0, shape = {4096, 1024}
INFO:hf-to-gguf:blk.2.attn_output.weight,    torch.bfloat16 --> Q8_0, shape = {4096, 4096}
INFO:hf-to-gguf:blk.2.attn_q.weight,         torch.bfloat16 --> Q8_0, shape = {4096, 4096}
INFO:hf-to-gguf:blk.2.attn_v.weight,         torch.bfloat16 --> Q8_0, shape = {4096, 1024}
INFO:hf-to-gguf:blk.3.attn_norm.weight,      torch.bfloat16 --> F32, shape = {4096}
INFO:hf-to-gguf:blk.3.ffn_down.weight,       torch.bfloat16 --> Q8_0, shape = {14336, 4096}
INFO:hf-to-gguf:blk.3.ffn_gate.weight,       torch.bfloat16 --> Q8_0, shape = {4096, 14336}
INFO:hf-to-gguf:blk.3.ffn_up.weight,         torch.bfloat16 --> Q8_0, shape = {4096, 14336}
INFO:hf-to-gguf:blk.3.ffn_norm.weight,       torch.bfloat16 --> F32, shape = {4096}
INFO:hf-to-gguf:blk.3.attn_k.weight,         torch.bfloat16 --> Q8_0, shape = {4096, 1024}
INFO:hf-to-gguf:blk.3.attn_output.weight,    torch.bfloat16 --> Q8_0, shape = {4096, 4096}
INFO:hf-to-gguf:blk.3.attn_q.weight,         torch.bfloat16 --> Q8_0, shape = {4096, 4096}
INFO:hf-to-gguf:blk.3.attn_v.weight,         torch.bfloat16 --> Q8_0, shape = {4096, 1024}
INFO:hf-to-gguf:blk.4.attn_norm.weight,      torch.bfloat16 --> F32, shape = {4096}
INFO:hf-to-gguf:blk.4.ffn_down.weight,       torch.bfloat16 --> Q8_0, shape = {14336, 4096}
INFO:hf-to-gguf:blk.4.ffn_gate.weight,       torch.bfloat16 --> Q8_0, shape = {4096, 14336}
INFO:hf-to-gguf:blk.4.ffn_up.weight,         torch.bfloat16 --> Q8_0, shape = {4096, 14336}
INFO:hf-to-gguf:blk.4.ffn_norm.weight,       torch.bfloat16 --> F32, shape = {4096}
INFO:hf-to-gguf:blk.4.attn_k.weight,         torch.bfloat16 --> Q8_0, shape = {4096, 1024}
INFO:hf-to-gguf:blk.4.attn_output.weight,    torch.bfloat16 --> Q8_0, shape = {4096, 4096}
INFO:hf-to-gguf:blk.4.attn_q.weight,         torch.bfloat16 --> Q8_0, shape = {4096, 4096}
INFO:hf-to-gguf:blk.4.attn_v.weight,         torch.bfloat16 --> Q8_0, shape = {4096, 1024}
INFO:hf-to-gguf:blk.5.attn_norm.weight,      torch.bfloat16 --> F32, shape = {4096}
INFO:hf-to-gguf:blk.5.ffn_down.weight,       torch.bfloat16 --> Q8_0, shape = {14336, 4096}
INFO:hf-to-gguf:blk.5.ffn_gate.weight,       torch.bfloat16 --> Q8_0, shape = {4096, 14336}
INFO:hf-to-gguf:blk.5.ffn_up.weight,         torch.bfloat16 --> Q8_0, shape = {4096, 14336}
INFO:hf-to-gguf:blk.5.ffn_norm.weight,       torch.bfloat16 --> F32, shape = {4096}
INFO:hf-to-gguf:blk.5.attn_k.weight,         torch.bfloat16 --> Q8_0, shape = {4096, 1024}
INFO:hf-to-gguf:blk.5.attn_output.weight,    torch.bfloat16 --> Q8_0, shape = {4096, 4096}
INFO:hf-to-gguf:blk.5.attn_q.weight,         torch.bfloat16 --> Q8_0, shape = {4096, 4096}
INFO:hf-to-gguf:blk.5.attn_v.weight,         torch.bfloat16 --> Q8_0, shape = {4096, 1024}
INFO:hf-to-gguf:blk.6.attn_norm.weight,      torch.bfloat16 --> F32, shape = {4096}
INFO:hf-to-gguf:blk.6.ffn_down.weight,       torch.bfloat16 --> Q8_0, shape = {14336, 4096}
INFO:hf-to-gguf:blk.6.ffn_gate.weight,       torch.bfloat16 --> Q8_0, shape = {4096, 14336}
INFO:hf-to-gguf:blk.6.ffn_up.weight,         torch.bfloat16 --> Q8_0, shape = {4096, 14336}
INFO:hf-to-gguf:blk.6.ffn_norm.weight,       torch.bfloat16 --> F32, shape = {4096}
INFO:hf-to-gguf:blk.6.attn_k.weight,         torch.bfloat16 --> Q8_0, shape = {4096, 1024}
INFO:hf-to-gguf:blk.6.attn_output.weight,    torch.bfloat16 --> Q8_0, shape = {4096, 4096}
INFO:hf-to-gguf:blk.6.attn_q.weight,         torch.bfloat16 --> Q8_0, shape = {4096, 4096}
INFO:hf-to-gguf:blk.6.attn_v.weight,         torch.bfloat16 --> Q8_0, shape = {4096, 1024}
INFO:hf-to-gguf:blk.7.attn_norm.weight,      torch.bfloat16 --> F32, shape = {4096}
INFO:hf-to-gguf:blk.7.ffn_down.weight,       torch.bfloat16 --> Q8_0, shape = {14336, 4096}
INFO:hf-to-gguf:blk.7.ffn_gate.weight,       torch.bfloat16 --> Q8_0, shape = {4096, 14336}
INFO:hf-to-gguf:blk.7.ffn_up.weight,         torch.bfloat16 --> Q8_0, shape = {4096, 14336}
INFO:hf-to-gguf:blk.7.ffn_norm.weight,       torch.bfloat16 --> F32, shape = {4096}
INFO:hf-to-gguf:blk.7.attn_k.weight,         torch.bfloat16 --> Q8_0, shape = {4096, 1024}
INFO:hf-to-gguf:blk.7.attn_output.weight,    torch.bfloat16 --> Q8_0, shape = {4096, 4096}
INFO:hf-to-gguf:blk.7.attn_q.weight,         torch.bfloat16 --> Q8_0, shape = {4096, 4096}
INFO:hf-to-gguf:blk.7.attn_v.weight,         torch.bfloat16 --> Q8_0, shape = {4096, 1024}
INFO:hf-to-gguf:blk.8.attn_norm.weight,      torch.bfloat16 --> F32, shape = {4096}
INFO:hf-to-gguf:blk.8.ffn_down.weight,       torch.bfloat16 --> Q8_0, shape = {14336, 4096}
INFO:hf-to-gguf:blk.8.ffn_gate.weight,       torch.bfloat16 --> Q8_0, shape = {4096, 14336}
INFO:hf-to-gguf:blk.8.ffn_up.weight,         torch.bfloat16 --> Q8_0, shape = {4096, 14336}
INFO:hf-to-gguf:blk.8.ffn_norm.weight,       torch.bfloat16 --> F32, shape = {4096}
INFO:hf-to-gguf:blk.8.attn_k.weight,         torch.bfloat16 --> Q8_0, shape = {4096, 1024}
INFO:hf-to-gguf:blk.8.attn_output.weight,    torch.bfloat16 --> Q8_0, shape = {4096, 4096}
INFO:hf-to-gguf:blk.8.attn_q.weight,         torch.bfloat16 --> Q8_0, shape = {4096, 4096}
INFO:hf-to-gguf:blk.8.attn_v.weight,         torch.bfloat16 --> Q8_0, shape = {4096, 1024}
INFO:hf-to-gguf:gguf: loading model part 'model-00002-of-00004.safetensors'
INFO:hf-to-gguf:blk.10.attn_norm.weight,     torch.bfloat16 --> F32, shape = {4096}
INFO:hf-to-gguf:blk.10.ffn_down.weight,      torch.bfloat16 --> Q8_0, shape = {14336, 4096}
INFO:hf-to-gguf:blk.10.ffn_gate.weight,      torch.bfloat16 --> Q8_0, shape = {4096, 14336}
INFO:hf-to-gguf:blk.10.ffn_up.weight,        torch.bfloat16 --> Q8_0, shape = {4096, 14336}
INFO:hf-to-gguf:blk.10.ffn_norm.weight,      torch.bfloat16 --> F32, shape = {4096}
INFO:hf-to-gguf:blk.10.attn_k.weight,        torch.bfloat16 --> Q8_0, shape = {4096, 1024}
INFO:hf-to-gguf:blk.10.attn_output.weight,   torch.bfloat16 --> Q8_0, shape = {4096, 4096}
INFO:hf-to-gguf:blk.10.attn_q.weight,        torch.bfloat16 --> Q8_0, shape = {4096, 4096}
INFO:hf-to-gguf:blk.10.attn_v.weight,        torch.bfloat16 --> Q8_0, shape = {4096, 1024}
INFO:hf-to-gguf:blk.11.attn_norm.weight,     torch.bfloat16 --> F32, shape = {4096}
INFO:hf-to-gguf:blk.11.ffn_down.weight,      torch.bfloat16 --> Q8_0, shape = {14336, 4096}
INFO:hf-to-gguf:blk.11.ffn_gate.weight,      torch.bfloat16 --> Q8_0, shape = {4096, 14336}
INFO:hf-to-gguf:blk.11.ffn_up.weight,        torch.bfloat16 --> Q8_0, shape = {4096, 14336}
INFO:hf-to-gguf:blk.11.ffn_norm.weight,      torch.bfloat16 --> F32, shape = {4096}
INFO:hf-to-gguf:blk.11.attn_k.weight,        torch.bfloat16 --> Q8_0, shape = {4096, 1024}
INFO:hf-to-gguf:blk.11.attn_output.weight,   torch.bfloat16 --> Q8_0, shape = {4096, 4096}
INFO:hf-to-gguf:blk.11.attn_q.weight,        torch.bfloat16 --> Q8_0, shape = {4096, 4096}
INFO:hf-to-gguf:blk.11.attn_v.weight,        torch.bfloat16 --> Q8_0, shape = {4096, 1024}
INFO:hf-to-gguf:blk.12.attn_norm.weight,     torch.bfloat16 --> F32, shape = {4096}
INFO:hf-to-gguf:blk.12.ffn_down.weight,      torch.bfloat16 --> Q8_0, shape = {14336, 4096}
INFO:hf-to-gguf:blk.12.ffn_gate.weight,      torch.bfloat16 --> Q8_0, shape = {4096, 14336}
INFO:hf-to-gguf:blk.12.ffn_up.weight,        torch.bfloat16 --> Q8_0, shape = {4096, 14336}
INFO:hf-to-gguf:blk.12.ffn_norm.weight,      torch.bfloat16 --> F32, shape = {4096}
INFO:hf-to-gguf:blk.12.attn_k.weight,        torch.bfloat16 --> Q8_0, shape = {4096, 1024}
INFO:hf-to-gguf:blk.12.attn_output.weight,   torch.bfloat16 --> Q8_0, shape = {4096, 4096}
INFO:hf-to-gguf:blk.12.attn_q.weight,        torch.bfloat16 --> Q8_0, shape = {4096, 4096}
INFO:hf-to-gguf:blk.12.attn_v.weight,        torch.bfloat16 --> Q8_0, shape = {4096, 1024}
INFO:hf-to-gguf:blk.13.attn_norm.weight,     torch.bfloat16 --> F32, shape = {4096}
INFO:hf-to-gguf:blk.13.ffn_down.weight,      torch.bfloat16 --> Q8_0, shape = {14336, 4096}
INFO:hf-to-gguf:blk.13.ffn_gate.weight,      torch.bfloat16 --> Q8_0, shape = {4096, 14336}
INFO:hf-to-gguf:blk.13.ffn_up.weight,        torch.bfloat16 --> Q8_0, shape = {4096, 14336}
INFO:hf-to-gguf:blk.13.ffn_norm.weight,      torch.bfloat16 --> F32, shape = {4096}
INFO:hf-to-gguf:blk.13.attn_k.weight,        torch.bfloat16 --> Q8_0, shape = {4096, 1024}
INFO:hf-to-gguf:blk.13.attn_output.weight,   torch.bfloat16 --> Q8_0, shape = {4096, 4096}
INFO:hf-to-gguf:blk.13.attn_q.weight,        torch.bfloat16 --> Q8_0, shape = {4096, 4096}
INFO:hf-to-gguf:blk.13.attn_v.weight,        torch.bfloat16 --> Q8_0, shape = {4096, 1024}
INFO:hf-to-gguf:blk.14.attn_norm.weight,     torch.bfloat16 --> F32, shape = {4096}
INFO:hf-to-gguf:blk.14.ffn_down.weight,      torch.bfloat16 --> Q8_0, shape = {14336, 4096}
INFO:hf-to-gguf:blk.14.ffn_gate.weight,      torch.bfloat16 --> Q8_0, shape = {4096, 14336}
INFO:hf-to-gguf:blk.14.ffn_up.weight,        torch.bfloat16 --> Q8_0, shape = {4096, 14336}
INFO:hf-to-gguf:blk.14.ffn_norm.weight,      torch.bfloat16 --> F32, shape = {4096}
INFO:hf-to-gguf:blk.14.attn_k.weight,        torch.bfloat16 --> Q8_0, shape = {4096, 1024}
INFO:hf-to-gguf:blk.14.attn_output.weight,   torch.bfloat16 --> Q8_0, shape = {4096, 4096}
INFO:hf-to-gguf:blk.14.attn_q.weight,        torch.bfloat16 --> Q8_0, shape = {4096, 4096}
INFO:hf-to-gguf:blk.14.attn_v.weight,        torch.bfloat16 --> Q8_0, shape = {4096, 1024}
INFO:hf-to-gguf:blk.15.attn_norm.weight,     torch.bfloat16 --> F32, shape = {4096}
INFO:hf-to-gguf:blk.15.ffn_down.weight,      torch.bfloat16 --> Q8_0, shape = {14336, 4096}
INFO:hf-to-gguf:blk.15.ffn_gate.weight,      torch.bfloat16 --> Q8_0, shape = {4096, 14336}
INFO:hf-to-gguf:blk.15.ffn_up.weight,        torch.bfloat16 --> Q8_0, shape = {4096, 14336}
INFO:hf-to-gguf:blk.15.ffn_norm.weight,      torch.bfloat16 --> F32, shape = {4096}
INFO:hf-to-gguf:blk.15.attn_k.weight,        torch.bfloat16 --> Q8_0, shape = {4096, 1024}
INFO:hf-to-gguf:blk.15.attn_output.weight,   torch.bfloat16 --> Q8_0, shape = {4096, 4096}
INFO:hf-to-gguf:blk.15.attn_q.weight,        torch.bfloat16 --> Q8_0, shape = {4096, 4096}
INFO:hf-to-gguf:blk.15.attn_v.weight,        torch.bfloat16 --> Q8_0, shape = {4096, 1024}
INFO:hf-to-gguf:blk.16.attn_norm.weight,     torch.bfloat16 --> F32, shape = {4096}
INFO:hf-to-gguf:blk.16.ffn_down.weight,      torch.bfloat16 --> Q8_0, shape = {14336, 4096}
INFO:hf-to-gguf:blk.16.ffn_gate.weight,      torch.bfloat16 --> Q8_0, shape = {4096, 14336}
INFO:hf-to-gguf:blk.16.ffn_up.weight,        torch.bfloat16 --> Q8_0, shape = {4096, 14336}
INFO:hf-to-gguf:blk.16.ffn_norm.weight,      torch.bfloat16 --> F32, shape = {4096}
INFO:hf-to-gguf:blk.16.attn_k.weight,        torch.bfloat16 --> Q8_0, shape = {4096, 1024}
INFO:hf-to-gguf:blk.16.attn_output.weight,   torch.bfloat16 --> Q8_0, shape = {4096, 4096}
INFO:hf-to-gguf:blk.16.attn_q.weight,        torch.bfloat16 --> Q8_0, shape = {4096, 4096}
INFO:hf-to-gguf:blk.16.attn_v.weight,        torch.bfloat16 --> Q8_0, shape = {4096, 1024}
INFO:hf-to-gguf:blk.17.attn_norm.weight,     torch.bfloat16 --> F32, shape = {4096}
INFO:hf-to-gguf:blk.17.ffn_down.weight,      torch.bfloat16 --> Q8_0, shape = {14336, 4096}
INFO:hf-to-gguf:blk.17.ffn_gate.weight,      torch.bfloat16 --> Q8_0, shape = {4096, 14336}
INFO:hf-to-gguf:blk.17.ffn_up.weight,        torch.bfloat16 --> Q8_0, shape = {4096, 14336}
INFO:hf-to-gguf:blk.17.ffn_norm.weight,      torch.bfloat16 --> F32, shape = {4096}
INFO:hf-to-gguf:blk.17.attn_k.weight,        torch.bfloat16 --> Q8_0, shape = {4096, 1024}
INFO:hf-to-gguf:blk.17.attn_output.weight,   torch.bfloat16 --> Q8_0, shape = {4096, 4096}
INFO:hf-to-gguf:blk.17.attn_q.weight,        torch.bfloat16 --> Q8_0, shape = {4096, 4096}
INFO:hf-to-gguf:blk.17.attn_v.weight,        torch.bfloat16 --> Q8_0, shape = {4096, 1024}
INFO:hf-to-gguf:blk.18.attn_norm.weight,     torch.bfloat16 --> F32, shape = {4096}
INFO:hf-to-gguf:blk.18.ffn_down.weight,      torch.bfloat16 --> Q8_0, shape = {14336, 4096}
INFO:hf-to-gguf:blk.18.ffn_gate.weight,      torch.bfloat16 --> Q8_0, shape = {4096, 14336}
INFO:hf-to-gguf:blk.18.ffn_up.weight,        torch.bfloat16 --> Q8_0, shape = {4096, 14336}
INFO:hf-to-gguf:blk.18.ffn_norm.weight,      torch.bfloat16 --> F32, shape = {4096}
INFO:hf-to-gguf:blk.18.attn_k.weight,        torch.bfloat16 --> Q8_0, shape = {4096, 1024}
INFO:hf-to-gguf:blk.18.attn_output.weight,   torch.bfloat16 --> Q8_0, shape = {4096, 4096}
INFO:hf-to-gguf:blk.18.attn_q.weight,        torch.bfloat16 --> Q8_0, shape = {4096, 4096}
INFO:hf-to-gguf:blk.18.attn_v.weight,        torch.bfloat16 --> Q8_0, shape = {4096, 1024}
INFO:hf-to-gguf:blk.19.attn_norm.weight,     torch.bfloat16 --> F32, shape = {4096}
INFO:hf-to-gguf:blk.19.ffn_down.weight,      torch.bfloat16 --> Q8_0, shape = {14336, 4096}
INFO:hf-to-gguf:blk.19.ffn_gate.weight,      torch.bfloat16 --> Q8_0, shape = {4096, 14336}
INFO:hf-to-gguf:blk.19.ffn_up.weight,        torch.bfloat16 --> Q8_0, shape = {4096, 14336}
INFO:hf-to-gguf:blk.19.ffn_norm.weight,      torch.bfloat16 --> F32, shape = {4096}
INFO:hf-to-gguf:blk.19.attn_k.weight,        torch.bfloat16 --> Q8_0, shape = {4096, 1024}
INFO:hf-to-gguf:blk.19.attn_output.weight,   torch.bfloat16 --> Q8_0, shape = {4096, 4096}
INFO:hf-to-gguf:blk.19.attn_q.weight,        torch.bfloat16 --> Q8_0, shape = {4096, 4096}
INFO:hf-to-gguf:blk.19.attn_v.weight,        torch.bfloat16 --> Q8_0, shape = {4096, 1024}
INFO:hf-to-gguf:blk.20.ffn_gate.weight,      torch.bfloat16 --> Q8_0, shape = {4096, 14336}
INFO:hf-to-gguf:blk.20.attn_k.weight,        torch.bfloat16 --> Q8_0, shape = {4096, 1024}
INFO:hf-to-gguf:blk.20.attn_output.weight,   torch.bfloat16 --> Q8_0, shape = {4096, 4096}
INFO:hf-to-gguf:blk.20.attn_q.weight,        torch.bfloat16 --> Q8_0, shape = {4096, 4096}
INFO:hf-to-gguf:blk.20.attn_v.weight,        torch.bfloat16 --> Q8_0, shape = {4096, 1024}
INFO:hf-to-gguf:blk.9.attn_norm.weight,      torch.bfloat16 --> F32, shape = {4096}
INFO:hf-to-gguf:blk.9.ffn_down.weight,       torch.bfloat16 --> Q8_0, shape = {14336, 4096}
INFO:hf-to-gguf:blk.9.ffn_gate.weight,       torch.bfloat16 --> Q8_0, shape = {4096, 14336}
INFO:hf-to-gguf:blk.9.ffn_up.weight,         torch.bfloat16 --> Q8_0, shape = {4096, 14336}
INFO:hf-to-gguf:blk.9.ffn_norm.weight,       torch.bfloat16 --> F32, shape = {4096}
INFO:hf-to-gguf:blk.9.attn_k.weight,         torch.bfloat16 --> Q8_0, shape = {4096, 1024}
INFO:hf-to-gguf:blk.9.attn_output.weight,    torch.bfloat16 --> Q8_0, shape = {4096, 4096}
INFO:hf-to-gguf:blk.9.attn_q.weight,         torch.bfloat16 --> Q8_0, shape = {4096, 4096}
INFO:hf-to-gguf:blk.9.attn_v.weight,         torch.bfloat16 --> Q8_0, shape = {4096, 1024}
INFO:hf-to-gguf:gguf: loading model part 'model-00003-of-00004.safetensors'
INFO:hf-to-gguf:blk.20.attn_norm.weight,     torch.bfloat16 --> F32, shape = {4096}
INFO:hf-to-gguf:blk.20.ffn_down.weight,      torch.bfloat16 --> Q8_0, shape = {14336, 4096}
INFO:hf-to-gguf:blk.20.ffn_up.weight,        torch.bfloat16 --> Q8_0, shape = {4096, 14336}
INFO:hf-to-gguf:blk.20.ffn_norm.weight,      torch.bfloat16 --> F32, shape = {4096}
INFO:hf-to-gguf:blk.21.attn_norm.weight,     torch.bfloat16 --> F32, shape = {4096}
INFO:hf-to-gguf:blk.21.ffn_down.weight,      torch.bfloat16 --> Q8_0, shape = {14336, 4096}
INFO:hf-to-gguf:blk.21.ffn_gate.weight,      torch.bfloat16 --> Q8_0, shape = {4096, 14336}
INFO:hf-to-gguf:blk.21.ffn_up.weight,        torch.bfloat16 --> Q8_0, shape = {4096, 14336}
INFO:hf-to-gguf:blk.21.ffn_norm.weight,      torch.bfloat16 --> F32, shape = {4096}
INFO:hf-to-gguf:blk.21.attn_k.weight,        torch.bfloat16 --> Q8_0, shape = {4096, 1024}
INFO:hf-to-gguf:blk.21.attn_output.weight,   torch.bfloat16 --> Q8_0, shape = {4096, 4096}
INFO:hf-to-gguf:blk.21.attn_q.weight,        torch.bfloat16 --> Q8_0, shape = {4096, 4096}
INFO:hf-to-gguf:blk.21.attn_v.weight,        torch.bfloat16 --> Q8_0, shape = {4096, 1024}
INFO:hf-to-gguf:blk.22.attn_norm.weight,     torch.bfloat16 --> F32, shape = {4096}
INFO:hf-to-gguf:blk.22.ffn_down.weight,      torch.bfloat16 --> Q8_0, shape = {14336, 4096}
INFO:hf-to-gguf:blk.22.ffn_gate.weight,      torch.bfloat16 --> Q8_0, shape = {4096, 14336}
INFO:hf-to-gguf:blk.22.ffn_up.weight,        torch.bfloat16 --> Q8_0, shape = {4096, 14336}
INFO:hf-to-gguf:blk.22.ffn_norm.weight,      torch.bfloat16 --> F32, shape = {4096}
INFO:hf-to-gguf:blk.22.attn_k.weight,        torch.bfloat16 --> Q8_0, shape = {4096, 1024}
INFO:hf-to-gguf:blk.22.attn_output.weight,   torch.bfloat16 --> Q8_0, shape = {4096, 4096}
INFO:hf-to-gguf:blk.22.attn_q.weight,        torch.bfloat16 --> Q8_0, shape = {4096, 4096}
INFO:hf-to-gguf:blk.22.attn_v.weight,        torch.bfloat16 --> Q8_0, shape = {4096, 1024}
INFO:hf-to-gguf:blk.23.attn_norm.weight,     torch.bfloat16 --> F32, shape = {4096}
INFO:hf-to-gguf:blk.23.ffn_down.weight,      torch.bfloat16 --> Q8_0, shape = {14336, 4096}
INFO:hf-to-gguf:blk.23.ffn_gate.weight,      torch.bfloat16 --> Q8_0, shape = {4096, 14336}
INFO:hf-to-gguf:blk.23.ffn_up.weight,        torch.bfloat16 --> Q8_0, shape = {4096, 14336}
INFO:hf-to-gguf:blk.23.ffn_norm.weight,      torch.bfloat16 --> F32, shape = {4096}
INFO:hf-to-gguf:blk.23.attn_k.weight,        torch.bfloat16 --> Q8_0, shape = {4096, 1024}
INFO:hf-to-gguf:blk.23.attn_output.weight,   torch.bfloat16 --> Q8_0, shape = {4096, 4096}
INFO:hf-to-gguf:blk.23.attn_q.weight,        torch.bfloat16 --> Q8_0, shape = {4096, 4096}
INFO:hf-to-gguf:blk.23.attn_v.weight,        torch.bfloat16 --> Q8_0, shape = {4096, 1024}
INFO:hf-to-gguf:blk.24.attn_norm.weight,     torch.bfloat16 --> F32, shape = {4096}
INFO:hf-to-gguf:blk.24.ffn_down.weight,      torch.bfloat16 --> Q8_0, shape = {14336, 4096}
INFO:hf-to-gguf:blk.24.ffn_gate.weight,      torch.bfloat16 --> Q8_0, shape = {4096, 14336}
INFO:hf-to-gguf:blk.24.ffn_up.weight,        torch.bfloat16 --> Q8_0, shape = {4096, 14336}
INFO:hf-to-gguf:blk.24.ffn_norm.weight,      torch.bfloat16 --> F32, shape = {4096}
INFO:hf-to-gguf:blk.24.attn_k.weight,        torch.bfloat16 --> Q8_0, shape = {4096, 1024}
INFO:hf-to-gguf:blk.24.attn_output.weight,   torch.bfloat16 --> Q8_0, shape = {4096, 4096}
INFO:hf-to-gguf:blk.24.attn_q.weight,        torch.bfloat16 --> Q8_0, shape = {4096, 4096}
INFO:hf-to-gguf:blk.24.attn_v.weight,        torch.bfloat16 --> Q8_0, shape = {4096, 1024}
INFO:hf-to-gguf:blk.25.attn_norm.weight,     torch.bfloat16 --> F32, shape = {4096}
INFO:hf-to-gguf:blk.25.ffn_down.weight,      torch.bfloat16 --> Q8_0, shape = {14336, 4096}
INFO:hf-to-gguf:blk.25.ffn_gate.weight,      torch.bfloat16 --> Q8_0, shape = {4096, 14336}
INFO:hf-to-gguf:blk.25.ffn_up.weight,        torch.bfloat16 --> Q8_0, shape = {4096, 14336}
INFO:hf-to-gguf:blk.25.ffn_norm.weight,      torch.bfloat16 --> F32, shape = {4096}
INFO:hf-to-gguf:blk.25.attn_k.weight,        torch.bfloat16 --> Q8_0, shape = {4096, 1024}
INFO:hf-to-gguf:blk.25.attn_output.weight,   torch.bfloat16 --> Q8_0, shape = {4096, 4096}
INFO:hf-to-gguf:blk.25.attn_q.weight,        torch.bfloat16 --> Q8_0, shape = {4096, 4096}
INFO:hf-to-gguf:blk.25.attn_v.weight,        torch.bfloat16 --> Q8_0, shape = {4096, 1024}
INFO:hf-to-gguf:blk.26.attn_norm.weight,     torch.bfloat16 --> F32, shape = {4096}
INFO:hf-to-gguf:blk.26.ffn_down.weight,      torch.bfloat16 --> Q8_0, shape = {14336, 4096}
INFO:hf-to-gguf:blk.26.ffn_gate.weight,      torch.bfloat16 --> Q8_0, shape = {4096, 14336}
INFO:hf-to-gguf:blk.26.ffn_up.weight,        torch.bfloat16 --> Q8_0, shape = {4096, 14336}
INFO:hf-to-gguf:blk.26.ffn_norm.weight,      torch.bfloat16 --> F32, shape = {4096}
INFO:hf-to-gguf:blk.26.attn_k.weight,        torch.bfloat16 --> Q8_0, shape = {4096, 1024}
INFO:hf-to-gguf:blk.26.attn_output.weight,   torch.bfloat16 --> Q8_0, shape = {4096, 4096}
INFO:hf-to-gguf:blk.26.attn_q.weight,        torch.bfloat16 --> Q8_0, shape = {4096, 4096}
INFO:hf-to-gguf:blk.26.attn_v.weight,        torch.bfloat16 --> Q8_0, shape = {4096, 1024}
INFO:hf-to-gguf:blk.27.attn_norm.weight,     torch.bfloat16 --> F32, shape = {4096}
INFO:hf-to-gguf:blk.27.ffn_down.weight,      torch.bfloat16 --> Q8_0, shape = {14336, 4096}
INFO:hf-to-gguf:blk.27.ffn_gate.weight,      torch.bfloat16 --> Q8_0, shape = {4096, 14336}
INFO:hf-to-gguf:blk.27.ffn_up.weight,        torch.bfloat16 --> Q8_0, shape = {4096, 14336}
INFO:hf-to-gguf:blk.27.ffn_norm.weight,      torch.bfloat16 --> F32, shape = {4096}
INFO:hf-to-gguf:blk.27.attn_k.weight,        torch.bfloat16 --> Q8_0, shape = {4096, 1024}
INFO:hf-to-gguf:blk.27.attn_output.weight,   torch.bfloat16 --> Q8_0, shape = {4096, 4096}
INFO:hf-to-gguf:blk.27.attn_q.weight,        torch.bfloat16 --> Q8_0, shape = {4096, 4096}
INFO:hf-to-gguf:blk.27.attn_v.weight,        torch.bfloat16 --> Q8_0, shape = {4096, 1024}
INFO:hf-to-gguf:blk.28.attn_norm.weight,     torch.bfloat16 --> F32, shape = {4096}
INFO:hf-to-gguf:blk.28.ffn_down.weight,      torch.bfloat16 --> Q8_0, shape = {14336, 4096}
INFO:hf-to-gguf:blk.28.ffn_gate.weight,      torch.bfloat16 --> Q8_0, shape = {4096, 14336}
INFO:hf-to-gguf:blk.28.ffn_up.weight,        torch.bfloat16 --> Q8_0, shape = {4096, 14336}
INFO:hf-to-gguf:blk.28.ffn_norm.weight,      torch.bfloat16 --> F32, shape = {4096}
INFO:hf-to-gguf:blk.28.attn_k.weight,        torch.bfloat16 --> Q8_0, shape = {4096, 1024}
INFO:hf-to-gguf:blk.28.attn_output.weight,   torch.bfloat16 --> Q8_0, shape = {4096, 4096}
INFO:hf-to-gguf:blk.28.attn_q.weight,        torch.bfloat16 --> Q8_0, shape = {4096, 4096}
INFO:hf-to-gguf:blk.28.attn_v.weight,        torch.bfloat16 --> Q8_0, shape = {4096, 1024}
INFO:hf-to-gguf:blk.29.attn_norm.weight,     torch.bfloat16 --> F32, shape = {4096}
INFO:hf-to-gguf:blk.29.ffn_down.weight,      torch.bfloat16 --> Q8_0, shape = {14336, 4096}
INFO:hf-to-gguf:blk.29.ffn_gate.weight,      torch.bfloat16 --> Q8_0, shape = {4096, 14336}
INFO:hf-to-gguf:blk.29.ffn_up.weight,        torch.bfloat16 --> Q8_0, shape = {4096, 14336}
INFO:hf-to-gguf:blk.29.ffn_norm.weight,      torch.bfloat16 --> F32, shape = {4096}
INFO:hf-to-gguf:blk.29.attn_k.weight,        torch.bfloat16 --> Q8_0, shape = {4096, 1024}
INFO:hf-to-gguf:blk.29.attn_output.weight,   torch.bfloat16 --> Q8_0, shape = {4096, 4096}
INFO:hf-to-gguf:blk.29.attn_q.weight,        torch.bfloat16 --> Q8_0, shape = {4096, 4096}
INFO:hf-to-gguf:blk.29.attn_v.weight,        torch.bfloat16 --> Q8_0, shape = {4096, 1024}
INFO:hf-to-gguf:blk.30.attn_norm.weight,     torch.bfloat16 --> F32, shape = {4096}
INFO:hf-to-gguf:blk.30.ffn_down.weight,      torch.bfloat16 --> Q8_0, shape = {14336, 4096}
INFO:hf-to-gguf:blk.30.ffn_gate.weight,      torch.bfloat16 --> Q8_0, shape = {4096, 14336}
INFO:hf-to-gguf:blk.30.ffn_up.weight,        torch.bfloat16 --> Q8_0, shape = {4096, 14336}
INFO:hf-to-gguf:blk.30.ffn_norm.weight,      torch.bfloat16 --> F32, shape = {4096}
INFO:hf-to-gguf:blk.30.attn_k.weight,        torch.bfloat16 --> Q8_0, shape = {4096, 1024}
INFO:hf-to-gguf:blk.30.attn_output.weight,   torch.bfloat16 --> Q8_0, shape = {4096, 4096}
INFO:hf-to-gguf:blk.30.attn_q.weight,        torch.bfloat16 --> Q8_0, shape = {4096, 4096}
INFO:hf-to-gguf:blk.30.attn_v.weight,        torch.bfloat16 --> Q8_0, shape = {4096, 1024}
INFO:hf-to-gguf:blk.31.ffn_gate.weight,      torch.bfloat16 --> Q8_0, shape = {4096, 14336}
INFO:hf-to-gguf:blk.31.ffn_up.weight,        torch.bfloat16 --> Q8_0, shape = {4096, 14336}
INFO:hf-to-gguf:blk.31.attn_k.weight,        torch.bfloat16 --> Q8_0, shape = {4096, 1024}
INFO:hf-to-gguf:blk.31.attn_output.weight,   torch.bfloat16 --> Q8_0, shape = {4096, 4096}
INFO:hf-to-gguf:blk.31.attn_q.weight,        torch.bfloat16 --> Q8_0, shape = {4096, 4096}
INFO:hf-to-gguf:blk.31.attn_v.weight,        torch.bfloat16 --> Q8_0, shape = {4096, 1024}
INFO:hf-to-gguf:gguf: loading model part 'model-00004-of-00004.safetensors'
INFO:hf-to-gguf:output.weight,               torch.bfloat16 --> Q8_0, shape = {4096, 128256}
INFO:hf-to-gguf:blk.31.attn_norm.weight,     torch.bfloat16 --> F32, shape = {4096}
INFO:hf-to-gguf:blk.31.ffn_down.weight,      torch.bfloat16 --> Q8_0, shape = {14336, 4096}
INFO:hf-to-gguf:blk.31.ffn_norm.weight,      torch.bfloat16 --> F32, shape = {4096}
INFO:hf-to-gguf:output_norm.weight,          torch.bfloat16 --> F32, shape = {4096}
INFO:hf-to-gguf:Set meta model
INFO:hf-to-gguf:Set model parameters
INFO:hf-to-gguf:gguf: context length = 131072
INFO:hf-to-gguf:gguf: embedding length = 4096
INFO:hf-to-gguf:gguf: feed forward length = 14336
INFO:hf-to-gguf:gguf: head count = 32
INFO:hf-to-gguf:gguf: key-value head count = 8
INFO:hf-to-gguf:gguf: rope theta = 500000.0
INFO:hf-to-gguf:gguf: rms norm epsilon = 1e-05
INFO:hf-to-gguf:gguf: file type = 7
INFO:hf-to-gguf:Set model tokenizer
INFO:gguf.vocab:Adding 280147 merge(s).
INFO:gguf.vocab:Setting special token type bos to 128000
INFO:gguf.vocab:Setting special token type eos to 128009
INFO:gguf.vocab:Setting special token type pad to 128004
INFO:gguf.vocab:Setting chat_template to {{- bos_token }}
{%- if custom_tools is defined %}
    {%- set tools = custom_tools %}
{%- endif %}
{%- if not tools_in_user_message is defined %}
    {%- set tools_in_user_message = true %}
{%- endif %}
{%- if not date_string is defined %}
    {%- set date_string = "26 Jul 2024" %}
{%- endif %}
{%- if not tools is defined %}
    {%- set tools = none %}
{%- endif %}

{#- This block extracts the system message, so we can slot it into the right place. #}
{%- if messages[0]['role'] == 'system' %}
    {%- set system_message = messages[0]['content']|trim %}
    {%- set messages = messages[1:] %}
{%- else %}
    {%- set system_message = "" %}
{%- endif %}

{#- System message + builtin tools #}
{{- "<|start_header_id|>system<|end_header_id|>\n\n" }}
{%- if builtin_tools is defined or tools is not none %}
    {{- "Environment: ipython\n" }}
{%- endif %}
{%- if builtin_tools is defined %}
    {{- "Tools: " + builtin_tools | reject('equalto', 'code_interpreter') | join(", ") + "\n\n"}}
{%- endif %}
{{- "Cutting Knowledge Date: December 2023\n" }}
{{- "Today Date: " + date_string + "\n\n" }}
{%- if tools is not none and not tools_in_user_message %}
    {{- "You have access to the following functions. To call a function, please respond with JSON for a function call." }}
    {{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }}
    {{- "Do not use variables.\n\n" }}
    {%- for t in tools %}
        {{- t | tojson(indent=4) }}
        {{- "\n\n" }}
    {%- endfor %}
{%- endif %}
{{- system_message }}
{{- "<|eot_id|>" }}

{#- Custom tools are passed in a user message with some extra guidance #}
{%- if tools_in_user_message and not tools is none %}
    {#- Extract the first user message so we can plug it in here #}
    {%- if messages | length != 0 %}
        {%- set first_user_message = messages[0]['content']|trim %}
        {%- set messages = messages[1:] %}
    {%- else %}
        {{- raise_exception("Cannot put tools in the first user message when there's no first user message!") }}
{%- endif %}
    {{- '<|start_header_id|>user<|end_header_id|>\n\n' -}}
    {{- "Given the following functions, please respond with a JSON for a function call " }}
    {{- "with its proper arguments that best answers the given prompt.\n\n" }}
    {{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }}
    {{- "Do not use variables.\n\n" }}
    {%- for t in tools %}
        {{- t | tojson(indent=4) }}
        {{- "\n\n" }}
    {%- endfor %}
    {{- first_user_message + "<|eot_id|>"}}
{%- endif %}

{%- for message in messages %}
    {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}
        {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' }}
    {%- elif 'tool_calls' in message %}
        {%- if not message.tool_calls|length == 1 %}
            {{- raise_exception("This model only supports single tool-calls at once!") }}
        {%- endif %}
        {%- set tool_call = message.tool_calls[0].function %}
        {%- if builtin_tools is defined and tool_call.name in builtin_tools %}
            {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}}
            {{- "<|python_tag|>" + tool_call.name + ".call(" }}
            {%- for arg_name, arg_val in tool_call.arguments | items %}
                {{- arg_name + '="' + arg_val + '"' }}
                {%- if not loop.last %}
                    {{- ", " }}
                {%- endif %}
                {%- endfor %}
            {{- ")" }}
        {%- else  %}
            {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}}
            {{- '{"name": "' + tool_call.name + '", ' }}
            {{- '"parameters": ' }}
            {{- tool_call.arguments | tojson }}
            {{- "}" }}
        {%- endif %}
        {%- if builtin_tools is defined %}
            {#- This means we're in ipython mode #}
            {{- "<|eom_id|>" }}
        {%- else %}
            {{- "<|eot_id|>" }}
        {%- endif %}
    {%- elif message.role == "tool" or message.role == "ipython" %}
        {{- "<|start_header_id|>ipython<|end_header_id|>\n\n" }}
        {%- if message.content is mapping or message.content is iterable %}
            {{- message.content | tojson }}
        {%- else %}
            {{- message.content }}
        {%- endif %}
        {{- "<|eot_id|>" }}
    {%- endif %}
{%- endfor %}
{%- if add_generation_prompt %}
    {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' }}
{%- endif %}

INFO:hf-to-gguf:Set model quantization version
INFO:gguf.gguf_writer:Writing the following files: