diff --git a/ci/run.sh b/ci/run.sh index b411be559..f1aca0db0 100755 --- a/ci/run.sh +++ b/ci/run.sh @@ -508,9 +508,175 @@ function gg_sum_open_llama_7b_v2 { # requires: GG_BUILD_CUDA function gg_run_mistral_7b_v0_1 { + cd ${SRC} + + gg_wget models-mnt/mistral/7B_v0_1/ https://huggingface.co/mistralai/Mistral-7B-v0.1/raw/main/config.json + gg_wget models-mnt/mistral/7B_v0_1/ https://huggingface.co/mistralai/Mistral-7B-v0.1/raw/main/generation_config.json + gg_wget models-mnt/mistral/7B_v0_1/ https://huggingface.co/mistralai/Mistral-7B-v0.1/resolve/main/model-00001-of-00002.safetensors + gg_wget models-mnt/mistral/7B_v0_1/ https://huggingface.co/mistralai/Mistral-7B-v0.1/resolve/main/model-00002-of-00002.safetensors + gg_wget models-mnt/mistral/7B_v0_1/ https://huggingface.co/mistralai/Mistral-7B-v0.1/raw/main/model.safetensors.index.json + gg_wget models-mnt/mistral/7B_v0_1/ https://huggingface.co/mistralai/Mistral-7B-v0.1/resolve/main/pytorch_model-00001-of-00002.bin + gg_wget models-mnt/mistral/7B_v0_1/ https://huggingface.co/mistralai/Mistral-7B-v0.1/resolve/main/pytorch_model-00002-of-00002.bin + gg_wget models-mnt/mistral/7B_v0_1/ https://huggingface.co/mistralai/Mistral-7B-v0.1/raw/main/pytorch_model.bin.index.json + gg_wget models-mnt/mistral/7B_v0_1/ https://huggingface.co/mistralai/Mistral-7B-v0.1/raw/main/special_tokens_map.json + gg_wget models-mnt/mistral/7B_v0_1/ https://huggingface.co/mistralai/Mistral-7B-v0.1/raw/main/tokenizer.json + gg_wget models-mnt/mistral/7B_v0_1/ https://huggingface.co/mistralai/Mistral-7B-v0.1/resolve/main/tokenizer.model + gg_wget models-mnt/mistral/7B_v0_1/ https://huggingface.co/mistralai/Mistral-7B-v0.1/raw/main/tokenizer_config.json + + gg_wget models-mnt/wikitext/ https://s3.amazonaws.com/research.metamind.io/wikitext/wikitext-2-raw-v1.zip + unzip -o models-mnt/wikitext/wikitext-2-raw-v1.zip -d models-mnt/wikitext/ + + path_models="../models-mnt/mistral/7B_v0_1" + path_wiki="../models-mnt/wikitext/wikitext-2-raw" + + rm -rf build-ci-release && mkdir build-ci-release && cd build-ci-release + + set -e + + (time cmake -DCMAKE_BUILD_TYPE=Release ${CMAKE_EXTRA} -DLLAMA_CUBLAS=1 .. ) 2>&1 | tee -a $OUT/${ci}-cmake.log + (time make -j ) 2>&1 | tee -a $OUT/${ci}-make.log + + python3 ../convert.py ${path_models} + + model_f16="${path_models}/ggml-model-f16.gguf" + model_q8_0="${path_models}/ggml-model-q8_0.gguf" + model_q4_0="${path_models}/ggml-model-q4_0.gguf" + model_q4_1="${path_models}/ggml-model-q4_1.gguf" + model_q5_0="${path_models}/ggml-model-q5_0.gguf" + model_q5_1="${path_models}/ggml-model-q5_1.gguf" + model_q2_k="${path_models}/ggml-model-q2_k.gguf" + model_q3_k="${path_models}/ggml-model-q3_k.gguf" + model_q4_k="${path_models}/ggml-model-q4_k.gguf" + model_q5_k="${path_models}/ggml-model-q5_k.gguf" + model_q6_k="${path_models}/ggml-model-q6_k.gguf" + + wiki_test="${path_wiki}/wiki.test.raw" + + ./bin/quantize ${model_f16} ${model_q8_0} q8_0 + ./bin/quantize ${model_f16} ${model_q4_0} q4_0 + ./bin/quantize ${model_f16} ${model_q4_1} q4_1 + ./bin/quantize ${model_f16} ${model_q5_0} q5_0 + ./bin/quantize ${model_f16} ${model_q5_1} q5_1 + ./bin/quantize ${model_f16} ${model_q2_k} q2_k + ./bin/quantize ${model_f16} ${model_q3_k} q3_k + ./bin/quantize ${model_f16} ${model_q4_k} q4_k + ./bin/quantize ${model_f16} ${model_q5_k} q5_k + ./bin/quantize ${model_f16} ${model_q6_k} q6_k + + (time ./bin/main --model ${model_f16} -t 1 -ngl 999 -s 1234 -n 256 --ignore-eos -p "I believe the meaning of life is" ) 2>&1 | tee -a $OUT/${ci}-tg-f16.log + (time ./bin/main --model ${model_q8_0} -t 1 -ngl 999 -s 1234 -n 256 --ignore-eos -p "I believe the meaning of life is" ) 2>&1 | tee -a $OUT/${ci}-tg-q8_0.log + (time ./bin/main --model ${model_q4_0} -t 1 -ngl 999 -s 1234 -n 256 --ignore-eos -p "I believe the meaning of life is" ) 2>&1 | tee -a $OUT/${ci}-tg-q4_0.log + (time ./bin/main --model ${model_q4_1} -t 1 -ngl 999 -s 1234 -n 256 --ignore-eos -p "I believe the meaning of life is" ) 2>&1 | tee -a $OUT/${ci}-tg-q4_1.log + (time ./bin/main --model ${model_q5_0} -t 1 -ngl 999 -s 1234 -n 256 --ignore-eos -p "I believe the meaning of life is" ) 2>&1 | tee -a $OUT/${ci}-tg-q5_0.log + (time ./bin/main --model ${model_q5_1} -t 1 -ngl 999 -s 1234 -n 256 --ignore-eos -p "I believe the meaning of life is" ) 2>&1 | tee -a $OUT/${ci}-tg-q5_1.log + (time ./bin/main --model ${model_q2_k} -t 1 -ngl 999 -s 1234 -n 256 --ignore-eos -p "I believe the meaning of life is" ) 2>&1 | tee -a $OUT/${ci}-tg-q2_k.log + (time ./bin/main --model ${model_q3_k} -t 1 -ngl 999 -s 1234 -n 256 --ignore-eos -p "I believe the meaning of life is" ) 2>&1 | tee -a $OUT/${ci}-tg-q3_k.log + (time ./bin/main --model ${model_q4_k} -t 1 -ngl 999 -s 1234 -n 256 --ignore-eos -p "I believe the meaning of life is" ) 2>&1 | tee -a $OUT/${ci}-tg-q4_k.log + (time ./bin/main --model ${model_q5_k} -t 1 -ngl 999 -s 1234 -n 256 --ignore-eos -p "I believe the meaning of life is" ) 2>&1 | tee -a $OUT/${ci}-tg-q5_k.log + (time ./bin/main --model ${model_q6_k} -t 1 -ngl 999 -s 1234 -n 256 --ignore-eos -p "I believe the meaning of life is" ) 2>&1 | tee -a $OUT/${ci}-tg-q6_k.log + + (time ./bin/perplexity --model ${model_f16} -f ${wiki_test} -t 1 -ngl 999 -c 2048 -b 512 --chunks 4 ) 2>&1 | tee -a $OUT/${ci}-tg-f16.log + (time ./bin/perplexity --model ${model_q8_0} -f ${wiki_test} -t 1 -ngl 999 -c 2048 -b 512 --chunks 4 ) 2>&1 | tee -a $OUT/${ci}-tg-q8_0.log + (time ./bin/perplexity --model ${model_q4_0} -f ${wiki_test} -t 1 -ngl 999 -c 2048 -b 512 --chunks 4 ) 2>&1 | tee -a $OUT/${ci}-tg-q4_0.log + (time ./bin/perplexity --model ${model_q4_1} -f ${wiki_test} -t 1 -ngl 999 -c 2048 -b 512 --chunks 4 ) 2>&1 | tee -a $OUT/${ci}-tg-q4_1.log + (time ./bin/perplexity --model ${model_q5_0} -f ${wiki_test} -t 1 -ngl 999 -c 2048 -b 512 --chunks 4 ) 2>&1 | tee -a $OUT/${ci}-tg-q5_0.log + (time ./bin/perplexity --model ${model_q5_1} -f ${wiki_test} -t 1 -ngl 999 -c 2048 -b 512 --chunks 4 ) 2>&1 | tee -a $OUT/${ci}-tg-q5_1.log + (time ./bin/perplexity --model ${model_q2_k} -f ${wiki_test} -t 1 -ngl 999 -c 2048 -b 512 --chunks 4 ) 2>&1 | tee -a $OUT/${ci}-tg-q2_k.log + (time ./bin/perplexity --model ${model_q3_k} -f ${wiki_test} -t 1 -ngl 999 -c 2048 -b 512 --chunks 4 ) 2>&1 | tee -a $OUT/${ci}-tg-q3_k.log + (time ./bin/perplexity --model ${model_q4_k} -f ${wiki_test} -t 1 -ngl 999 -c 2048 -b 512 --chunks 4 ) 2>&1 | tee -a $OUT/${ci}-tg-q4_k.log + (time ./bin/perplexity --model ${model_q5_k} -f ${wiki_test} -t 1 -ngl 999 -c 2048 -b 512 --chunks 4 ) 2>&1 | tee -a $OUT/${ci}-tg-q5_k.log + (time ./bin/perplexity --model ${model_q6_k} -f ${wiki_test} -t 1 -ngl 999 -c 2048 -b 512 --chunks 4 ) 2>&1 | tee -a $OUT/${ci}-tg-q6_k.log + + (time ./bin/imatrix --model ${model_f16} -f ${wiki_test} -t 1 -ngl 999 -c 2048 -b 512 --chunks 4 ) 2>&1 | tee -a $OUT/${ci}-imatrix.log + + (time ./bin/save-load-state --model ${model_q4_0} ) 2>&1 | tee -a $OUT/${ci}-save-load-state.log + + function check_ppl { + qnt="$1" + ppl=$(echo "$2" | grep -oE "[0-9]+\.[0-9]+" | tail -n 1) + + if [ $(echo "$ppl > 20.0" | bc) -eq 1 ]; then + printf ' - %s @ %s (FAIL: ppl > 20.0)\n' "$qnt" "$ppl" + return 20 + fi + + printf ' - %s @ %s OK\n' "$qnt" "$ppl" + return 0 + } + + check_ppl "f16" "$(cat $OUT/${ci}-tg-f16.log | grep "^\[1\]")" | tee -a $OUT/${ci}-ppl.log + check_ppl "q8_0" "$(cat $OUT/${ci}-tg-q8_0.log | grep "^\[1\]")" | tee -a $OUT/${ci}-ppl.log + check_ppl "q4_0" "$(cat $OUT/${ci}-tg-q4_0.log | grep "^\[1\]")" | tee -a $OUT/${ci}-ppl.log + check_ppl "q4_1" "$(cat $OUT/${ci}-tg-q4_1.log | grep "^\[1\]")" | tee -a $OUT/${ci}-ppl.log + check_ppl "q5_0" "$(cat $OUT/${ci}-tg-q5_0.log | grep "^\[1\]")" | tee -a $OUT/${ci}-ppl.log + check_ppl "q5_1" "$(cat $OUT/${ci}-tg-q5_1.log | grep "^\[1\]")" | tee -a $OUT/${ci}-ppl.log + check_ppl "q2_k" "$(cat $OUT/${ci}-tg-q2_k.log | grep "^\[1\]")" | tee -a $OUT/${ci}-ppl.log + check_ppl "q3_k" "$(cat $OUT/${ci}-tg-q3_k.log | grep "^\[1\]")" | tee -a $OUT/${ci}-ppl.log + check_ppl "q4_k" "$(cat $OUT/${ci}-tg-q4_k.log | grep "^\[1\]")" | tee -a $OUT/${ci}-ppl.log + check_ppl "q5_k" "$(cat $OUT/${ci}-tg-q5_k.log | grep "^\[1\]")" | tee -a $OUT/${ci}-ppl.log + check_ppl "q6_k" "$(cat $OUT/${ci}-tg-q6_k.log | grep "^\[1\]")" | tee -a $OUT/${ci}-ppl.log + + cat $OUT/${ci}-imatrix.log | grep "Final" >> $OUT/${ci}-imatrix-sum.log + + # lora + function compare_ppl { + qnt="$1" + ppl1=$(echo "$2" | grep -oE "[0-9]+\.[0-9]+" | tail -n 1) + ppl2=$(echo "$3" | grep -oE "[0-9]+\.[0-9]+" | tail -n 1) + + if [ $(echo "$ppl1 < $ppl2" | bc) -eq 1 ]; then + printf ' - %s @ %s (FAIL: %s > %s)\n' "$qnt" "$ppl" "$ppl1" "$ppl2" + return 20 + fi + + printf ' - %s @ %s %s OK\n' "$qnt" "$ppl1" "$ppl2" + return 0 + } + + path_lora="../models-mnt/mistral/7B-v2/lora" + path_shakespeare="../models-mnt/shakespeare" + + shakespeare="${path_shakespeare}/shakespeare.txt" + lora_shakespeare="${path_lora}/ggml-adapter-model.bin" + +# TODO - we need mistral lora + gg_wget ${path_lora} https://huggingface.co/slaren/open_llama_7b_v2_shakespeare_lora/resolve/main/adapter_config.json + gg_wget ${path_lora} https://huggingface.co/slaren/open_llama_7b_v2_shakespeare_lora/resolve/main/adapter_model.bin + gg_wget ${path_shakespeare} https://huggingface.co/slaren/open_llama_7b_v2_shakespeare_lora/resolve/main/shakespeare.txt + + python3 ../convert-lora-to-ggml.py ${path_lora} + + # f16 + (time ./bin/perplexity --model ${model_f16} -f ${shakespeare} -t 1 -ngl 999 -c 2048 -b 512 --chunks 3 ) 2>&1 | tee -a $OUT/${ci}-ppl-shakespeare-f16.log + (time ./bin/perplexity --model ${model_f16} -f ${shakespeare} --lora ${lora_shakespeare} -t 1 -ngl 999 -c 2048 -b 512 --chunks 3 ) 2>&1 | tee -a $OUT/${ci}-ppl-shakespeare-lora-f16.log + compare_ppl "f16 shakespeare" "$(cat $OUT/${ci}-ppl-shakespeare-f16.log | grep "^\[1\]")" "$(cat $OUT/${ci}-ppl-shakespeare-lora-f16.log | grep "^\[1\]")" | tee -a $OUT/${ci}-lora-ppl.log + + + set +e } function gg_sum_mistral_7b_v0_1 { + gg_printf '### %s\n\n' "${ci}" + + gg_printf 'MisTral 7B-v0.1:\n' + gg_printf '- status: %s\n' "$(cat $OUT/${ci}.exit)" + gg_printf '- perplexity:\n%s\n' "$(cat $OUT/${ci}-ppl.log)" + gg_printf '- imatrix:\n```\n%s\n```\n' "$(cat $OUT/${ci}-imatrix-sum.log)" + gg_printf '- lora:\n%s\n' "$(cat $OUT/${ci}-lora-ppl.log)" + gg_printf '- f16: \n```\n%s\n```\n' "$(cat $OUT/${ci}-tg-f16.log)" + gg_printf '- q8_0:\n```\n%s\n```\n' "$(cat $OUT/${ci}-tg-q8_0.log)" + gg_printf '- q4_0:\n```\n%s\n```\n' "$(cat $OUT/${ci}-tg-q4_0.log)" + gg_printf '- q4_1:\n```\n%s\n```\n' "$(cat $OUT/${ci}-tg-q4_1.log)" + gg_printf '- q5_0:\n```\n%s\n```\n' "$(cat $OUT/${ci}-tg-q5_0.log)" + gg_printf '- q5_1:\n```\n%s\n```\n' "$(cat $OUT/${ci}-tg-q5_1.log)" + gg_printf '- q2_k:\n```\n%s\n```\n' "$(cat $OUT/${ci}-tg-q2_k.log)" + gg_printf '- q3_k:\n```\n%s\n```\n' "$(cat $OUT/${ci}-tg-q3_k.log)" + gg_printf '- q4_k:\n```\n%s\n```\n' "$(cat $OUT/${ci}-tg-q4_k.log)" + gg_printf '- q5_k:\n```\n%s\n```\n' "$(cat $OUT/${ci}-tg-q5_k.log)" + gg_printf '- q6_k:\n```\n%s\n```\n' "$(cat $OUT/${ci}-tg-q6_k.log)" + gg_printf '- save-load-state: \n```\n%s\n```\n' "$(cat $OUT/${ci}-save-load-state.log)" + gg_printf '- shakespeare (f16):\n```\n%s\n```\n' "$(cat $OUT/${ci}-ppl-shakespeare-f16.log)" + gg_printf '- shakespeare (f16 lora):\n```\n%s\n```\n' "$(cat $OUT/${ci}-ppl-shakespeare-lora-f16.log)" } ## main @@ -537,6 +703,7 @@ if [ -z ${GG_BUILD_LOW_PERF} ]; then test $ret -eq 0 && gg_run open_llama_3b_v2 else test $ret -eq 0 && gg_run open_llama_7b_v2 + test $ret -eq 0 && gg_run mistral_7b_v0_1 fi fi fi