Skip to content

bert : add tests + fix quantization #5475

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 3 commits into from
Feb 13, 2024
Merged

bert : add tests + fix quantization #5475

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
ce730ad
llama : do not quantize pos embd and token type tensors
ggerganov Feb 13, 2024
09b5943
ci : add BERT tests
ggerganov Feb 13, 2024
1ab4f15
ci : do not do BERT tests on low-perf nodes
ggerganov Feb 13, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
46 changes: 46 additions & 0 deletions ci/run.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -568,6 +568,50 @@ function gg_sum_open_llama_7b_v2 {
#gg_printf '- shakespeare (q8_0 / f16 base lora):\n```\n%s\n```\n' "$(cat $OUT/${ci}-ppl-shakespeare-lora-q8_0-f16.log)"
}

# bge-small

function gg_run_embd_bge_small {
cd ${SRC}

gg_wget models-mnt/bge-small/ https://huggingface.co/BAAI/bge-small-en-v1.5/raw/main/config.json
gg_wget models-mnt/bge-small/ https://huggingface.co/BAAI/bge-small-en-v1.5/resolve/main/tokenizer.model
gg_wget models-mnt/bge-small/ https://huggingface.co/BAAI/bge-small-en-v1.5/raw/main/tokenizer_config.json
gg_wget models-mnt/bge-small/ https://huggingface.co/BAAI/bge-small-en-v1.5/raw/main/special_tokens_map.json
gg_wget models-mnt/bge-small/ https://huggingface.co/BAAI/bge-small-en-v1.5/resolve/main/pytorch_model.bin
gg_wget models-mnt/bge-small/ https://huggingface.co/BAAI/bge-small-en-v1.5/raw/main/sentence_bert_config.json
gg_wget models-mnt/bge-small/ https://huggingface.co/BAAI/bge-small-en-v1.5/raw/main/vocab.txt

path_models="../models-mnt/bge-small"

rm -rf build-ci-release && mkdir build-ci-release && cd build-ci-release

set -e

(time cmake -DCMAKE_BUILD_TYPE=Release ${CMAKE_EXTRA} .. ) 2>&1 | tee -a $OUT/${ci}-cmake.log
(time make -j ) 2>&1 | tee -a $OUT/${ci}-make.log

python3 ../convert-hf-to-gguf.py ${path_models}

model_f16="${path_models}/ggml-model-f16.gguf"
model_q8_0="${path_models}/ggml-model-q8_0.gguf"

./bin/quantize ${model_f16} ${model_q8_0} q8_0

(time ./bin/embedding --model ${model_f16} -p "I believe the meaning of life is" ) 2>&1 | tee -a $OUT/${ci}-tg-f16.log
(time ./bin/embedding --model ${model_q8_0} -p "I believe the meaning of life is" ) 2>&1 | tee -a $OUT/${ci}-tg-q8_0.log

set +e
}

function gg_sum_embd_bge_small {
gg_printf '### %s\n\n' "${ci}"

gg_printf 'BGE Small (BERT):\n'
gg_printf '- status: %s\n' "$(cat $OUT/${ci}.exit)"
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)"
}

## main

if [ -z ${GG_BUILD_LOW_PERF} ]; then
Expand All @@ -591,6 +635,8 @@ test $ret -eq 0 && gg_run ctest_debug
test $ret -eq 0 && gg_run ctest_release

if [ -z ${GG_BUILD_LOW_PERF} ]; then
test $ret -eq 0 && gg_run embd_bge_small

if [ -z ${GG_BUILD_VRAM_GB} ] || [ ${GG_BUILD_VRAM_GB} -ge 8 ]; then
if [ -z ${GG_BUILD_CUDA} ]; then
test $ret -eq 0 && gg_run open_llama_3b_v2
Expand Down
6 changes: 5 additions & 1 deletion llama.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -10444,7 +10444,11 @@ static void llama_model_quantize_internal(const std::string & fname_inp, const s
quantize &= !params->only_copy;

// do not quantize expert gating tensors
quantize &= name.find("ffn_gate_inp.weight") == std::string::npos;
quantize &= name != LLM_TN(model.arch)(LLM_TENSOR_FFN_GATE_INP, "weight");

// do not quantize positional embeddings and token types (BERT)
quantize &= name != LLM_TN(model.arch)(LLM_TENSOR_POS_EMBD, "weight");
quantize &= name != LLM_TN(model.arch)(LLM_TENSOR_TOKEN_TYPES, "weight");

enum ggml_type new_type;
void * new_data;
Expand Down