feat: update go-gpt2 (#359)

Signed-off-by: mudler <mudler@mocaccino.org>
This commit is contained in:
Ettore Di Giacinto 2023-05-23 21:47:47 +02:00 committed by GitHub
parent 43d3fb3eba
commit 9decd0813c
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
10 changed files with 131 additions and 156 deletions

View file

@ -6,7 +6,7 @@ BINARY_NAME=local-ai
GOLLAMA_VERSION?=ccf23adfb278c0165d388389a5d60f3fe38e4854
GPT4ALL_REPO?=https://github.com/nomic-ai/gpt4all
GPT4ALL_VERSION?=8119ff4df0a99bde44255db2b8c7290b5582ac2b
GOGPT2_VERSION?=7bff56f0224502c1c9ed6258d2a17e8084628827
GOGGMLTRANSFORMERS_VERSION?=14fd6c9
RWKV_REPO?=https://github.com/donomii/go-rwkv.cpp
RWKV_VERSION?=07166da10cb2a9e8854395a4f210464dcea76e47
WHISPER_CPP_VERSION?=041be06d5881d3c759cc4ed45d655804361237cd
@ -29,8 +29,8 @@ WHITE := $(shell tput -Txterm setaf 7)
CYAN := $(shell tput -Txterm setaf 6)
RESET := $(shell tput -Txterm sgr0)
C_INCLUDE_PATH=$(shell pwd)/go-llama:$(shell pwd)/go-stable-diffusion/:$(shell pwd)/gpt4all/gpt4all-bindings/golang/:$(shell pwd)/go-gpt2:$(shell pwd)/go-rwkv:$(shell pwd)/whisper.cpp:$(shell pwd)/go-bert:$(shell pwd)/bloomz
LIBRARY_PATH=$(shell pwd)/go-llama:$(shell pwd)/go-stable-diffusion/:$(shell pwd)/gpt4all/gpt4all-bindings/golang/:$(shell pwd)/go-gpt2:$(shell pwd)/go-rwkv:$(shell pwd)/whisper.cpp:$(shell pwd)/go-bert:$(shell pwd)/bloomz
C_INCLUDE_PATH=$(shell pwd)/go-llama:$(shell pwd)/go-stable-diffusion/:$(shell pwd)/gpt4all/gpt4all-bindings/golang/:$(shell pwd)/go-ggml-transformers:$(shell pwd)/go-rwkv:$(shell pwd)/whisper.cpp:$(shell pwd)/go-bert:$(shell pwd)/bloomz
LIBRARY_PATH=$(shell pwd)/go-llama:$(shell pwd)/go-stable-diffusion/:$(shell pwd)/gpt4all/gpt4all-bindings/golang/:$(shell pwd)/go-ggml-transformers:$(shell pwd)/go-rwkv:$(shell pwd)/whisper.cpp:$(shell pwd)/go-bert:$(shell pwd)/bloomz
ifeq ($(BUILD_TYPE),openblas)
CGO_LDFLAGS+=-lopenblas
@ -117,23 +117,23 @@ gpt4all/gpt4all-bindings/golang/libgpt4all.a: gpt4all
$(MAKE) -C gpt4all/gpt4all-bindings/golang/ libgpt4all.a
## CEREBRAS GPT
go-gpt2:
git clone --recurse-submodules https://github.com/go-skynet/go-gpt2.cpp go-gpt2
cd go-gpt2 && git checkout -b build $(GOGPT2_VERSION) && git submodule update --init --recursive --depth 1
go-ggml-transformers:
git clone --recurse-submodules https://github.com/go-skynet/go-ggml-transformers.cpp go-ggml-transformers
cd go-ggml-transformers && git checkout -b build $(GOGPT2_VERSION) && git submodule update --init --recursive --depth 1
# This is hackish, but needed as both go-llama and go-gpt4allj have their own version of ggml..
@find ./go-gpt2 -type f -name "*.c" -exec sed -i'' -e 's/ggml_/ggml_gpt2_/g' {} +
@find ./go-gpt2 -type f -name "*.cpp" -exec sed -i'' -e 's/ggml_/ggml_gpt2_/g' {} +
@find ./go-gpt2 -type f -name "*.h" -exec sed -i'' -e 's/ggml_/ggml_gpt2_/g' {} +
@find ./go-gpt2 -type f -name "*.cpp" -exec sed -i'' -e 's/gpt_print_usage/gpt2_print_usage/g' {} +
@find ./go-gpt2 -type f -name "*.h" -exec sed -i'' -e 's/gpt_print_usage/gpt2_print_usage/g' {} +
@find ./go-gpt2 -type f -name "*.cpp" -exec sed -i'' -e 's/gpt_params_parse/gpt2_params_parse/g' {} +
@find ./go-gpt2 -type f -name "*.h" -exec sed -i'' -e 's/gpt_params_parse/gpt2_params_parse/g' {} +
@find ./go-gpt2 -type f -name "*.cpp" -exec sed -i'' -e 's/gpt_random_prompt/gpt2_random_prompt/g' {} +
@find ./go-gpt2 -type f -name "*.h" -exec sed -i'' -e 's/gpt_random_prompt/gpt2_random_prompt/g' {} +
@find ./go-gpt2 -type f -name "*.cpp" -exec sed -i'' -e 's/json_/json_gpt2_/g' {} +
@find ./go-ggml-transformers -type f -name "*.c" -exec sed -i'' -e 's/ggml_/ggml_gpt2_/g' {} +
@find ./go-ggml-transformers -type f -name "*.cpp" -exec sed -i'' -e 's/ggml_/ggml_gpt2_/g' {} +
@find ./go-ggml-transformers -type f -name "*.h" -exec sed -i'' -e 's/ggml_/ggml_gpt2_/g' {} +
@find ./go-ggml-transformers -type f -name "*.cpp" -exec sed -i'' -e 's/gpt_print_usage/gpt2_print_usage/g' {} +
@find ./go-ggml-transformers -type f -name "*.h" -exec sed -i'' -e 's/gpt_print_usage/gpt2_print_usage/g' {} +
@find ./go-ggml-transformers -type f -name "*.cpp" -exec sed -i'' -e 's/gpt_params_parse/gpt2_params_parse/g' {} +
@find ./go-ggml-transformers -type f -name "*.h" -exec sed -i'' -e 's/gpt_params_parse/gpt2_params_parse/g' {} +
@find ./go-ggml-transformers -type f -name "*.cpp" -exec sed -i'' -e 's/gpt_random_prompt/gpt2_random_prompt/g' {} +
@find ./go-ggml-transformers -type f -name "*.h" -exec sed -i'' -e 's/gpt_random_prompt/gpt2_random_prompt/g' {} +
@find ./go-ggml-transformers -type f -name "*.cpp" -exec sed -i'' -e 's/json_/json_gpt2_/g' {} +
go-gpt2/libgpt2.a: go-gpt2
$(MAKE) -C go-gpt2 libgpt2.a
go-ggml-transformers/libtransformers.a: go-ggml-transformers
$(MAKE) -C go-ggml-transformers libtransformers.a
whisper.cpp:
git clone https://github.com/ggerganov/whisper.cpp.git
@ -155,21 +155,21 @@ go-llama/libbinding.a: go-llama
replace:
$(GOCMD) mod edit -replace github.com/go-skynet/go-llama.cpp=$(shell pwd)/go-llama
$(GOCMD) mod edit -replace github.com/nomic-ai/gpt4all/gpt4all-bindings/golang=$(shell pwd)/gpt4all/gpt4all-bindings/golang
$(GOCMD) mod edit -replace github.com/go-skynet/go-gpt2.cpp=$(shell pwd)/go-gpt2
$(GOCMD) mod edit -replace github.com/go-skynet/go-ggml-transformers.cpp=$(shell pwd)/go-ggml-transformers
$(GOCMD) mod edit -replace github.com/donomii/go-rwkv.cpp=$(shell pwd)/go-rwkv
$(GOCMD) mod edit -replace github.com/ggerganov/whisper.cpp=$(shell pwd)/whisper.cpp
$(GOCMD) mod edit -replace github.com/go-skynet/go-bert.cpp=$(shell pwd)/go-bert
$(GOCMD) mod edit -replace github.com/go-skynet/bloomz.cpp=$(shell pwd)/bloomz
$(GOCMD) mod edit -replace github.com/mudler/go-stable-diffusion=$(shell pwd)/go-stable-diffusion
prepare-sources: go-llama go-gpt2 gpt4all go-rwkv whisper.cpp go-bert bloomz go-stable-diffusion replace
prepare-sources: go-llama go-ggml-transformers gpt4all go-rwkv whisper.cpp go-bert bloomz go-stable-diffusion replace
$(GOCMD) mod download
## GENERIC
rebuild: ## Rebuilds the project
$(MAKE) -C go-llama clean
$(MAKE) -C gpt4all/gpt4all-bindings/golang/ clean
$(MAKE) -C go-gpt2 clean
$(MAKE) -C go-ggml-transformers clean
$(MAKE) -C go-rwkv clean
$(MAKE) -C whisper.cpp clean
$(MAKE) -C go-stable-diffusion clean
@ -177,13 +177,13 @@ rebuild: ## Rebuilds the project
$(MAKE) -C bloomz clean
$(MAKE) build
prepare: prepare-sources gpt4all/gpt4all-bindings/golang/libgpt4all.a $(OPTIONAL_TARGETS) go-llama/libbinding.a go-bert/libgobert.a go-gpt2/libgpt2.a go-rwkv/librwkv.a whisper.cpp/libwhisper.a bloomz/libbloomz.a ## Prepares for building
prepare: prepare-sources gpt4all/gpt4all-bindings/golang/libgpt4all.a $(OPTIONAL_TARGETS) go-llama/libbinding.a go-bert/libgobert.a go-ggml-transformers/libtransformers.a go-rwkv/librwkv.a whisper.cpp/libwhisper.a bloomz/libbloomz.a ## Prepares for building
clean: ## Remove build related file
rm -fr ./go-llama
rm -rf ./gpt4all
rm -rf ./go-stable-diffusion
rm -rf ./go-gpt2
rm -rf ./go-ggml-transformers
rm -rf ./go-rwkv
rm -rf ./go-bert
rm -rf ./bloomz
@ -213,7 +213,7 @@ run: prepare ## run local-ai
test-models/testmodel:
mkdir test-models
mkdir test-dir
wget https://huggingface.co/concedo/cerebras-111M-ggml/resolve/main/cerberas-111m-q4_0.bin -O test-models/testmodel
wget https://huggingface.co/nnakasato/ggml-model-test/resolve/main/ggml-model-q4.bin -O test-models/testmodel
wget https://huggingface.co/ggerganov/whisper.cpp/resolve/main/ggml-base.en.bin -O test-models/whisper-en
wget https://huggingface.co/skeskinen/ggml/resolve/main/all-MiniLM-L6-v2/ggml-model-q4_0.bin -O test-models/bert
wget https://cdn.openai.com/whisper/draft-20220913a/micro-machines.wav -O test-dir/audio.wav