dearwolf/LocalAI
1
0
Fork 0
mirror of https://github.com/mudler/LocalAI.git synced 2025-06-12 22:04:59 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 13

feat(transformers): add embeddings with Automodel (#1308)

Browse source 
* Update huggingface.py

Switch SentenceTransformer for AutoModel in order to set trust_remote_code needed to use the encode method with embeddings models like jinai-v2

Signed-off-by: Lucas Hänke de Cansino <lhc@next-boss.eu>

* feat(transformers): split in separate backend

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

---------

Signed-off-by: Lucas Hänke de Cansino <lhc@next-boss.eu>
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Co-authored-by: Lucas Hänke de Cansino <lhc@next-boss.eu>
This commit is contained in:
Ettore Di Giacinto 2023-11-20 21:21:17 +01:00 • committed by GitHub
parent ff9afdb0fe
commit 92cbc4d516
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
23 changed files with 783 additions and 34 deletions
Download patch file Download diff file Expand all files Collapse all files

20
Makefile
View file

@ -296,7 +296,7 @@ test: prepare test-models/testmodel grpcs
@echo 'Running tests'
export GO_TAGS="tts stablediffusion"
$(MAKE) prepare-test
HUGGINGFACE_GRPC=$(abspath ./)/backend/python/huggingface/run.sh TEST_DIR=$(abspath ./)/test-dir/ FIXTURES=$(abspath ./)/tests/fixtures CONFIG_FILE=$(abspath ./)/test-models/config.yaml MODELS_PATH=$(abspath ./)/test-models \
HUGGINGFACE_GRPC=$(abspath ./)/backend/python/sentencetransformers/run.sh TEST_DIR=$(abspath ./)/test-dir/ FIXTURES=$(abspath ./)/tests/fixtures CONFIG_FILE=$(abspath ./)/test-models/config.yaml MODELS_PATH=$(abspath ./)/test-models \
$(GOCMD) run github.com/onsi/ginkgo/v2/ginkgo --label-filter="!gpt4all && !llama && !llama-gguf" --flake-attempts 5 --fail-fast -v -r ./api ./pkg
$(MAKE) test-gpt4all
$(MAKE) test-llama
@ -367,13 +367,14 @@ protogen-go:
backend/backend.proto
protogen-python:
python3 -m grpc_tools.protoc -Ipkg/grpc/proto/ --python_out=backend/python/huggingface/ --grpc_python_out=backend/python/huggingface/ backend/backend.proto
python3 -m grpc_tools.protoc -Ipkg/grpc/proto/ --python_out=backend/python/autogptq/ --grpc_python_out=backend/python/autogptq/ backend/backend.proto
python3 -m grpc_tools.protoc -Ipkg/grpc/proto/ --python_out=backend/python/exllama/ --grpc_python_out=backend/python/exllama/ backend/backend.proto
python3 -m grpc_tools.protoc -Ipkg/grpc/proto/ --python_out=backend/python/bark/ --grpc_python_out=backend/python/bark/ backend/backend.proto
python3 -m grpc_tools.protoc -Ipkg/grpc/proto/ --python_out=backend/python/diffusers/ --grpc_python_out=backend/python/diffusers/ backend/backend.proto
python3 -m grpc_tools.protoc -Ipkg/grpc/proto/ --python_out=backend/python/vall-e-x/ --grpc_python_out=backend/python/vall-e-x/ backend/backend.proto
python3 -m grpc_tools.protoc -Ipkg/grpc/proto/ --python_out=backend/python/vllm/ --grpc_python_out=backend/python/vllm/ backend/backend.proto
python3 -m grpc_tools.protoc -Ibackend/ --python_out=backend/python/sentencetransformers/ --grpc_python_out=backend/python/sentencetransformers/ backend/backend.proto
python3 -m grpc_tools.protoc -Ibackend/ --python_out=backend/python/transformers/ --grpc_python_out=backend/python/transformers/ backend/backend.proto
python3 -m grpc_tools.protoc -Ibackend/ --python_out=backend/python/autogptq/ --grpc_python_out=backend/python/autogptq/ backend/backend.proto
python3 -m grpc_tools.protoc -Ibackend/ --python_out=backend/python/exllama/ --grpc_python_out=backend/python/exllama/ backend/backend.proto
python3 -m grpc_tools.protoc -Ibackend/ --python_out=backend/python/bark/ --grpc_python_out=backend/python/bark/ backend/backend.proto
python3 -m grpc_tools.protoc -Ibackend/ --python_out=backend/python/diffusers/ --grpc_python_out=backend/python/diffusers/ backend/backend.proto
python3 -m grpc_tools.protoc -Ibackend/ --python_out=backend/python/vall-e-x/ --grpc_python_out=backend/python/vall-e-x/ backend/backend.proto
python3 -m grpc_tools.protoc -Ibackend/ --python_out=backend/python/vllm/ --grpc_python_out=backend/python/vllm/ backend/backend.proto
## GRPC
# Note: it is duplicated in the Dockerfile
@ -382,7 +383,8 @@ prepare-extra-conda-environments:
$(MAKE) -C backend/python/bark
$(MAKE) -C backend/python/diffusers
$(MAKE) -C backend/python/vllm
$(MAKE) -C backend/python/huggingface
$(MAKE) -C backend/python/sentencetransformers
$(MAKE) -C backend/python/transformers
$(MAKE) -C backend/python/vall-e-x
$(MAKE) -C backend/python/exllama