mirror of
https://github.com/mudler/LocalAI.git
synced 2026-02-03 11:13:31 -05:00
Compare commits
1 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
ca65e9ee9b |
43
.github/workflows/release.yaml
vendored
43
.github/workflows/release.yaml
vendored
@@ -100,13 +100,7 @@ jobs:
|
||||
go install google.golang.org/protobuf/cmd/protoc-gen-go@v1.34.0
|
||||
export PATH=$PATH:$GOPATH/bin
|
||||
export PATH=/usr/local/cuda/bin:$PATH
|
||||
sudo rm -rf /usr/aarch64-linux-gnu/lib/libstdc++.so.6
|
||||
sudo cp -rf /usr/aarch64-linux-gnu/lib/libstdc++.so* /usr/aarch64-linux-gnu/lib/libstdc++.so.6
|
||||
GO_TAGS=p2p \
|
||||
BACKEND_LIBS="./grpc/cmake/cross_build/third_party/re2/libre2.a ./grpc/cmake/cross_build/libgrpc.a ./grpc/cmake/cross_build/libgrpc++.a ./grpc/cmake/cross_build/third_party/protobuf/libprotobuf.a /usr/aarch64-linux-gnu/lib/libc.so.6 /usr/aarch64-linux-gnu/lib/libstdc++.so.6 /usr/aarch64-linux-gnu/lib/libgomp.so.1 /usr/aarch64-linux-gnu/lib/libm.so.6 /usr/aarch64-linux-gnu/lib/libgcc_s.so.1 /usr/aarch64-linux-gnu/lib/libdl.so.2 /usr/aarch64-linux-gnu/lib/libpthread.so.0" \
|
||||
GOOS=linux \
|
||||
GOARCH=arm64 \
|
||||
CMAKE_ARGS="-DProtobuf_INCLUDE_DIRS=$CROSS_STAGING_PREFIX/include -DProtobuf_DIR=$CROSS_STAGING_PREFIX/lib/cmake/protobuf -DgRPC_DIR=$CROSS_STAGING_PREFIX/lib/cmake/grpc -DCMAKE_TOOLCHAIN_FILE=$CMAKE_CROSS_TOOLCHAIN -DCMAKE_C_COMPILER=aarch64-linux-gnu-gcc -DCMAKE_CXX_COMPILER=aarch64-linux-gnu-g++" make dist-cross-linux-arm64
|
||||
GO_TAGS=p2p GOOS=linux GOARCH=arm64 CMAKE_ARGS="-DProtobuf_INCLUDE_DIRS=$CROSS_STAGING_PREFIX/include -DProtobuf_DIR=$CROSS_STAGING_PREFIX/lib/cmake/protobuf -DgRPC_DIR=$CROSS_STAGING_PREFIX/lib/cmake/grpc -DCMAKE_TOOLCHAIN_FILE=$CMAKE_CROSS_TOOLCHAIN -DCMAKE_C_COMPILER=aarch64-linux-gnu-gcc -DCMAKE_CXX_COMPILER=aarch64-linux-gnu-g++" make dist-cross-linux-arm64
|
||||
- uses: actions/upload-artifact@v4
|
||||
with:
|
||||
name: LocalAI-linux-arm64
|
||||
@@ -117,13 +111,7 @@ jobs:
|
||||
with:
|
||||
files: |
|
||||
release/*
|
||||
- name: Setup tmate session if tests fail
|
||||
if: ${{ failure() }}
|
||||
uses: mxschmitt/action-tmate@v3.18
|
||||
with:
|
||||
detached: true
|
||||
connect-timeout-seconds: 180
|
||||
limit-access-to-actor: true
|
||||
|
||||
build-linux:
|
||||
runs-on: arc-runner-set
|
||||
steps:
|
||||
@@ -202,7 +190,6 @@ jobs:
|
||||
- name: Install gRPC
|
||||
run: |
|
||||
cd grpc && cd cmake/build && sudo make --jobs 5 --output-sync=target install
|
||||
# BACKEND_LIBS needed for gpu-workload: /opt/intel/oneapi/*/lib/libiomp5.so /opt/intel/oneapi/*/lib/libmkl_core.so /opt/intel/oneapi/*/lib/libmkl_core.so.2 /opt/intel/oneapi/*/lib/libmkl_intel_ilp64.so /opt/intel/oneapi/*/lib/libmkl_intel_ilp64.so.2 /opt/intel/oneapi/*/lib/libmkl_sycl_blas.so /opt/intel/oneapi/*/lib/libmkl_sycl_blas.so.4 /opt/intel/oneapi/*/lib/libmkl_tbb_thread.so /opt/intel/oneapi/*/lib/libmkl_tbb_thread.so.2 /opt/intel/oneapi/*/lib/libsycl.so /opt/intel/oneapi/*/lib/libsycl.so.7 /opt/intel/oneapi/*/lib/libsycl.so.7.1.0 /opt/rocm-*/lib/libamdhip64.so /opt/rocm-*/lib/libamdhip64.so.5 /opt/rocm-*/lib/libamdhip64.so.6 /opt/rocm-*/lib/libamdhip64.so.6.1.60100 /opt/rocm-*/lib/libhipblas.so /opt/rocm-*/lib/libhipblas.so.2 /opt/rocm-*/lib/libhipblas.so.2.1.60100 /opt/rocm-*/lib/librocblas.so /opt/rocm-*/lib/librocblas.so.4 /opt/rocm-*/lib/librocblas.so.4.1.60100 /usr/lib/x86_64-linux-gnu/libstdc++.so.6 /usr/lib/x86_64-linux-gnu/libOpenCL.so.1 /usr/lib/x86_64-linux-gnu/libOpenCL.so.1.0.0 /usr/lib/x86_64-linux-gnu/libm.so.6 /usr/lib/x86_64-linux-gnu/libgcc_s.so.1 /usr/lib/x86_64-linux-gnu/libc.so.6 /usr/lib/x86_64-linux-gnu/librt.so.1 /usr/local/cuda-*/targets/x86_64-linux/lib/libcublas.so /usr/local/cuda-*/targets/x86_64-linux/lib/libcublasLt.so /usr/local/cuda-*/targets/x86_64-linux/lib/libcudart.so /usr/local/cuda-*/targets/x86_64-linux/lib/stubs/libcuda.so
|
||||
- name: Build
|
||||
id: build
|
||||
run: |
|
||||
@@ -212,9 +199,7 @@ jobs:
|
||||
export PATH=/usr/local/cuda/bin:$PATH
|
||||
export PATH=/opt/rocm/bin:$PATH
|
||||
source /opt/intel/oneapi/setvars.sh
|
||||
GO_TAGS=p2p \
|
||||
BACKEND_LIBS="/usr/lib/x86_64-linux-gnu/libstdc++.so.6 /usr/lib/x86_64-linux-gnu/libm.so.6 /usr/lib/x86_64-linux-gnu/libgcc_s.so.1 /usr/lib/x86_64-linux-gnu/libc.so.6 /usr/lib/x86_64-linux-gnu/libgomp.so.1" \
|
||||
make -j4 dist
|
||||
GO_TAGS=p2p make -j4 dist
|
||||
- uses: actions/upload-artifact@v4
|
||||
with:
|
||||
name: LocalAI-linux
|
||||
@@ -225,13 +210,7 @@ jobs:
|
||||
with:
|
||||
files: |
|
||||
release/*
|
||||
- name: Setup tmate session if tests fail
|
||||
if: ${{ failure() }}
|
||||
uses: mxschmitt/action-tmate@v3.18
|
||||
with:
|
||||
detached: true
|
||||
connect-timeout-seconds: 180
|
||||
limit-access-to-actor: true
|
||||
|
||||
build-stablediffusion:
|
||||
runs-on: ubuntu-latest
|
||||
steps:
|
||||
@@ -278,6 +257,10 @@ jobs:
|
||||
with:
|
||||
go-version: '1.21.x'
|
||||
cache: false
|
||||
- name: Setup tmate session if tests fail
|
||||
uses: mxschmitt/action-tmate@v3.18
|
||||
with:
|
||||
limit-access-to-actor: true
|
||||
- name: Dependencies
|
||||
run: |
|
||||
brew install protobuf grpc
|
||||
@@ -289,8 +272,7 @@ jobs:
|
||||
export C_INCLUDE_PATH=/usr/local/include
|
||||
export CPLUS_INCLUDE_PATH=/usr/local/include
|
||||
export PATH=$PATH:$GOPATH/bin
|
||||
|
||||
BACKEND_LIBS="$(ls /opt/homebrew/opt/grpc/lib/*.dylib /opt/homebrew/opt/re2/lib/*.dylib /opt/homebrew/opt/openssl@3/lib/*.dylib /opt/homebrew/opt/protobuf/lib/*.dylib /opt/homebrew/opt/abseil/lib/*.dylib | xargs)" GO_TAGS=p2p make dist
|
||||
GO_TAGS=p2p make dist
|
||||
- uses: actions/upload-artifact@v4
|
||||
with:
|
||||
name: LocalAI-MacOS-arm64
|
||||
@@ -301,10 +283,3 @@ jobs:
|
||||
with:
|
||||
files: |
|
||||
release/*
|
||||
- name: Setup tmate session if tests fail
|
||||
if: ${{ failure() }}
|
||||
uses: mxschmitt/action-tmate@v3.18
|
||||
with:
|
||||
detached: true
|
||||
connect-timeout-seconds: 180
|
||||
limit-access-to-actor: true
|
||||
17
Makefile
17
Makefile
@@ -5,7 +5,7 @@ BINARY_NAME=local-ai
|
||||
|
||||
# llama.cpp versions
|
||||
GOLLAMA_STABLE_VERSION?=2b57a8ae43e4699d3dc5d1496a1ccd42922993be
|
||||
CPPLLAMA_VERSION?=21be9cab94e0b5b53cb6edeeebf8c8c799baad03
|
||||
CPPLLAMA_VERSION?=963552903f51043ee947a8deeaaa7ec00bc3f1a4
|
||||
|
||||
# gpt4all version
|
||||
GPT4ALL_REPO?=https://github.com/nomic-ai/gpt4all
|
||||
@@ -16,7 +16,7 @@ RWKV_REPO?=https://github.com/donomii/go-rwkv.cpp
|
||||
RWKV_VERSION?=661e7ae26d442f5cfebd2a0881b44e8c55949ec6
|
||||
|
||||
# whisper.cpp version
|
||||
WHISPER_CPP_VERSION?=b29b3b29240aac8b71ce8e5a4360c1f1562ad66f
|
||||
WHISPER_CPP_VERSION?=420b6abc54008ab634f5887dc45bd77122c2f320
|
||||
|
||||
# bert.cpp version
|
||||
BERT_VERSION?=710044b124545415f555e4260d16b146c725a6e4
|
||||
@@ -313,10 +313,6 @@ build: prepare backend-assets grpcs ## Build the project
|
||||
$(info ${GREEN}I BUILD_TYPE: ${YELLOW}$(BUILD_TYPE)${RESET})
|
||||
$(info ${GREEN}I GO_TAGS: ${YELLOW}$(GO_TAGS)${RESET})
|
||||
$(info ${GREEN}I LD_FLAGS: ${YELLOW}$(LD_FLAGS)${RESET})
|
||||
ifneq ($(BACKEND_LIBS),)
|
||||
$(MAKE) backend-assets/lib
|
||||
cp -r $(BACKEND_LIBS) backend-assets/lib/
|
||||
endif
|
||||
CGO_LDFLAGS="$(CGO_LDFLAGS)" $(GOCMD) build -ldflags "$(LD_FLAGS)" -tags "$(GO_TAGS)" -o $(BINARY_NAME) ./
|
||||
|
||||
build-minimal:
|
||||
@@ -325,11 +321,8 @@ build-minimal:
|
||||
build-api:
|
||||
BUILD_GRPC_FOR_BACKEND_LLAMA=true BUILD_API_ONLY=true GO_TAGS=none $(MAKE) build
|
||||
|
||||
backend-assets/lib:
|
||||
mkdir -p backend-assets/lib
|
||||
|
||||
dist:
|
||||
$(MAKE) backend-assets/grpc/llama-cpp-avx2
|
||||
STATIC=true $(MAKE) backend-assets/grpc/llama-cpp-avx2
|
||||
ifeq ($(OS),Darwin)
|
||||
$(info ${GREEN}I Skip CUDA/hipblas build on MacOS${RESET})
|
||||
else
|
||||
@@ -338,7 +331,7 @@ else
|
||||
$(MAKE) backend-assets/grpc/llama-cpp-sycl_f16
|
||||
$(MAKE) backend-assets/grpc/llama-cpp-sycl_f32
|
||||
endif
|
||||
STATIC=true $(MAKE) build
|
||||
$(MAKE) build
|
||||
mkdir -p release
|
||||
# if BUILD_ID is empty, then we don't append it to the binary name
|
||||
ifeq ($(BUILD_ID),)
|
||||
@@ -351,7 +344,7 @@ endif
|
||||
|
||||
dist-cross-linux-arm64:
|
||||
CMAKE_ARGS="$(CMAKE_ARGS) -DLLAMA_NATIVE=off" GRPC_BACKENDS="backend-assets/grpc/llama-cpp-fallback backend-assets/grpc/llama-cpp-grpc backend-assets/util/llama-cpp-rpc-server" \
|
||||
STATIC=true $(MAKE) build
|
||||
$(MAKE) build
|
||||
mkdir -p release
|
||||
# if BUILD_ID is empty, then we don't append it to the binary name
|
||||
ifeq ($(BUILD_ID),)
|
||||
|
||||
@@ -65,7 +65,6 @@ docker run -ti --name local-ai -p 8080:8080 localai/localai:latest-aio-cpu
|
||||
|
||||
[Roadmap](https://github.com/mudler/LocalAI/issues?q=is%3Aissue+is%3Aopen+label%3Aroadmap)
|
||||
|
||||
- 🆕 You can browse now the model gallery without LocalAI! Check out https://models.localai.io
|
||||
- 🔥🔥 Decentralized llama.cpp: https://github.com/mudler/LocalAI/pull/2343 (peer2peer llama.cpp!) 👉 Docs https://localai.io/features/distribute/
|
||||
- 🔥🔥 Openvoice: https://github.com/mudler/LocalAI/pull/2334
|
||||
- 🆕 Function calls without grammars and mixed mode: https://github.com/mudler/LocalAI/pull/2328
|
||||
|
||||
@@ -43,7 +43,6 @@ type RunCMD struct {
|
||||
Address string `env:"LOCALAI_ADDRESS,ADDRESS" default:":8080" help:"Bind address for the API server" group:"api"`
|
||||
CORS bool `env:"LOCALAI_CORS,CORS" help:"" group:"api"`
|
||||
CORSAllowOrigins string `env:"LOCALAI_CORS_ALLOW_ORIGINS,CORS_ALLOW_ORIGINS" group:"api"`
|
||||
LibraryPath string `env:"LOCALAI_LIBRARY_PATH,LIBRARY_PATH" help:"Path to the library directory (for e.g. external libraries used by backends)" default:"/usr/share/local-ai/libs" group:"backends"`
|
||||
CSRF bool `env:"LOCALAI_CSRF" help:"Enables fiber CSRF middleware" group:"api"`
|
||||
UploadLimit int `env:"LOCALAI_UPLOAD_LIMIT,UPLOAD_LIMIT" default:"15" help:"Default upload-limit in MB" group:"api"`
|
||||
APIKeys []string `env:"LOCALAI_API_KEY,API_KEY" help:"List of API Keys to enable API authentication. When this is set, all the requests must be authenticated with one of these API keys" group:"api"`
|
||||
@@ -81,7 +80,6 @@ func (r *RunCMD) Run(ctx *cliContext.Context) error {
|
||||
config.WithCors(r.CORS),
|
||||
config.WithCorsAllowOrigins(r.CORSAllowOrigins),
|
||||
config.WithCsrf(r.CSRF),
|
||||
config.WithLibPath(r.LibraryPath),
|
||||
config.WithThreads(r.Threads),
|
||||
config.WithBackendAssets(ctx.BackendAssets),
|
||||
config.WithBackendAssetsOutput(r.BackendAssetsPath),
|
||||
|
||||
@@ -15,7 +15,6 @@ type ApplicationConfig struct {
|
||||
Context context.Context
|
||||
ConfigFile string
|
||||
ModelPath string
|
||||
LibPath string
|
||||
UploadLimitMB, Threads, ContextSize int
|
||||
DisableWebUI bool
|
||||
F16 bool
|
||||
@@ -102,12 +101,6 @@ func WithModelLibraryURL(url string) AppOption {
|
||||
}
|
||||
}
|
||||
|
||||
func WithLibPath(path string) AppOption {
|
||||
return func(o *ApplicationConfig) {
|
||||
o.LibPath = path
|
||||
}
|
||||
}
|
||||
|
||||
var EnableWatchDog = func(o *ApplicationConfig) {
|
||||
o.WatchDog = true
|
||||
}
|
||||
|
||||
@@ -9,7 +9,6 @@ import (
|
||||
"github.com/go-skynet/LocalAI/core/services"
|
||||
"github.com/go-skynet/LocalAI/internal"
|
||||
"github.com/go-skynet/LocalAI/pkg/assets"
|
||||
"github.com/go-skynet/LocalAI/pkg/library"
|
||||
"github.com/go-skynet/LocalAI/pkg/model"
|
||||
pkgStartup "github.com/go-skynet/LocalAI/pkg/startup"
|
||||
"github.com/go-skynet/LocalAI/pkg/xsysinfo"
|
||||
@@ -110,11 +109,6 @@ func Startup(opts ...config.AppOption) (*config.BackendConfigLoader, *model.Mode
|
||||
}
|
||||
}
|
||||
|
||||
if options.LibPath != "" {
|
||||
// If there is a lib directory, set LD_LIBRARY_PATH to include it
|
||||
library.LoadExternal(options.LibPath)
|
||||
}
|
||||
|
||||
// turn off any process that was started by GRPC if the context is canceled
|
||||
go func() {
|
||||
<-options.Context.Done()
|
||||
|
||||
@@ -85,7 +85,7 @@ Images with `core` in the tag are smaller and do not contain any python dependen
|
||||
| Description | Quay | Docker Hub |
|
||||
| --- | --- |-----------------------------------------------|
|
||||
| Latest images from the branch (development) | `quay.io/go-skynet/local-ai:master` | `localai/localai:master` |
|
||||
| Latest tag | `quay.io/go-skynet/local-ai:latest-cpu` | `localai/localai:latest-cpu` |
|
||||
| Latest tag | `quay.io/go-skynet/local-ai:latest` | `localai/localai:latest` |
|
||||
| Versioned image | `quay.io/go-skynet/local-ai:{{< version >}}` | `localai/localai:{{< version >}}` |
|
||||
| Versioned image including FFMpeg| `quay.io/go-skynet/local-ai:{{< version >}}-ffmpeg` | `localai/localai:{{< version >}}-ffmpeg` |
|
||||
| Versioned image including FFMpeg, no python | `quay.io/go-skynet/local-ai:{{< version >}}-ffmpeg-core` | `localai/localai:{{< version >}}-ffmpeg-core` |
|
||||
@@ -97,7 +97,7 @@ Images with `core` in the tag are smaller and do not contain any python dependen
|
||||
| Description | Quay | Docker Hub |
|
||||
| --- | --- |-------------------------------------------------------------|
|
||||
| Latest images from the branch (development) | `quay.io/go-skynet/local-ai:master-cublas-cuda11` | `localai/localai:master-cublas-cuda11` |
|
||||
| Latest tag | `quay.io/go-skynet/local-ai:latest-gpu-nvidia-cuda-11` | `localai/localai:latest-gpu-nvidia-cuda-11` |
|
||||
| Latest tag | `quay.io/go-skynet/local-ai:latest-cublas-cuda11` | `localai/localai:latest-cublas-cuda11` |
|
||||
| Versioned image | `quay.io/go-skynet/local-ai:{{< version >}}-cublas-cuda11` | `localai/localai:{{< version >}}-cublas-cuda11` |
|
||||
| Versioned image including FFMpeg| `quay.io/go-skynet/local-ai:{{< version >}}-cublas-cuda11-ffmpeg` | `localai/localai:{{< version >}}-cublas-cuda11-ffmpeg` |
|
||||
| Versioned image including FFMpeg, no python | `quay.io/go-skynet/local-ai:{{< version >}}-cublas-cuda11-ffmpeg-core` | `localai/localai:{{< version >}}-cublas-cuda11-ffmpeg-core` |
|
||||
@@ -109,7 +109,7 @@ Images with `core` in the tag are smaller and do not contain any python dependen
|
||||
| Description | Quay | Docker Hub |
|
||||
| --- | --- |-------------------------------------------------------------|
|
||||
| Latest images from the branch (development) | `quay.io/go-skynet/local-ai:master-cublas-cuda12` | `localai/localai:master-cublas-cuda12` |
|
||||
| Latest tag | `quay.io/go-skynet/local-ai:latest-gpu-nvidia-cuda-12` | `localai/localai:latest-gpu-nvidia-cuda-12` |
|
||||
| Latest tag | `quay.io/go-skynet/local-ai:latest-cublas-cuda12` | `localai/localai:latest-cublas-cuda12` |
|
||||
| Versioned image | `quay.io/go-skynet/local-ai:{{< version >}}-cublas-cuda12` | `localai/localai:{{< version >}}-cublas-cuda12` |
|
||||
| Versioned image including FFMpeg| `quay.io/go-skynet/local-ai:{{< version >}}-cublas-cuda12-ffmpeg` | `localai/localai:{{< version >}}-cublas-cuda12-ffmpeg` |
|
||||
| Versioned image including FFMpeg, no python | `quay.io/go-skynet/local-ai:{{< version >}}-cublas-cuda12-ffmpeg-core` | `localai/localai:{{< version >}}-cublas-cuda12-ffmpeg-core` |
|
||||
@@ -121,7 +121,7 @@ Images with `core` in the tag are smaller and do not contain any python dependen
|
||||
| Description | Quay | Docker Hub |
|
||||
| --- | --- |-------------------------------------------------------------|
|
||||
| Latest images from the branch (development) | `quay.io/go-skynet/local-ai:master-sycl-f16` | `localai/localai:master-sycl-f16` |
|
||||
| Latest tag | `quay.io/go-skynet/local-ai:latest-gpu-intel-f16` | `localai/localai:latest-gpu-intel-f16` |
|
||||
| Latest tag | `quay.io/go-skynet/local-ai:latest-sycl-f16` | `localai/localai:latest-sycl-f16` |
|
||||
| Versioned image | `quay.io/go-skynet/local-ai:{{< version >}}-sycl-f16` | `localai/localai:{{< version >}}-sycl-f16` |
|
||||
| Versioned image including FFMpeg| `quay.io/go-skynet/local-ai:{{< version >}}-sycl-f16-ffmpeg` | `localai/localai:{{< version >}}-sycl-f16-ffmpeg` |
|
||||
| Versioned image including FFMpeg, no python | `quay.io/go-skynet/local-ai:{{< version >}}-sycl-f16-ffmpeg-core` | `localai/localai:{{< version >}}-sycl-f16-ffmpeg-core` |
|
||||
@@ -133,7 +133,7 @@ Images with `core` in the tag are smaller and do not contain any python dependen
|
||||
| Description | Quay | Docker Hub |
|
||||
| --- | --- |-------------------------------------------------------------|
|
||||
| Latest images from the branch (development) | `quay.io/go-skynet/local-ai:master-sycl-f32` | `localai/localai:master-sycl-f32` |
|
||||
| Latest tag | `quay.io/go-skynet/local-ai:latest-gpu-intel-f32` | `localai/localai:latest-gpu-intel-f32` |
|
||||
| Latest tag | `quay.io/go-skynet/local-ai:latest-sycl-f32` | `localai/localai:latest-sycl-f32` |
|
||||
| Versioned image | `quay.io/go-skynet/local-ai:{{< version >}}-sycl-f32` | `localai/localai:{{< version >}}-sycl-f32` |
|
||||
| Versioned image including FFMpeg| `quay.io/go-skynet/local-ai:{{< version >}}-sycl-f32-ffmpeg` | `localai/localai:{{< version >}}-sycl-f32-ffmpeg` |
|
||||
| Versioned image including FFMpeg, no python | `quay.io/go-skynet/local-ai:{{< version >}}-sycl-f32-ffmpeg-core` | `localai/localai:{{< version >}}-sycl-f32-ffmpeg-core` |
|
||||
@@ -145,7 +145,7 @@ Images with `core` in the tag are smaller and do not contain any python dependen
|
||||
| Description | Quay | Docker Hub |
|
||||
| --- | --- |-------------------------------------------------------------|
|
||||
| Latest images from the branch (development) | `quay.io/go-skynet/local-ai:master-hipblas` | `localai/localai:master-hipblas` |
|
||||
| Latest tag | `quay.io/go-skynet/local-ai:latest-gpu-hipblas` | `localai/localai:latest-gpu-hipblas` |
|
||||
| Latest tag | `quay.io/go-skynet/local-ai:latest-hipblas` | `localai/localai:latest-hipblas` |
|
||||
| Versioned image | `quay.io/go-skynet/local-ai:{{< version >}}-hipblas` | `localai/localai:{{< version >}}-hipblas` |
|
||||
| Versioned image including FFMpeg| `quay.io/go-skynet/local-ai:{{< version >}}-hipblas-ffmpeg` | `localai/localai:{{< version >}}-hipblas-ffmpeg` |
|
||||
| Versioned image including FFMpeg, no python | `quay.io/go-skynet/local-ai:{{< version >}}-hipblas-ffmpeg-core` | `localai/localai:{{< version >}}-hipblas-ffmpeg-core` |
|
||||
|
||||
@@ -22,53 +22,6 @@
|
||||
- filename: Qwen2-7B-Instruct-Q4_K_M.gguf
|
||||
sha256: 8d0d33f0d9110a04aad1711b1ca02dafc0fa658cd83028bdfa5eff89c294fe76
|
||||
uri: huggingface://bartowski/Qwen2-7B-Instruct-GGUF/Qwen2-7B-Instruct-Q4_K_M.gguf
|
||||
- !!merge <<: *qwen2
|
||||
name: "dolphin-2.9.2-qwen2-72b"
|
||||
icon: https://cdn-uploads.huggingface.co/production/uploads/63111b2d88942700629f5771/ldkN1J0WIDQwU4vutGYiD.png
|
||||
urls:
|
||||
- https://huggingface.co/cognitivecomputations/dolphin-2.9.2-qwen2-72b-gguf
|
||||
description: |
|
||||
Dolphin 2.9.2 Qwen2 72B 🐬
|
||||
|
||||
Curated and trained by Eric Hartford, Lucas Atkins, and Fernando Fernandes, and Cognitive Computations
|
||||
overrides:
|
||||
parameters:
|
||||
model: dolphin-2.9.2-qwen2-Q4_K_M.gguf
|
||||
files:
|
||||
- filename: dolphin-2.9.2-qwen2-Q4_K_M.gguf
|
||||
sha256: 44a0e82cbc2a201b2f4b9e16099a0a4d97b6f0099d45bcc5b354601f38dbb709
|
||||
uri: huggingface://cognitivecomputations/dolphin-2.9.2-qwen2-72b-gguf/qwen2-Q4_K_M.gguf
|
||||
- !!merge <<: *qwen2
|
||||
name: "dolphin-2.9.2-qwen2-7b"
|
||||
description: |
|
||||
Dolphin 2.9.2 Qwen2 7B 🐬
|
||||
|
||||
Curated and trained by Eric Hartford, Lucas Atkins, and Fernando Fernandes, and Cognitive Computations
|
||||
urls:
|
||||
- https://huggingface.co/cognitivecomputations/dolphin-2.9.2-qwen2-7b
|
||||
- https://huggingface.co/cognitivecomputations/dolphin-2.9.2-qwen2-7b-gguf
|
||||
icon: https://cdn-uploads.huggingface.co/production/uploads/63111b2d88942700629f5771/ldkN1J0WIDQwU4vutGYiD.png
|
||||
overrides:
|
||||
parameters:
|
||||
model: dolphin-2.9.2-qwen2-7b-Q4_K_M.gguf
|
||||
files:
|
||||
- filename: dolphin-2.9.2-qwen2-7b-Q4_K_M.gguf
|
||||
sha256: a15b5db4df6be4f4bfb3632b2009147332ef4c57875527f246b4718cb0d3af1f
|
||||
uri: huggingface://cognitivecomputations/dolphin-2.9.2-qwen2-7b-gguf/dolphin-2.9.2-qwen2-7b-Q4_K_M.gguf
|
||||
- !!merge <<: *qwen2
|
||||
name: "samantha-qwen-2-7B"
|
||||
description: |
|
||||
Samantha based on qwen2
|
||||
urls:
|
||||
- https://huggingface.co/bartowski/Samantha-Qwen-2-7B-GGUF
|
||||
- https://huggingface.co/macadeliccc/Samantha-Qwen2-7B
|
||||
overrides:
|
||||
parameters:
|
||||
model: Samantha-Qwen-2-7B-Q4_K_M.gguf
|
||||
files:
|
||||
- filename: Samantha-Qwen-2-7B-Q4_K_M.gguf
|
||||
sha256: 5d1cf1c35a7a46c536a96ba0417d08b9f9e09c24a4e25976f72ad55d4904f6fe
|
||||
uri: huggingface://bartowski/Samantha-Qwen-2-7B-GGUF/Samantha-Qwen-2-7B-Q4_K_M.gguf
|
||||
## START Mistral
|
||||
- &mistral03
|
||||
url: "github:mudler/LocalAI/gallery/mistral-0.3.yaml@master"
|
||||
@@ -223,37 +176,6 @@
|
||||
- filename: gemma-2b.Q4_K_M.gguf
|
||||
sha256: 37d50c21ef7847926204ad9b3007127d9a2722188cfd240ce7f9f7f041aa71a5
|
||||
uri: huggingface://mlabonne/gemma-2b-GGUF/gemma-2b.Q4_K_M.gguf
|
||||
- !!merge <<: *gemma
|
||||
name: "firefly-gemma-7b-iq-imatrix"
|
||||
icon: "https://cdn-uploads.huggingface.co/production/uploads/65d4cf2693a0a3744a27536c/SrOekTxdpnxHyWWmMiAvc.jpeg"
|
||||
urls:
|
||||
- https://huggingface.co/Lewdiculous/firefly-gemma-7b-GGUF-IQ-Imatrix
|
||||
- https://huggingface.co/YeungNLP/firefly-gemma-7b
|
||||
description: |
|
||||
firefly-gemma-7b is trained based on gemma-7b to act as a helpful and harmless AI assistant. We use Firefly to train the model on a single V100 GPU with QLoRA.
|
||||
overrides:
|
||||
parameters:
|
||||
model: firefly-gemma-7b-Q4_K_S-imatrix.gguf
|
||||
files:
|
||||
- filename: firefly-gemma-7b-Q4_K_S-imatrix.gguf
|
||||
sha256: 622e0b8e4f12203cc40c7f87915abf99498c2e0582203415ca236ea37643e428
|
||||
uri: huggingface://Lewdiculous/firefly-gemma-7b-GGUF-IQ-Imatrix/firefly-gemma-7b-Q4_K_S-imatrix.gguf
|
||||
- !!merge <<: *gemma
|
||||
name: "gemma-1.1-7b-it"
|
||||
urls:
|
||||
- https://huggingface.co/bartowski/gemma-1.1-7b-it-GGUF
|
||||
- https://huggingface.co/google/gemma-1.1-7b-it
|
||||
description: |
|
||||
This is Gemma 1.1 7B (IT), an update over the original instruction-tuned Gemma release.
|
||||
|
||||
Gemma 1.1 was trained using a novel RLHF method, leading to substantial gains on quality, coding capabilities, factuality, instruction following and multi-turn conversation quality. We also fixed a bug in multi-turn conversations, and made sure that model responses don't always start with "Sure,".
|
||||
overrides:
|
||||
parameters:
|
||||
model: gemma-1.1-7b-it-Q4_K_M.gguf
|
||||
files:
|
||||
- filename: gemma-1.1-7b-it-Q4_K_M.gguf
|
||||
sha256: 47821da72ee9e80b6fd43c6190ad751b485fb61fa5664590f7a73246bcd8332e
|
||||
uri: huggingface://bartowski/gemma-1.1-7b-it-GGUF/gemma-1.1-7b-it-Q4_K_M.gguf
|
||||
- &llama3
|
||||
url: "github:mudler/LocalAI/gallery/llama3-instruct.yaml@master"
|
||||
icon: https://cdn-uploads.huggingface.co/production/uploads/642cc1c253e76b4c2286c58e/aJJxKus1wP5N-euvHEUq7.png
|
||||
@@ -1133,21 +1055,6 @@
|
||||
- filename: Tess-2.0-Llama-3-8B-Q4_K_M.gguf
|
||||
sha256: 3b5fbd6c59d7d38205ab81970c0227c74693eb480acf20d8c2f211f62e3ca5f6
|
||||
uri: huggingface://bartowski/Tess-2.0-Llama-3-8B-GGUF/Tess-2.0-Llama-3-8B-Q4_K_M.gguf
|
||||
- !!merge <<: *llama3
|
||||
url: "github:mudler/LocalAI/gallery/chatml.yaml@master"
|
||||
name: "tess-v2.5-phi-3-medium-128k-14b"
|
||||
urls:
|
||||
- https://huggingface.co/bartowski/Tess-v2.5-Phi-3-medium-128k-14B-GGUF
|
||||
icon: https://huggingface.co/migtissera/Tess-2.0-Mixtral-8x22B/resolve/main/Tess-2.png
|
||||
description: |
|
||||
Tess, short for Tesoro (Treasure in Italian), is a general purpose Large Language Model series.
|
||||
overrides:
|
||||
parameters:
|
||||
model: Tess-v2.5-Phi-3-medium-128k-14B-Q4_K_M.gguf
|
||||
files:
|
||||
- filename: Tess-v2.5-Phi-3-medium-128k-14B-Q4_K_M.gguf
|
||||
sha256: 9efb6ebc00de74012d0fb36134cce07d624a870fc12f38b16b57ce447b86e27e
|
||||
uri: huggingface://bartowski/Tess-v2.5-Phi-3-medium-128k-14B-GGUF/Tess-v2.5-Phi-3-medium-128k-14B-Q4_K_M.gguf
|
||||
- !!merge <<: *llama3
|
||||
name: "llama3-iterative-dpo-final"
|
||||
urls:
|
||||
@@ -1795,20 +1702,6 @@
|
||||
- filename: Llama-3-Update-3.0-mmproj-model-f16.gguf
|
||||
sha256: 3d2f36dff61d6157cadf102df86a808eb9f8a230be1bc0bc99039d81a895468a
|
||||
uri: huggingface://Nitral-AI/Llama-3-Update-3.0-mmproj-model-f16/Llama-3-Update-3.0-mmproj-model-f16.gguf
|
||||
- !!merge <<: *llama3
|
||||
name: "hathor_stable-v0.2-l3-8b"
|
||||
urls:
|
||||
- https://huggingface.co/bartowski/Hathor_Stable-v0.2-L3-8B-GGUF
|
||||
description: |
|
||||
Hathor-v0.2 is a model based on the LLaMA 3 architecture: Designed to seamlessly integrate the qualities of creativity, intelligence, and robust performance. Making it an ideal tool for a wide range of applications; such as creative writing, educational support and human/computer interaction.
|
||||
icon: https://cdn-uploads.huggingface.co/production/uploads/65d4cf2693a0a3744a27536c/FLvA7-CWp3UhBuR2eGSh7.webp
|
||||
overrides:
|
||||
parameters:
|
||||
model: Hathor_Stable-v0.2-L3-8B-Q4_K_M.gguf
|
||||
files:
|
||||
- filename: Hathor_Stable-v0.2-L3-8B-Q4_K_M.gguf
|
||||
sha256: 291cd30421f519ec00e04ae946a4f639d8d1b7c294cb2b2897b35da6d498fdc4
|
||||
uri: huggingface://bartowski/Hathor_Stable-v0.2-L3-8B-GGUF/Hathor_Stable-v0.2-L3-8B-Q4_K_M.gguf
|
||||
- !!merge <<: *llama3
|
||||
name: "bunny-llama-3-8b-v"
|
||||
urls:
|
||||
|
||||
@@ -6,8 +6,6 @@ import (
|
||||
"io/fs"
|
||||
"os"
|
||||
"path/filepath"
|
||||
|
||||
"github.com/go-skynet/LocalAI/pkg/library"
|
||||
)
|
||||
|
||||
func ResolvePath(dir string, paths ...string) string {
|
||||
@@ -56,7 +54,22 @@ func ExtractFiles(content embed.FS, extractDir string) error {
|
||||
// If there is a lib directory, set LD_LIBRARY_PATH to include it
|
||||
// we might use this mechanism to carry over e.g. Nvidia CUDA libraries
|
||||
// from the embedded FS to the target directory
|
||||
library.LoadExtractedLibs(extractDir)
|
||||
|
||||
// Skip this if LOCALAI_SKIP_LD_LIBRARY_PATH is set
|
||||
if os.Getenv("LOCALAI_SKIP_LD_LIBRARY_PATH") != "" {
|
||||
return err
|
||||
}
|
||||
|
||||
for _, libDir := range []string{filepath.Join(extractDir, "backend_assets", "lib"), filepath.Join(extractDir, "lib")} {
|
||||
if _, err := os.Stat(libDir); err == nil {
|
||||
ldLibraryPath := os.Getenv("LD_LIBRARY_PATH")
|
||||
if ldLibraryPath == "" {
|
||||
ldLibraryPath = libDir
|
||||
} else {
|
||||
ldLibraryPath = fmt.Sprintf("%s:%s", ldLibraryPath, libDir)
|
||||
}
|
||||
os.Setenv("LD_LIBRARY_PATH", ldLibraryPath)
|
||||
}
|
||||
}
|
||||
return err
|
||||
}
|
||||
|
||||
@@ -1,41 +0,0 @@
|
||||
package library
|
||||
|
||||
import (
|
||||
"fmt"
|
||||
"os"
|
||||
"path/filepath"
|
||||
"runtime"
|
||||
)
|
||||
|
||||
func LoadExtractedLibs(dir string) {
|
||||
// Skip this if LOCALAI_SKIP_LIBRARY_PATH is set
|
||||
if os.Getenv("LOCALAI_SKIP_LIBRARY_PATH") != "" {
|
||||
return
|
||||
}
|
||||
|
||||
for _, libDir := range []string{filepath.Join(dir, "backend-assets", "lib"), filepath.Join(dir, "lib")} {
|
||||
LoadExternal(libDir)
|
||||
}
|
||||
}
|
||||
|
||||
func LoadExternal(dir string) {
|
||||
// Skip this if LOCALAI_SKIP_LIBRARY_PATH is set
|
||||
if os.Getenv("LOCALAI_SKIP_LIBRARY_PATH") != "" {
|
||||
return
|
||||
}
|
||||
|
||||
lpathVar := "LD_LIBRARY_PATH"
|
||||
if runtime.GOOS == "darwin" {
|
||||
lpathVar = "DYLD_FALLBACK_LIBRARY_PATH" // should it be DYLD_LIBRARY_PATH ?
|
||||
}
|
||||
|
||||
if _, err := os.Stat(dir); err == nil {
|
||||
ldLibraryPath := os.Getenv(lpathVar)
|
||||
if ldLibraryPath == "" {
|
||||
ldLibraryPath = dir
|
||||
} else {
|
||||
ldLibraryPath = fmt.Sprintf("%s:%s", ldLibraryPath, dir)
|
||||
}
|
||||
os.Setenv(lpathVar, ldLibraryPath)
|
||||
}
|
||||
}
|
||||
Reference in New Issue
Block a user