From 68148f2a1a848f89280c2f59236587cc0ae87ede Mon Sep 17 00:00:00 2001 From: "LocalAI [bot]" <139863280+localai-bot@users.noreply.github.com> Date: Mon, 17 Jun 2024 02:18:44 +0200 Subject: [PATCH 01/11] :arrow_up: Update ggerganov/llama.cpp (#2584) Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com> Co-authored-by: mudler <2420543+mudler@users.noreply.github.com> --- Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Makefile b/Makefile index d038199e2c0..bbdb851380f 100644 --- a/Makefile +++ b/Makefile @@ -5,7 +5,7 @@ BINARY_NAME=local-ai # llama.cpp versions GOLLAMA_STABLE_VERSION?=2b57a8ae43e4699d3dc5d1496a1ccd42922993be -CPPLLAMA_VERSION?=0c7b3595b9e5ad2355818e259f06b0dc3f0065b3 +CPPLLAMA_VERSION?=19b7a836f6658e18e973af532a5cc6ad6b3a27f8 # gpt4all version GPT4ALL_REPO?=https://github.com/nomic-ai/gpt4all From b58b7cad9456878e188b3b59ecdd8262659f658e Mon Sep 17 00:00:00 2001 From: Ettore Di Giacinto Date: Mon, 17 Jun 2024 10:08:29 +0200 Subject: [PATCH 02/11] models(gallery): add samantha-qwen2 (#2586) Signed-off-by: Ettore Di Giacinto --- gallery/index.yaml | 14 ++++++++++++++ 1 file changed, 14 insertions(+) diff --git a/gallery/index.yaml b/gallery/index.yaml index 83c94c15601..770f5a78aea 100644 --- a/gallery/index.yaml +++ b/gallery/index.yaml @@ -55,6 +55,20 @@ - 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" From 2437a2769def9550513395b84e3e1a6d798842be Mon Sep 17 00:00:00 2001 From: Ettore Di Giacinto Date: Mon, 17 Jun 2024 14:13:27 +0200 Subject: [PATCH 03/11] models(gallery): add gemma-1.1-7b-it (#2588) Signed-off-by: Ettore Di Giacinto --- gallery/index.yaml | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) diff --git a/gallery/index.yaml b/gallery/index.yaml index 770f5a78aea..a458b33df71 100644 --- a/gallery/index.yaml +++ b/gallery/index.yaml @@ -238,6 +238,22 @@ - 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 From 2f297979a7c8fe564e176e1544151794e75d70d0 Mon Sep 17 00:00:00 2001 From: "LocalAI [bot]" <139863280+localai-bot@users.noreply.github.com> Date: Mon, 17 Jun 2024 17:28:19 +0200 Subject: [PATCH 04/11] :arrow_up: Update ggerganov/llama.cpp (#2587) Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com> Co-authored-by: mudler <2420543+mudler@users.noreply.github.com> --- Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Makefile b/Makefile index bbdb851380f..0671f22d930 100644 --- a/Makefile +++ b/Makefile @@ -5,7 +5,7 @@ BINARY_NAME=local-ai # llama.cpp versions GOLLAMA_STABLE_VERSION?=2b57a8ae43e4699d3dc5d1496a1ccd42922993be -CPPLLAMA_VERSION?=19b7a836f6658e18e973af532a5cc6ad6b3a27f8 +CPPLLAMA_VERSION?=21be9cab94e0b5b53cb6edeeebf8c8c799baad03 # gpt4all version GPT4ALL_REPO?=https://github.com/nomic-ai/gpt4all From c30b57a6297e6adee5c749eb4e2458ef7b94e4cb Mon Sep 17 00:00:00 2001 From: "LocalAI [bot]" <139863280+localai-bot@users.noreply.github.com> Date: Tue, 18 Jun 2024 03:47:04 +0200 Subject: [PATCH 05/11] :arrow_up: Update docs version mudler/LocalAI (#2593) Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com> Co-authored-by: mudler <2420543+mudler@users.noreply.github.com> --- docs/data/version.json | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/docs/data/version.json b/docs/data/version.json index d4af2be33b0..bb64a98a2d2 100644 --- a/docs/data/version.json +++ b/docs/data/version.json @@ -1,3 +1,3 @@ { - "version": "v2.16.0" + "version": "v2.17.0" } From c926469b9cea1e00f168c15c7dcab84087b8b565 Mon Sep 17 00:00:00 2001 From: "LocalAI [bot]" <139863280+localai-bot@users.noreply.github.com> Date: Tue, 18 Jun 2024 05:06:31 +0200 Subject: [PATCH 06/11] :arrow_up: Update ggerganov/llama.cpp (#2594) Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com> Co-authored-by: mudler <2420543+mudler@users.noreply.github.com> --- Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Makefile b/Makefile index 0671f22d930..8ec61e04c16 100644 --- a/Makefile +++ b/Makefile @@ -5,7 +5,7 @@ BINARY_NAME=local-ai # llama.cpp versions GOLLAMA_STABLE_VERSION?=2b57a8ae43e4699d3dc5d1496a1ccd42922993be -CPPLLAMA_VERSION?=21be9cab94e0b5b53cb6edeeebf8c8c799baad03 +CPPLLAMA_VERSION?=a94e6ff8774b7c9f950d9545baf0ce35e8d1ed2f # gpt4all version GPT4ALL_REPO?=https://github.com/nomic-ai/gpt4all From 7f13e3a783ef93f7562467bde2ed58632401dd62 Mon Sep 17 00:00:00 2001 From: Ettore Di Giacinto Date: Tue, 18 Jun 2024 08:42:30 +0200 Subject: [PATCH 07/11] docs(models): fixup top message Signed-off-by: Ettore Di Giacinto --- .github/ci/modelslist.go | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/.github/ci/modelslist.go b/.github/ci/modelslist.go index a350f0984e2..ab0aa90bf89 100644 --- a/.github/ci/modelslist.go +++ b/.github/ci/modelslist.go @@ -114,12 +114,12 @@ var modelPageTemplate string = `

- 🖼️ Available {{.AvailableModels}} models repositories + 🖼️ Available {{.AvailableModels}} models

- Refer to Model gallery for more information on how to use the models with LocalAI. + Refer to the Model gallery for more information on how to use the models with LocalAI.
You can install models with the CLI command local-ai models install . or by using the WebUI.

From ecbb61cbf4ae99f62d8f5816c9aa733a1bef0fdc Mon Sep 17 00:00:00 2001 From: Ettore Di Giacinto Date: Tue, 18 Jun 2024 15:09:39 +0200 Subject: [PATCH 08/11] feat(sd-3): add stablediffusion 3 support (#2591) * feat(sd-3): add stablediffusion 3 support Signed-off-by: Ettore Di Giacinto * deps(diffusers): add sentencepiece Signed-off-by: Ettore Di Giacinto * models(gallery): add stablediffusion-3 Signed-off-by: Ettore Di Giacinto --------- Signed-off-by: Ettore Di Giacinto --- backend/python/diffusers/backend.py | 13 ++++++++++++- backend/python/diffusers/requirements.txt | 3 ++- gallery/index.yaml | 15 +++++++++++++++ gallery/stablediffusion3.yaml | 14 ++++++++++++++ 4 files changed, 43 insertions(+), 2 deletions(-) create mode 100644 gallery/stablediffusion3.yaml diff --git a/backend/python/diffusers/backend.py b/backend/python/diffusers/backend.py index ec2dea6050e..1496fa9466d 100755 --- a/backend/python/diffusers/backend.py +++ b/backend/python/diffusers/backend.py @@ -17,7 +17,7 @@ import grpc -from diffusers import StableDiffusionXLPipeline, StableDiffusionDepth2ImgPipeline, DPMSolverMultistepScheduler, StableDiffusionPipeline, DiffusionPipeline, EulerAncestralDiscreteScheduler +from diffusers import StableDiffusion3Pipeline, StableDiffusionXLPipeline, StableDiffusionDepth2ImgPipeline, DPMSolverMultistepScheduler, StableDiffusionPipeline, DiffusionPipeline, EulerAncestralDiscreteScheduler from diffusers import StableDiffusionImg2ImgPipeline, AutoPipelineForText2Image, ControlNetModel, StableVideoDiffusionPipeline from diffusers.pipelines.stable_diffusion import safety_checker from diffusers.utils import load_image,export_to_video @@ -225,6 +225,17 @@ def LoadModel(self, request, context): torch_dtype=torchType, use_safetensors=True, variant=variant) + elif request.PipelineType == "StableDiffusion3Pipeline": + if fromSingleFile: + self.pipe = StableDiffusion3Pipeline.from_single_file(modelFile, + torch_dtype=torchType, + use_safetensors=True) + else: + self.pipe = StableDiffusion3Pipeline.from_pretrained( + request.Model, + torch_dtype=torchType, + use_safetensors=True, + variant=variant) if CLIPSKIP and request.CLIPSkip != 0: self.clip_skip = request.CLIPSkip diff --git a/backend/python/diffusers/requirements.txt b/backend/python/diffusers/requirements.txt index 1c663adc3d0..188fb5dc025 100644 --- a/backend/python/diffusers/requirements.txt +++ b/backend/python/diffusers/requirements.txt @@ -5,6 +5,7 @@ grpcio==1.64.0 opencv-python pillow protobuf +sentencepiece torch transformers -certifi \ No newline at end of file +certifi diff --git a/gallery/index.yaml b/gallery/index.yaml index a458b33df71..e92f35dbcf2 100644 --- a/gallery/index.yaml +++ b/gallery/index.yaml @@ -2580,6 +2580,21 @@ - filename: DreamShaper_8_pruned.safetensors uri: huggingface://Lykon/DreamShaper/DreamShaper_8_pruned.safetensors sha256: 879db523c30d3b9017143d56705015e15a2cb5628762c11d086fed9538abd7fd +- name: stable-diffusion-3-medium + icon: https://huggingface.co/leo009/stable-diffusion-3-medium/resolve/main/sd3demo.jpg + license: other + description: | + Stable Diffusion 3 Medium is a Multimodal Diffusion Transformer (MMDiT) text-to-image model that features greatly improved performance in image quality, typography, complex prompt understanding, and resource-efficiency. + urls: + - https://huggingface.co/stabilityai/stable-diffusion-3-medium + - https://huggingface.co/leo009/stable-diffusion-3-medium + tags: + - text-to-image + - stablediffusion + - python + - sd-3 + - gpu + url: "github:mudler/LocalAI/gallery/stablediffusion3.yaml@master" - &whisper ## Whisper url: "github:mudler/LocalAI/gallery/whisper-base.yaml@master" diff --git a/gallery/stablediffusion3.yaml b/gallery/stablediffusion3.yaml new file mode 100644 index 00000000000..855c8b51ebc --- /dev/null +++ b/gallery/stablediffusion3.yaml @@ -0,0 +1,14 @@ +--- +name: "stable-diffusion-3-medium" + +config_file: | + backend: diffusers + diffusers: + cuda: true + enable_parameters: negative_prompt,num_inference_steps + pipeline_type: StableDiffusion3Pipeline + f16: false + name: sd3 + parameters: + model: v2ray/stable-diffusion-3-medium-diffusers + step: 25 From 06de54203206577fb8cfa779be11ba880d7430c0 Mon Sep 17 00:00:00 2001 From: Ettore Di Giacinto Date: Tue, 18 Jun 2024 15:10:01 +0200 Subject: [PATCH 09/11] feat(talk): display an informative box, better colors (#2600) Signed-off-by: Ettore Di Giacinto --- core/http/views/talk.html | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/core/http/views/talk.html b/core/http/views/talk.html index 862520d1fb2..0846a0c83cb 100644 --- a/core/http/views/talk.html +++ b/core/http/views/talk.html @@ -50,6 +50,10 @@
+ +
+ Note: You need an LLM a audio-transcription(whisper) and a tts model installed in order for this to work. Select the appropariate model from the toolbox and then click the 'Talk' button to start recording. The recording will continue until you click 'Stop recording'. Make sure your microphone is set up and enabled. +