From 45b91d501e80eb37d8b2e8097e219c4496b84574 Mon Sep 17 00:00:00 2001 From: "dependabot[bot]" <49699333+dependabot[bot]@users.noreply.github.com> Date: Mon, 2 Dec 2024 22:47:37 +0000 Subject: [PATCH 1/5] chore(deps): Bump docs/themes/hugo-theme-relearn from `28fce6b` to `be85052` (#4305) chore(deps): Bump docs/themes/hugo-theme-relearn Bumps [docs/themes/hugo-theme-relearn](https://github.com/McShelby/hugo-theme-relearn) from `28fce6b` to `be85052`. - [Release notes](https://github.com/McShelby/hugo-theme-relearn/releases) - [Commits](https://github.com/McShelby/hugo-theme-relearn/compare/28fce6b04c414523280c53ee02f9f3a94d9d23da...be85052efea3a0aaef45ecb0126d390c1bbac760) --- updated-dependencies: - dependency-name: docs/themes/hugo-theme-relearn dependency-type: direct:production ... Signed-off-by: dependabot[bot] Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> --- docs/themes/hugo-theme-relearn | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/docs/themes/hugo-theme-relearn b/docs/themes/hugo-theme-relearn index 28fce6b0..be85052e 160000 --- a/docs/themes/hugo-theme-relearn +++ b/docs/themes/hugo-theme-relearn @@ -1 +1 @@ -Subproject commit 28fce6b04c414523280c53ee02f9f3a94d9d23da +Subproject commit be85052efea3a0aaef45ecb0126d390c1bbac760 From 5f339629327c5ae0995021f548e842426fa2a909 Mon Sep 17 00:00:00 2001 From: "LocalAI [bot]" <139863280+localai-bot@users.noreply.github.com> Date: Tue, 3 Dec 2024 09:20:59 +0100 Subject: [PATCH 2/5] chore: :arrow_up: Update ggerganov/llama.cpp to `8648c521010620c2daccfa1d26015c668ba2c717` (#4307) :arrow_up: Update ggerganov/llama.cpp 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 bbc8a7dd..a96b9c82 100644 --- a/Makefile +++ b/Makefile @@ -8,7 +8,7 @@ DETECT_LIBS?=true # llama.cpp versions GOLLAMA_REPO?=https://github.com/go-skynet/go-llama.cpp GOLLAMA_VERSION?=2b57a8ae43e4699d3dc5d1496a1ccd42922993be -CPPLLAMA_VERSION?=5e1ed95583ca552a98d8528b73e1ff81249c2bf9 +CPPLLAMA_VERSION?=8648c521010620c2daccfa1d26015c668ba2c717 # whisper.cpp version WHISPER_REPO?=https://github.com/ggerganov/whisper.cpp From 7b70f0543b0fb401552a37b7e56cb17f2225a441 Mon Sep 17 00:00:00 2001 From: Ettore Di Giacinto Date: Tue, 3 Dec 2024 18:55:49 +0100 Subject: [PATCH 3/5] chore(model gallery): add sparse-llama-3.1-8b-2of4 (#4309) 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 bffeb067..3e3c4e3e 100644 --- a/gallery/index.yaml +++ b/gallery/index.yaml @@ -3340,6 +3340,20 @@ - filename: Skywork-o1-Open-Llama-3.1-8B.Q4_K_M.gguf sha256: ef6a203ba585aab14f5d2ec463917a45b3ac571abd89c39e9a96a5e395ea8eea uri: huggingface://QuantFactory/Skywork-o1-Open-Llama-3.1-8B-GGUF/Skywork-o1-Open-Llama-3.1-8B.Q4_K_M.gguf +- !!merge <<: *llama31 + name: "sparse-llama-3.1-8b-2of4" + urls: + - https://huggingface.co/QuantFactory/Sparse-Llama-3.1-8B-2of4-GGUF + - https://huggingface.co/QuantFactory/Sparse-Llama-3.1-8B-2of4-GGUF + description: | + This is the 2:4 sparse version of Llama-3.1-8B. On the OpenLLM benchmark (version 1), it achieves an average score of 62.16, compared to 63.19 for the dense model—demonstrating a 98.37% accuracy recovery. On the Mosaic Eval Gauntlet benchmark (version v0.3), it achieves an average score of 53.85, versus 55.34 for the dense model—representing a 97.3% accuracy recovery. + overrides: + parameters: + model: Sparse-Llama-3.1-8B-2of4.Q4_K_M.gguf + files: + - filename: Sparse-Llama-3.1-8B-2of4.Q4_K_M.gguf + sha256: c481e7089ffaedd5ae8c74dccc7fb45f6509640b661fa086ae979f6fefc3fdba + uri: huggingface://QuantFactory/Sparse-Llama-3.1-8B-2of4-GGUF/Sparse-Llama-3.1-8B-2of4.Q4_K_M.gguf - &deepseek ## Deepseek url: "github:mudler/LocalAI/gallery/deepseek.yaml@master" From 236a60bab8f4607646a8d4768baaf2712430c344 Mon Sep 17 00:00:00 2001 From: Ettore Di Giacinto Date: Tue, 3 Dec 2024 18:56:03 +0100 Subject: [PATCH 4/5] chore(model gallery): add qwen2.5-7b-homercreative-mix (#4310) Signed-off-by: Ettore Di Giacinto --- gallery/index.yaml | 25 +++++++++++++++++++++++++ 1 file changed, 25 insertions(+) diff --git a/gallery/index.yaml b/gallery/index.yaml index 3e3c4e3e..a2381f3b 100644 --- a/gallery/index.yaml +++ b/gallery/index.yaml @@ -1725,6 +1725,31 @@ - filename: Teleut-7b.Q4_K_M.gguf sha256: 844a633ea01d793c638e99f2e07413606b3812b759e9264fbaf69c8d94eaa093 uri: huggingface://QuantFactory/Teleut-7b-GGUF/Teleut-7b.Q4_K_M.gguf +- !!merge <<: *qwen25 + name: "qwen2.5-7b-homercreative-mix" + urls: + - https://huggingface.co/ZeroXClem/Qwen2.5-7B-HomerCreative-Mix + - https://huggingface.co/QuantFactory/Qwen2.5-7B-HomerCreative-Mix-GGUF + description: | + ZeroXClem/Qwen2.5-7B-HomerCreative-Mix is an advanced language model meticulously crafted by merging four pre-trained models using the powerful mergekit framework. This fusion leverages the Model Stock merge method to combine the creative prowess of Qandora, the instructive capabilities of Qwen-Instruct-Fusion, the sophisticated blending of HomerSlerp1, and the foundational conversational strengths of Homer-v0.5-Qwen2.5-7B. The resulting model excels in creative text generation, contextual understanding, and dynamic conversational interactions. + 🚀 Merged Models + + This model merge incorporates the following: + + bunnycore/Qandora-2.5-7B-Creative: Specializes in creative text generation, enhancing the model's ability to produce imaginative and diverse content. + + bunnycore/Qwen2.5-7B-Instruct-Fusion: Focuses on instruction-following capabilities, improving the model's performance in understanding and executing user commands. + + allknowingroger/HomerSlerp1-7B: Utilizes spherical linear interpolation (SLERP) to blend model weights smoothly, ensuring a harmonious integration of different model attributes. + + newsbang/Homer-v0.5-Qwen2.5-7B: Acts as the foundational conversational model, providing robust language comprehension and generation capabilities. + overrides: + parameters: + model: Qwen2.5-7B-HomerCreative-Mix.Q4_K_M.gguf + files: + - filename: Qwen2.5-7B-HomerCreative-Mix.Q4_K_M.gguf + sha256: fc3fdb41e068646592f89a8ae62d7b330f2bd4e97bf615aef2977930977c8ba5 + uri: huggingface://QuantFactory/Qwen2.5-7B-HomerCreative-Mix-GGUF/Qwen2.5-7B-HomerCreative-Mix.Q4_K_M.gguf - &archfunct license: apache-2.0 tags: From 074b52bbfeab1cd252fd1debf503c81be3e4046d Mon Sep 17 00:00:00 2001 From: Ettore Di Giacinto Date: Tue, 3 Dec 2024 18:56:53 +0100 Subject: [PATCH 5/5] chore(model gallery): add bggpt-gemma-2-2.6b-it-v1.0 (#4311) 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 a2381f3b..fd0e27e8 100644 --- a/gallery/index.yaml +++ b/gallery/index.yaml @@ -4944,6 +4944,22 @@ - filename: Volare.i1-Q4_K_M.gguf sha256: fa8fb9d4cb19fcb44be8d53561c9e2840f45aed738de545983ebb158ebba461b uri: huggingface://mradermacher/Volare-i1-GGUF/Volare.i1-Q4_K_M.gguf +- !!merge <<: *gemma + name: "bggpt-gemma-2-2.6b-it-v1.0" + icon: https://cdn-uploads.huggingface.co/production/uploads/637e1f8cf7e01589cc17bf7e/p6d0YFHjWCQ3S12jWqO1m.png + urls: + - https://huggingface.co/QuantFactory/BgGPT-Gemma-2-2.6B-IT-v1.0-GGUF + - https://huggingface.co/QuantFactory/BgGPT-Gemma-2-2.6B-IT-v1.0-GGUF + description: | + INSAIT introduces BgGPT-Gemma-2-2.6B-IT-v1.0, a state-of-the-art Bulgarian language model based on google/gemma-2-2b and google/gemma-2-2b-it. BgGPT-Gemma-2-2.6B-IT-v1.0 is free to use and distributed under the Gemma Terms of Use. This model was created by INSAIT, part of Sofia University St. Kliment Ohridski, in Sofia, Bulgaria. + The model was built on top of Google’s Gemma 2 2B open models. It was continuously pre-trained on around 100 billion tokens (85 billion in Bulgarian) using the Branch-and-Merge strategy INSAIT presented at EMNLP’24, allowing the model to gain outstanding Bulgarian cultural and linguistic capabilities while retaining its English performance. During the pre-training stage, we use various datasets, including Bulgarian web crawl data, freely available datasets such as Wikipedia, a range of specialized Bulgarian datasets sourced by the INSAIT Institute, and machine translations of popular English datasets. The model was then instruction-fine-tuned on a newly constructed Bulgarian instruction dataset created using real-world conversations. For more information check our blogpost. + overrides: + parameters: + model: BgGPT-Gemma-2-2.6B-IT-v1.0.Q4_K_M.gguf + files: + - filename: BgGPT-Gemma-2-2.6B-IT-v1.0.Q4_K_M.gguf + sha256: 1e92fe80ccad80e97076ee26b002c2280f075dfe2507d534b46a4391a077f319 + uri: huggingface://QuantFactory/BgGPT-Gemma-2-2.6B-IT-v1.0-GGUF/BgGPT-Gemma-2-2.6B-IT-v1.0.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