From 30b883affe62b6b000105350a3034af057b087c6 Mon Sep 17 00:00:00 2001 From: Ettore Di Giacinto Date: Thu, 27 Jun 2024 23:08:22 +0200 Subject: [PATCH] models(gallery): add gemma2-9b-it and gemma2-27b-it (#2670) Signed-off-by: Ettore Di Giacinto --- gallery/index.yaml | 28 ++++++++++++++++++++++++++++ 1 file changed, 28 insertions(+) diff --git a/gallery/index.yaml b/gallery/index.yaml index 990c2b18..6ae5f889 100644 --- a/gallery/index.yaml +++ b/gallery/index.yaml @@ -312,6 +312,34 @@ - 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 +- !!merge <<: *gemma + name: "gemma-2-27b-it" + urls: + - https://huggingface.co/google/gemma-2-27b-it + - https://huggingface.co/bartowski/gemma-2-27b-it-GGUF + description: | + Gemma is a family of lightweight, state-of-the-art open models from Google, built from the same research and technology used to create the Gemini models. They are text-to-text, decoder-only large language models, available in English, with open weights for both pre-trained variants and instruction-tuned variants. Gemma models are well-suited for a variety of text generation tasks, including question answering, summarization, and reasoning. Their relatively small size makes it possible to deploy them in environments with limited resources such as a laptop, desktop or your own cloud infrastructure, democratizing access to state of the art AI models and helping foster innovation for everyone. + overrides: + parameters: + model: gemma-2-27b-it-Q4_K_M.gguf + files: + - filename: gemma-2-27b-it-Q4_K_M.gguf + sha256: e54e7b800d464af4fa9966020e4a1b1d386cd9346de2d851a7bfe7d0797c44c4 + uri: huggingface://bartowski/gemma-2-27b-it-GGUF/gemma-2-27b-it-Q4_K_M.gguf +- !!merge <<: *gemma + name: "gemma-2-9b-it" + urls: + - https://huggingface.co/google/gemma-2-9b-it + - https://huggingface.co/bartowski/gemma-2-9b-it-GGUF + description: | + Gemma is a family of lightweight, state-of-the-art open models from Google, built from the same research and technology used to create the Gemini models. They are text-to-text, decoder-only large language models, available in English, with open weights for both pre-trained variants and instruction-tuned variants. Gemma models are well-suited for a variety of text generation tasks, including question answering, summarization, and reasoning. Their relatively small size makes it possible to deploy them in environments with limited resources such as a laptop, desktop or your own cloud infrastructure, democratizing access to state of the art AI models and helping foster innovation for everyone. + overrides: + parameters: + model: gemma-2-9b-it-Q4_K_M.gguf + files: + - filename: gemma-2-9b-it-Q4_K_M.gguf + sha256: 0874bf61be2e4b3d0a4a75e58fbd442dc410745d513c1e1e5de0b54ae33e65db + uri: huggingface://bartowski/gemma-2-9b-it-GGUF/gemma-2-9b-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