From 2437a2769def9550513395b84e3e1a6d798842be Mon Sep 17 00:00:00 2001 From: Ettore Di Giacinto Date: Mon, 17 Jun 2024 14:13:27 +0200 Subject: [PATCH] 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 770f5a78..a458b33d 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