From ad1a23748bd03ce2c17d65505d2f914efeebc337 Mon Sep 17 00:00:00 2001 From: Ettore Di Giacinto Date: Mon, 6 Jan 2025 10:36:51 +0100 Subject: [PATCH] chore(model gallery): add triangulum-10b Signed-off-by: Ettore Di Giacinto --- gallery/index.yaml | 23 +++++++++++++++++++++++ 1 file changed, 23 insertions(+) diff --git a/gallery/index.yaml b/gallery/index.yaml index 27f45850843e..67138ddae3f6 100644 --- a/gallery/index.yaml +++ b/gallery/index.yaml @@ -9309,6 +9309,29 @@ - filename: Bio-Medical-Llama-3-8B.Q4_K_M.gguf sha256: 672939e0487d02c55734132c25a59f26e4deaac7cd49445a7028f2291139edcc uri: huggingface://QuantFactory/Bio-Medical-Llama-3-8B-GGUF/Bio-Medical-Llama-3-8B.Q4_K_M.gguf +- !!merge <<: *llama3 + name: "triangulum-10b" + icon: https://cdn-uploads.huggingface.co/production/uploads/65bb837dbfb878f46c77de4c/By0OJ1lMvP5ZvVvfEGvz5.png + urls: + - https://huggingface.co/prithivMLmods/Triangulum-10B + - https://huggingface.co/mradermacher/Triangulum-10B-GGUF + description: | + Triangulum 10B is a collection of pretrained and instruction-tuned generative models, designed for multilingual applications. These models are trained using synthetic datasets based on long chains of thought, enabling them to perform complex reasoning tasks effectively. + Key Features + Foundation Model: Built upon LLaMA's autoregressive language model, leveraging an optimized transformer architecture for enhanced performance. + Instruction Tuning: Includes supervised fine-tuning (SFT) and reinforcement learning with human feedback (RLHF) to align model outputs with human preferences for helpfulness and safety. + Multilingual Support: Designed to handle multiple languages, ensuring broad applicability across diverse linguistic contexts. + Training Approach + Synthetic Datasets: Utilizes long chain-of-thought synthetic data to enhance reasoning capabilities. + Supervised Fine-Tuning (SFT): Aligns the model to specific tasks through curated datasets. + Reinforcement Learning with Human Feedback (RLHF): Ensures the model adheres to human values and safety guidelines through iterative training processes. + overrides: + parameters: + model: Triangulum-10B.Q4_K_M.gguf + files: + - filename: Triangulum-10B.Q4_K_M.gguf + sha256: dd071f99edf6b166044bf229cdeec19419c4c348e3fc3d6587cfcc55e6fb85fa + uri: huggingface://mradermacher/Triangulum-10B-GGUF/Triangulum-10B.Q4_K_M.gguf - &command-R ### START Command-r url: "github:mudler/LocalAI/gallery/command-r.yaml@master"