From fac70e9642b6dab31fa5d8ba4bab9a20b1031316 Mon Sep 17 00:00:00 2001 From: Ettore Di Giacinto Date: Tue, 18 Feb 2025 11:49:26 +0100 Subject: [PATCH] chore(model gallery): add allenai_llama-3.1-tulu-3.1-8b (#4859) Signed-off-by: Ettore Di Giacinto --- gallery/index.yaml | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) diff --git a/gallery/index.yaml b/gallery/index.yaml index f4661241..beb267cd 100644 --- a/gallery/index.yaml +++ b/gallery/index.yaml @@ -5828,6 +5828,23 @@ - filename: DavidBrowne17_LlamaThink-8B-instruct-Q4_K_M.gguf sha256: 6aea4e13f03347e03d6989c736a7ccab82582115eb072cacfeb7f0b645a8bec0 uri: huggingface://bartowski/DavidBrowne17_LlamaThink-8B-instruct-GGUF/DavidBrowne17_LlamaThink-8B-instruct-Q4_K_M.gguf +- !!merge <<: *llama31 + name: "allenai_llama-3.1-tulu-3.1-8b" + icon: https://huggingface.co/datasets/allenai/blog-images/resolve/main/tulu3/Tulu3-logo.png + urls: + - https://huggingface.co/allenai/Llama-3.1-Tulu-3.1-8B + - https://huggingface.co/bartowski/allenai_Llama-3.1-Tulu-3.1-8B-GGUF + description: | + Tülu 3 is a leading instruction following model family, offering a post-training package with fully open-source data, code, and recipes designed to serve as a comprehensive guide for modern techniques. This is one step of a bigger process to training fully open-source models, like our OLMo models. Tülu 3 is designed for state-of-the-art performance on a diversity of tasks in addition to chat, such as MATH, GSM8K, and IFEval. + + Version 3.1 update: The new version of our Tülu model is from an improvement only in the final RL stage of training. We switched from PPO to GRPO (no reward model) and did further hyperparameter tuning to achieve substantial performance improvements across the board over the original Tülu 3 8B model. + overrides: + parameters: + model: allenai_Llama-3.1-Tulu-3.1-8B-Q4_K_M.gguf + files: + - filename: allenai_Llama-3.1-Tulu-3.1-8B-Q4_K_M.gguf + sha256: 5eae0f1a9bcdea7cad9f1d0d5ba7540bb3de3e2d72293c076a23f24db1c2c7da + uri: huggingface://bartowski/allenai_Llama-3.1-Tulu-3.1-8B-GGUF/allenai_Llama-3.1-Tulu-3.1-8B-Q4_K_M.gguf - &deepseek url: "github:mudler/LocalAI/gallery/deepseek.yaml@master" ## Deepseek name: "deepseek-coder-v2-lite-instruct"