From 05841c24354519555b3a0f5db4970b954eb07c52 Mon Sep 17 00:00:00 2001 From: Ettore Di Giacinto Date: Sat, 4 Jan 2025 09:44:14 +0100 Subject: [PATCH] chore(model gallery): add drt-o1-7b (#4533) Signed-off-by: Ettore Di Giacinto --- gallery/index.yaml | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) diff --git a/gallery/index.yaml b/gallery/index.yaml index be624e9f..3251397c 100644 --- a/gallery/index.yaml +++ b/gallery/index.yaml @@ -2560,6 +2560,26 @@ - filename: Qwenwify2.5-32B-v4.5.Q4_K_M.gguf sha256: 52670acdc285356c01259f45b1953860f34deb4f80345ca63b60acc19165280c uri: huggingface://mradermacher/Qwenwify2.5-32B-v4.5-GGUF/Qwenwify2.5-32B-v4.5.Q4_K_M.gguf +- !!merge <<: *qwen25 + name: "drt-o1-7b" + urls: + - https://huggingface.co/Krystalan/DRT-o1-7B + - https://huggingface.co/QuantFactory/DRT-o1-7B-GGUF + description: | + In this work, we introduce DRT-o1, an attempt to bring the success of long thought reasoning to neural machine translation (MT). To this end, + + ๐ŸŒŸ We mine English sentences with similes or metaphors from existing literature books, which are suitable for translation via long thought. + ๐ŸŒŸ We propose a designed multi-agent framework with three agents (i.e., a translator, an advisor and an evaluator) to synthesize the MT samples with long thought. There are 22,264 synthesized samples in total. + ๐ŸŒŸ We train DRT-o1-8B, DRT-o1-7B and DRT-o1-14B using Llama-3.1-8B-Instruct, Qwen2.5-7B-Instruct and Qwen2.5-14B-Instruct as backbones. + + Our goal is not to achieve competitive performance with OpenAIโ€™s O1 in neural machine translation (MT). Instead, we explore technical routes to bring the success of long thought to MT. To this end, we introduce DRT-o1, a byproduct of our exploration, and we hope it could facilitate the corresponding research in this direction. + overrides: + parameters: + model: DRT-o1-7B.Q4_K_M.gguf + files: + - filename: DRT-o1-7B.Q4_K_M.gguf + sha256: f592a2523f92ae29630b45fbb501bba7f2fbd99355975cd05fa989faf8d3597d + uri: huggingface://QuantFactory/DRT-o1-7B-GGUF/DRT-o1-7B.Q4_K_M.gguf - &smollm ## SmolLM url: "github:mudler/LocalAI/gallery/chatml.yaml@master"