From d96addfa9dfc197d4e29c97368f1b30dc736ee45 Mon Sep 17 00:00:00 2001 From: Ettore Di Giacinto Date: Fri, 14 Feb 2025 12:03:46 +0100 Subject: [PATCH] chore(model gallery): add open-thoughts_openthinker-32b (#4827) Signed-off-by: Ettore Di Giacinto --- gallery/index.yaml | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) diff --git a/gallery/index.yaml b/gallery/index.yaml index 5818c6e8..1e7bb4e3 100644 --- a/gallery/index.yaml +++ b/gallery/index.yaml @@ -3783,6 +3783,25 @@ - filename: nvidia_AceInstruct-72B-Q4_K_M.gguf sha256: c8452b2d6c33693d5fd1b5f3aa476451fbd4e78c9621b9baf39ad1a3f2b91503 uri: huggingface://bartowski/nvidia_AceInstruct-72B-GGUF/nvidia_AceInstruct-72B-Q4_K_M.gguf +- !!merge <<: *qwen25 + name: "open-thoughts_openthinker-32b" + icon: https://huggingface.co/datasets/open-thoughts/open-thoughts-114k/resolve/main/open_thoughts.png + urls: + - https://huggingface.co/open-thoughts/OpenThinker-32B + - https://huggingface.co/bartowski/open-thoughts_OpenThinker-32B-GGUF + description: | + This model is a fine-tuned version of Qwen/Qwen2.5-32B-Instruct on the OpenThoughts-114k dataset. + + The dataset is derived by distilling DeepSeek-R1 using the data pipeline available on github. More info about the dataset can be found on the dataset card at OpenThoughts-114k dataset. + + The numbers reported in the table below are evaluated with our open-source tool Evalchemy. + overrides: + parameters: + model: open-thoughts_OpenThinker-32B-Q4_K_M.gguf + files: + - filename: open-thoughts_OpenThinker-32B-Q4_K_M.gguf + sha256: 6795de6e7025e4a77042232908fe7be304b6b6b465c5feb71ba6861f37038aaf + uri: huggingface://bartowski/open-thoughts_OpenThinker-32B-GGUF/open-thoughts_OpenThinker-32B-Q4_K_M.gguf - &llama31 url: "github:mudler/LocalAI/gallery/llama3.1-instruct.yaml@master" ## LLama3.1 icon: https://avatars.githubusercontent.com/u/153379578