From fb83238e9eb8dbff7a2a677f5a263ab66f449795 Mon Sep 17 00:00:00 2001 From: Ettore Di Giacinto Date: Fri, 11 Apr 2025 10:06:05 +0200 Subject: [PATCH] chore(model gallery): add zyphra_zr1-1.5b (#5157) Signed-off-by: Ettore Di Giacinto --- gallery/index.yaml | 14 ++++++++++++++ 1 file changed, 14 insertions(+) diff --git a/gallery/index.yaml b/gallery/index.yaml index 4b3c830e..d5afccca 100644 --- a/gallery/index.yaml +++ b/gallery/index.yaml @@ -8550,6 +8550,20 @@ - filename: agentica-org_DeepCoder-1.5B-Preview-Q4_K_M.gguf sha256: 9ddd89eddf8d56b1c16317932af56dc59b49ca2beec735d1332f5a3e0f225714 uri: huggingface://bartowski/agentica-org_DeepCoder-1.5B-Preview-GGUF/agentica-org_DeepCoder-1.5B-Preview-Q4_K_M.gguf +- !!merge <<: *deepseek-r1 + name: "zyphra_zr1-1.5b" + urls: + - https://huggingface.co/Zyphra/ZR1-1.5B + - https://huggingface.co/bartowski/Zyphra_ZR1-1.5B-GGUF + description: | + ZR1-1.5B is a small reasoning model trained extensively on both verified coding and mathematics problems with reinforcement learning. The model outperforms Llama-3.1-70B-Instruct on hard coding tasks and improves upon the base R1-Distill-1.5B model by over 50%, while achieving strong scores on math evaluations and a 37.91% pass@1 accuracy on GPQA-Diamond with just 1.5B parameters. + overrides: + parameters: + model: Zyphra_ZR1-1.5B-Q4_K_M.gguf + files: + - filename: Zyphra_ZR1-1.5B-Q4_K_M.gguf + sha256: 5442a9303f651eec30d8d17cd649982ddedf3629ff4faf3bf08d187900a7e7bd + uri: huggingface://bartowski/Zyphra_ZR1-1.5B-GGUF/Zyphra_ZR1-1.5B-Q4_K_M.gguf - &qwen2 url: "github:mudler/LocalAI/gallery/chatml.yaml@master" ## Start QWEN2 name: "qwen2-7b-instruct"