From c27ce6c54df8fa627c85f919c92198878e55e849 Mon Sep 17 00:00:00 2001 From: Ettore Di Giacinto Date: Thu, 20 Feb 2025 15:52:28 +0100 Subject: [PATCH] chore(model gallery): add internlm_oreal-32b (#4872) Signed-off-by: Ettore Di Giacinto --- gallery/index.yaml | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) diff --git a/gallery/index.yaml b/gallery/index.yaml index ffb44355..ed401325 100644 --- a/gallery/index.yaml +++ b/gallery/index.yaml @@ -3959,6 +3959,22 @@ - filename: open-r1_OpenR1-Qwen-7B-Q4_K_M.gguf sha256: d3bf99666cd19b637948ec9943044b591d3b906d0ee4f3ef1b3eb693ac8f66a6 uri: huggingface://bartowski/open-r1_OpenR1-Qwen-7B-GGUF/open-r1_OpenR1-Qwen-7B-Q4_K_M.gguf +- !!merge <<: *qwen25 + name: "internlm_oreal-32b" + urls: + - https://huggingface.co/internlm/OREAL-32B + - https://huggingface.co/bartowski/internlm_OREAL-32B-GGUF + description: | + We introduce OREAL-7B and OREAL-32B, a mathematical reasoning model series trained using Outcome REwArd-based reinforcement Learning, a novel RL framework designed for tasks where only binary outcome rewards are available. + + With OREAL, a 7B model achieves 94.0 pass@1 accuracy on MATH-500, matching the performance of previous 32B models. OREAL-32B further surpasses previous distillation-trained 32B models, reaching 95.0 pass@1 accuracy on MATH-500. + overrides: + parameters: + model: internlm_OREAL-32B-Q4_K_M.gguf + files: + - filename: internlm_OREAL-32B-Q4_K_M.gguf + sha256: 5af1b3f66e3a1f95931a54500d03368c0cc7ca42cc67370338b29c18362e4a94 + uri: huggingface://bartowski/internlm_OREAL-32B-GGUF/internlm_OREAL-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