From a6a0121118e8f5ac0ac4d48812779a0bf2bffffa Mon Sep 17 00:00:00 2001 From: Ettore Di Giacinto Date: Sat, 22 Feb 2025 11:19:04 +0100 Subject: [PATCH] chore(model gallery): add rombo-org_rombo-llm-v3.0-qwen-72b (#4882) Signed-off-by: Ettore Di Giacinto --- gallery/index.yaml | 15 +++++++++++++++ 1 file changed, 15 insertions(+) diff --git a/gallery/index.yaml b/gallery/index.yaml index 79a8ac1d..e44e0807 100644 --- a/gallery/index.yaml +++ b/gallery/index.yaml @@ -4021,6 +4021,21 @@ - filename: smirki_UIGEN-T1.1-Qwen-7B-Q4_K_M.gguf sha256: e5d78dea15d4281455d64aef1c0f18da5674c6f15285a2991e63208d264b61ae uri: huggingface://bartowski/smirki_UIGEN-T1.1-Qwen-7B-GGUF/smirki_UIGEN-T1.1-Qwen-7B-Q4_K_M.gguf +- !!merge <<: *qwen25 + name: "rombo-org_rombo-llm-v3.0-qwen-72b" + icon: https://cdn-uploads.huggingface.co/production/uploads/642cc1c253e76b4c2286c58e/wp9qOi2K2WGzkey0I3SgH.jpeg + urls: + - https://huggingface.co/Rombo-Org/Rombo-LLM-V3.0-Qwen-72b + - https://huggingface.co/bartowski/Rombo-Org_Rombo-LLM-V3.0-Qwen-72b-GGUF + description: | + Rombos-LLM-V3.0-Qwen-72b is a continues finetuned version of the Rombo-LLM-V2.5-Qwen-72b on a Reasoning and Non-reasoning dataset. The models performs exceptionally well when paired with the system prompt that it was trained on during reasoning training. Nearing SOTA levels even quantized to 4-bit. + overrides: + parameters: + model: Rombo-Org_Rombo-LLM-V3.0-Qwen-72b-Q4_K_M.gguf + files: + - filename: Rombo-Org_Rombo-LLM-V3.0-Qwen-72b-Q4_K_M.gguf + sha256: 3f159ffb494338d03502096c52db5e062a81b09acfd3cc4f6352ca61d6f489df + uri: huggingface://bartowski/Rombo-Org_Rombo-LLM-V3.0-Qwen-72b-GGUF/Rombo-Org_Rombo-LLM-V3.0-Qwen-72b-Q4_K_M.gguf - &llama31 url: "github:mudler/LocalAI/gallery/llama3.1-instruct.yaml@master" ## LLama3.1 icon: https://avatars.githubusercontent.com/u/153379578