From 1689740269ef97e9778d75e78ae4d844520a113c Mon Sep 17 00:00:00 2001 From: Ettore Di Giacinto Date: Sun, 29 Sep 2024 20:39:39 +0200 Subject: [PATCH] models(gallery): add replete-llm-v2.5-qwen-14b (#3688) Signed-off-by: Ettore Di Giacinto --- gallery/index.yaml | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) diff --git a/gallery/index.yaml b/gallery/index.yaml index 847e004ce2f..7701efd5e68 100644 --- a/gallery/index.yaml +++ b/gallery/index.yaml @@ -237,6 +237,23 @@ - filename: BigQwen2.5-52B-Instruct-Q4_K_M.gguf sha256: 9c939f08e366b51b07096eb2ecb5cc2a82894ac7baf639e446237ad39889c896 uri: huggingface://bartowski/BigQwen2.5-52B-Instruct-GGUF/BigQwen2.5-52B-Instruct-Q4_K_M.gguf +- !!merge <<: *qwen25 + name: "replete-llm-v2.5-qwen-14b" + icon: https://cdn-uploads.huggingface.co/production/uploads/642cc1c253e76b4c2286c58e/ihnWXDEgV-ZKN_B036U1J.png + urls: + - https://huggingface.co/Replete-AI/Replete-LLM-V2.5-Qwen-14b + - https://huggingface.co/bartowski/Replete-LLM-V2.5-Qwen-14b-GGUF + description: | + Replete-LLM-V2.5-Qwen-14b is a continues finetuned version of Qwen2.5-14B. I noticed recently that the Qwen team did not learn from my methods of continuous finetuning, the great benefits, and no downsides of it. So I took it upon myself to merge the instruct model with the base model myself using the Ties merge method + + This version of the model shows higher performance than the original instruct and base models. + overrides: + parameters: + model: Replete-LLM-V2.5-Qwen-14b-Q4_K_M.gguf + files: + - filename: Replete-LLM-V2.5-Qwen-14b-Q4_K_M.gguf + sha256: 17d0792ff5e3062aecb965629f66e679ceb407e4542e8045993dcfe9e7e14d9d + uri: huggingface://bartowski/Replete-LLM-V2.5-Qwen-14b-GGUF/Replete-LLM-V2.5-Qwen-14b-Q4_K_M.gguf - &smollm ## SmolLM url: "github:mudler/LocalAI/gallery/chatml.yaml@master"