From 59cbf38b4b52a807097d9b88f9e570706f487f07 Mon Sep 17 00:00:00 2001 From: Ettore Di Giacinto Date: Sat, 14 Dec 2024 21:21:27 +0100 Subject: [PATCH 1/2] fix(gallery): correct syntax typo Signed-off-by: Ettore Di Giacinto --- gallery/index.yaml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/gallery/index.yaml b/gallery/index.yaml index dcf8df58f1ea..89569cc4ee0c 100644 --- a/gallery/index.yaml +++ b/gallery/index.yaml @@ -2022,7 +2022,7 @@ name: "fusechat-qwen-2.5-7b-instruct" icon: https://huggingface.co/FuseAI/FuseChat-Qwen-2.5-7B-Instruct/resolve/main/FuseChat-3.0.png urls: - -https://huggingface.co/FuseAI/FuseChat-Qwen-2.5-7B-Instruct + - https://huggingface.co/FuseAI/FuseChat-Qwen-2.5-7B-Instruct - https://huggingface.co/bartowski/FuseChat-Qwen-2.5-7B-Instruct-GGUF description: | We present FuseChat-3.0, a series of models crafted to enhance performance by integrating the strengths of multiple source LLMs into more compact target LLMs. To achieve this fusion, we utilized four powerful source LLMs: Gemma-2-27B-It, Mistral-Large-Instruct-2407, Qwen-2.5-72B-Instruct, and Llama-3.1-70B-Instruct. For the target LLMs, we employed three widely-used smaller models—Llama-3.1-8B-Instruct, Gemma-2-9B-It, and Qwen-2.5-7B-Instruct—along with two even more compact models—Llama-3.2-3B-Instruct and Llama-3.2-1B-Instruct. The implicit model fusion process involves a two-stage training pipeline comprising Supervised Fine-Tuning (SFT) to mitigate distribution discrepancies between target and source LLMs, and Direct Preference Optimization (DPO) for learning preferences from multiple source LLMs. The resulting FuseChat-3.0 models demonstrated substantial improvements in tasks related to general conversation, instruction following, mathematics, and coding. Notably, when Llama-3.1-8B-Instruct served as the target LLM, our fusion approach achieved an average improvement of 6.8 points across 14 benchmarks. Moreover, it showed significant improvements of 37.1 and 30.1 points on instruction-following test sets AlpacaEval-2 and Arena-Hard respectively. We have released the FuseChat-3.0 models on Huggingface, stay tuned for the forthcoming dataset and code. From e37bbbaacc85897b324422aa123e395e931d44aa Mon Sep 17 00:00:00 2001 From: Jason Godsey Date: Sat, 14 Dec 2024 13:25:51 -0700 Subject: [PATCH 2/2] fix: correct gallery/index.yaml (#4384) Update index.yaml DBG YAML errors: line 2025: cannot unmarshal !!str `-https:...` into []string Signed-off-by: Jason Godsey