From 2d66ea8a31439d2eb926283d0ac451b7c692be25 Mon Sep 17 00:00:00 2001 From: Mengwei Xu Date: Sun, 14 Jul 2024 10:40:12 +0800 Subject: [PATCH] Update README.md --- README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/README.md b/README.md index 7282e546..e0f743fa 100644 --- a/README.md +++ b/README.md @@ -12,7 +12,7 @@ Wait.. why on-device multimodal LLM? - It's a key building block for [intelligent personal agent](https://arxiv.org/pdf/2401.05459.pdf), text-based image searching/retrieval, screen VQA, and many more exciting mobile apps, without giving away your private data (chat history, screenshots, taken photos, etc). ## Recent update -- [Comming soon] Add new backend: NPU +- [:fire::fire:Comming soon] Supporting Qualcomm NPU: [>1000 tokens/second prefilling!](https://arxiv.org/pdf/2407.05858v1) - [2024 May 29] Support new model: Mistral V0.2 7B https://github.com/UbiquitousLearning/mllm/pull/83 - [2024 May 4] Support new model: QWen V1.5 0.5B https://github.com/UbiquitousLearning/mllm/pull/79 - [2024 April 9] Support new model: Gemma 2B https://github.com/UbiquitousLearning/mllm/pull/75