From ceb7726f22c4f98ab85f05729cb66bcd557364ae Mon Sep 17 00:00:00 2001 From: AT Date: Mon, 12 Aug 2024 18:15:58 -0400 Subject: [PATCH] Add some news about our latest translation release. (#2848) Signed-off-by: Adam Treat Signed-off-by: Jared Van Bortel Co-authored-by: Jared Van Bortel --- gpt4all-chat/metadata/latestnews.md | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) diff --git a/gpt4all-chat/metadata/latestnews.md b/gpt4all-chat/metadata/latestnews.md index 1b24122a..ccd7f916 100644 --- a/gpt4all-chat/metadata/latestnews.md +++ b/gpt4all-chat/metadata/latestnews.md @@ -1,6 +1,9 @@ ## Latest News -* **New Model Support**: LLaMa 3.1 8b, Gemma, Mixtral, GPT-NeoX, Gemma 2, OpenELM, ChatGLM, Jais architectures, StarCoder2, XVERSE, Command R, and OLMo (all with Vulkan support) -* **Suggested Follow Up Questions**: Get follow up questions on your LocalDocs or chats automatically suggested +We're happy to announce that version 3.2.0 has been released! This new version brings: -Roadmap: we're planning support for tools in GPT4All that models like LLaMa 3.1 can use. Share suggestions on Discord! +* **Official Language Translations**: Translations for Simplified Chinese, Traditional Chinese, Italian, Portuguese, Romanian, and Spanish +* **Context Window Improvements**: Significantly faster context recalculation when context runs out +* **Bugfixes**: Models no longer stop generating when they run out of context + +Also, Qwen2-1.5B-Instruct was recently added to the model list, which has good Chinese support.