diff --git a/gpt4all-chat/metadata/latestnews.md b/gpt4all-chat/metadata/latestnews.md index d6a9ad31..f46fb721 100644 --- a/gpt4all-chat/metadata/latestnews.md +++ b/gpt4all-chat/metadata/latestnews.md @@ -1,17 +1,16 @@ ## Latest News -GPT4All v3.7.0 was released on January 23rd. Changes include: +GPT4All v3.8.0 was released on January 30th. Changes include: -* **Windows ARM Support:** GPT4All now supports the Windows ARM platform, ensuring compatibility with devices powered by Qualcomm Snapdragon and Microsoft SQ-series processors. - * **NOTE:** Support for GPU and/or NPU acceleration is not available at this time. Only the CPU will be used to run LLMs. - * **NOTE:** You must install the new *Windows ARM* version of GPT4All from the website. The standard *Windows* version will not work due to emulation limitations. -* **Fixed Updating on macOS:** The maintenance tool no longer crashes when attempting to update or uninstall GPT4All on Sequoia. - * **NOTE:** If you have installed the version from the GitHub releases as a workaround for this issue, you can safely uninstall it and switch back to the version from the website. -* **Fixed Chat Saving on macOS:** Chats now save as expected when the application is quit with Command-Q. -* **Code Interpreter Improvements:** - * The behavior when the code takes too long to execute and times out has been improved. - * console.log now accepts multiple arguments for better compatibility with native JavaScript. -* **Chat Templating Improvements:** - * Two crashes and one compatibility issue have been fixed in the chat template parser. - * The default chat template for EM German Mistral has been fixed. - * Automatic replacements have been added for five new models as we continue to improve compatibility with common chat templates. +* **Native DeepSeek-R1-Distill Support:** GPT4All now has robust support for the DeepSeek-R1 family of distillations. + * Several model variants are now available on the downloads page. + * Reasoning (wrapped in "think" tags) is displayed similarly to the Reasoner model. + * The DeepSeek-R1 Qwen pretokenizer is now supported, resolving the loading failure in previous versions. + * The model is now configured with a GPT4All-compatible prompt template by default. +* **Chat Templating Overhaul:** The template parser has been *completely* replaced with one that has much better compatibility with common models. +* **Code Interpreter Fixes:** + * An issue preventing the code interpreter from logging a single string in v3.7.0 has been fixed. + * The UI no longer freezes while the code interpreter is running a computation. +* **Local Server Fixes:** + * An issue preventing the server from using LocalDocs after the first request since v3.5.0 has been fixed. + * System messages are now correctly hidden from the message history. diff --git a/gpt4all-chat/metadata/release.json b/gpt4all-chat/metadata/release.json index 7b40dbe3..70d1595e 100644 --- a/gpt4all-chat/metadata/release.json +++ b/gpt4all-chat/metadata/release.json @@ -263,5 +263,10 @@ "version": "3.7.0", "notes": "* **Windows ARM Support:** GPT4All now supports the Windows ARM platform, ensuring compatibility with devices powered by Qualcomm Snapdragon and Microsoft SQ-series processors.\n * **NOTE:** Support for GPU and/or NPU acceleration is not available at this time. Only the CPU will be used to run LLMs.\n * **NOTE:** You must install the new *Windows ARM* version of GPT4All from the website. The standard *Windows* version will not work due to emulation limitations.\n* **Fixed Updating on macOS:** The maintenance tool no longer crashes when attempting to update or uninstall GPT4All on Sequoia.\n * **NOTE:** If you have installed the version from the GitHub releases as a workaround for this issue, you can safely uninstall it and switch back to the version from the website.\n* **Fixed Chat Saving on macOS:** Chats now save as expected when the application is quit with Command-Q.\n* **Code Interpreter Improvements:**\n * The behavior when the code takes too long to execute and times out has been improved.\n * console.log now accepts multiple arguments for better compatibility with native JavaScript.\n* **Chat Templating Improvements:**\n * Two crashes and one compatibility issue have been fixed in the chat template parser.\n * The default chat template for EM German Mistral has been fixed.\n * Automatic replacements have been added for five new models as we continue to improve compatibility with common chat templates.\n", "contributors": "* Jared Van Bortel (Nomic AI)\n* Adam Treat (Nomic AI)\n* Riccardo Giovanetti (`@Harvester62`)" + }, + { + "version": "3.8.0", + "notes": "* **Native DeepSeek-R1-Distill Support:** GPT4All now has robust support for the DeepSeek-R1 family of distillations.\n * Several model variants are now available on the downloads page.\n * Reasoning (wrapped in \"think\" tags) is displayed similarly to the Reasoner model.\n * The DeepSeek-R1 Qwen pretokenizer is now supported, resolving the loading failure in previous versions.\n * The model is now configured with a GPT4All-compatible prompt template by default.\n* **Chat Templating Overhaul:** The template parser has been *completely* replaced with one that has much better compatibility with common models.\n* **Code Interpreter Fixes:**\n * An issue preventing the code interpreter from logging a single string in v3.7.0 has been fixed.\n * The UI no longer freezes while the code interpreter is running a computation.\n* **Local Server Fixes:**\n * An issue preventing the server from using LocalDocs after the first request since v3.5.0 has been fixed.\n * System messages are now correctly hidden from the message history.\n", + "contributors": "* Jared Van Bortel (Nomic AI)\n* Adam Treat (Nomic AI)\n* ThiloteE (`@ThiloteE`)" } ]