.circleci/config.yml

@@ -1,7 +1,7 @@
 version: 2.1
 setup: true
 orbs:
-  path-filtering: circleci/path-filtering@1.3.0
+  path-filtering: circleci/path-filtering@1.1.0
 
 workflows:
   version: 2.1

README.md

@@ -35,11 +35,6 @@ GPT4All is made possible by our compute partner <a href="https://www.paperspace.
     <img src="gpt4all-bindings/python/docs/assets/windows.png" style="height: 1em; width: auto" /> Windows Installer
   </a> &mdash;
 </p>
-<p>
-  &mdash; <a href="https://gpt4all.io/installers/gpt4all-installer-win64-arm.exe">
-    <img src="gpt4all-bindings/python/docs/assets/windows.png" style="height: 1em; width: auto" /> Windows ARM Installer
-  </a> &mdash;
-</p>
 <p>
   &mdash; <a href="https://gpt4all.io/installers/gpt4all-installer-darwin.dmg">
     <img src="gpt4all-bindings/python/docs/assets/mac.png" style="height: 1em; width: auto" /> macOS Installer
@@ -51,16 +46,10 @@ GPT4All is made possible by our compute partner <a href="https://www.paperspace.
   </a> &mdash;
 </p>
 <p>
-  The Windows and Linux builds require Intel Core i3 2nd Gen / AMD Bulldozer, or better.
+  Windows and Linux require Intel Core i3 2nd Gen / AMD Bulldozer, or better. x86-64 only, no ARM.
 </p>
 <p>
-  The Windows ARM build supports Qualcomm Snapdragon and Microsoft SQ1/SQ2 processors.
+  macOS requires Monterey 12.6 or newer. Best results with Apple Silicon M-series processors.
-</p>
-<p>
-  The Linux build is x86-64 only (no ARM).
-</p>
-<p>
-  The macOS build requires Monterey 12.6 or newer. Best results with Apple Silicon M-series processors.
 </p>
 
 See the full [System Requirements](gpt4all-chat/system_requirements.md) for more details.

gpt4all-chat/CMakeLists.txt

@@ -4,9 +4,9 @@ include(../common/common.cmake)
 
 set(APP_VERSION_MAJOR 3)
 set(APP_VERSION_MINOR 10)
-set(APP_VERSION_PATCH 1)
+set(APP_VERSION_PATCH 0)
 set(APP_VERSION_BASE "${APP_VERSION_MAJOR}.${APP_VERSION_MINOR}.${APP_VERSION_PATCH}")
-set(APP_VERSION "${APP_VERSION_BASE}-dev0")
+set(APP_VERSION "${APP_VERSION_BASE}")
 
 project(gpt4all VERSION ${APP_VERSION_BASE} LANGUAGES CXX C)
 

gpt4all-chat/metadata/latestnews.md

@@ -1,15 +1,26 @@
 ## Latest News
 
-GPT4All v3.10.0 was released on February 24th. Changes include:
+GPT4All v3.9.0 was released on February 4th. Changes include:
 
-* **Remote Models:**
+* **LocalDocs Fix:** LocalDocs no longer shows an error on later messages with reasoning models.
-  * The Add Model page now has a dedicated tab for remote model providers.
+* **DeepSeek Fix:** DeepSeek-R1 reasoning (in 'think' tags) no longer appears in chat names and follow-up questions.
-  * Groq, OpenAI, and Mistral remote models are now easier to configure.
+* **Windows ARM Improvements:**
-* **CUDA Compatibility:** GPUs with CUDA compute capability 5.0 such as the GTX 750 are now supported by the CUDA backend.
+  * Graphical artifacts on some SoCs have been fixed.
-* **New Model:** The non-MoE Granite model is now supported.
+  * A crash when adding a collection of PDFs to LocalDocs has been fixed.
-* **Translation Updates:**
+* **Template Parser Fixes:** Chat templates containing an unclosed comment no longer freeze GPT4All.
-  * The Italian translation has been updated.
+* **New Models:** OLMoE and Granite MoE models are now supported.
-  * The Simplified Chinese translation has been significantly improved.
+
-* **Better Chat Templates:** The default chat templates for OLMoE 7B 0924/0125 and Granite 3.1 3B/8B have been improved.
+GPT4All v3.8.0 was released on January 30th. Changes include:
-* **Whitespace Fixes:** DeepSeek-R1-based models now have better whitespace behavior in their output.
+
-* **Crash Fixes:** Several issues that could potentially cause GPT4All to crash have been fixed.
+* **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.

gpt4all-chat/metadata/release.json

@@ -273,10 +273,5 @@
     "version": "3.9.0",
     "notes": "* **LocalDocs Fix:** LocalDocs no longer shows an error on later messages with reasoning models.\n* **DeepSeek Fix:** DeepSeek-R1 reasoning (in 'think' tags) no longer appears in chat names and follow-up questions.\n* **Windows ARM Improvements:**\n  * Graphical artifacts on some SoCs have been fixed.\n  * A crash when adding a collection of PDFs to LocalDocs has been fixed.\n* **Template Parser Fixes:** Chat templates containing an unclosed comment no longer freeze GPT4All.\n* **New Models:** OLMoE and Granite MoE models are now supported.\n",
     "contributors": "* Jared Van Bortel (Nomic AI)\n* Adam Treat (Nomic AI)\n* ThiloteE (`@ThiloteE`)"
-  },
-  {
-    "version": "3.10.0",
-    "notes": "* **Remote Models:**\n  * The Add Model page now has a dedicated tab for remote model providers.\n  * Groq, OpenAI, and Mistral remote models are now easier to configure.\n* **CUDA Compatibility:** GPUs with CUDA compute capability 5.0 such as the GTX 750 are now supported by the CUDA backend.\n* **New Model:** The non-MoE Granite model is now supported.\n* **Translation Updates:**\n  * The Italian translation has been updated.\n  * The Simplified Chinese translation has been significantly improved.\n* **Better Chat Templates:** The default chat templates for OLMoE 7B 0924/0125 and Granite 3.1 3B/8B have been improved.\n* **Whitespace Fixes:** DeepSeek-R1-based models now have better whitespace behavior in their output.\n* **Crash Fixes:** Several issues that could potentially cause GPT4All to crash have been fixed.\n",
-    "contributors": "* Jared Van Bortel (Nomic AI)\n* Adam Treat (Nomic AI)\n* ThiloteE (`@ThiloteE`)\n* Lil Bob (`@Junior2Ran`)\n* Riccardo Giovanetti (`@Harvester62`)"
   }
 ]