add js side of dispose

Signed-off-by: Andriy Mulyar <andriy.mulyar@gmail.com>

README.md

@@ -1,11 +1,9 @@
 <h1 align="center">GPT4All</h1>
 
-<p align="center">Open-source assistant-style large language models that run locally on your CPU</p>
-
-<p align="center"><strong>New</strong>: Now with Nomic Vulkan Universal GPU support. <a href="https://blog.nomic.ai/posts/gpt4all-gpu-inference-with-vulkan">Learn more</a>.</p>
+<p align="center">Open-source large language models that run locally on your CPU and nearly any GPU</p>
 
 <p align="center">
-<a href="https://gpt4all.io">GPT4All Website</a>
+<a href="https://gpt4all.io">GPT4All Website and Models</a>
 </p>
 
 <p align="center">
@@ -32,13 +30,24 @@ Run on an M1 macOS Device (not sped up!)
 </p>
 
 ## GPT4All: An ecosystem of open-source on-edge large language models.
-GPT4All is an ecosystem to train and deploy **powerful** and **customized** large language models that run locally on consumer grade CPUs. Note that your CPU needs to support [AVX or AVX2 instructions](https://en.wikipedia.org/wiki/Advanced_Vector_Extensions).
+
+> [!IMPORTANT]
+> GPT4All v2.5.0 and newer only supports models in GGUF format (.gguf). Models used with a previous version of GPT4All (.bin extension) will no longer work.
+
+GPT4All is an ecosystem to run **powerful** and **customized** large language models that work locally on consumer grade CPUs and any GPU. Note that your CPU needs to support [AVX or AVX2 instructions](https://en.wikipedia.org/wiki/Advanced_Vector_Extensions).
 
 Learn more in the [documentation](https://docs.gpt4all.io).
 
-The goal is simple - be the best instruction tuned assistant-style language model that any person or enterprise can freely use, distribute and build on.
+A GPT4All model is a 3GB - 8GB file that you can download and plug into the GPT4All open-source ecosystem software. **Nomic AI** supports and maintains this software ecosystem to enforce quality and security alongside spearheading the effort to allow any person or enterprise to easily train and deploy their own on-edge large language models.
 
-A GPT4All model is a 3GB - 8GB file that you can download and plug into the GPT4All open-source ecosystem software. **Nomic AI** supports and maintains this software ecosystem to enforce quality and security alongside spearheading the effort to allow any person or enterprise to easily train and deploy their own on-edge large language models. 
+### What's New ([Issue Tracker](https://github.com/orgs/nomic-ai/projects/2))
+- **October 19th, 2023**: GGUF Support Launches with Support for:
+    - Mistral 7b base model, an updated model gallery on [gpt4all.io](https://gpt4all.io), several new local code models including Rift Coder v1.5
+    - [Nomic Vulkan](https://blog.nomic.ai/posts/gpt4all-gpu-inference-with-vulkan) support for Q4_0, Q6 quantizations in GGUF.
+    - Offline build support for running old versions of the GPT4All Local LLM Chat Client.
+- **September 18th, 2023**: [Nomic Vulkan](https://blog.nomic.ai/posts/gpt4all-gpu-inference-with-vulkan) launches supporting local LLM inference on AMD, Intel, Samsung, Qualcomm and NVIDIA GPUs.
+- **August 15th, 2023**: GPT4All API launches allowing inference of local LLMs from docker containers.
+- **July 2023**: Stable support for LocalDocs, a GPT4All Plugin that allows you to privately and locally chat with your data.
 
 
 ### Chat Client

gpt4all-api/gpt4all_api/Dockerfile.buildkit

@@ -18,6 +18,6 @@ COPY gpt4all_api/app /app
 RUN mkdir -p /models
 
 # Include the following line to bake a model into the image and not have to download it on API start.
-RUN wget -q --show-progress=off https://gpt4all.io/models/gguf/${MODEL_BIN} -P /models \
+RUN wget -q --show-progress=off https://gpt4all.io/models/${MODEL_BIN} -P /models \
   && md5sum /models/${MODEL_BIN}
 

gpt4all-backend/llama.cpp-mainline

@@ -1 +1 @@
-Subproject commit a8ed8c858985ef94d97a3cf2c97085b680c6d5d0
+Subproject commit 2dee60214b0001cf03e1cec0a53a61a17b55c1eb

gpt4all-backend/llmodel.cpp

@@ -10,6 +10,7 @@
 #include <cassert>
 #include <cstdlib>
 #include <sstream>
+#include <regex>
 #ifdef _MSC_VER
 #include <intrin.h>
 #endif
@@ -81,6 +82,13 @@ const std::vector<LLModel::Implementation> &LLModel::Implementation::implementat
     static auto* libs = new std::vector<Implementation>([] () {
         std::vector<Implementation> fres;
 
+        std::string impl_name_re = "(bert|llama|gptj|llamamodel-mainline)";
+        if (requires_avxonly()) {
+            impl_name_re += "-avxonly";
+        } else {
+            impl_name_re += "-(default|metal)";
+        }
+        std::regex re(impl_name_re);
         auto search_in_directory = [&](const std::string& paths) {
             std::stringstream ss(paths);
             std::string path;
@@ -90,7 +98,10 @@ const std::vector<LLModel::Implementation> &LLModel::Implementation::implementat
                 // Iterate over all libraries
                 for (const auto& f : std::filesystem::directory_iterator(fs_path)) {
                     const std::filesystem::path& p = f.path();
+
                     if (p.extension() != LIB_FILE_EXT) continue;
+                    if (!std::regex_search(p.stem().string(), re)) continue;
+
                     // Add to list if model implementation
                     try {
                         Dlhandle dl(p.string());

gpt4all-bindings/cli/README.md

@@ -40,5 +40,5 @@ directory, if necessary.
 If you have already saved a model beforehand, specify its path with the `-m`/`--model` argument,
 for example:
 ```shell
-python app.py repl --model /home/user/my-gpt4all-models/GPT4All-13B-snoozy.ggmlv3.q4_0.bin
+python app.py repl --model /home/user/my-gpt4all-models/gpt4all-13b-snoozy-q4_0.gguf
 ```

gpt4all-bindings/cli/app.py

@@ -1,3 +1,4 @@
+#!/usr/bin/env python3
 """GPT4All CLI
 
 The GPT4All CLI is a self-contained script based on the `gpt4all` and `typer` packages. It offers a
@@ -53,7 +54,7 @@ def repl(
     model: Annotated[
         str,
         typer.Option("--model", "-m", help="Model to use for chatbot"),
-    ] = "ggml-gpt4all-j-v1.3-groovy",
+    ] = "mistral-7b-instruct-v0.1.Q4_0.gguf",
     n_threads: Annotated[
         int,
         typer.Option("--n-threads", "-t", help="Number of threads to use for chatbot"),

gpt4all-bindings/csharp/build_linux.sh

@@ -1,3 +1,4 @@
+#!/bin/sh
 mkdir -p runtimes
 rm -rf runtimes/linux-x64
 mkdir -p runtimes/linux-x64/native

gpt4all-bindings/python/README.md

@@ -50,7 +50,7 @@ Test it out! In a Python script or console:
 
 ```python
 from gpt4all import GPT4All
-model = GPT4All("orca-mini-3b.ggmlv3.q4_0.bin")
+model = GPT4All("orca-mini-3b-gguf2-q4_0.gguf")
 output = model.generate("The capital of France is ", max_tokens=3)
 print(output)
 ```
@@ -59,7 +59,7 @@ print(output)
 GPU Usage
 ```python
 from gpt4all import GPT4All
-model = GPT4All("orca-mini-3b.ggmlv3.q4_0.bin", device='gpu') # device='amd', device='intel'
+model = GPT4All("orca-mini-3b-gguf2-q4_0.gguf", device='gpu') # device='amd', device='intel'
 output = model.generate("The capital of France is ", max_tokens=3)
 print(output)
 ```

gpt4all-bindings/python/docs/gpt4all_cli.md

@@ -166,7 +166,7 @@ If you want to use a different model, you can do so with the `-m`/`--model` para
 model file name is provided, it will again check in `.cache/gpt4all/` and might start downloading.
 If instead given a path to an existing model, the command could for example look like this:
 ```shell
-python app.py repl --model /home/user/my-gpt4all-models/GPT4All-13B-snoozy.ggmlv3.q4_0.bin
+python app.py repl --model /home/user/my-gpt4all-models/gpt4all-13b-snoozy-q4_0.gguf
 ```
 
 When you're done and want to end a session, simply type `/exit`.

gpt4all-bindings/python/docs/gpt4all_python.md

@@ -11,7 +11,7 @@ pip install gpt4all
 === "GPT4All Example"
     ``` py
     from gpt4all import GPT4All
-    model = GPT4All("orca-mini-3b.ggmlv3.q4_0.bin")
+    model = GPT4All("orca-mini-3b-gguf2-q4_0.gguf")
     output = model.generate("The capital of France is ", max_tokens=3)
     print(output)
     ```
@@ -35,7 +35,7 @@ Use the GPT4All `chat_session` context manager to hold chat conversations with t
 
 === "GPT4All Example"
     ``` py
-    model = GPT4All(model_name='orca-mini-3b.ggmlv3.q4_0.bin')
+    model = GPT4All(model_name='orca-mini-3b-gguf2-q4_0.gguf')
     with model.chat_session():
         response1 = model.generate(prompt='hello', temp=0)
         response2 = model.generate(prompt='write me a short poem', temp=0)
@@ -89,7 +89,7 @@ To interact with GPT4All responses as the model generates, use the `streaming=Tr
 === "GPT4All Streaming Example"
     ``` py
     from gpt4all import GPT4All
-    model = GPT4All("orca-mini-3b.ggmlv3.q4_0.bin")
+    model = GPT4All("orca-mini-3b-gguf2-q4_0.gguf")
     tokens = []
     for token in model.generate("The capital of France is", max_tokens=20, streaming=True):
         tokens.append(token)
@@ -135,7 +135,7 @@ is the same as if it weren't provided; that is, `~/.cache/gpt4all/` is the defau
     ``` py
     from pathlib import Path
     from gpt4all import GPT4All
-    model = GPT4All(model_name='orca-mini-3b.ggmlv3.q4_0.bin',
+    model = GPT4All(model_name='orca-mini-3b-gguf2-q4_0.gguf',
                     model_path=(Path.home() / '.cache' / 'gpt4all'),
                     allow_download=False)
     response = model.generate('my favorite 3 fruits are:', temp=0)
@@ -152,7 +152,7 @@ If you want to point it at the chat GUI's default folder, it should be:
     from pathlib import Path
     from gpt4all import GPT4All
 
-    model_name = 'orca-mini-3b.ggmlv3.q4_0.bin'
+    model_name = 'orca-mini-3b-gguf2-q4_0.gguf'
     model_path = Path.home() / 'Library' / 'Application Support' / 'nomic.ai' / 'GPT4All'
     model = GPT4All(model_name, model_path)
     ```
@@ -161,7 +161,7 @@ If you want to point it at the chat GUI's default folder, it should be:
     from pathlib import Path
     from gpt4all import GPT4All
     import os
-    model_name = 'orca-mini-3b.ggmlv3.q4_0.bin'
+    model_name = 'orca-mini-3b-gguf2-q4_0.gguf'
     model_path = Path(os.environ['LOCALAPPDATA']) / 'nomic.ai' / 'GPT4All'
     model = GPT4All(model_name, model_path)
     ```
@@ -170,7 +170,7 @@ If you want to point it at the chat GUI's default folder, it should be:
     from pathlib import Path
     from gpt4all import GPT4All
 
-    model_name = 'orca-mini-3b.ggmlv3.q4_0.bin'
+    model_name = 'orca-mini-3b-gguf2-q4_0.gguf'
     model_path = Path.home() / '.local' / 'share' / 'nomic.ai' / 'GPT4All'
     model = GPT4All(model_name, model_path)
     ```
@@ -182,7 +182,7 @@ from pathlib import Path
 import gpt4all.gpt4all
 gpt4all.gpt4all.DEFAULT_MODEL_DIRECTORY = Path.home() / 'my' / 'models-directory'
 from gpt4all import GPT4All
-model = GPT4All('orca-mini-3b.ggmlv3.q4_0.bin')
+model = GPT4All('orca-mini-3b-gguf2-q4_0.gguf')
 ...
 ```
 
@@ -193,7 +193,7 @@ Session templates can be customized when starting a `chat_session` context:
 === "GPT4All Custom Session Templates Example"
     ``` py
     from gpt4all import GPT4All
-    model = GPT4All('ggml-Wizard-Vicuna-7B-Uncensored.ggmlv3.q4_1.bin')
+    model = GPT4All('wizardlm-13b-v1.2.Q4_0.gguf')
     system_template = 'A chat between a curious user and an artificial intelligence assistant.'
     # many models use triple hash '###' for keywords, Vicunas are simpler:
     prompt_template = 'USER: {0}\nASSISTANT: '
@@ -222,7 +222,7 @@ To do the same outside a session, the input has to be formatted manually. For ex
 
 === "GPT4All Templates Outside a Session Example"
     ``` py
-    model = GPT4All('ggml-Wizard-Vicuna-7B-Uncensored.ggmlv3.q4_1.bin')
+    model = GPT4All('wizardlm-13b-v1.2.Q4_0.gguf')
     system_template = 'A chat between a curious user and an artificial intelligence assistant.'
     prompt_template = 'USER: {0}\nASSISTANT: '
     prompts = ['name 3 colors', 'now name 3 fruits', 'what were the 3 colors in your earlier response?']
@@ -285,7 +285,7 @@ customized in a subclass. As an example:
     ```
 === "GPT4All Custom Subclass Example"
     ``` py
-    model = RotatingTemplateGPT4All('ggml-Wizard-Vicuna-7B-Uncensored.ggmlv3.q4_1.bin')
+    model = RotatingTemplateGPT4All('wizardlm-13b-v1.2.Q4_0.gguf')
     with model.chat_session():  # starting a session is optional in this example
         response1 = model.generate("hi, who are you?")
         print(response1)
@@ -345,7 +345,7 @@ logging infrastructure offers [many more customization options][py-logging-cookb
     import logging
     from gpt4all import GPT4All
     logging.basicConfig(level=logging.INFO)
-    model = GPT4All('nous-hermes-13b.ggmlv3.q4_0.bin')
+    model = GPT4All('nous-hermes-llama2-13b.Q4_0.gguf')
     with model.chat_session('You are a geography expert.\nBe terse.',
                             '### Instruction:\n{0}\n### Response:\n'):
         response = model.generate('who are you?', temp=0)
@@ -414,7 +414,7 @@ If you know exactly when a model should stop responding, you can add a custom ca
 === "GPT4All Custom Stop Callback"
     ``` py
     from gpt4all import GPT4All
-    model = GPT4All('orca-mini-3b.ggmlv3.q4_0.bin')
+    model = GPT4All('orca-mini-3b-gguf2-q4_0.gguf')
 
     def stop_on_token_callback(token_id, token_string):
         # one sentence is enough:

gpt4all-bindings/python/docs/index.md

@@ -9,7 +9,7 @@ GPT4All software is optimized to run inference of 3-13 billion parameter large l
 === "GPT4All Example"
     ``` py
     from gpt4all import GPT4All
-    model = GPT4All("orca-mini-3b.ggmlv3.q4_0.bin")
+    model = GPT4All("orca-mini-3b-gguf2-q4_0.gguf")
     output = model.generate("The capital of France is ", max_tokens=3)
     print(output)
     ```

gpt4all-bindings/python/gpt4all/gpt4all.py

@@ -75,7 +75,7 @@ class GPT4All:
         Constructor
 
         Args:
-            model_name: Name of GPT4All or custom model. Including ".bin" file extension is optional but encouraged.
+            model_name: Name of GPT4All or custom model. Including ".gguf" file extension is optional but encouraged.
             model_path: Path to directory containing model file or, if file does not exist, where to download model.
                 Default is None, in which case models will be stored in `~/.cache/gpt4all/`.
             model_type: Model architecture. This argument currently does not have any functionality and is just used as
@@ -141,7 +141,7 @@ class GPT4All:
             Model config.
         """
 
-        model_filename = append_bin_suffix_if_missing(model_name)
+        model_filename = append_extension_if_missing(model_name)
 
         # get the config for the model
         config: ConfigType = DEFAULT_MODEL_CONFIG
@@ -201,7 +201,7 @@ class GPT4All:
         Download model from https://gpt4all.io.
 
         Args:
-            model_filename: Filename of model (with .bin extension).
+            model_filename: Filename of model (with .gguf extension).
             model_path: Path to download model to.
             verbose: If True (default), print debug messages.
             url: the models remote url (e.g. may be hosted on HF)
@@ -456,7 +456,7 @@ def empty_chat_session(system_prompt: str = "") -> List[MessageType]:
     return [{"role": "system", "content": system_prompt}]
 
 
-def append_bin_suffix_if_missing(model_name):
+def append_extension_if_missing(model_name):
     if not model_name.endswith((".bin", ".gguf")):
-        model_name += ".bin"
+        model_name += ".gguf"
     return model_name

gpt4all-bindings/python/gpt4all/tests/test_embed_timings.py

@@ -1,3 +1,4 @@
+#!/usr/bin/env python3
 import sys
 import time
 from io import StringIO

gpt4all-bindings/python/gpt4all/tests/test_gpt4all.py

@@ -8,7 +8,7 @@ import pytest
 
 
 def test_inference():
-    model = GPT4All(model_name='orca-mini-3b.ggmlv3.q4_0.bin')
+    model = GPT4All(model_name='orca-mini-3b-gguf2-q4_0.gguf')
     output_1 = model.generate('hello', top_k=1)
 
     with model.chat_session():
@@ -47,49 +47,44 @@ def do_long_input(model):
 
 
 def test_inference_long_orca_3b():
-    model = GPT4All(model_name="orca-mini-3b.ggmlv3.q4_0.bin")
+    model = GPT4All(model_name="orca-mini-3b-gguf2-q4_0.gguf")
     do_long_input(model)
 
 
 def test_inference_long_falcon():
-    model = GPT4All(model_name='ggml-model-gpt4all-falcon-q4_0.bin')
+    model = GPT4All(model_name='gpt4all-falcon-q4_0.gguf')
     do_long_input(model)
 
 
 def test_inference_long_llama_7b():
-    model = GPT4All(model_name="orca-mini-7b.ggmlv3.q4_0.bin")
+    model = GPT4All(model_name="mistral-7b-openorca.Q4_0.gguf")
     do_long_input(model)
 
 
 def test_inference_long_llama_13b():
-    model = GPT4All(model_name='ggml-nous-hermes-13b.ggmlv3.q4_0.bin')
+    model = GPT4All(model_name='nous-hermes-llama2-13b.Q4_0.gguf')
     do_long_input(model)
 
 
 def test_inference_long_mpt():
-    model = GPT4All(model_name='ggml-mpt-7b-chat.bin')
+    model = GPT4All(model_name='mpt-7b-chat-q4_0.gguf')
     do_long_input(model)
 
 
 def test_inference_long_replit():
-    model = GPT4All(model_name='ggml-replit-code-v1-3b.bin')
-    do_long_input(model)
-
-
-def test_inference_long_groovy():
-    model = GPT4All(model_name='ggml-gpt4all-j-v1.3-groovy.bin')
+    model = GPT4All(model_name='replit-code-v1_5-3b-q4_0.gguf')
     do_long_input(model)
 
 
 def test_inference_hparams():
-    model = GPT4All(model_name='orca-mini-3b.ggmlv3.q4_0.bin')
+    model = GPT4All(model_name='orca-mini-3b-gguf2-q4_0.gguf')
 
     output = model.generate("The capital of france is ", max_tokens=3)
     assert 'Paris' in output
 
 
 def test_inference_falcon():
-    model = GPT4All(model_name='ggml-model-gpt4all-falcon-q4_0.bin')
+    model = GPT4All(model_name='gpt4all-falcon-q4_0.gguf')
     prompt = 'hello'
     output = model.generate(prompt)
     assert isinstance(output, str)
@@ -97,7 +92,7 @@ def test_inference_falcon():
 
 
 def test_inference_mpt():
-    model = GPT4All(model_name='ggml-mpt-7b-chat.bin')
+    model = GPT4All(model_name='mpt-7b-chat-q4_0.gguf')
     prompt = 'hello'
     output = model.generate(prompt)
     assert isinstance(output, str)

gpt4all-bindings/python/setup.py

@@ -61,7 +61,7 @@ copy_prebuilt_C_lib(SRC_CLIB_DIRECtORY,
 
 setup(
     name=package_name,
-    version="2.0.0",
+    version="2.0.1",
     description="Python bindings for GPT4All",
     author="Nomic and the Open Source Community",
     author_email="support@nomic.ai",

gpt4all-bindings/typescript/index.cc

@@ -15,7 +15,8 @@ Napi::Function NodeModelWrapper::GetClass(Napi::Env env) {
        InstanceMethod("initGpuByString", &NodeModelWrapper::InitGpuByString),
        InstanceMethod("hasGpuDevice", &NodeModelWrapper::HasGpuDevice),
        InstanceMethod("listGpu", &NodeModelWrapper::GetGpuDevices),
-       InstanceMethod("memoryNeeded", &NodeModelWrapper::GetRequiredMemory)
+       InstanceMethod("memoryNeeded", &NodeModelWrapper::GetRequiredMemory),
+       InstanceMethod("dispose", &NodeModelWrapper::Dispose)
     });
     // Keep a static reference to the constructor
     //
@@ -313,7 +314,9 @@ Napi::Value NodeModelWrapper::GetRequiredMemory(const Napi::CallbackInfo& info)
     threadSafeContext->nativeThread = std::thread(threadEntry, threadSafeContext);
     return threadSafeContext->deferred_.Promise();
   }
-
+  void NodeModelWrapper::Dispose(const Napi::CallbackInfo& info) {
+    llmodel_model_destroy(inference_);
+  }
   void NodeModelWrapper::SetThreadCount(const Napi::CallbackInfo& info) {
     if(info[0].IsNumber()) {
         llmodel_setThreadCount(GetInference(), info[0].As<Napi::Number>().Int64Value());

gpt4all-bindings/typescript/index.h

@@ -24,6 +24,7 @@ public:
    */
   Napi::Value Prompt(const Napi::CallbackInfo& info);
   void SetThreadCount(const Napi::CallbackInfo& info);
+  void Dispose(const Napi::CallbackInfo& info);
   Napi::Value getName(const Napi::CallbackInfo& info);
   Napi::Value ThreadCount(const Napi::CallbackInfo& info);
   Napi::Value GenerateEmbedding(const Napi::CallbackInfo& info);

gpt4all-bindings/typescript/spec/chat.mjs

@@ -42,6 +42,8 @@ const completion2 = await createCompletion(model, [
 
 console.log(completion2.choices[0].message)
 
+//CALLING DISPOSE WILL INVALID THE NATIVE MODEL. USE THIS TO CLEANUP
+model.dispose()
 // At the moment, from testing this code, concurrent model prompting is not possible. 
 // Behavior: The last prompt gets answered, but the rest are cancelled
 // my experience with threading is not the best, so if anyone who is good is willing to give this a shot,

gpt4all-bindings/typescript/src/gpt4all.d.ts

@@ -61,6 +61,11 @@ declare class InferenceModel {
         prompt: string,
         options?: Partial<LLModelPromptContext>
     ): Promise<string>;
+
+   /**
+     * delete and cleanup the native model
+    */
+    dispose(): void
 }
 
 declare class EmbeddingModel {
@@ -69,6 +74,12 @@ declare class EmbeddingModel {
     config: ModelConfig;
 
     embed(text: string): Float32Array;
+
+    /**
+      * delete and cleanup the native model
+     */
+    dispose(): void
+
 }
 
 /**
@@ -163,6 +174,11 @@ declare class LLModel {
       * @returns 
       */
     listGpu() : GpuDevice[]
+
+    /**
+      * delete and cleanup the native model
+     */
+    dispose(): void
 }
 /** 
   * an object that contains gpu data on this machine.

gpt4all-bindings/typescript/src/models.js

@@ -15,6 +15,10 @@ class InferenceModel {
         const result = this.llm.raw_prompt(prompt, normalizedPromptContext, () => {});
         return result;
     }
+
+    dispose() {
+        this.llm.dispose();
+    }
 }
 
 class EmbeddingModel {
@@ -29,6 +33,10 @@ class EmbeddingModel {
     embed(text) {
         return this.llm.embed(text)
     }
+
+    dispose() {
+        this.llm.dispose();
+    }
 }
 
 

gpt4all-chat/CMakeLists.txt

@@ -18,7 +18,7 @@ endif()
 
 set(APP_VERSION_MAJOR 2)
 set(APP_VERSION_MINOR 5)
-set(APP_VERSION_PATCH 1)
+set(APP_VERSION_PATCH 2)
 set(APP_VERSION "${APP_VERSION_MAJOR}.${APP_VERSION_MINOR}.${APP_VERSION_PATCH}")
 
 # Include the binary directory for the generated header file

gpt4all-chat/cmake/sign_dmg.py

@@ -1,3 +1,4 @@
+#!/usr/bin/env python3
 import os
 import subprocess
 import tempfile

gpt4all-chat/main.qml

@@ -282,8 +282,8 @@ Window {
                     highlighted: comboBox.highlightedIndex === index
                 }
                 Accessible.role: Accessible.ComboBox
-                Accessible.name: qsTr("ComboBox for displaying/picking the current model")
-                Accessible.description: qsTr("Use this for picking the current model to use; the first item is the current model")
+                Accessible.name: qsTr("List of available models")
+                Accessible.description: qsTr("The top item is the current model")
                 onActivated: function (index) {
                     currentChat.stopGenerating()
                     currentChat.reset();
@@ -307,7 +307,7 @@ Window {
                     running: parent.visible
                     Accessible.role: Accessible.Animation
                     Accessible.name: qsTr("Busy indicator")
-                    Accessible.description: qsTr("Displayed when the model is loading")
+                    Accessible.description: qsTr("loading model...")
                 }
 
                 Label {
@@ -339,8 +339,8 @@ Window {
         padding: 15
 
         Accessible.role: Accessible.ButtonMenu
-        Accessible.name: qsTr("Hamburger button")
-        Accessible.description: qsTr("Hamburger button that reveals a drawer on the left of the application")
+        Accessible.name: qsTr("Main menu")
+        Accessible.description: qsTr("Navigation drawer with options")
 
         background: Item {
             anchors.centerIn: parent
@@ -389,7 +389,7 @@ Window {
         Item {
             Accessible.role: Accessible.Dialog
             Accessible.name: qsTr("Network dialog")
-            Accessible.description: qsTr("Dialog for opt-in to sharing feedback/conversations")
+            Accessible.description: qsTr("opt-in to share feedback/conversations")
         }
     }
 
@@ -405,7 +405,7 @@ Window {
         padding: 15
         toggled: MySettings.networkIsActive
         source: "qrc:/gpt4all/icons/network.svg"
-        Accessible.name: qsTr("Network button")
+        Accessible.name: qsTr("Network")
         Accessible.description: qsTr("Reveals a dialogue where you can opt-in for sharing data over network")
 
         onClicked: {
@@ -441,8 +441,8 @@ Window {
         padding: 15
         toggled: currentChat.collectionList.length
         source: "qrc:/gpt4all/icons/db.svg"
-        Accessible.name: qsTr("Add collections of documents to the chat")
-        Accessible.description: qsTr("Provides a button to add collections of documents to the chat")
+        Accessible.name: qsTr("Add documents")
+        Accessible.description: qsTr("add collections of documents to the chat")
 
         onClicked: {
             collectionsDialog.open()
@@ -460,8 +460,8 @@ Window {
         z: 200
         padding: 15
         source: "qrc:/gpt4all/icons/settings.svg"
-        Accessible.name: qsTr("Settings button")
-        Accessible.description: qsTr("Reveals a dialogue where you can change various settings")
+        Accessible.name: qsTr("Settings")
+        Accessible.description: qsTr("Reveals a dialogue with settings")
 
         onClicked: {
             settingsDialog.open()
@@ -528,7 +528,7 @@ Window {
         z: 200
         padding: 15
         source: "qrc:/gpt4all/icons/copy.svg"
-        Accessible.name: qsTr("Copy button")
+        Accessible.name: qsTr("Copy")
         Accessible.description: qsTr("Copy the conversation to the clipboard")
 
         TextEdit{
@@ -595,7 +595,7 @@ Window {
         source: "qrc:/gpt4all/icons/regenerate.svg"
 
         Accessible.name: text
-        Accessible.description: qsTr("Reset the context which erases current conversation")
+        Accessible.description: qsTr("Reset the context and erase current conversation")
 
         onClicked: {
             Network.sendResetContext(chatModel.count)
@@ -623,7 +623,7 @@ Window {
             font.pixelSize: theme.fontSizeLarge
             Accessible.role: Accessible.Dialog
             Accessible.name: text
-            Accessible.description: qsTr("Dialog indicating an error")
+            Accessible.description: qsTr("Error dialog")
         }
         background: Rectangle {
             anchors.fill: parent
@@ -641,7 +641,7 @@ Window {
         height: window.height - (window.height * .1)
         Item {
             Accessible.role: Accessible.Dialog
-            Accessible.name: qsTr("Download new models dialog")
+            Accessible.name: qsTr("Download new models")
             Accessible.description: qsTr("Dialog for downloading new models")
         }
     }
@@ -740,8 +740,8 @@ Window {
                     ScrollBar.vertical: ScrollBar { policy: ScrollBar.AlwaysOn }
 
                     Accessible.role: Accessible.List
-                    Accessible.name: qsTr("List of prompt/response pairs")
-                    Accessible.description: qsTr("This is the list of prompt/response pairs comprising the actual conversation with the model")
+                    Accessible.name: qsTr("Conversation with the model")
+                    Accessible.description: qsTr("prompt / response pairs from the conversation")
 
                     delegate: TextArea {
                         id: myTextArea
@@ -811,7 +811,7 @@ Window {
                                     running: (currentResponse ? true : false) && value === "" && currentChat.responseInProgress
                                     Accessible.role: Accessible.Animation
                                     Accessible.name: qsTr("Busy indicator")
-                                    Accessible.description: qsTr("Displayed when the model is thinking")
+                                    Accessible.description: qsTr("The model is thinking")
                                 }
                                 Label {
                                     anchors.verticalCenter: parent.verticalCenter
@@ -1053,7 +1053,7 @@ Window {
                 }
                 Accessible.role: Accessible.EditableText
                 Accessible.name: placeholderText
-                Accessible.description: qsTr("Textfield for sending messages/prompts to the model")
+                Accessible.description: qsTr("Send messages/prompts to the model")
                 Keys.onReturnPressed: (event)=> {
                     if (event.modifiers & Qt.ControlModifier || event.modifiers & Qt.ShiftModifier)
                         event.accepted = false;
@@ -1090,7 +1090,7 @@ Window {
             height: 30
             visible: !currentChat.isServer
             source: "qrc:/gpt4all/icons/send_message.svg"
-            Accessible.name: qsTr("Send the message button")
+            Accessible.name: qsTr("Send message")
             Accessible.description: qsTr("Sends the message/prompt contained in textfield to the model")
 
             onClicked: {

gpt4all-chat/metadata/models2.json

@@ -94,17 +94,17 @@
   },
   {
     "order": "h",
-    "md5sum": "f5bc6a52f72efd9128efb2eeed802c86",
+    "md5sum": "cf5e8f73747f9d7c6fe72a629808c1de",
     "name": "MPT Chat",
-    "filename": "mpt-7b-chat-q4_0.gguf",
-    "filesize": "3911522272",
+    "filename": "mpt-7b-chat-merges-q4_0.gguf",
+    "filesize": "3796133728",
     "requires": "2.5.0",
     "ramrequired": "8",
     "parameters": "7 billion",
     "quant": "q4_0",
     "type": "MPT",
     "description": "<strong>Good model with novel architecture</strong><br><ul><li>Fast responses<li>Chat based<li>Trained by Mosaic ML<li>Cannot be used commercially</ul>",
-    "url": "https://gpt4all.io/models/gguf/mpt-7b-chat-q4_0.gguf",
+    "url": "https://gpt4all.io/models/gguf/mpt-7b-chat-merges-q4_0.gguf",
     "promptTemplate": "<|im_start|>user\n%1<|im_end|><|im_start|>assistant\n",
     "systemPrompt": "<|im_start|>system\n- You are a helpful assistant chatbot trained by MosaicML.\n- You answer questions.\n- You are excited to be able to help the user, but will refuse to do anything that could be considered harmful to the user.\n- You are more than just an information source, you are also able to write poetry, short stories, and make jokes.<|im_end|>"
   },

gpt4all-chat/metadata/release.json

@@ -550,6 +550,21 @@
 * Jared Van Bortel (Nomic AI)
 * Adam Treat (Nomic AI)
 * Community (beta testers, bug reporters, bindings authors)
+"
+  },
+  {
+    "version": "2.5.1",
+    "notes":
+"
+* Accessibility fixes
+* Bugfix for crasher on Windows
+",
+    "contributors":
+"
+* Aaron Miller (Nomic AI)
+* Jared Van Bortel (Nomic AI)
+* Victor Tsaran <vtsaran@yahoo.com>
+* Community (beta testers, bug reporters, bindings authors)
 "
   }
 ]

gpt4all-chat/qml/ApplicationSettings.qml

@@ -35,8 +35,8 @@ MySettingsTab {
             Layout.fillWidth: false
             model: ["Dark", "Light"]
             Accessible.role: Accessible.ComboBox
-            Accessible.name: qsTr("ComboBox for displaying/picking the color theme")
-            Accessible.description: qsTr("Use this for picking the color theme for the chat client to use")
+            Accessible.name: qsTr("Color theme")
+            Accessible.description: qsTr("Color theme for the chat client to use")
             function updateModel() {
                 themeBox.currentIndex = themeBox.indexOfValue(MySettings.chatTheme);
             }
@@ -70,8 +70,8 @@ MySettingsTab {
             Layout.fillWidth: false
             model: ["Small", "Medium", "Large"]
             Accessible.role: Accessible.ComboBox
-            Accessible.name: qsTr("ComboBox for displaying/picking the font size")
-            Accessible.description: qsTr("Use this for picking the font size of the chat client")
+            Accessible.name: qsTr("Font size")
+            Accessible.description: qsTr("Font size of the chat client")
             function updateModel() {
                 fontBox.currentIndex = fontBox.indexOfValue(MySettings.fontSize);
             }
@@ -105,8 +105,8 @@ MySettingsTab {
             Layout.fillWidth: false
             model: MySettings.deviceList
             Accessible.role: Accessible.ComboBox
-            Accessible.name: qsTr("ComboBox for displaying/picking the device")
-            Accessible.description: qsTr("Use this for picking the device of the chat client")
+            Accessible.name: qsTr("Device")
+            Accessible.description: qsTr("Device of the chat client")
             function updateModel() {
                 deviceBox.currentIndex = deviceBox.indexOfValue(MySettings.device);
             }
@@ -143,8 +143,8 @@ MySettingsTab {
             Layout.fillWidth: true
             model: ModelList.userDefaultModelList
             Accessible.role: Accessible.ComboBox
-            Accessible.name: qsTr("ComboBox for displaying/picking the default model")
-            Accessible.description: qsTr("Use this for picking the default model to use; the first item is the current default model")
+            Accessible.name: qsTr("Default model")
+            Accessible.description: qsTr("Default model to use; the first item is the current default model")
             function updateModel() {
                 comboBox.currentIndex = comboBox.indexOfValue(MySettings.userDefaultModel);
             }
@@ -194,7 +194,7 @@ MySettingsTab {
             Layout.row: 5
             Layout.column: 2
             text: qsTr("Browse")
-            Accessible.description: qsTr("Opens a folder picker dialog to choose where to save model files")
+            Accessible.description: qsTr("Choose where to save model files")
             onClicked: {
                 openFolderDialog("file://" + MySettings.modelPath, function(selectedFolder) {
                     MySettings.modelPath = selectedFolder

gpt4all-chat/qml/ChatDrawer.qml

@@ -31,8 +31,8 @@ Drawer {
         anchors.margins: 10
 
         Accessible.role: Accessible.Pane
-        Accessible.name: qsTr("Drawer on the left of the application")
-        Accessible.description: qsTr("Drawer that is revealed by pressing the hamburger button")
+        Accessible.name: qsTr("Drawer")
+        Accessible.description: qsTr("Main navigation drawer")
 
         MyButton {
             id: newChat
@@ -42,7 +42,7 @@ Drawer {
             topPadding: 20
             bottomPadding: 20
             text: qsTr("\uFF0B New chat")
-            Accessible.description: qsTr("Use this to create a new chat")
+            Accessible.description: qsTr("Create a new chat")
             background: Rectangle {
                 border.color: newChat.down ? theme.backgroundLightest : theme.buttonBorder
                 border.width: 2
@@ -135,7 +135,7 @@ Drawer {
                         }
                         Accessible.role: Accessible.Button
                         Accessible.name: qsTr("Select the current chat")
-                        Accessible.description: qsTr("Provides a button to select the current chat or edit the chat when in edit mode")
+                        Accessible.description: qsTr("Select the current chat or edit the chat when in edit mode")
                     }
                     Row {
                         id: buttons
@@ -155,8 +155,7 @@ Drawer {
                                 chatName.readOnly = false
                                 chatName.selectByMouse = true
                             }
-                            Accessible.name: qsTr("Edit the chat name")
-                            Accessible.description: qsTr("Provides a button to edit the chat name")
+                            Accessible.name: qsTr("Edit chat name")
                         }
                         MyToolButton {
                             id: trashButton
@@ -168,8 +167,7 @@ Drawer {
                                 trashQuestionDisplayed = true
                                 timer.start()
                             }
-                            Accessible.name: qsTr("Delete of the chat")
-                            Accessible.description: qsTr("Provides a button to delete the chat")
+                            Accessible.name: qsTr("Delete chat")
                         }
                     }
                     Rectangle {
@@ -207,8 +205,7 @@ Drawer {
                                     Network.sendRemoveChat()
                                 }
                                 Accessible.role: Accessible.Button
-                                Accessible.name: qsTr("Confirm delete of the chat")
-                                Accessible.description: qsTr("Provides a button to confirm delete of the chat")
+                                Accessible.name: qsTr("Confirm chat deletion")
                             }
                             Button {
                                 id: cancel
@@ -230,8 +227,7 @@ Drawer {
                                     trashQuestionDisplayed = false
                                 }
                                 Accessible.role: Accessible.Button
-                                Accessible.name: qsTr("Cancel the delete of the chat")
-                                Accessible.description: qsTr("Provides a button to cancel delete of the chat")
+                                Accessible.name: qsTr("Cancel chat deletion")
                             }
                         }
                     }
@@ -256,7 +252,7 @@ Drawer {
             anchors.bottomMargin: 10
             text: qsTr("Updates")
             font.pixelSize: theme.fontSizeLarge
-            Accessible.description: qsTr("Use this to launch an external application that will check for updates to the installer")
+            Accessible.description: qsTr("Launch an external application that will check for updates to the installer")
             onClicked: {
                 if (!LLM.checkForUpdates())
                     checkForUpdatesError.open()
@@ -270,7 +266,7 @@ Drawer {
             anchors.bottom: aboutButton.top
             anchors.bottomMargin: 10
             text: qsTr("Downloads")
-            Accessible.description: qsTr("Use this to launch a dialog to download new models")
+            Accessible.description: qsTr("Launch a dialog to download new models")
             onClicked: {
                 downloadClicked()
             }
@@ -282,7 +278,7 @@ Drawer {
             anchors.right: parent.right
             anchors.bottom: parent.bottom
             text: qsTr("About")
-            Accessible.description: qsTr("Use this to launch a dialog to show the about page")
+            Accessible.description: qsTr("Launch a dialog to show the about page")
             onClicked: {
                 aboutClicked()
             }

gpt4all-chat/qml/LocalDocsSettings.qml

@@ -83,7 +83,7 @@ MySettingsTab {
                     text: qsTr("Add")
                     Accessible.role: Accessible.Button
                     Accessible.name: text
-                    Accessible.description: qsTr("Add button")
+                    Accessible.description: qsTr("Add collection")
                     onClicked: {
                         var isError = false;
                         if (root.collection === "") {

gpt4all-chat/qml/ModelDownloaderDialog.qml

@@ -125,7 +125,7 @@ MyDialog {
                                     Layout.fillWidth: true
                                     Layout.alignment: Qt.AlignTop | Qt.AlignHCenter
                                     visible: !isChatGPT && !installed && !calcHash && downloadError === ""
-                                    Accessible.description: qsTr("Cancel/Resume/Download button to stop/restart/start the download")
+                                    Accessible.description: qsTr("Stop/restart/start the download")
                                     background: Rectangle {
                                         border.color: downloadButton.down ? theme.backgroundLightest : theme.buttonBorder
                                         border.width: 2
@@ -151,7 +151,7 @@ MyDialog {
                                     Layout.fillWidth: true
                                     Layout.alignment: Qt.AlignTop | Qt.AlignHCenter
                                     visible: installed || downloadError !== ""
-                                    Accessible.description: qsTr("Remove button to remove model from filesystem")
+                                    Accessible.description: qsTr("Remove model from filesystem")
                                     background: Rectangle {
                                         border.color: removeButton.down ? theme.backgroundLightest : theme.buttonBorder
                                         border.width: 2
@@ -186,8 +186,8 @@ MyDialog {
                                             Download.installModel(filename, openaiKey.text);
                                     }
                                     Accessible.role: Accessible.Button
-                                    Accessible.name: qsTr("Install button")
-                                    Accessible.description: qsTr("Install button to install chatgpt model")
+                                    Accessible.name: qsTr("Install")
+                                    Accessible.description: qsTr("Install chatGPT model")
                                 }
 
                                 ColumnLayout {
@@ -385,7 +385,7 @@ MyDialog {
                             linkColor: theme.textColor
                             Accessible.role: Accessible.Paragraph
                             Accessible.name: qsTr("Description")
-                            Accessible.description: qsTr("The description of the file")
+                            Accessible.description: qsTr("File description")
                             onLinkActivated: Qt.openUrlExternally(link)
                         }
                     }
@@ -456,7 +456,7 @@ MyDialog {
             }
             MyButton {
                 text: qsTr("Browse")
-                Accessible.description: qsTr("Opens a folder picker dialog to choose where to save model files")
+                Accessible.description: qsTr("Choose where to save model files")
                 onClicked: modelPathDialog.open()
             }
         }

gpt4all-chat/qml/MySettingsTab.qml

@@ -69,7 +69,7 @@ Item {
                     font.pixelSize: theme.fontSizeLarge
                     Accessible.role: Accessible.Button
                     Accessible.name: text
-                    Accessible.description: qsTr("Restores the settings dialog to a default state")
+                    Accessible.description: qsTr("Restores settings dialog to a default state")
                     onClicked: {
                         root.restoreDefaultsClicked();
                     }

gpt4all-chat/qml/NetworkDialog.qml

@@ -89,7 +89,7 @@ NOTE: By turning on this feature, you will be sending your data to the GPT4All O
             }
             Accessible.role: Accessible.EditableText
             Accessible.name: qsTr("Attribution (optional)")
-            Accessible.description: qsTr("Textfield for providing attribution")
+            Accessible.description: qsTr("Provide attribution")
             onEditingFinished: {
                 MySettings.networkAttribution = attribution.text;
             }
@@ -103,12 +103,12 @@ NOTE: By turning on this feature, you will be sending your data to the GPT4All O
         spacing: 10
         MyButton {
             text: qsTr("Enable")
-            Accessible.description: qsTr("Enable opt-in button")
+            Accessible.description: qsTr("Enable opt-in")
             DialogButtonBox.buttonRole: DialogButtonBox.AcceptRole
         }
         MyButton {
             text: qsTr("Cancel")
-            Accessible.description: qsTr("Cancel opt-in button")
+            Accessible.description: qsTr("Cancel opt-in")
             DialogButtonBox.buttonRole: DialogButtonBox.RejectRole
         }
         background: Rectangle {

gpt4all-chat/qml/SettingsDialog.qml

@@ -21,8 +21,8 @@ MyDialog {
 
     Item {
         Accessible.role: Accessible.Dialog
-        Accessible.name: qsTr("Settings dialog")
-        Accessible.description: qsTr("Dialog containing various application settings")
+        Accessible.name: qsTr("Settings")
+        Accessible.description: qsTr("Contains various application settings")
     }
 
     ListModel {

gpt4all-chat/qml/StartupDialog.qml

@@ -133,7 +133,6 @@ model release that uses your data!")
                 font.pixelSize: theme.fontSizeLarge
                 Accessible.role: Accessible.Paragraph
                 Accessible.name: qsTr("Opt-in for anonymous usage statistics")
-                Accessible.description: qsTr("Label for opt-in")
             }
 
             ButtonGroup {
@@ -162,7 +161,7 @@ model release that uses your data!")
                     font.pixelSize: theme.fontSizeLarge
                     Accessible.role: Accessible.RadioButton
                     Accessible.name: qsTr("Opt-in for anonymous usage statistics")
-                    Accessible.description: qsTr("Radio button to allow opt-in for anonymous usage statistics")
+                    Accessible.description: qsTr("Allow opt-in for anonymous usage statistics")
 
                     background: Rectangle {
                         color: "transparent"
@@ -203,7 +202,7 @@ model release that uses your data!")
                     font.pixelSize: theme.fontSizeLarge
                     Accessible.role: Accessible.RadioButton
                     Accessible.name: qsTr("Opt-out for anonymous usage statistics")
-                    Accessible.description: qsTr("Radio button to allow opt-out for anonymous usage statistics")
+                    Accessible.description: qsTr("Allow opt-out for anonymous usage statistics")
 
                     background: Rectangle {
                         color: "transparent"
@@ -249,7 +248,7 @@ model release that uses your data!")
                 font.pixelSize: theme.fontSizeLarge
                 Accessible.role: Accessible.Paragraph
                 Accessible.name: qsTr("Opt-in for network")
-                Accessible.description: qsTr("Checkbox to allow opt-in for network")
+                Accessible.description: qsTr("Allow opt-in for network")
             }
 
             ButtonGroup {
@@ -276,7 +275,7 @@ model release that uses your data!")
                     font.pixelSize: theme.fontSizeLarge
                     Accessible.role: Accessible.RadioButton
                     Accessible.name: qsTr("Opt-in for network")
-                    Accessible.description: qsTr("Radio button to allow opt-in anonymous sharing of chats to the GPT4All Datalake")
+                    Accessible.description: qsTr("Allow opt-in anonymous sharing of chats to the GPT4All Datalake")
 
                     background: Rectangle {
                         color: "transparent"
@@ -317,7 +316,7 @@ model release that uses your data!")
                     font.pixelSize: theme.fontSizeLarge
                     Accessible.role: Accessible.RadioButton
                     Accessible.name: qsTr("Opt-out for network")
-                    Accessible.description: qsTr("Radio button to allow opt-out anonymous sharing of chats to the GPT4All Datalake")
+                    Accessible.description: qsTr("Allow opt-out anonymous sharing of chats to the GPT4All Datalake")
 
                     background: Rectangle {
                         color: "transparent"

gpt4all-training/build_map.py

@@ -1,3 +1,4 @@
+#!/usr/bin/env python3
 import numpy as np
 from nomic import atlas
 import glob
@@ -51,4 +52,4 @@ atlas.map_embeddings(embeddings,
                      colorable_fields=["source", "loss", "trained_on"],
                      build_topic_model=True,
                      topic_label_field="inputs",
-                     reset_project_if_exists=True,)
+                     reset_project_if_exists=True,)

gpt4all-training/clean.py

@@ -1,3 +1,4 @@
+#!/usr/bin/env python3
 import numpy as np
 import glob
 import os
@@ -71,4 +72,4 @@ for file in glob.glob(os.path.join(prompt_generation_dir, "*.jsonl")):
 
     clean_name = file.split(".jsonl")[0] + "_clean.jsonl"
     print(f"writing to {curr_len} rows to {clean_name}")
-    df.to_json(clean_name, orient="records", lines=True)
+    df.to_json(clean_name, orient="records", lines=True)

gpt4all-training/eval_figures.py

@@ -1,3 +1,4 @@
+#!/usr/bin/env python3
 import glob
 import pickle
 import numpy as np

gpt4all-training/eval_self_instruct.py

@@ -1,3 +1,4 @@
+#!/usr/bin/env python3
 import json
 import torch
 import pickle

gpt4all-training/generate.py

@@ -1,3 +1,4 @@
+#!/usr/bin/env python3
 from transformers import AutoModelForCausalLM, AutoTokenizer
 from peft import PeftModelForCausalLM
 from read import read_config

gpt4all-training/inference.py

@@ -1,3 +1,4 @@
+#!/usr/bin/env python3
 from transformers import AutoModelForCausalLM, AutoTokenizer
 import torch
 import torch.nn as nn

gpt4all-training/train.py

@@ -1,3 +1,4 @@
+#!/usr/bin/env python3
 import os
 from transformers import AutoModelForCausalLM, AutoTokenizer, get_scheduler
 import torch