Update README.md

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-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/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/gpt4all/tests/test_embed_timings.py

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

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/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-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