python: bump bindings version for AMD fixes

Signed-off-by: cebtenzzre <cebtenzzre@gmail.com>

.codespellrc

@@ -1,3 +1,3 @@
 [codespell]
-ignore-words-list = blong, belong, afterall, som, assistent
+ignore-words-list = blong, afterall, som, assistent, crasher
 skip = .git,*.pdf,*.svg,*.lock

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/bert.cpp

@@ -884,7 +884,7 @@ DLL_EXPORT bool magic_match(const char * fname) {
     if (!ctx_gguf)
         return false;
 
-    bool isValid = gguf_get_version(ctx_gguf) <= 2;
+    bool isValid = gguf_get_version(ctx_gguf) <= 3;
     isValid = isValid && get_arch_name(ctx_gguf) == "bert";
 
     gguf_free(ctx_gguf);

gpt4all-backend/gptj.cpp

@@ -806,7 +806,7 @@ DLL_EXPORT bool magic_match(const char * fname) {
     if (!ctx_gguf)
         return false;
 
-    bool isValid = gguf_get_version(ctx_gguf) <= 2;
+    bool isValid = gguf_get_version(ctx_gguf) <= 3;
     isValid = isValid && get_arch_name(ctx_gguf) == "gptj";
 
     gguf_free(ctx_gguf);

gpt4all-backend/llamamodel.cpp

@@ -395,7 +395,7 @@ DLL_EXPORT bool magic_match(const char * fname) {
     if (!ctx_gguf)
         return false;
 
-    bool isValid = gguf_get_version(ctx_gguf) <= 2;
+    bool isValid = gguf_get_version(ctx_gguf) <= 3;
     auto arch = get_arch_name(ctx_gguf);
     isValid = isValid && (arch == "llama" || arch == "starcoder" || arch == "falcon" || arch == "mpt");
 

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
@@ -7,4 +8,3 @@ cmake --build runtimes/linux-x64/build --parallel --config Release
 cp runtimes/linux-x64/build/libllmodel.so  runtimes/linux-x64/native/libllmodel.so
 cp runtimes/linux-x64/build/libgptj*.so  runtimes/linux-x64/native/
 cp runtimes/linux-x64/build/libllama*.so  runtimes/linux-x64/native/
-cp runtimes/linux-x64/build/libmpt*.so  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-bindings/python/setup.py

@@ -61,7 +61,7 @@ copy_prebuilt_C_lib(SRC_CLIB_DIRECtORY,
 
 setup(
     name=package_name,
-    version="2.0.1",
+    version="2.0.2",
     description="Python bindings for GPT4All",
     author="Nomic and the Open Source Community",
     author_email="support@nomic.ai",

gpt4all-bindings/typescript/scripts/build_unix.sh

@@ -25,9 +25,6 @@ mkdir -p "$NATIVE_DIR" "$BUILD_DIR"
 cmake -S ../../gpt4all-backend -B "$BUILD_DIR" &&
 cmake --build "$BUILD_DIR" -j --config Release && {
   cp "$BUILD_DIR"/libbert*.$LIB_EXT   "$NATIVE_DIR"/
-  cp "$BUILD_DIR"/libfalcon*.$LIB_EXT "$NATIVE_DIR"/
-  cp "$BUILD_DIR"/libreplit*.$LIB_EXT "$NATIVE_DIR"/
   cp "$BUILD_DIR"/libgptj*.$LIB_EXT   "$NATIVE_DIR"/
   cp "$BUILD_DIR"/libllama*.$LIB_EXT  "$NATIVE_DIR"/
-  cp "$BUILD_DIR"/libmpt*.$LIB_EXT    "$NATIVE_DIR"/
 }

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 3)
 set(APP_VERSION "${APP_VERSION_MAJOR}.${APP_VERSION_MINOR}.${APP_VERSION_PATCH}")
 
 # Include the binary directory for the generated header file

gpt4all-chat/build_and_run.md

@@ -47,7 +47,9 @@ Under this release, select the following additional components:
 - Qt Quick 3D
 - Qt 5 Compatibility Module
 - Qt Shader Tools
-- Additional Libraries (clicking the checkbox to the left of this item enables all of them)
+- Additional Libraries:
+  - Qt HTTP Server
+  - Qt PDF
 - Qt Debug information Files
 - Qt Quick Timeline
 

gpt4all-chat/chat.cpp

@@ -142,17 +142,9 @@ QString Chat::response() const
     return m_response;
 }
 
-QString Chat::responseState() const
+Chat::ResponseState Chat::responseState() const
 {
-    switch (m_responseState) {
-    case ResponseStopped: return QStringLiteral("response stopped");
-    case LocalDocsRetrieval: return QStringLiteral("retrieving ") + m_collections.join(", ");
-    case LocalDocsProcessing: return QStringLiteral("processing ") + m_collections.join(", ");
-    case PromptProcessing: return QStringLiteral("processing");
-    case ResponseGeneration: return QStringLiteral("generating response");
-    };
-    Q_UNREACHABLE();
-    return QString();
+    return m_responseState;
 }
 
 void Chat::handleResponseChanged(const QString &response)
@@ -403,6 +395,7 @@ bool Chat::deserialize(QDataStream &stream, int version)
     emit idChanged(m_id);
     stream >> m_name;
     stream >> m_userName;
+    m_generatedName = QLatin1String("nonempty");
     emit nameChanged();
 
     QString modelId;

gpt4all-chat/chat.h

@@ -21,7 +21,7 @@ class Chat : public QObject
     Q_PROPERTY(bool responseInProgress READ responseInProgress NOTIFY responseInProgressChanged)
     Q_PROPERTY(bool isRecalc READ isRecalc NOTIFY recalcChanged)
     Q_PROPERTY(bool isServer READ isServer NOTIFY isServerChanged)
-    Q_PROPERTY(QString responseState READ responseState NOTIFY responseStateChanged)
+    Q_PROPERTY(ResponseState responseState READ responseState NOTIFY responseStateChanged)
     Q_PROPERTY(QList<QString> collectionList READ collectionList NOTIFY collectionListChanged)
     Q_PROPERTY(QString modelLoadingError READ modelLoadingError NOTIFY modelLoadingErrorChanged)
     Q_PROPERTY(QString tokenSpeed READ tokenSpeed NOTIFY tokenSpeedChanged);
@@ -68,7 +68,7 @@ public:
 
     QString response() const;
     bool responseInProgress() const { return m_responseInProgress; }
-    QString responseState() const;
+    ResponseState responseState() const;
     ModelInfo modelInfo() const;
     void setModelInfo(const ModelInfo &modelInfo);
     bool isRecalc() const;

gpt4all-chat/chatllm.cpp

@@ -378,6 +378,32 @@ bool ChatLLM::isModelLoaded() const
     return m_llModelInfo.model && m_llModelInfo.model->isModelLoaded();
 }
 
+std::string remove_leading_whitespace(const std::string& input) {
+    auto first_non_whitespace = std::find_if(input.begin(), input.end(), [](unsigned char c) {
+        return !std::isspace(c);
+    });
+
+    if (first_non_whitespace == input.end())
+        return std::string();
+
+    return std::string(first_non_whitespace, input.end());
+}
+
+std::string trim_whitespace(const std::string& input) {
+    auto first_non_whitespace = std::find_if(input.begin(), input.end(), [](unsigned char c) {
+        return !std::isspace(c);
+    });
+
+    if (first_non_whitespace == input.end())
+        return std::string();
+
+    auto last_non_whitespace = std::find_if(input.rbegin(), input.rend(), [](unsigned char c) {
+        return !std::isspace(c);
+    }).base();
+
+    return std::string(first_non_whitespace, last_non_whitespace);
+}
+
 void ChatLLM::regenerateResponse()
 {
     // ChatGPT uses a different semantic meaning for n_past than local models. For ChatGPT, the meaning
@@ -409,29 +435,6 @@ void ChatLLM::resetContext()
     m_ctx = LLModel::PromptContext();
 }
 
-std::string remove_leading_whitespace(const std::string& input) {
-    auto first_non_whitespace = std::find_if(input.begin(), input.end(), [](unsigned char c) {
-        return !std::isspace(c);
-    });
-
-    return std::string(first_non_whitespace, input.end());
-}
-
-std::string trim_whitespace(const std::string& input) {
-    auto first_non_whitespace = std::find_if(input.begin(), input.end(), [](unsigned char c) {
-        return !std::isspace(c);
-    });
-
-    if (first_non_whitespace == input.end())
-        return std::string();
-
-    auto last_non_whitespace = std::find_if(input.rbegin(), input.rend(), [](unsigned char c) {
-        return !std::isspace(c);
-    }).base();
-
-    return std::string(first_non_whitespace, last_non_whitespace);
-}
-
 QString ChatLLM::response() const
 {
     return QString::fromStdString(remove_leading_whitespace(m_response));
@@ -476,7 +479,7 @@ bool ChatLLM::handleResponse(int32_t token, const std::string &response)
     // check for error
     if (token < 0) {
         m_response.append(response);
-        emit responseChanged(QString::fromStdString(m_response));
+        emit responseChanged(QString::fromStdString(remove_leading_whitespace(m_response)));
         return false;
     }
 
@@ -486,7 +489,7 @@ bool ChatLLM::handleResponse(int32_t token, const std::string &response)
     m_timer->inc();
     Q_ASSERT(!response.empty());
     m_response.append(response);
-    emit responseChanged(QString::fromStdString(m_response));
+    emit responseChanged(QString::fromStdString(remove_leading_whitespace(m_response)));
     return !m_stopGenerating;
 }
 
@@ -503,6 +506,11 @@ bool ChatLLM::handleRecalculate(bool isRecalc)
 }
 bool ChatLLM::prompt(const QList<QString> &collectionList, const QString &prompt)
 {
+    if (m_restoreStateFromText) {
+        Q_ASSERT(m_state.isEmpty());
+        processRestoreStateFromText();
+    }
+
     if (!m_processedSystemPrompt)
         processSystemPrompt();
     const QString promptTemplate = MySettings::globalInstance()->modelPromptTemplate(m_modelInfo);
@@ -906,11 +914,6 @@ void ChatLLM::restoreState()
         return;
     }
 
-    if (m_restoreStateFromText) {
-        Q_ASSERT(m_state.isEmpty());
-        processRestoreStateFromText();
-    }
-
 #if defined(DEBUG)
     qDebug() << "restoreState" << m_llmThread.objectName() << "size:" << m_state.size();
 #endif

gpt4all-chat/cmake/deploy-qt-mac.cmake.in

@@ -3,20 +3,15 @@ set(COMPONENT_NAME_MAIN "@COMPONENT_NAME_MAIN@")
 set(CMAKE_CURRENT_SOURCE_DIR "@CMAKE_CURRENT_SOURCE_DIR@")
 execute_process(COMMAND ${MACDEPLOYQT} ${CPACK_TEMPORARY_INSTALL_DIRECTORY}/packages/${COMPONENT_NAME_MAIN}/data/bin/gpt4all.app -qmldir=${CMAKE_CURRENT_SOURCE_DIR} -verbose=2)
 file(GLOB MYGPTJLIBS ${CPACK_TEMPORARY_INSTALL_DIRECTORY}/packages/${COMPONENT_NAME_MAIN}/data/lib/libgptj*)
-file(GLOB MYMPTLIBS ${CPACK_TEMPORARY_INSTALL_DIRECTORY}/packages/${COMPONENT_NAME_MAIN}/data/lib/libmpt*)
 file(GLOB MYLLAMALIBS ${CPACK_TEMPORARY_INSTALL_DIRECTORY}/packages/${COMPONENT_NAME_MAIN}/data/lib/libllama*)
 file(GLOB MYBERTLLIBS ${CPACK_TEMPORARY_INSTALL_DIRECTORY}/packages/${COMPONENT_NAME_MAIN}/data/lib/libbert*)
 file(GLOB MYLLMODELLIBS ${CPACK_TEMPORARY_INSTALL_DIRECTORY}/packages/${COMPONENT_NAME_MAIN}/data/lib/libllmodel.*)
 file(COPY ${MYGPTJLIBS}
      DESTINATION ${CPACK_TEMPORARY_INSTALL_DIRECTORY}/packages/${COMPONENT_NAME_MAIN}/data/bin/gpt4all.app/Contents/Frameworks)
-file(COPY ${MYMPTLIBS}
-     DESTINATION ${CPACK_TEMPORARY_INSTALL_DIRECTORY}/packages/${COMPONENT_NAME_MAIN}/data/bin/gpt4all.app/Contents/Frameworks)
 file(COPY ${MYLLAMALIBS}
      DESTINATION ${CPACK_TEMPORARY_INSTALL_DIRECTORY}/packages/${COMPONENT_NAME_MAIN}/data/bin/gpt4all.app/Contents/Frameworks)
 file(COPY ${MYBERTLLIBS}
      DESTINATION ${CPACK_TEMPORARY_INSTALL_DIRECTORY}/packages/${COMPONENT_NAME_MAIN}/data/bin/gpt4all.app/Contents/Frameworks)
-file(COPY ${MYLLAMALIBS}
-     DESTINATION ${CPACK_TEMPORARY_INSTALL_DIRECTORY}/packages/${COMPONENT_NAME_MAIN}/data/bin/gpt4all.app/Contents/Frameworks)
 file(COPY ${MYLLMODELLIBS}
      DESTINATION ${CPACK_TEMPORARY_INSTALL_DIRECTORY}/packages/${COMPONENT_NAME_MAIN}/data/bin/gpt4all.app/Contents/Frameworks)
 file(COPY "${CMAKE_CURRENT_SOURCE_DIR}/icons/favicon.icns"

gpt4all-chat/cmake/sign_dmg.py

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

gpt4all-chat/main.qml

@@ -815,8 +815,17 @@ Window {
                                 }
                                 Label {
                                     anchors.verticalCenter: parent.verticalCenter
-                                    text: currentChat.responseState + "..."
                                     color: theme.textAccent
+                                    text: {
+                                        switch (currentChat.responseState) {
+                                        case Chat.ResponseStopped: return "response stopped ...";
+                                        case Chat.LocalDocsRetrieval: return "retrieving " + currentChat.collectionList.join(", ") + " ...";
+                                        case Chat.LocalDocsProcessing: return "processing " + currentChat.collectionList.join(", ") + " ...";
+                                        case Chat.PromptProcessing: return "processing ..."
+                                        case Chat.ResponseGeneration: return "generating response ...";
+                                        default: return ""; // handle unexpected values
+                                        }
+                                    }
                                 }
                             }
                         }

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 +550,38 @@
 * 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)
+"
+  },
+  {
+    "version": "2.5.2",
+    "notes":
+"
+* Support for GGUF v3 models
+* Important fixes for AMD GPUs
+* Don't start recalculating context immediately for saved chats
+* UI fixes for chat name generation
+* UI fixes for leading whitespaces in chat generation
+",
+    "contributors":
+"
+* Jared Van Bortel (Nomic AI)
+* Adam Treat (Nomic AI)
+* 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