Merge pull request #1070 from bmaltais/dev2

Runpod setup

.gitignore

@@ -1,23 +1,44 @@
+# Python
 venv
 __pycache__
-cudnn_windows
-.vscode
 *.egg-info
 build
 wd14_tagger_model
+
+# IDE and Editor specific
+.vscode
+
+# CUDNN for Windows
+cudnn_windows
+
+# Cache and temporary files
+.cache
 .DS_Store
+
+# Scripts and executables
 locon
 gui-user.bat
 gui-user.ps1
-.vscode
+
+# Version control
+SmilingWolf
 wandb
+
+# Setup and logs
 setup.log
 logs
-SmilingWolf
+
+# Miscellaneous
 uninstall.txt
+
+# Test files
 test/output
 test/logs
 test/*.json
 test/ft
+
+# Temporary requirements
 requirements_tmp_for_setup.txt
-0.13.3
+
+# Version specific
+0.13.3

config_files/accelerate/runpod.yaml

@@ -0,0 +1,22 @@
+command_file: null
+commands: null
+compute_environment: LOCAL_MACHINE
+deepspeed_config: {}
+distributed_type: 'NO'
+downcast_bf16: 'no'
+dynamo_backend: 'NO'
+fsdp_config: {}
+gpu_ids: all
+machine_rank: 0
+main_process_ip: null
+main_process_port: null
+main_training_function: main
+megatron_lm_config: {}
+mixed_precision: 'no'
+num_machines: 1
+num_processes: 1
+rdzv_backend: static
+same_network: true
+tpu_name: null
+tpu_zone: null
+use_cpu: false

gui.sh

@@ -29,9 +29,10 @@ SCRIPT_DIR=$(cd -- "$(dirname -- "$0")" && pwd)
 # Step into GUI local directory
 cd "$SCRIPT_DIR" || exit 1
 
-if [ "$RUNPOD" = false ]; then
-    # Activate the virtual environment
+if [ -d "$SCRIPT_DIR/venv" ]; then
     source "$SCRIPT_DIR/venv/bin/activate" || exit 1
+else
+    echo "venv folder does not exist. Not activating..."
 fi
 
 # Check if LD_LIBRARY_PATH environment variable exists
@@ -45,6 +46,8 @@ if [[ -z "${LD_LIBRARY_PATH}" ]]; then
     echo -e "${YELLOW}Certain functionalities may not work correctly.${RESET}"
     echo -e "${YELLOW}Please ensure that the required libraries are properly configured.${RESET}"
     echo -e " "
+    echo -e "${YELLOW}If you use WSL2 you may want to: export LD_LIBRARY_PATH=/usr/lib/wsl/lib/${RESET}"
+    echo -e " "
 fi
 
 # Determine the requirements file based on the system

requirements_runpod.txt

@@ -1,4 +1,4 @@
-torch==2.0.1+cu117 torchvision==0.15.2+cu117 --extra-index-url https://download.pytorch.org/whl/cu117 # no_verify leave this to specify not checking this a verification stage
+torch==2.0.1+cu118 torchvision==0.15.2+cu118 --extra-index-url https://download.pytorch.org/whl/cu118 # no_verify leave this to specify not checking this a verification stage
 xformers==0.0.20 bitsandbytes==0.39.1
 accelerate==0.15.0 tensorboard==2.12.1 tensorflow==2.12.0
 tensorrt

setup-runpod.sh

@@ -0,0 +1,28 @@
+#!/usr/bin/env bash
+
+# This gets the directory the script is run from so pathing can work relative to the script where needed.
+SCRIPT_DIR="$(cd -- "$(dirname -- "$0")" && pwd)"
+
+# Install tk and python3.10-venv
+echo "Installing tk and python3.10-venv..."
+apt update -y && apt install -y python3-tk python3.10-venv
+
+# Check if the venv folder doesn't exist
+if [ ! -d "$SCRIPT_DIR/venv" ]; then
+    echo "Creating venv..."
+    python3 -m venv "$SCRIPT_DIR/venv"
+fi
+
+# Activate the virtual environment
+echo "Activating venv..."
+source "$SCRIPT_DIR/venv/bin/activate" || exit 1
+
+# Run setup_linux.py script with platform requirements
+echo "Running setup_linux.py..."
+python "$SCRIPT_DIR/setup/setup_linux.py" --platform-requirements-file=requirements_runpod.txt
+
+# Configure accelerate
+echo "Configuring accelerate..."
+mkdir -p "/root/.cache/huggingface/accelerate"
+cp "$SCRIPT_DIR/config_files/accelerate/runpod.yaml" "/root/.cache/huggingface/accelerate/default_config.yaml"
+# echo "To manually configure accelerate run: $SCRIPT_DIR/venv/bin/activate"