Merge branch 'nomic-ai:main' into main

.gitignore

@@ -161,4 +161,9 @@ cython_debug/
 #  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
 #  and can be added to the global gitignore or merged into this file.  For a more nuclear
 #  option (not recommended) you can uncomment the following to ignore the entire idea folder.
-#.idea/
+#.idea/
+
+
+# vs code
+.vscode
+*.bin

README.md

@@ -22,7 +22,7 @@ Run on M1 Mac (not sped up!)
 
 # Try it yourself
 
-Here's how to get started with the CPU quantized gpt4all model checkpoint:
+Here's how to get started with the CPU quantized GPT4All model checkpoint:
 
 1. Download the `gpt4all-lora-quantized.bin` file from [Direct Link](https://the-eye.eu/public/AI/models/nomic-ai/gpt4all/gpt4all-lora-quantized.bin) or [[Torrent-Magnet]](https://tinyurl.com/gpt4all-lora-quantized).
 2. Clone this repository, navigate to `chat`, and place the downloaded file there.
@@ -119,9 +119,10 @@ You can reproduce our trained model by doing the following:
 
 Clone the repo
 
-`git clone --recurse-submodules https://github.com/nomic-ai/gpt4all.git`
+```
-
+git clone --recurse-submodules https://github.com/nomic-ai/gpt4all.git
-`git submodule configure && git submodule update`
+git submodule update --init
+```
 
 Setup the environment
 

TRAINING_LOG.md

@@ -160,7 +160,7 @@ We realized that we had two bugs however:
 - We accidentally duplicated data and effectively trained for 2 epochs instead of 1
 - We added an eos token to every sequence, even those that we truncated (e.g. long code that exceeds the 1024).
 
-## Conditonal EOS and 1 Epoch
+## Conditional EOS and 1 Epoch
 
 Using the same parameters, we then trained a model using a "conditional" eos token where we only add an `eos` when the inputs are less than the maximum sequence length for one epoch.
 

data.py

@@ -68,7 +68,7 @@ def load_data(config, tokenizer):
         dataset = load_dataset("json", data_files=files, split="train")
 
     else:
-        dataset = load_dataset(dataset_path)
+        dataset = load_dataset(dataset_path,split='train')
 
     dataset = dataset.train_test_split(test_size=.05, seed=config["seed"])
 

launcher.sh

@@ -0,0 +1,88 @@
+#!/bin/bash
+
+# Display header
+echo "=========================================================="
+echo " ██████  ██████  ████████ ██   ██  █████  ██      ██      "
+echo "██       ██   ██    ██    ██   ██ ██   ██ ██      ██      "
+echo "██   ███ ██████     ██    ███████ ███████ ██      ██      "
+echo "██    ██ ██         ██         ██ ██   ██ ██      ██      "
+echo " ██████  ██         ██         ██ ██   ██ ███████ ███████ "
+echo " └─> https://github.com/nomic-ai/gpt4all"
+
+# Function to detect macOS architecture and set the binary filename
+detect_mac_arch() {
+  local mac_arch
+  mac_arch=$(uname -m)
+  case "$mac_arch" in
+    arm64)
+      os_type="M1 Mac/OSX"
+      binary_filename="gpt4all-lora-quantized-OSX-m1"
+      ;;
+    x86_64)
+      os_type="Intel Mac/OSX"
+      binary_filename="gpt4all-lora-quantized-OSX-intel"
+      ;;
+    *)
+      echo "Unknown macOS architecture"
+      exit 1
+      ;;
+  esac
+}
+
+# Detect operating system and set the binary filename
+case "$(uname -s)" in
+  Darwin*)
+    detect_mac_arch
+    ;;
+  Linux*)
+    if grep -q Microsoft /proc/version; then
+      os_type="Windows (WSL)"
+      binary_filename="gpt4all-lora-quantized-win64.exe"
+    else
+      os_type="Linux"
+      binary_filename="gpt4all-lora-quantized-linux-x86"
+    fi
+    ;;
+  CYGWIN*|MINGW32*|MSYS*|MINGW*)
+    os_type="Windows (Cygwin/MSYS/MINGW)"
+    binary_filename="gpt4all-lora-quantized-win64.exe"
+    ;;
+  *)
+    echo "Unknown operating system"
+    exit 1
+    ;;
+esac
+echo "================================"
+echo "== You are using $os_type."
+
+
+# Change to the chat directory
+cd chat
+
+# List .bin files and prompt user to select one
+bin_files=(*.bin)
+echo "== Available .bin files:"
+for i in "${!bin_files[@]}"; do
+  echo "   [$((i+1))] ${bin_files[i]}"
+done
+
+# Function to get user input and validate it
+get_valid_user_input() {
+  local input_valid=false
+
+  while ! $input_valid; do
+    echo "==> Please enter a number:"
+    read -r user_selection
+    if [[ $user_selection =~ ^[0-9]+$ ]] && (( user_selection >= 1 && user_selection <= ${#bin_files[@]} )); then
+      input_valid=true
+    else
+      echo "Invalid input. Please enter a number between 1 and ${#bin_files[@]}."
+    fi
+  done
+}
+
+get_valid_user_input
+selected_bin_file="${bin_files[$((user_selection-1))]}"
+
+# Run the selected .bin file with the appropriate command
+./"$binary_filename" -m "$selected_bin_file"