CLI for interacting with InstructLab

These details have been verified by PyPI

Project links

GitHub Statistics

Maintainers

tiran

These details have not been verified by PyPI

Project links

homepage

Project description

InstructLab 🐶 (`ilab`)

Lint Tests Build Release License

📖 Contents

Welcome to the InstructLab CLI
❓ What is ilab
📋 Requirements
✅ Getting started
💻 Creating new knowledge or skills and training the model
📣 Chat with the new model (not optional this time)
🚀 Upgrade InstructLab to latest version
🎁 Submit your new knowledge or skills
📬 Contributing

Welcome to the InstructLab CLI

InstructLab 🐶 uses a novel synthetic data-based alignment tuning method for Large Language Models (LLMs.) The "lab" in InstructLab 🐶 stands for Large-Scale Alignment for ChatBots [1].

[1] Shivchander Sudalairaj*, Abhishek Bhandwaldar*, Aldo Pareja*, Kai Xu, David D. Cox, Akash Srivastava*. "LAB: Large-Scale Alignment for ChatBots", arXiv preprint arXiv: 2403.01081, 2024. (* denotes equal contributions)

❓ What is `ilab`

ilab is a Command-Line Interface (CLI) tool that allows you to perform the following actions:

Download a pre-trained Large Language Model (LLM).
Chat with the LLM.

To add new knowledge and skills to the pre-trained LLM, add information to the companion taxonomy repository.

After you have added knowledge and skills to the taxonomy, you can perform the following actions:

Use ilab to generate new synthetic training data based on the changes in your local taxonomy repository.
Re-train the LLM with the new training data.
Chat with the re-trained LLM to see the results.

graph TD;
  download-->chat
  chat[Chat with the LLM]-->add
  add[Add new knowledge<br/>or skill to taxonomy]-->generate[generate new<br/>synthetic training data]
  generate-->train
  train[Re-train]-->|Chat with<br/>the re-trained LLM<br/>to see the results|chat

For an overview of the full workflow, see the workflow diagram.

[!IMPORTANT] We have optimized InstructLab so that community members with commodity hardware can perform these steps. However, running InstructLab on a laptop will provide a low-fidelity approximation of synthetic data generation (using the ilab data generate command) and model instruction tuning (using the ilab model train command, which uses QLoRA). To achieve higher quality, use more sophisticated hardware and configure InstructLab to use a larger teacher model such as Mixtral.

📋 Requirements

🍎 Apple M1/M2/M3 Mac or 🐧 Linux system (tested on Fedora). We anticipate support for more operating systems in the future.
C++ compiler
Python 3.10 or Python 3.11
Approximately 60GB disk space (entire process)

NOTE: Python 3.12 is currently not supported, because some dependencies don't work on Python 3.12, yet.

NOTE: When installing the ilab CLI on macOS, you may have to run the xcode-select --install command, installing the required packages previously listed.

✅ Getting started

🧰 Installing `ilab`

When installing on Fedora Linux, install C++, Python 3.10 or 3.11, and other necessary tools by running the following command:
```
sudo dnf install gcc gcc-c++ make git python3.11 python3.11-devel
```
If you are running on macOS, this installation is not necessary and you can begin your process with the following step.
Create a new directory called instructlab to store the files the ilab CLI needs when running and cd into the directory by running the following command:
```
mkdir instructlab
cd instructlab
```
NOTE: The following steps in this document use Python venv for virtual environments. However, if you use another tool such as pyenv or Conda Miniforge for managing Python environments on your machine continue to use that tool instead. Otherwise, you may have issues with packages that are installed but not found in venv.
There are a few ways you can locally install the ilab CLI. Select your preferred installation method from the following instructions. You can then install ilab and activate your venv environment.

NOTE: ⏳ The python3 binary shown in the following steps is the Python version that you installed in the above step. The command can also be python3.11 or python3.10 instead of python3. You can check Python's version by python3 -V.

NOTE: ⏳ pip install may take some time, depending on your internet connection. In case installation fails with error unsupported instruction `vpdpbusd', append -C cmake.args="-DLLAMA_NATIVE=off" to pip install command.

See the GPU acceleration documentation for how to to enable hardware acceleration for interaction and training on AMD ROCm, Apple Metal Performance Shaders (MPS), and Nvidia CUDA.

Install using PyTorch without CUDA bindings and no GPU acceleration
```
python3 -m venv --upgrade-deps venv
source venv/bin/activate
pip install instructlab
```
NOTE: Additional Build Argument for Intel Macs

If you have an Mac with an Intel CPU, you must add a prefix of CMAKE_ARGS="-DLLAMA_METAL=off" to the pip install command to ensure that the build is done without Apple M-series GPU support.

(venv) $ CMAKE_ARGS="-DLLAMA_METAL=off" pip install ...

Install with AMD ROCm
```
python3 -m venv --upgrade-deps venv
source venv/bin/activate
pip cache remove llama_cpp_python
pip install 'instructlab[rocm]' \
   --extra-index-url https://download.pytorch.org/whl/rocm6.0 \
   -C cmake.args="-DLLAMA_HIPBLAS=on" \
   -C cmake.args="-DAMDGPU_TARGETS=all" \
   -C cmake.args="-DCMAKE_C_COMPILER=/opt/rocm/llvm/bin/clang" \
   -C cmake.args="-DCMAKE_CXX_COMPILER=/opt/rocm/llvm/bin/clang++" \
   -C cmake.args="-DCMAKE_PREFIX_PATH=/opt/rocm" \
   -C cmake.args="-DLLAMA_NATIVE=off"
```
On Fedora 40+, use -DCMAKE_C_COMPILER=clang-17 and -DCMAKE_CXX_COMPILER=clang++-17.

Install with Apple Metal on M1/M2/M3 Macs

NOTE: Make sure your system Python build is Mach-O 64-bit executable arm64 by using file -b $(command -v python), or if your system is setup with pyenv by using the file -b $(pyenv which python) command.

NOTE: Also, ensure that both python3 -c 'import platform; print(platform.machine())' and arch return arm64. If arch returns i386 or python3 returns x86_64, it means your terminal or Python is running in Intel emulation mode, which isn't optimized for Apple Silicon. This is especially important if you have synced data from an Intel-based Mac to an Apple Silicon Mac (M1/M2/M3), as you may need to review and update your environment, especially tools like Homebrew or Bash that were previously installed under Intel.
```
python3 -m venv --upgrade-deps venv
source venv/bin/activate
pip cache remove llama_cpp_python
pip install 'instructlab[mps]'
```
Install with Nvidia CUDA

For the best CUDA experience, installing vLLM is necessary to serve Safetensors format models.
```
python3 -m venv --upgrade-deps venv
source venv/bin/activate
pip cache remove llama_cpp_python
pip install 'instructlab[cuda]' \
   -C cmake.args="-DLLAMA_CUDA=on" \
   -C cmake.args="-DLLAMA_NATIVE=off"
pip install vllm@git+https://github.com/opendatahub-io/vllm@2024.08.01
```

From your venv environment, verify ilab is installed correctly, by running the ilab command.

ilab

Example output of the ilab command

(venv) $ ilab
Usage: ilab [OPTIONS] COMMAND [ARGS]...

CLI for interacting with InstructLab.

If this is your first time running InstructLab, it's best to start with `ilab config init` to create the environment.

Options:
--config PATH  Path to a configuration file.  [default:
               /home/user/.config/instructlab/config.yaml]
-v, --verbose  Enable debug logging (repeat for even more verbosity)
--version      Show the version and exit.
--help         Show this message and exit.

Commands:
config    Command Group for Interacting with the Config of InstructLab.
data      Command Group for Interacting with the Data generated by...
model     Command Group for Interacting with the Models in InstructLab.
system    Command group for all system-related command calls
taxonomy  Command Group for Interacting with the Taxonomy of InstructLab.

Aliases:
chat      model chat
convert   model convert
diff      taxonomy diff
download  model download
evaluate  model evaluate
generate  data generate
init      config init
list      model model_list
serve     model serve
sysinfo   system info
test      model test
train     model train

IMPORTANT Every ilab command needs to be run from within your Python virtual environment. You can enter the Python environment by running the source venv/bin/activate command.

Optional: You can enable tab completion for the ilab command.

Bash (version 4.4 or newer)

Enable tab completion in bash with the following command:
```
eval "$(_ILAB_COMPLETE=bash_source ilab)"
```
To have this enabled automatically every time you open a new shell, you can save the completion script and source it from ~/.bashrc:
```
_ILAB_COMPLETE=bash_source ilab > ~/.ilab-complete.bash
echo ". ~/.ilab-complete.bash" >> ~/.bashrc
```
Zsh

Enable tab completion in zsh with the following command:
```
eval "$(_ILAB_COMPLETE=zsh_source ilab)"
```
To have this enabled automatically every time you open a new shell, you can save the completion script and source it from ~/.zshrc:
```
_ILAB_COMPLETE=zsh_source ilab > ~/.ilab-complete.zsh
echo ". ~/.ilab-complete.zsh" >> ~/.zshrc
```
Fish

Enable tab completion in fish with the following command:
```
_ILAB_COMPLETE=fish_source ilab | source
```
To have this enabled automatically every time you open a new shell, you can save the completion script and source it from ~/.bashrc:
```
_ILAB_COMPLETE=fish_source ilab > ~/.config/fish/completions/ilab.fish
```

🏗️ Initialize `ilab`

Initialize ilab by running the following command:

ilab config init

Example output

Welcome to InstructLab CLI. This guide will help you set up your environment.
Please provide the following values to initiate the environment [press Enter for defaults]:
Path to taxonomy repo [taxonomy]: <ENTER>

When prompted by the interface, press Enter to add a new default config.yaml file.
When prompted, clone the https://github.com/instructlab/taxonomy.git repository into the current directory by typing y.

Optional: If you want to point to an existing local clone of the taxonomy repository, you can pass the path interactively or alternatively with the --taxonomy-path flag.

Example output after initializing ilab
```
(venv) $ ilab config init
Welcome to InstructLab CLI. This guide will help you set up your environment.
Please provide the following values to initiate the environment [press Enter for defaults]:
Path to taxonomy repo [taxonomy]: <ENTER>
`taxonomy` seems to not exists or is empty. Should I clone https://github.com/instructlab/taxonomy.git for you? [y/N]: y
Cloning https://github.com/instructlab/taxonomy.git...
```
ilab will use the default configuration file unless otherwise specified. You can override this behavior with the --config parameter for any ilab command.

When prompted, provide the path to your default model. Otherwise, the default of a quantized Merlinite model will be used - you can download this model with ilab model download (see below).

(venv) $ ilab config init
Welcome to InstructLab CLI. This guide will help you set up your environment.
Please provide the following values to initiate the environment [press Enter for defaults]:
Path to taxonomy repo [taxonomy]: <ENTER>
`taxonomy` seems to not exists or is empty. Should I clone https://github.com/instructlab/taxonomy.git for you? [y/N]: y
Cloning https://github.com/instructlab/taxonomy.git...
Path to your model [/home/user/.cache/instructlab/models/merlinite-7b-lab-Q4_K_M.gguf]: <ENTER>

When prompted, please choose a train profile. Train profiles are GPU specific profiles that enable accelerated training behavior. If you are on MacOS or a Linux machine without a dedicated GPU, please choose No Profile (CPU, Apple Metal, AMD ROCm) by hitting Enter. There are various flags you can utilize with individual ilab commands that allow you to utilize your GPU if applicable.

Welcome to InstructLab CLI. This guide will help you to setup your environment.
Please provide the following values to initiate the environment [press Enter for defaults]:
Path to taxonomy repo [/home/user/.local/share/instructlab/taxonomy]:
Path to your model [/home/user/.cache/instructlab/models/merlinite-7b-lab-Q4_K_M.gguf]:
Generating `/home/user/.config/instructlab/config.yaml` and `/home/user/.local/share/instructlab/internal/train_configuration/profiles`...
Please choose a train profile to use.
Train profiles assist with the complexity of configuring specific GPU hardware with the InstructLab Training library.
You can still take advantage of hardware acceleration for training even if your hardware is not listed.
[0] No profile (CPU, Apple Metal, AMD ROCm)
[1] Nvidia A100/H100 x2 (A100_H100_x2.yaml)
[2] Nvidia A100/H100 x4 (A100_H100_x4.yaml)
[3] Nvidia A100/H100 x8 (A100_H100_x8.yaml)
[4] Nvidia L40 x4 (L40_x4.yaml)
[5] Nvidia L40 x8 (L40_x8.yaml)
[6] Nvidia L4 x8 (L4_x8.yaml)
Enter the number of your choice [hit enter for no profile] [0]:
No profile selected - any hardware acceleration for training must be configured manually.
Initialization completed successfully, you're ready to start using `ilab`. Enjoy!

The GPU profiles are listed by GPU type and number of GPUs present. If you happen to have a GPU configuration with a similar amount of vRAM as any of the above profiles, feel free to try them out!

`ilab` directory layout after initializing your system

After running ilab config init your directories will look like the following on a Linux system:

├─ ~/.cache/instructlab/models/ (1)
├─ ~/.local/share/instructlab/datasets (2)
├─ ~/.local/share/instructlab/taxonomy (3)
├─ ~/.local/share/instructlab/checkpoints (4)

~/.cache/instructlab/models/: Contains all downloaded large language models, including the saved output of ones you generate with ilab.
~/.local/share/instructlab/datasets/: Contains data output from the SDG phase, built on modifications to the taxonomy repository.
~/.local/share/instructlab/taxonomy/: Contains the skill and knowledge data.
~/.local/share/instructlab/checkpoints/: Contains the output of the training process

📥 Download the model

Run the ilab model download command.
```
ilab model download
```
ilab model download downloads a compact pre-trained version of the model (~4.4G) from HuggingFace:
```
(venv) $ ilab model download
Downloading model from Hugging Face: instructlab/merlinite-7b-lab-GGUF@main to /home/user/.cache/instructlab/models...
...
INFO 2024-08-01 15:05:48,464 huggingface_hub.file_download:1893: Download complete. Moving file to /home/user/.cache/instructlab/models/merlinite-7b-lab-Q4_K_M.gguf
```
NOTE ⏳ This command can take few minutes or immediately depending on your internet connection or model is cached. If you have issues connecting to Hugging Face, refer to the Hugging Face discussion forum for more details.

Downloading a specific model from a Hugging Face repository
Specify repository, model, and a Hugging Face token if necessary. More information about Hugging Face tokens can be found here
```
HF_TOKEN=<YOUR HUGGINGFACE TOKEN GOES HERE> ilab model download --repository=TheBloke/Mixtral-8x7B-Instruct-v0.1-GGUF --filename=mixtral-8x7b-instruct-v0.1.Q4_K_M.gguf
```
Downloading an entire Hugging Face repository (Safetensors Model)
Specify repository, and a Hugging Face token if necessary. For example:
```
HF_TOKEN=<YOUR HUGGINGFACE TOKEN GOES HERE> ilab model download --repository=instructlab/granite-7b-lab
```
These types of models are useful for GPU-enabled systems or anyone looking to serve a model using vLLM. InstructLab provides Safetensor versions of our Granite models on HuggingFace.

Listing downloaded models

All downloaded models can be seen with ilab model list.

ilab model list

Example output of ilab model list after ilab model download

(venv) $ ilab model list
+------------------------------+---------------------+--------+
| Model Name                   | Last Modified       | Size   |
+------------------------------+---------------------+--------+
| merlinite-7b-lab-Q4_K_M.gguf | 2024-08-01 15:05:48 | 4.1 GB |
+------------------------------+---------------------+--------+

🍴 Serving the model

Serve the model by running the following command:
```
ilab model serve
```

Serve a non-default model (e.g. Mixtral-8x7B-Instruct-v0.1):

ilab model serve --model-path models/mixtral-8x7b-instruct-v0.1.Q4_K_M.gguf

Once the model is served and ready, you'll see the following output:

(venv) $ ilab model serve
INFO 2024-03-02 02:21:11,352 lab.py:201 Using model 'models/ggml-merlinite-7b-lab-Q4_K_M.gguf' with -1 gpu-layers and 4096 max context size.
Starting server process
After application startup complete see http://127.0.0.1:8000/docs for API.
Press CTRL+C to shut down the server.

NOTE: If multiple ilab clients try to connect to the same InstructLab server at the same time, the 1st will connect to the server while the others will start their own temporary server. This will require additional resources on the host machine.

Serve a non-default Safetensors model (e.g. granite-7b-lab). NOTE: this requires a GPU.

Ensure vllm is installed:

pip show vllm

If it is not, please run:

pip install vllm@git+https://github.com/opendatahub-io/vllm@2024.08.01

ilab model serve --model-path ~/.cache/instructlab/models/instructlab/granite-7b-lab

📣 Chat with the model (Optional)

Because you're serving the model in one terminal window, you will have to create a new window and re-activate your Python virtual environment to run ilab model chat command:

source venv/bin/activate
ilab model chat

Chat with a non-default model (e.g. Mixtral-8x7B-Instruct-v0.1):

source venv/bin/activate
ilab model chat --model models/mixtral-8x7b-instruct-v0.1.Q4_K_M.gguf

Please note that usage of --model necessitates that the existing server has that model. If not, you must exit the server. --model in ilab model chat has the ability to start a server on your behalf with the specified model if one is not already running on the port.

Before you start adding new skills and knowledge to your model, you can check its baseline performance by asking it a question such as what is the capital of Canada?.

NOTE: the model needs to be trained with the generated synthetic data to use the new skills or knowledge

(venv) $ ilab model chat
╭────────────────────────────────────────────────────────────────────────────────────────────────────────────────── system ──────────────────────────────────────────────────────────────────────────────────────────────────────────────────╮
│ Welcome to InstructLab Chat w/ GGML-MERLINITE-7B-lab-Q4_K_M (type /h for help)                                                                                                                                                             │
╰────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
>>> what is the capital of Canada?                                                                                                                                                                                                [S][default]
╭────────────────────────────────────────────────────────────────────────────────────────────────────── ggml-merlinite-7b-lab-Q4_K_M ───────────────────────────────────────────────────────────────────────────────────────────────────────╮
│ The capital city of Canada is Ottawa. It is located in the province of Ontario, on the southern banks of the Ottawa River in the eastern portion of southern Ontario. The city serves as the political center for Canada, as it is home to │
│ Parliament Hill, which houses the House of Commons, Senate, Supreme Court, and Cabinet of Canada. Ottawa has a rich history and cultural significance, making it an essential part of Canada's identity.                                   │
╰─────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────── elapsed 12.008 seconds ─╯
>>>                                                                                                                                                                                                                               [S][default]

💻 Creating new knowledge or skills and training the model

🎁 Contribute knowledge or compositional skills

Contribute new knowledge or compositional skills to your local taxonomy repository.

Detailed contribution instructions can be found in the taxonomy repository.

[!IMPORTANT] There is a limit to how much content can exist in the question/answer pairs for the model to process. Due to this, only add a maximum of around 2300 words to your question and answer seed example pairs in the qna.yaml file.

📜 List and validate your new data

You can use the ilab taxonomy diff command to ensure ilab is registering your new knowledge or skills and your contributions are properly formatted. This command displays any new or modified YAML files within your taxonomy tree. For example, the following is the expected result of a valid compositional skill contribution after adding a new skill called foo-lang to the freeform writing subdirectory:

(venv) $ ilab taxonomy diff
compositional_skills/writing/freeform/foo-lang/qna.yaml
Taxonomy in $HOME/.local/share/instructlab/taxonomy is valid :)

You can also validate your entire taxonomy by performing a diff against an empty base by using the --taxonomy-base=empty argument:

(venv) $ ilab taxonomy diff --taxonomy-base=empty
compositional_skills/general/tables/empty/qna.yaml
compositional_skills/general/tables/editing/add_remove/qna.yaml
...
Taxonomy in $HOME/.local/share/instructlab/taxonomy is valid :)

🚀 Generate a synthetic dataset

Before following these instructions, ensure the existing model you are adding skills or knowledge to is still running. Alternatively, ilab data generate can start a server for you if you provide a fully qualified model path via --model.

To generate a synthetic dataset based on your newly added knowledge or skill set in taxonomy repository, run the following command:

With GPU acceleration:

ilab data generate --pipeline full --gpus <NUM_OF_GPUS>

Without GPU acceleration:

ilab data generate --pipeline simple

Use a non-default model (e.g. Mixtral-8x7B-Instruct-v0.1) to generate data, run the following command:

ilab data generate --model ~/.cache/instructlab/models/mistralai/mixtral-8x7b-instruct-v0.1 --pipeline full --gpus 4

NOTE: ⏳ This can take from 15 minutes to 1+ hours to complete, depending on your computing resources.

Example output of ilab data generate

(venv) $ ilab data generate
INFO 2024-07-30 19:57:44,093 numexpr.utils:161: NumExpr defaulting to 8 threads.
INFO 2024-07-30 19:57:44,452 datasets:58: PyTorch version 2.3.1 available.
Generating synthetic data using 'simple' pipeline, '$HOME/.cache/instructlab/models/mixtral-8x7b-instruct-v0.1.Q4_K_M.gguf' model, './taxonomy' taxonomy, against http://localhost:8000/v1 server
INFO 2024-07-30 19:57:45,084 instructlab.sdg:375: Synthesizing new instructions. If you aren't satisfied with the generated instructions, interrupt training (Ctrl-C) and try adjusting your YAML files. Adding more examples may help.
INFO 2024-07-30 19:57:45,090 instructlab.sdg.pipeline:153: Running pipeline single-threaded
INFO 2024-07-30 19:57:47,820 instructlab.sdg.llmblock:51: LLM server supports batched inputs: False
INFO 2024-07-30 19:57:47,820 instructlab.sdg.pipeline:197: Running block: gen_skill_freeform
INFO 2024-07-30 19:57:47,820 instructlab.sdg.pipeline:198: Dataset({
   features: ['task_description', 'seed_question', 'seed_response'],
   num_rows: 5
})
INFO 2024-07-30 20:02:16,455 instructlab.sdg:411: Generated 1 samples
...

The synthetic data set will be two files in the newly created in the datasets directory: ~/.local/share/instructlab/datasets. These files will be named skills_train_msgs_*.jsonl and knowledge_train_msgs_*.jsonl.

Verify the files have been created by running the ls datasets command. Note: you must be in your XDG_DATA_HOME/instructlab directory.

(venv) $ ls datasets/
node_datasets_2024-08-12T20_31_15                          test_mixtral-8x7b-instruct-v0-1_2024-08-12T20_23_06.jsonl
knowledge_recipe_2024-08-12T20_31_15.yaml                      node_datasets_2024-08-13T19_51_48                          test_mixtral-8x7b-instruct-v0-1_2024-08-12T20_31_15.jsonl
knowledge_recipe_2024-08-13T19_51_48.yaml                      skills_recipe_2024-08-12T20_31_15.yaml                     test_mixtral-8x7b-instruct-v0-1_2024-08-13T19_47_59.jsonl
knowledge_train_msgs_2024-08-12T20_31_15.jsonl                 skills_recipe_2024-08-13T19_51_48.yaml                     test_mixtral-8x7b-instruct-v0-1_2024-08-13T19_51_48.jsonl
knowledge_train_msgs_2024-08-13T19_51_48.jsonl                 skills_train_msgs_2024-08-12T20_31_15.jsonl                train_mixtral-8x7b-instruct-v0-1_2024-08-12T20_31_15.jsonl
messages_mixtral-8x7b-instruct-v0-1_2024-08-12T20_31_15.jsonl  skills_train_msgs_2024-08-13T19_51_48.jsonl                train_mixtral-8x7b-instruct-v0-1_2024-08-13T19_51_48.jsonl
messages_mixtral-8x7b-instruct-v0-1_2024-08-13T19_51_48.jsonl  test_mixtral-8x7b-instruct-v0-1_2024-08-12T20_13_21.jsonl

Optional: It is also possible to run the generate step against a different model via an OpenAI-compatible API. For example, the one spawned by ilab model serve or any remote or locally hosted LLM (e.g. via ollama, LM Studio, etc.). Run the following command:

ilab data generate --endpoint-url http://localhost:8000/v1

Note that it is also possible to generate a synthetic dataset based on the entire contents of the taxonomy repo using the --taxonomy-base=empty option:

ilab data generate --taxonomy-base=empty

👩‍🏫 Training the model

There are many options for training the model with your synthetic data-enhanced dataset.

Note: Every ilab command needs to run from within your Python virtual environment.

ilab model training pipelines

ilab model train has three pipelines: simple, full, and accelerated. The default is accelerated.

simple uses an SFT Trainer on Linux and MLX on MacOS. This type of training takes roughly an hour and produces the lowest fidelity model but should indicate if your data is being picked up by the training process.
full uses a custom training loop and data processing funcions for the granite family of models. This loop is optimizied for CPU and MPS functionality. Please use --pipeline=full in combination with --device=cpu (Linux) or --device=mps (MacOS). You can also use --device=cpu on a MacOS machine. However, MPS is optimized for better performance on these systems.
accelerated uses the instructlab-training library which supports GPU accelerated and distributed training. The full loop and data processing functions are either pulled directly from or based off of the work in this library.

Train the model locally

ilab model train

NOTE: ⏳ This step can potentially take several hours to complete depending on your computing resources. Please stop ilab model chat and ilab model serve first to free resources.

If you are using ilab model train --pipeline=simple on Linux:

ilab model train outputs a brand-new model that can be served in the models directory called ggml-model-f16.gguf.

If you are using ilab model train --pipeline=simple on MacOS:

ilab model train outputs a brand-new model that is saved in the <model_name>-mlx-q directory.

If you are using ilab model train --pipeline=full on Linux or MacOS:

ilab model train outputs brand-new .bin and .gguf models in the ~/.local/share/instructlab/checkpoints/hf_format directory. in each samples_* directory you will find two GGUF models. One is quantized and one is full precision, the quantized one has a Q4-M-K suffix.

If you are using ilab model train --pipeline=accelerated on Linux:

ilab model train outputs brand-new models that can be served in the ~/.local/share/instructlab/checkpoints directory. These models can be run through ilab model evaluate to choose the best one.

If you are using ilab model train --strategy lab-multiphase on Linux:

ilab model train outputs brand-new models that can be served in ~/.local/share/instructlab/phased/phase1/checkpoints and ~/.local/share/instructlab/phased/phase2/checkpoints. Phase 1 correlates to knowledge training and phase 2 correlates to skills training.

When running multi phase training evaluation is run on each phase, we will tell you which checkpoint in this folder performs the best.

Train the model locally on an M-series Mac or on Linux using the full pipeline

To train the model locally on your M-Series Mac using our full pipeline and MPS or on your Linux laptop/deskop using CPU:

ilab model train --pipeline full --device mps

ilab model train --pipeline full --device cpu

Note: ⏳ This process will take a while to complete. If you run for ~8 epochs it will take several hours.

ilab model train outputs a directory for each epoch that resembles the following structure:

$ ls ~/.local/share/instructlab/checkpoints/hf_format/samples_0/
added_tokens.json  pytorch_model.bin   special_tokens_map.json   tokenizer.json
config.json        pytorch_model.gguf  pytorch_model-Q4_K_M.gguf tokenizer_config.json    tokenizer.model

this entire folder can be served on a system that supports vLLM using the .bin model. However, on most laptops you can serve either the full precision gguf: pytorch_model.gguf or the 4-bit-quantized one: pytorch_model-Q4_K_M.gguf.

Train the model locally on an M-series Mac or on Linux using the simple pipeline

To train the model locally on your M-Series Mac using our simple pipeline and MLX or on your Linux laptop/deskop using an SFT Trainer:

ilab model train --pipeline simple

Note: ⏳ This process will take a little while to complete (time can vary based on hardware and output of ilab data generate but on the order of 5 to 15 minutes)

on a Mac ilab model train outputs a brand-new model that is saved in the <model_name>-mlx-q directory called adapters.npz (in Numpy compressed array format). For example:

(venv) $ ls instructlab-merlinite-7b-lab-mlx-q
adapters-010.npz        adapters-050.npz        adapters-090.npz        config.json             tokenizer.model
adapters-020.npz        adapters-060.npz        adapters-100.npz        model.safetensors       tokenizer_config.json
adapters-030.npz        adapters-070.npz        adapters.npz            special_tokens_map.json
adapters-040.npz        adapters-080.npz        added_tokens.json       tokenizer.json

on Linux ilab model train outputs a brand-new model that can be served in the models directory called ggml-model-f16.gguf.

Train the model locally with GPU acceleration

Training has experimental support for GPU acceleration with Nvidia CUDA or AMD ROCm. Please see the GPU acceleration documentation for more details. At present, hardware acceleration requires a data center GPU or high-end consumer GPU with at least 18 GB free memory.

ilab model train --pipeline accelerated --device cuda

This version of ilab model train outputs brand-new models that can be served in the ~/.local/share/instructlab/checkpoints directory. These models can be run through ilab model evaluate to choose the best one.

Train the model locally with multi-phase training and GPU acceleration

ilab model train supports multi-phase training. This results in the following workflow:

We train the model on knowledge
Evaluate the trained model to find the best checkpoint
We train the model on skills
We evaluate the model to find the best overall checkpoint

ilab model train --strategy lab-multiphase --phased-phase1-data <knowledge train messages jsonl> --phased-phase2-data <skills train messages jsonl> -y

This command takes in two .jsonl files from your datasets directory, one is the knowledge jsonl and the other is a skills jsonl. The -y flag skips an interactive prompt asking the user if they are sure they want to run multi-phase training.

Note: this command may take 3 or more hours depending on the size of the data and number of training epochs you run.

Train the model in the cloud

Follow the instructions in Training.

⏳ Approximate amount of time taken on each platform:

Google Colab: 5-10 minutes with a T4 GPU
Kaggle: ~30 minutes with a P100 GPU.

After that's done, you can play with your model directly in the Google Colab or Kaggle notebook. Model trained on the cloud will be saved on the cloud. The model can also be downloaded and served locally.

📜 Test the newly trained model

Run the following command to test the model:
```
ilab model test
```
The output from the command will consist of a series of outputs from the model before and after training.

🧪 Evaluate the newly trained model

You can use the ilab model evaluate command to evaluate the models you are training with several benchmarks. Currently, four benchmarks are supported.

Benchmark	Measures	Full Name	Description	Reference
MMLU	Knowledge	Massive Multitask Language Understanding	Tests a model against a standardized set of knowledge data and produces a score based on the model's performance	Measuring Massive Multitask Language Understanding
MMLUBranch	Knowledge	N/A	Tests your knowledge contributions against a base model and produces a score based on the difference in performance	N/A
MTBench	Skills	Multi-turn Benchmark	Tests a model's skill at applying its knowledge against a judge model and produces a score based on the model's performance	MT-Bench (Multi-turn Benchmark)
MTBenchBranch	Skills	N/A	Tests your skill contributions against a judge model and produces a score based on the difference in performance	N/A

[!NOTE] MTBench and MTBenchBranch use prometheus-8x7b-v2.0 as the judge model by default. While you do not need to use this model as your judge, it is strongly recommended to do so if you have the necessary hardware resources. You can download it via ilab model download.

Running MMLU

Below is an example of running MMLU on a local model with minimal tasks:

$ export INSTRUCTLAB_EVAL_MMLU_MIN_TASKS=true   # don't set this if you want to run full MMLU
$ export ILAB_MODELS_DIR=$HOME/.local/share/instructlab/models
$ ilab model evaluate --benchmark mmlu --model $ILAB_MODELS_DIR/instructlab/granite-7b-lab
...
# KNOWLEDGE EVALUATION REPORT

## MODEL
/home/example-user/.local/share/instructlab/models/instructlab/granite-7b-lab

### AVERAGE:
0.45 (across 3)

### SCORES:
mmlu_abstract_algebra - 0.35
mmlu_anatomy - 0.44
mmlu_astronomy - 0.55

Below is an example of running MMLU on a Hugging Face model with minimal tasks:

$ export INSTRUCTLAB_EVAL_MMLU_MIN_TASKS=true   # don't set this if you want to run full MMLU
$ ilab model evaluate --benchmark mmlu --model instructlab/granite-7b-lab
...
# KNOWLEDGE EVALUATION REPORT

## MODEL
instructlab/granite-7b-lab

### AVERAGE:
0.45 (across 3)

### SCORES:
mmlu_abstract_algebra - 0.35
mmlu_anatomy - 0.44
mmlu_astronomy - 0.55

[!NOTE] Currently, MMLU can only be run against a safetensors model directory, either locally or on Hugging Face. GGUFs are not currently supported.

Running MMLUBranch

Below is an example of running MMLUBranch with a local safetensors model directory:

$ export ILAB_MODELS_DIR=$HOME/.local/share/instructlab/models
$ ilab model evaluate --benchmark mmlu_branch --model $ILAB_MODELS_DIR/instructlab/granite-7b-lab --base-model $ILAB_MODELS_DIR/instructlab/granite-7b-lab
...
# KNOWLEDGE EVALUATION REPORT

## BASE MODEL
/home/example-user/.local/share/instructlab/models/instructlab/granite-7b-lab

## MODEL
/home/example-user/.local/share/instructlab/models/instructlab/granite-7b-lab

### AVERAGE:
+0.0 (across 1)

### NO CHANGE:
1. tonsils

Below is an example of running MMLUBranch with Hugging Face models:

$ ilab model evaluate --benchmark mmlu_branch --model instructlab/granite-7b-lab --base-model instructlab/granite-7b-lab
...
# KNOWLEDGE EVALUATION REPORT

## BASE MODEL
instructlab/granite-7b-lab

## MODEL
instructlab/granite-7b-lab

### AVERAGE:
+0.0 (across 1)

### NO CHANGE:
1. tonsils

[!TIP] You can mix and match running local models and remote models on Hugging Face, so long as a safetensors model is present.

Running MTBench

Below is an example of running MTBench with a local safetensors model directory:

$ export ILAB_MODELS_DIR=$HOME/.local/share/instructlab/models
$ ilab model evaluate --benchmark mt_bench --model $ILAB_MODELS_DIR/instructlab/granite-7b-lab --judge-model $ILAB_MODELS_DIR/instructlab/granite-7b-lab
...
# SKILL EVALUATION REPORT

## MODEL
/home/example-user/.local/share/instructlab/models/instructlab/granite-7b-lab

### AVERAGE:
8.07 (across 91)

### TURN ONE:
8.64

### TURN TWO:
7.19

### ERROR RATE:
0.43

Below is an example of running MTBench with local GGUF models:

$ export ILAB_MODELS_DIR=$HOME/.local/share/instructlab/models
$ ilab model evaluate --benchmark mt_bench --model $ILAB_MODELS_DIR/granite-7b-lab-Q4_K_M.gguf --judge-model $ILAB_MODELS_DIR/granite-7b-lab-Q4_K_M.gguf
...
# SKILL EVALUATION REPORT

## MODEL
/home/example/.local/share/instructlab/models/granite-7b-lab-Q4_K_M.gguf

### AVERAGE:
5.0 (across 1)

### TURN ONE:
5.0

### TURN TWO:
N/A

### ERROR RATE:
0.99

[!NOTE] Currently, MTBench must be used with local models. Using models directly from Hugging Face without downloading them is unsupported.

Running MTBenchBranch

Below is an example of running MTBenchBranch with a local safetensors model directory:

$ export ILAB_MODELS_DIR=$HOME/.local/share/instructlab/models
$ export ILAB_TAXONOMY_DIR=$HOME/.local/share/instructlab/taxonomy
$ ilab model evaluate --benchmark mt_bench_branch \
   --model $ILAB_MODELS_DIR/instructlab/granite-7b-lab \
   --judge-model $ILAB_MODELS_DIR/instructlab/granite-7b-lab \
   --base-model $ILAB_MODELS_DIR/instructlab/granite-7b-lab \
   --taxonomy-path $ILAB_TAXONOMY_DIR \
   --branch rc \
   --base-branch main
...
# SKILL EVALUATION REPORT

## BASE MODEL
/home/example/.local/share/instructlab/models/instructlab/granite-7b-lab

## MODEL
/home/example/.local/share/instructlab/models/instructlab/granite-7b-lab

### IMPROVEMENTS:
1. compositional_skills/extraction/receipt/markdown/qna.yaml (+4.0)
2. compositional_skills/STEM/science/units_conversion/temperature_conversion/qna.yaml (+3.0)
3. compositional_skills/extraction/commercial_lease_agreement/bullet_points/qna.yaml (+3.0)
...

### REGRESSIONS:
1. compositional_skills/extraction/abstractive/title/qna.yaml (-5.0)
2. compositional_skills/extraction/receipt/bullet_points/qna.yaml (-4.5)
3. compositional_skills/writing/grounded/summarization/wiki_insights/one_line/qna.yaml (-4.0)
...

### NO CHANGE:
1. compositional_skills/STEM/math/reasoning/qna.yaml
2. compositional_skills/extraction/commercial_lease_agreement/csv/qna.yaml
3. compositional_skills/roleplay/explain_like_i_am/graduate/qna.yaml
...

### NEW:
1. compositional_skills/linguistics/organize_lists/qna.yaml
2. compositional_skills/extraction/invoice/plain_text/qna.yaml
3. compositional_skills/writing/grounded/summarization/wiki_insights/concise/qna.yaml
...

### ERROR RATE:
0.32

Below is an example of running MTBenchBranch with local GGUF models:

$ export ILAB_MODELS_DIR=$HOME/.local/share/instructlab/models
$ export ILAB_TAXONOMY_DIR=$HOME/.local/share/instructlab/taxonomy
$ ilab model evaluate --benchmark mt_bench_branch --model $ILAB_MODELS_DIR/granite-7b-lab-Q4_K_M.gguf --judge-model $ILAB_MODELS_DIR/granite-7b-lab-Q4_K_M.gguf --base-model $ILAB_MODELS_DIR/granite-7b-lab-Q4_K_M.gguf --taxonomy-path $ILAB_TAXONOMY_DIR --branch rc --base-branch main
...
# SKILL EVALUATION REPORT

## BASE MODEL
/home/ec2-user/.local/share/instructlab/models/granite-7b-lab-Q4_K_M.gguf

## MODEL
/home/ec2-user/.local/share/instructlab/models/granite-7b-lab-Q4_K_M.gguf

### NO CHANGE:
1. compositional_skills/STEM/math/distance_conversion/qna.yaml

### NEW:
1. compositional_skills/linguistics/organize_lists/qna.yaml
2. compositional_skills/extraction/annual_report/reasoning/qna.yaml
3. compositional_skills/extraction/email/plain_text/qna.yaml
4. compositional_skills/extraction/technical_paper/tables/bullet_points/qna.yaml
5. compositional_skills/extraction/technical_paper/abstract/reasoning/qna.yaml

### ERROR RATE:
0.98

[!NOTE] Currently, MTBenchBranch must be used with local models. Using models directly from Hugging Face without downloading them is unsupported.

🍴 Serve the newly trained model

Stop the server you have running by entering ctrl+c keys in the terminal running the server.

IMPORTANT:
- 🍎 This step is only implemented for macOS with M-series chips (for now).
- Before serving the newly trained model you must convert it to work with the ilab cli. The ilab model convert command converts the new model into quantized GGUF format which is required by the server to host the model in the ilab model serve command.
Convert the newly trained model by running the following command:
```
ilab model convert
```
Serve the newly trained model locally via ilab model serve command with the --model-path argument to specify your new model:
```
ilab model serve --model-path <new model path>
```
Which model should you select to serve? After running the ilab model convert command, some files and a directory are generated. The model you will want to serve ends with an extension of .gguf and exists in a directory with the suffix trained. For example: instructlab-merlinite-7b-lab-trained/instructlab-merlinite-7b-lab-Q4_K_M.gguf.

📣 Chat with the new model (not optional this time)

Try the fine-tuned model out live using the chat interface, and see if the results are better than the untrained version of the model with chat by running the following command:
```
ilab model chat -m <New model path>
```
If you are interested in optimizing the quality of the model's responses, please see TROUBLESHOOTING.md

🚀 Upgrade InstructLab to latest version

To upgrade InstructLab to the latest version, use the following command:
```
pip install instructlab --upgrade
```

🎁 Submit your new knowledge or skills

Of course, the final step is, if you've improved the model, to open a pull-request in the taxonomy repository that includes the files (e.g. qna.yaml) with your improved data.

📬 Contributing

Check out our contributing guide to learn how to contribute.

Project details

These details have been verified by PyPI

Project links

GitHub Statistics

Maintainers

tiran

These details have not been verified by PyPI

Project links

homepage

Release history Release notifications | RSS feed

0.21.0

Nov 16, 2024

0.21.0a1 pre-release

Nov 6, 2024

0.21.0a0 pre-release

Nov 5, 2024

0.20.1

Nov 4, 2024

0.20.0

Oct 31, 2024

0.20.0a2 pre-release

Oct 29, 2024

0.20.0a1 pre-release

Oct 28, 2024

This version

0.19.5

Nov 13, 2024

0.19.4

Oct 18, 2024

0.19.3

Oct 8, 2024

0.19.2

Oct 6, 2024

0.19.1

Oct 2, 2024

0.19.0

Oct 1, 2024

0.19.0rc1 pre-release

Sep 27, 2024

0.19.0b1 pre-release

Sep 20, 2024

0.19.0a1 pre-release

Sep 13, 2024

0.18.4

Aug 29, 2024

0.18.3

Aug 22, 2024

0.18.2

Aug 19, 2024

0.18.1

Aug 16, 2024

0.18.0

Aug 15, 2024

0.18.0rc7 pre-release

Aug 12, 2024

0.18.0rc6 pre-release

Aug 9, 2024

0.18.0rc5 pre-release

Aug 9, 2024

0.18.0rc4 pre-release

Aug 8, 2024

0.18.0rc3 pre-release

Aug 7, 2024

0.18.0rc2 pre-release

Aug 7, 2024

0.18.0rc1 pre-release

Aug 6, 2024

0.18.0b6 pre-release

Aug 1, 2024

0.18.0b5 pre-release

Jul 31, 2024

0.18.0b4 pre-release

Jul 30, 2024

0.18.0b3 pre-release

Jul 29, 2024

0.18.0b2 pre-release

Jul 26, 2024

0.18.0b1 pre-release

Jul 25, 2024

0.18.0a7 pre-release

Jul 24, 2024

0.18.0a6 pre-release

Jul 23, 2024

0.18.0a5 pre-release

Jul 22, 2024

0.18.0a4 pre-release

Jul 19, 2024

0.18.0a3 pre-release

Jul 18, 2024

0.18.0a2 pre-release

Jul 17, 2024

0.18.0a1 pre-release

Jul 17, 2024

0.17.2

Nov 7, 2024

0.17.1

Jun 18, 2024

0.17.0

Jun 14, 2024

0.16.1

Jun 7, 2024

0.16.0

May 31, 2024

0.15.1

May 23, 2024

0.14.0 yanked

May 4, 2024

Reason this release was yanked:

test release

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

instructlab-0.19.5.tar.gz (6.9 MB view details)

Uploaded Nov 13, 2024 Source

Built Distribution

instructlab-0.19.5-py3-none-any.whl (182.2 kB view details)

Uploaded Nov 13, 2024 Python 3

File details

Details for the file instructlab-0.19.5.tar.gz.

File metadata

Download URL: instructlab-0.19.5.tar.gz
Upload date: Nov 13, 2024
Size: 6.9 MB
Tags: Source
Uploaded using Trusted Publishing? Yes
Uploaded via: twine/5.1.1 CPython/3.12.7

File hashes

Hashes for instructlab-0.19.5.tar.gz
Algorithm	Hash digest
SHA256	`9f875dd7021ff5d5d52df5184b4c3585a0900f8a7f00d57d77521472f465f1b9`
MD5	`bd5ae74674356c1f4eb205130a0f45e7`
BLAKE2b-256	`11cb05942fc7991960d25fa09523532209bbfa2e40ba6bc2c700f69e2e7b7968`

See more details on using hashes here.

File details

Details for the file instructlab-0.19.5-py3-none-any.whl.

File metadata

Download URL: instructlab-0.19.5-py3-none-any.whl
Upload date: Nov 13, 2024
Size: 182.2 kB
Tags: Python 3
Uploaded using Trusted Publishing? Yes
Uploaded via: twine/5.1.1 CPython/3.12.7

File hashes

Hashes for instructlab-0.19.5-py3-none-any.whl
Algorithm	Hash digest
SHA256	`16a230f0213d02d6ee4586703ad8b053635b62793de4a09e5ac3931628bcf84f`
MD5	`f407271cce04c7f10ac1679a7d2bff92`
BLAKE2b-256	`8a0bd671f4bfc07432d2d0054bc1b973516aa0fac75ccd4a6ca2de71f254e810`

See more details on using hashes here.

instructlab 0.19.5

Navigation

Verified details

Project links

GitHub Statistics

Maintainers

Unverified details

Project links

Meta

Classifiers

Project description

InstructLab 🐶 (ilab)

📖 Contents

Welcome to the InstructLab CLI

❓ What is ilab

📋 Requirements

✅ Getting started

🧰 Installing ilab

Install using PyTorch without CUDA bindings and no GPU acceleration

Install with AMD ROCm

Install with Apple Metal on M1/M2/M3 Macs

Install with Nvidia CUDA

Bash (version 4.4 or newer)

Zsh

Fish

🏗️ Initialize ilab

ilab directory layout after initializing your system

📥 Download the model

Downloading a specific model from a Hugging Face repository

Downloading an entire Hugging Face repository (Safetensors Model)

Listing downloaded models

🍴 Serving the model

📣 Chat with the model (Optional)

💻 Creating new knowledge or skills and training the model

🎁 Contribute knowledge or compositional skills

📜 List and validate your new data

🚀 Generate a synthetic dataset

👩‍🏫 Training the model

ilab model training pipelines

Train the model locally

Train the model locally on an M-series Mac or on Linux using the full pipeline

Train the model locally on an M-series Mac or on Linux using the simple pipeline

Train the model locally with GPU acceleration

Train the model locally with multi-phase training and GPU acceleration

Train the model in the cloud

📜 Test the newly trained model

🧪 Evaluate the newly trained model

Running MMLU

Running MMLUBranch

Running MTBench

Running MTBenchBranch

🍴 Serve the newly trained model

📣 Chat with the new model (not optional this time)

🚀 Upgrade InstructLab to latest version

🎁 Submit your new knowledge or skills

📬 Contributing

Project details

Verified details

Project links

GitHub Statistics

Maintainers

Unverified details

Project links

Meta

Classifiers

Release history Release notifications | RSS feed

Download files

Source Distribution

Built Distribution

File details

File metadata

File hashes

File details

File metadata

File hashes

InstructLab 🐶 (`ilab`)

❓ What is `ilab`

🧰 Installing `ilab`

🏗️ Initialize `ilab`

`ilab` directory layout after initializing your system