Upload 17 files

.dockerignore

@@ -0,0 +1,17 @@
+.git
+.github
+.mypy_cache
+.neptune
+bundles
+wandb
+.pytest_cache
+data
+documentation
+jenkins
+notebooks
+output
+reports
+tests
+.coverage
+*.log
+*.ipynb

.flake8

@@ -0,0 +1,17 @@
+[flake8]
+exclude=.cache, .local, server.wave, output, data, reports
+max-line-length = 88
+# E203, W503 - black-compatible config
+extend-ignore = E203, W503
+# E501 line too long (text for testing)
+per-file-ignores =
+    */__init__.py: F401
+    train.py: E402
+    prompt.py: E402
+    train_wave.py: E402, I001, I003
+    app.py: E402
+    publish_to_hugging_face.py: E402
+    tests/src/datasets/test_text_dpo_modeling_ds.py: E501
+    tests/src/models/test_dpo_modeling_model.py: E501
+
+inline-quotes = "

.gitignore

@@ -0,0 +1,164 @@
+# Folder
+bundles/
+input/
+notebooks/
+demo_data/
+output*/
+tmp/
+data/
+examples/data_oasst2
+examples/output_oasst2
+data_old/
+tests_tmp/
+subs/
+/datasets/
+.idea/
+.local/
+
+output
+
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+.neptune/
+wandb/
+.vscode/
+
+# C extensions
+*.so
+*.c
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+pip-wheel-metadata/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+reports/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Documentation
+node_modules
+tmp
+.docusaurus 
+.cach-loader
+
+# PyBuilder
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+*.ipynb
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+.python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+h2o_wave.state
+.DS_Store
+
+# IDE
+.vscode
+
+# playwright
+test-results/

CODE_OF_CONDUCT.md

@@ -0,0 +1,133 @@
+
+# Contributor Covenant Code of Conduct
+
+## Our Pledge
+
+We as members, contributors, and leaders pledge to make participation in our
+community a harassment-free experience for everyone, regardless of age, body
+size, visible or invisible disability, ethnicity, sex characteristics, gender
+identity and expression, level of experience, education, socio-economic status,
+nationality, personal appearance, race, caste, color, religion, or sexual identity
+and orientation.
+
+We pledge to act and interact in ways that contribute to an open, welcoming,
+diverse, inclusive, and healthy community.
+
+## Our Standards
+
+Examples of behavior that contributes to a positive environment for our
+community include:
+
+* Demonstrating empathy and kindness toward other people
+* Being respectful of differing opinions, viewpoints, and experiences
+* Giving and gracefully accepting constructive feedback
+* Accepting responsibility and apologizing to those affected by our mistakes,
+  and learning from the experience
+* Focusing on what is best not just for us as individuals, but for the
+  overall community
+
+Examples of unacceptable behavior include:
+
+* The use of sexualized language or imagery, and sexual attention or
+  advances of any kind
+* Trolling, insulting or derogatory comments, and personal or political attacks
+* Public or private harassment
+* Publishing others' private information, such as a physical or email
+  address, without their explicit permission
+* Other conduct which could reasonably be considered inappropriate in a
+  professional setting
+
+## Enforcement Responsibilities
+
+Community leaders are responsible for clarifying and enforcing our standards of
+acceptable behavior and will take appropriate and fair corrective action in
+response to any behavior that they deem inappropriate, threatening, offensive,
+or harmful.
+
+Community leaders have the right and responsibility to remove, edit, or reject
+comments, commits, code, wiki edits, issues, and other contributions that are
+not aligned to this Code of Conduct, and will communicate reasons for moderation
+decisions when appropriate.
+
+## Scope
+
+This Code of Conduct applies within all community spaces, and also applies when
+an individual is officially representing the community in public spaces.
+Examples of representing our community include using an official e-mail address,
+posting via an official social media account, or acting as an appointed
+representative at an online or offline event.
+
+## Enforcement
+
+Instances of abusive, harassing, or otherwise unacceptable behavior may be
+reported to the community leaders responsible for enforcement at
+this repository.
+All complaints will be reviewed and investigated promptly and fairly.
+
+All community leaders are obligated to respect the privacy and security of the
+reporter of any incident.
+
+## Enforcement Guidelines
+
+Community leaders will follow these Community Impact Guidelines in determining
+the consequences for any action they deem in violation of this Code of Conduct:
+
+### 1. Correction
+
+**Community Impact**: Use of inappropriate language or other behavior deemed
+unprofessional or unwelcome in the community.
+
+**Consequence**: A private, written warning from community leaders, providing
+clarity around the nature of the violation and an explanation of why the
+behavior was inappropriate. A public apology may be requested.
+
+### 2. Warning
+
+**Community Impact**: A violation through a single incident or series
+of actions.
+
+**Consequence**: A warning with consequences for continued behavior. No
+interaction with the people involved, including unsolicited interaction with
+those enforcing the Code of Conduct, for a specified period of time. This
+includes avoiding interactions in community spaces as well as external channels
+like social media. Violating these terms may lead to a temporary or
+permanent ban.
+
+### 3. Temporary Ban
+
+**Community Impact**: A serious violation of community standards, including
+sustained inappropriate behavior.
+
+**Consequence**: A temporary ban from any sort of interaction or public
+communication with the community for a specified period of time. No public or
+private interaction with the people involved, including unsolicited interaction
+with those enforcing the Code of Conduct, is allowed during this period.
+Violating these terms may lead to a permanent ban.
+
+### 4. Permanent Ban
+
+**Community Impact**: Demonstrating a pattern of violation of community
+standards, including sustained inappropriate behavior,  harassment of an
+individual, or aggression toward or disparagement of classes of individuals.
+
+**Consequence**: A permanent ban from any sort of public interaction within
+the community.
+
+## Attribution
+
+This Code of Conduct is adapted from the [Contributor Covenant][homepage],
+version 2.0, available at
+[https://www.contributor-covenant.org/version/2/0/code_of_conduct.html][v2.0].
+
+Community Impact Guidelines were inspired by
+[Mozilla's code of conduct enforcement ladder][Mozilla CoC].
+
+For answers to common questions about this code of conduct, see the FAQ at
+[https://www.contributor-covenant.org/faq][FAQ]. Translations are available
+at [https://www.contributor-covenant.org/translations][translations].
+
+[homepage]: https://www.contributor-covenant.org
+[v2.0]: https://www.contributor-covenant.org/version/2/0/code_of_conduct.html
+[Mozilla CoC]: https://github.com/mozilla/diversity
+[FAQ]: https://www.contributor-covenant.org/faq
+[translations]: https://www.contributor-covenant.org/translations

CONTRIBUTING.md

@@ -0,0 +1,67 @@
+# Contributing to H2O LLM STUDIO
+
+H2O LLM Studio is an open source project released under the Apache Software Licence v2. Open Source projects live by
+their user and developer communities. We welcome and encourage your contributions of any kind!
+
+## Bug Reports and Feature Requests
+
+Found a bug or have an idea for a new feature? Your feedback is invaluable! To ensure a smooth and collaborative
+process, please follow these steps:
+
+1. Provide the full error message and stack trace, if applicable.
+2. Attach the model configuration yaml file if the error is related to model training.
+3. Specify the commit hash of the version you are using (running `git rev-parse HEAD`) in your report. If you are
+   pasting the UI error message, the commit hash will also be included in the error message.
+4. If the error is reproducible, kindly include the steps to reproduce it.
+5. If possible, attempt to reproduce the error using the default dataset.
+6. Please mention any other details that might be useful, e.g. if you are using LLM Studio in a Docker container, etc.
+
+## Pull Requests
+
+You can contribute to the project by fixing bugs, adding new features, refactoring code, or enhancing documentation.
+To ensure a smooth and collaborative process for everyone, please follow these guidelines:
+
+1. Check if the issue you plan to address is already [reported](https://github.com/h2oai/h2o-llmstudio/issues). If not,
+   please open a new issue
+   to discuss your proposed changes.
+2. Avoid duplicating work by commenting on the issue you're working on and feel free to seek assistance or ask
+   questions; our team is happy to help.
+3. Fork the repository and create a new branch from `main`. To develop, please follow the setup instructions below.
+4. Implement your changes and commit them to your branch.
+5. When you feel ready, open a pull request with your changes. You can also open the PR as a draft to receive early
+   feedback. To facilitate the review process, we have provided a PR checklist below.
+6. Our team will review your pull request and provide feedback. Once everything looks good, we will proceed to merge
+   your contribution.
+
+## Setting up your development environment
+
+Follow the instructions in [README](https://github.com/h2oai/h2o-llmstudio/blob/main/README.md) to set up your
+environment. Run `make setup-dev` instead of `make setup` to install the development dependencies.
+
+## Running linters and tests
+
+Before submitting your pull request, ensure that your code passes the linters and tests.
+To format your code, run `make format`. You can check for any style issues by running `make style`. To run the tests,
+run `make test`.
+
+## PR checklist
+
+Please make sure your pull request fulfills the following checklist:
+
+☐ The PR title should provide a clear summary of your contribution.  
+☐ Link the related issue (e.g., closes #123) in your PR description.  
+☐ If your contribution is still a work in progress, change the PR to draft mode.  
+☐ Ensure that the existing tests pass by running `make test`.  
+☐ Make sure `make style` passes to maintain consistent code style.  
+
+## Installing custom packages
+
+If you need to install additional Python packages into the environment, you can do so using pip after activating your virtual environment via ```make shell```. For example, to install flash-attention, you would use the following commands:
+
+```bash
+make shell
+pip install flash-attn --no-build-isolation
+pip install git+https://github.com/HazyResearch/flash-attention.git#subdirectory=csrc/rotary
+```
+
+For a PR, update the Pipfile and the Pipfile.lock via ```pipenv install package_name```.

Dockerfile

@@ -0,0 +1,92 @@
+FROM nvidia/cuda:12.1.0-devel-ubuntu22.04
+
+ARG DEBIAN_FRONTEND=noninteractive
+
+# git is needed for flash-attention
+# curl is needed to download get-pip.py
+# software-properties-common is needed for add-apt-repository
+# We get python 3.10 from the deadsnakes PPA to have the latest version
+# We install pip from the get-pip.py script to have the latest version
+RUN apt-get update \
+    && apt-get upgrade -y \
+    && apt-get install -y \
+    git \
+    curl \
+    software-properties-common \
+    && add-apt-repository ppa:deadsnakes/ppa \
+    && apt-get update \
+    && apt install -y \
+    python3.10 \
+    python3.10-distutils \
+    && rm -rf /var/lib/apt/lists/*
+
+# Pick an unusual UID for the llmstudio user.
+# In particular, don't pick 1000, which is the default ubuntu user number.
+# Force ourselves to test with UID mismatches in the common case.
+RUN adduser --uid 1999 llmstudio
+USER llmstudio
+ENV HOME=/home/llmstudio
+
+# Static application code lives in /workspace/
+WORKDIR /workspace
+
+ENV PATH=/home/llmstudio/.local/bin:$PATH
+RUN \
+    curl -sS https://bootstrap.pypa.io/get-pip.py | python3.10 && \
+    chmod -R a+w /home/llmstudio
+COPY Makefile Pipfile Pipfile.lock /workspace/
+
+# Python virtualenv is installed in /workspace/.venv/
+# give read and write permissions to the /workspace/.venv/ directory for all users to allow wave to write files
+ENV PIPENV_VENV_IN_PROJECT=1
+RUN make setup && chmod -R 777 /workspace/.venv
+
+# Add the venv to the PATH
+ENV PATH=/workspace/.venv/bin:$PATH
+
+# We need to create a mount point for the user to mount their volume
+# All persistent data lives in /home/llmstudio/mount
+RUN mkdir -p /home/llmstudio/mount
+ENV H2O_LLM_STUDIO_WORKDIR=/home/llmstudio/mount
+
+# Download the demo datasets and place in the /workspace/demo directory
+# Set the environment variable for the demo datasets
+ENV H2O_LLM_STUDIO_DEMO_DATASETS=/workspace/demo
+COPY llm_studio/download_default_datasets.py /workspace/
+RUN python download_default_datasets.py
+
+COPY . /workspace
+
+# Remove unnecessary packages remove build packages again
+# Prevent removal of cuda packages
+USER root
+RUN apt-get purge -y git curl python3.10-distutils software-properties-common \
+    && apt-get autoremove -y \
+    && rm -rf /var/lib/apt/lists/*
+
+USER llmstudio
+
+ENV HF_HUB_DISABLE_TELEMETRY=1
+ENV DO_NOT_TRACK=1
+
+# Set the environment variables for the wave server
+ENV H2O_WAVE_APP_ADDRESS=http://127.0.0.1:8756
+ENV H2O_WAVE_MAX_REQUEST_SIZE=25MB
+ENV H2O_WAVE_NO_LOG=true
+ENV H2O_WAVE_PRIVATE_DIR="/download/@/home/llmstudio/mount/output/download"
+
+USER root
+
+# Make all of the files in the llmstudio directory read & writable for all users so that the
+# application can install other (non-persisted) new packages and other things
+# if it wants to. e.g. triton uses /home/llmstudio/.triton as a cache directory.
+RUN chmod -R 777 /home/llmstudio
+
+# Make the entrypoint.sh script executable by all users
+RUN chmod 755 /workspace/entrypoint.sh
+
+USER llmstudio
+
+EXPOSE 10101
+
+ENTRYPOINT [ "/workspace/entrypoint.sh" ]

LICENSE

@@ -0,0 +1,191 @@
+
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   Copyright 2023 H2O.ai, Inc.
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this repository except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

Makefile

@@ -0,0 +1,279 @@
+SHELL := /bin/bash
+
+PYTHON_VERSION ?= 3.10
+PYTHON ?= python$(PYTHON_VERSION)
+PIP ?= $(PYTHON) -m pip
+PIPENV ?= $(PYTHON) -m pipenv
+PIPENV_PYTHON = $(PIPENV) run python
+PIPENV_PIP = $(PIPENV_PYTHON) -m pip
+PWD = $(shell pwd)
+DOCKER_IMAGE ?= gcr.io/vorvan/h2oai/h2o-llmstudio:nightly
+APP_VERSION=$(shell sed -n 's/^version = //p' pyproject.toml | tr -d '"')
+
+ifeq ($(origin H2O_LLM_STUDIO_WORKDIR), environment)
+    WORKDIR := $(H2O_LLM_STUDIO_WORKDIR)
+else
+    WORKDIR := $(shell pwd)
+endif
+
+ifeq ($(LOG_LEVEL), $(filter $(LOG_LEVEL), debug trace))
+    PW_DEBUG = DEBUG=pw:api
+else
+    PW_DEBUG =
+endif
+
+.PHONY: pipenv
+pipenv:
+	$(PIP) install pip==24.2
+	$(PIP) install pipenv==2024.0.1
+
+.PHONY: setup
+setup: pipenv
+	$(PIPENV) install --verbose --python $(PYTHON_VERSION)
+	-$(PIPENV_PIP) install flash-attn==2.6.1 --no-build-isolation --upgrade --no-cache-dir
+
+.PHONY: setup-dev
+setup-dev: pipenv
+	$(PIPENV) install --verbose --dev --python $(PYTHON_VERSION)
+	-$(PIPENV_PIP) install flash-attn==2.6.1 --no-build-isolation --upgrade --no-cache-dir
+	$(PIPENV) run playwright install
+
+.PHONY: setup-no-flash
+setup-no-flash: pipenv
+	$(PIPENV) install --verbose --python $(PYTHON_VERSION)
+
+.PHONY: setup-conda-nightly
+setup-conda:
+	@bash -c '\
+		set -e; \
+		source $$(conda info --base)/etc/profile.d/conda.sh; \
+		conda deactivate; \
+		conda create -n llmstudio python=3.10 -y; \
+		conda activate llmstudio; \
+		conda install -c nvidia/label/cuda-12.4.0 cuda-toolkit -y; \
+		conda install pytorch pytorch-cuda=12.4 -c pytorch-nightly -c nvidia -y; \
+		grep -v "nvidia" requirements.txt | grep -v "torch" | python -m pip install -r /dev/stdin; \
+		python -m pip install flash-attn==2.6.1 --no-build-isolation --upgrade --no-cache-dir; \
+	'
+
+.PHONY: setup-ui
+setup-ui: pipenv
+	$(PIPENV) install --verbose --categories=dev-packages --python $(PYTHON_VERSION)
+	$(PIPENV) run playwright install
+
+.PHONY: export-requirements
+export-requirements: pipenv
+	$(PIPENV) requirements > requirements.txt
+
+clean-env:
+	$(PIPENV) --rm
+
+clean-data:
+	rm -rf data
+
+clean-output:
+	rm -rf output
+
+reports:
+	mkdir -p reports
+
+.PHONY: style
+style: reports pipenv
+	@echo -n > reports/flake8_errors.log
+	@echo -n > reports/mypy_errors.log
+	@echo -n > reports/mypy.log
+	@echo
+
+	-$(PIPENV) run flake8 | tee -a reports/flake8_errors.log
+	@if [ -s reports/flake8_errors.log ]; then exit 1; fi
+
+	-$(PIPENV) run mypy . --check-untyped-defs | tee -a reports/mypy.log
+	@if ! grep -Eq "Success: no issues found in [0-9]+ source files" reports/mypy.log ; then exit 1; fi
+
+.PHONY: format
+format: pipenv
+	$(PIPENV) run isort .
+	$(PIPENV) run black .
+
+.PHONY: isort
+isort: pipenv
+	$(PIPENV) run isort .
+
+.PHONY: black
+black: pipenv
+	$(PIPENV) run black .
+
+.PHONY: test
+test: reports
+	@bash -c 'set -o pipefail; export PYTHONPATH=$(PWD); \
+	$(PIPENV) run pytest -v --junitxml=reports/junit.xml \
+	--import-mode importlib \
+	--html=./reports/pytest.html \
+	--cov=llm_studio \
+	--cov-report term \
+	--cov-report html:./reports/coverage.html \
+    -o log_cli=true -o log_level=INFO -o log_file=reports/tests.log \
+    tests/* 2>&1 | tee reports/tests.log'
+
+# Use to quickly run a single test (e.g. make test-debug test=test_encode)
+.PHONY: test-debug
+test-debug: reports
+	@bash -c 'set -o pipefail; export PYTHONPATH=$(PWD); \
+	$(PIPENV) run pytest -v --junitxml=reports/junit.xml \
+	--import-mode importlib \
+	--html=./reports/pytest.html \
+	-k $(test) \
+	-s \
+    -o log_cli=false -o log_level=WARNING -o log_file=/dev/null \
+    tests/*'
+
+# Only run the unit-tests (src)
+.PHONY: test-unit
+test-unit: reports
+	@bash -c 'set -o pipefail; export PYTHONPATH=$(PWD); \
+	$(PIPENV) run pytest -v --junitxml=reports/junit.xml \
+	--import-mode importlib \
+	--html=./reports/pytest.html \
+	-k src \
+	--cov=llm_studio/src \
+	--cov-report term \
+	--cov-report html:./reports/coverage.html \
+    -o log_cli=true -o log_level=INFO -o log_file=reports/tests.log \
+    tests/* 2>&1 | tee reports/tests.log'
+
+.PHONY: test-ui
+test-ui: reports setup-ui
+	@bash -c 'set -o pipefail; \
+	$(PW_DEBUG) $(PIPENV) run pytest \
+	-v \
+	--junitxml=reports/junit_ui.xml \
+	--html=./reports/pytest_ui.html \
+	-o log_cli=true \
+	-o log_level=$(LOG_LEVEL) \
+	-o log_file=reports/tests_ui.log \
+	tests/ui/test.py 2>&1 | tee reports/tests_ui.log'
+
+.PHONY: test-ui-headed
+test-ui-headed: setup-ui
+	$(PW_DEBUG) $(PIPENV) run pytest \
+	-vvs \
+	-s \
+	--headed \
+	--video=on \
+	--screenshot=on \
+	--slowmo=1000 \
+	tests/ui/test.py 2>&1 | tee reports/tests.log
+
+.PHONY: test-ui-github-actions  # Run UI tests in GitHub Actions. Starts the Wave server and runs the tests locally.
+test-ui-github-actions: reports setup-ui
+	@echo "Starting the server..."
+	make llmstudio &
+	@echo "Server started in background."
+	@echo "Waiting 10s for the server to start..."
+	sleep 10
+	@echo "Running the tests..."
+	LOCAL_LOGIN=True \
+	PYTEST_BASE_URL=localhost:10101 \
+	make test-ui
+	@echo "Stopping the server..."
+	make stop-llmstudio
+	@echo "Server stopped."
+
+.PHONY: wave
+wave:
+	HF_HUB_DISABLE_TELEMETRY=1 \
+	H2O_WAVE_APP_ACCESS_KEY_ID=dev \
+	H2O_WAVE_APP_ACCESS_KEY_SECRET=dev \
+	H2O_WAVE_MAX_REQUEST_SIZE=25MB \
+	H2O_WAVE_NO_LOG=true \
+	H2O_WAVE_PRIVATE_DIR="/download/@$(WORKDIR)/output/download" \
+	$(PIPENV) run wave run llm_studio.app
+
+.PHONY: llmstudio
+llmstudio:
+	nvidia-smi && \
+	HF_HUB_DISABLE_TELEMETRY=1 \
+	H2O_WAVE_MAX_REQUEST_SIZE=25MB \
+	H2O_WAVE_NO_LOG=true \
+	H2O_WAVE_PRIVATE_DIR="/download/@$(WORKDIR)/output/download" \
+	$(PIPENV) run wave run --no-reload llm_studio.app
+
+.PHONY: llmstudio-conda
+llmstudio-conda:
+	CONDA_ACTIVATE="source $$(conda info --base)/etc/profile.d/conda.sh ; conda activate llmstudio" && \
+	bash -c "$$CONDA_ACTIVATE && \
+		nvidia-smi && \
+		HF_HUB_DISABLE_TELEMETRY=1 \
+		H2O_WAVE_MAX_REQUEST_SIZE=25MB \
+		H2O_WAVE_NO_LOG=true \
+		H2O_WAVE_PRIVATE_DIR="/download/@$(WORKDIR)/output/download" \
+		wave run --no-reload llm_studio.app"
+
+.PHONY: stop-llmstudio
+stop-llmstudio:
+	@kill $$(lsof -ti :10101)
+
+.PHONY: docker-build-nightly
+docker-build-nightly:
+	docker build -t $(DOCKER_IMAGE) .
+
+# Run the Docker container with the nightly image
+# Uses the local `llmstudio_mnt` directory as the mount point for the container
+.PHONY: docker-run-nightly
+docker-run-nightly:
+ifeq (,$(wildcard ./llmstudio_mnt))
+	mkdir llmstudio_mnt
+endif
+	docker run \
+		--runtime=nvidia \
+		--shm-size=64g \
+		--init \
+		--rm \
+		-it \
+		-u `id -u`:`id -g` \
+		-p 10101:10101 \
+		-v `pwd`/llmstudio_mnt:/home/llmstudio/mount \
+		$(DOCKER_IMAGE)
+
+# Perform a local Trivy scan for CVEs
+# Get Trivy from https://aquasecurity.github.io/trivy/v0.53/getting-started/installation/
+.PHONY: trivy-local
+trivy-local: docker-build-nightly
+	trivy image --scanners vuln --severity  CRITICAL,HIGH --timeout 60m $(DOCKER_IMAGE)
+
+.PHONY: docker-clean-all
+docker-clean-all:
+	@CONTAINERS=$$(docker ps -a -q --filter ancestor=$(DOCKER_IMAGE)); \
+	if [ -n "$$CONTAINERS" ]; then \
+		docker stop $$CONTAINERS; \
+		docker rm $$CONTAINERS; \
+	fi
+	docker rmi $(DOCKER_IMAGE)
+
+.PHONY: bundles
+bundles:
+	rm -f -r bundles
+	mkdir -p bundles
+	cp -r static about.md bundles/
+	sed 's/{{VERSION}}/${APP_VERSION}/g' app.toml.template > bundles/app.toml
+	cd bundles && zip -r ai.h2o.llmstudio.${APP_VERSION}.wave *
+
+.PHONY: shell
+shell:
+	$(PIPENV) shell
+
+setup-doc:  # Install documentation dependencies
+	cd documentation && npm install 
+
+run-doc:  # Run the doc locally
+	cd documentation && npm start
+
+update-documentation-infrastructure:
+	cd documentation && npm update @h2oai/makersaurus
+	cd documentation && npm ls
+
+build-doc-locally:  # Bundles your website into static files for production 
+	cd documentation && npm run build
+
+serve-doc-locally:  # Serves the built website locally 
+	cd documentation && npm run serve

Pipfile

@@ -0,0 +1,75 @@
+[[source]]
+name = "pypi"
+url = "https://pypi.org/simple"
+verify_ssl = true
+
+[[source]]
+name = "pytorch"
+url = "https://download.pytorch.org/whl/cu121"
+verify_ssl = false
+
+[requires]
+python_version = "3.10"
+
+[packages]
+torch = {index = "pytorch", version = "==2.4.0+cu121"}
+tqdm = ">=4.65.0, <5.0.0"
+transformers = "==4.45.0"
+numpy = ">=1.26.0, <2.0.0"
+pandas = ">=2.2.0, <3.0.0"
+scikit-learn = ">=1.5.1, <2.0.0"
+boto3 = ">=1.20.24, <2.0.0"
+SQLAlchemy = ">=2.0.25, <3.0.0"
+dill = ">=0.3.8, <0.4.0"
+pyarrow = ">=14.0.1"
+kaggle = ">=1.6.14, <2.0.0, !=1.6.15"
+coolname = ">=2.2.0, <3.0.0"
+bokeh = ">=3.5.0, <4.0.0"
+beautifulsoup4 = ">=4.11.1, <5.0.0"
+sqlitedict = "==1.7.0"
+sentencepiece = ">=0.1.96, <0.2.0"
+sacrebleu = "==2.0.0"
+toml = ">=0.10.2, <0.11.0"
+pyyaml = ">=6.0.0, <7.0.0"
+protobuf = "==3.20.3"
+fastparquet = ">=2023.7.0"
+gputil = ">=1.4.0, <2.0.0"
+huggingface-hub = "==0.24.6"
+bitsandbytes = "==0.43.3"
+accelerate = "==0.34.2"
+openai = ">=1.12.0, <2.0.0"
+einops = "==0.8.0"
+datasets = ">=2.20.0, <3.0.0"
+neptune = "==1.10.4, <2.0.0"
+wandb = ">=0.17.5, <1.0.0"
+Jinja2 = ">=3.1.3, <4.0.0"
+h2o-drive = ">=3.0.0, <4.0.0"
+h2o-wave = ">=1.4.0, <2.0.0"
+tiktoken = "==0.7.0"
+hf-transfer = "==0.1.8"
+peft = "==0.12.0"
+azure-storage-file-datalake = ">=12.12.0"
+deepspeed = "==0.14.4"
+keyring = ">=25.2.1, <26.0.0"
+pydantic = ">=2.8.2, <3.0.0"
+
+[dev-packages]
+black = "==24.4.2"
+coverage = "==7.5.1"
+flake8 = "==7.0.0"
+flake8-black = "==0.3.6"
+flake8-isort = "==6.1.1"
+isort = "==5.13.2"
+mypy = "==1.10.0"
+pytest = "==8.2.0"
+pytest-cov = "==5.0.0"
+pytest-dependency = "==0.6.0"
+pytest-html = ">=4.1.1, <5.0.0"
+types-pyyaml = ">=6.0"
+types-requests = ">=2.31"
+types-toml = ">=0.10"
+wheel = "==0.43.0"
+pytest-bdd = "==7.1.2"
+hac-playwright = { file = "http://h2o-public-test-data.s3.amazonaws.com/e2e-testing/hac_playwright-1.45.0-py3-none-any.whl" }
+pytest-base-url = "==2.1.0"
+pytest-mock = "==3.14.0"

README.md

@@ -1,10 +1,303 @@
----
-title: Llm Studio
-emoji: ⚡
-colorFrom: pink
-colorTo: green
-sdk: docker
-pinned: false
----
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+<p align="center"><img src="llm_studio/app_utils/static/llm-studio-logo-light.png#gh-dark-mode-only"></p>
+<p align="center"><img src="llm_studio/app_utils/static/llm-studio-logo.png#gh-light-mode-only"></p>
+
+<h3 align="center">
+    <p>Welcome to H2O LLM Studio, a framework and no-code GUI designed for<br />
+    fine-tuning state-of-the-art large language models (LLMs).
+</p>
+</h3>
+
+<a href="https://user-images.githubusercontent.com/1069138/233859311-32aa1f8c-4d68-47ac-8cd9-9313171ff9f9.png"><img width="50%" alt="home" src="https://user-images.githubusercontent.com/1069138/233859311-32aa1f8c-4d68-47ac-8cd9-9313171ff9f9.png"></a><a href="https://user-images.githubusercontent.com/1069138/233859315-e6928aa7-28d2-420b-8366-bc7323c368ca.png"><img width="50%" alt="logs" src="https://user-images.githubusercontent.com/1069138/233859315-e6928aa7-28d2-420b-8366-bc7323c368ca.png"></a>
+
+## Jump to
+
+- [With H2O LLM Studio, you can](#with-h2o-llm-studio-you-can)
+- [Quickstart](#quickstart)
+- [What's New](#whats-new)
+- [Setup](#setup)
+  - [Recommended Install](#recommended-install)
+  - [Virtual Environments](#virtual-environments)
+- [Run H2O LLM Studio GUI](#run-h2o-llm-studio-gui)
+- [Run H2O LLM Studio GUI using Docker](#run-h2o-llm-studio-gui-using-docker)
+- [Run H2O LLM Studio with command line interface (CLI)](#run-h2o-llm-studio-with-command-line-interface-cli)
+- [Troubleshooting](#troubleshooting)
+- [Data format and example data](#data-format-and-example-data)
+- [Training your model](#training-your-model)
+- [Example: Run on OASST data via CLI](#example-run-on-oasst-data-via-cli)
+- [Model checkpoints](#model-checkpoints)
+- [Documentation](#documentation)
+- [Contributing](#contributing)
+- [License](#license)
+
+## With H2O LLM Studio, you can
+
+- easily and effectively fine-tune LLMs **without the need for any coding experience**.
+- use a **graphic user interface (GUI)** specially designed for large language models.
+- finetune any LLM using a large variety of hyperparameters.
+- use recent finetuning techniques such as [Low-Rank Adaptation (LoRA)](https://arxiv.org/abs/2106.09685) and 8-bit model training with a low memory footprint.
+- use Reinforcement Learning (RL) to finetune your model (experimental)
+- use advanced evaluation metrics to judge generated answers by the model.
+- track and compare your model performance visually. In addition, [Neptune](https://neptune.ai/) and [W&B](https://wandb.ai/) integration can be used.
+- chat with your model and get instant feedback on your model performance.
+- easily export your model to the [Hugging Face Hub](https://huggingface.co/) and share it with the community.
+
+## Quickstart
+
+For questions, discussing, or just hanging out, come and join our [Discord](https://discord.gg/WKhYMWcVbq)!
+
+Use cloud-based runpod.io instance to run the H2O LLM Studio GUI.
+
+[![open_in_runpod](https://github.com/user-attachments/assets/0dffd945-0be0-4ef0-85cd-4e6f260d4e6c)](https://www.runpod.io/console/deploy?template=3oh3easrlu)
+
+Using CLI for fine-tuning LLMs:
+
+[![Kaggle](https://kaggle.com/static/images/open-in-kaggle.svg)](https://www.kaggle.com/code/ilu000/h2o-llm-studio-cli/) [![Open in Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/drive/1soqfJjwDJwjjH-VzZYO_pUeLx5xY4N1K?usp=sharing)
+
+## What's New
+
+- [PR 788](https://github.com/h2oai/h2o-llmstudio/pull/788) New problem type for Causal Regression Modeling allows to train single target regression data using LLMs.
+- [PR 747](https://github.com/h2oai/h2o-llmstudio/pull/747) Fully removed RLHF in favor of DPO/IPO/KTO optimization.
+- [PR 741](https://github.com/h2oai/h2o-llmstudio/pull/741) Removing separate max length settings for prompt and answer in favor of a single `max_length` settings better resembling `chat_template` functionality from `transformers`.
+- [PR 592](https://github.com/h2oai/h2o-llmstudio/pull/599) Added `KTOPairLoss` for DPO modeling allowing to train models with simple preference data. Data currently needs to be manually prepared by randomly matching positive and negative examples as pairs.
+- [PR 592](https://github.com/h2oai/h2o-llmstudio/pull/592) Starting to deprecate RLHF in favor of DPO/IPO optimization. Training is disabled, but old experiments are still viewable. RLHF will be fully removed in a future release.
+- [PR 530](https://github.com/h2oai/h2o-llmstudio/pull/530) Introduced a new problem type for DPO/IPO optimization. This optimization technique can be used as an alternative to RLHF.
+- [PR 288](https://github.com/h2oai/h2o-llmstudio/pull/288) Introduced Deepspeed for sharded training allowing to train larger models on machines with multiple GPUs. Requires NVLink. This feature replaces FSDP and offers more flexibility. Deepspeed requires a system installation of cudatoolkit and we recommend using version 12.1. See [Recommended Install](#recommended-install).
+- [PR 449](https://github.com/h2oai/h2o-llmstudio/pull/449) New problem type for Causal Classification Modeling allows to train binary and multiclass models using LLMs.
+- [PR 364](https://github.com/h2oai/h2o-llmstudio/pull/364) User secrets are now handled more securely and flexible. Support for handling secrets using the 'keyring' library was added. User settings are tried to be migrated automatically.
+
+Please note that due to current rapid development we cannot guarantee full backwards compatibility of new functionality. We thus recommend to pin the version of the framework to the one you used for your experiments. For resetting, please delete/backup your `data` and `output` folders.
+
+## Setup
+
+H2O LLM Studio requires a machine with Ubuntu 16.04+ and at least one recent Nvidia GPU with Nvidia drivers version >= 470.57.02. For larger models, we recommend at least 24GB of GPU memory.
+
+For more information about installation prerequisites, see the [Set up H2O LLM Studio](https://docs.h2o.ai/h2o-llmstudio/get-started/set-up-llm-studio#prerequisites) guide in the documentation.
+
+For a performance comparison of different GPUs, see the [H2O LLM Studio performance](https://h2oai.github.io/h2o-llmstudio/get-started/llm-studio-performance) guide in the documentation.
+
+### Recommended Install
+
+The recommended way to install H2O LLM Studio is using pipenv with Python 3.10. To install Python 3.10 on Ubuntu 16.04+, execute the following commands:
+
+#### System installs (Python 3.10)
+
+```bash
+sudo add-apt-repository ppa:deadsnakes/ppa
+sudo apt install python3.10
+sudo apt-get install python3.10-distutils
+curl -sS https://bootstrap.pypa.io/get-pip.py | python3.10
+```
+
+#### Installing NVIDIA Drivers (if required)
+
+If deploying on a 'bare metal' machine running Ubuntu, one may need to install the required Nvidia drivers and CUDA. The following commands show how to retrieve the latest drivers for a machine running Ubuntu 20.04 as an example. One can update the following based on their OS.
+
+```bash
+wget https://developer.download.nvidia.com/compute/cuda/repos/ubuntu2004/x86_64/cuda-ubuntu2004.pin
+sudo mv cuda-ubuntu2004.pin /etc/apt/preferences.d/cuda-repository-pin-600
+wget https://developer.download.nvidia.com/compute/cuda/12.1.0/local_installers/cuda-repo-ubuntu2004-12-1-local_12.1.0-530.30.02-1_amd64.deb
+sudo dpkg -i cuda-repo-ubuntu2004-12-1-local_12.1.0-530.30.02-1_amd64.deb
+sudo cp /var/cuda-repo-ubuntu2004-12-1-local/cuda-*-keyring.gpg /usr/share/keyrings/
+sudo apt-get update
+sudo apt-get -y install cuda
+```
+
+alternatively, one can install cudatoolkits in a conda environment:
+
+```bash
+conda create -n llmstudio python=3.10
+conda activate llmstudio
+conda install -c "nvidia/label/cuda-12.1.0" cuda-toolkit
+```
+
+### Virtual environments
+
+We offer various ways of setting up the necessary python environment.
+
+#### Pipenv virtual environment
+
+The following command will create a virtual environment using pipenv and will install the dependencies using pipenv:
+
+```bash
+make setup
+```
+
+If you are having troubles installing the flash_attn package, consider running
+
+```bash
+make setup-no-flash
+```
+
+instead. This will install the dependencies without the flash_attn package. Note that this will disable the use of Flash Attention 2 and model training will be slower and consume more memory.
+
+#### Nightly Conda virtual environment
+
+You can also setup a conda virtual environment that can also deviate from the recommended setup. The ```Makefile``` contains a command ```setup-conda-nightly``` that installs a fresh conda environment with CUDA 12.4 and current nightly PyTorch.
+
+#### Using requirements.txt
+
+If you wish to use another virtual environment, you can also install the dependencies using the requirements.txt file:
+
+```bash
+pip install -r requirements.txt
+pip install flash-attn==2.6.1 --no-build-isolation  # optional for Flash Attention 2
+```
+
+## Run H2O LLM Studio GUI
+
+You can start H2O LLM Studio using the following command:
+
+```bash
+make llmstudio
+```
+
+This command will start the [H2O wave](https://github.com/h2oai/wave) server and app.
+Navigate to <http://localhost:10101/> (we recommend using Chrome) to access H2O LLM Studio and start fine-tuning your models!
+
+If you are running H2O LLM Studio with a custom environment other than Pipenv, you need to start the app as follows:
+
+```bash
+H2O_WAVE_MAX_REQUEST_SIZE=25MB \
+H2O_WAVE_NO_LOG=true \
+H2O_WAVE_PRIVATE_DIR="/download/@output/download" \
+wave run llm_studio.app
+```
+
+If you are using the [nightly conda environment](#nightly-conda-virtual-environment), you can run ```make llmstudio-conda```.
+
+## Run H2O LLM Studio GUI using Docker
+
+Install Docker first by following instructions from [NVIDIA Containers](https://docs.nvidia.com/datacenter/cloud-native/container-toolkit/install-guide.html#docker). Make sure to have `nvidia-container-toolkit` installed on your machine as outlined in the instructions.
+
+H2O LLM Studio images are stored in the h2oai dockerhub container repository.
+
+```bash
+mkdir -p `pwd`/llmstudio_mnt
+
+# make sure to pull latest image if you still have a prior version cached
+docker pull h2oairelease/h2oai-llmstudio-app:latest
+
+# run the container
+docker run \
+    --runtime=nvidia \
+    --shm-size=64g \
+    --init \
+    --rm \
+    -it \
+    -u `id -u`:`id -g` \
+    -p 10101:10101 \
+    -v `pwd`/llmstudio_mnt:/home/llmstudio/mount \
+    -v ~/.cache:/home/llmstudio/.cache \
+    h2oairelease/h2oai-llmstudio-app:latest
+```
+
+Navigate to <http://localhost:10101/> (we recommend using Chrome) to access H2O LLM Studio and start fine-tuning your models!
+
+(Note other helpful docker commands are `docker ps` and `docker kill`.)
+
+If you prefer to build your own Docker image from source, follow the instructions below.
+
+```bash
+docker build -t h2o-llmstudio .
+
+mkdir -p `pwd`/llmstudio_mnt
+
+docker run \
+    --runtime=nvidia \
+    --shm-size=64g \
+    --init \
+    --rm \
+    -it \
+    -u `id -u`:`id -g` \
+    -p 10101:10101 \
+    -v `pwd`/llmstudio_mnt:/home/llmstudio/mount \
+    -v ~/.cache:/home/llmstudio/.cache \
+    h2o-llmstudio
+```
+
+## Run H2O LLM Studio with command line interface (CLI)
+
+You can also use H2O LLM Studio with the command line interface (CLI) and specify the configuration .yaml file that contains all the experiment parameters. To finetune using H2O LLM Studio with CLI, activate the pipenv environment by running `make shell`, and then use the following command:
+
+```bash
+python llm_studio/train.py -Y {path_to_config_yaml_file}
+```
+
+To run on multiple GPUs in DDP mode, run the following command:
+
+```bash
+bash distributed_train.sh {NR_OF_GPUS} -Y {path_to_config_yaml_file}
+```
+
+By default, the framework will run on the first `k` GPUs. If you want to specify specific GPUs to run on, use the `CUDA_VISIBLE_DEVICES` environment variable before the command.
+
+To start an interactive chat with your trained model, use the following command:
+
+```bash
+python llm_studio/prompt.py -e {experiment_name}
+```
+
+where `experiment_name` is the output folder of the experiment you want to chat with (see configuration).
+The interactive chat will also work with model that were finetuned using the UI.
+
+To publish the model to Hugging Face, use the following command:
+
+```bash
+make shell 
+
+python llm_studio/publish_to_hugging_face.py -p {path_to_experiment} -d {device} -a {api_key} -u {user_id} -m {model_name} -s {safe_serialization}
+```
+
+`path_to_experiment` is the output folder of the experiment.
+`device` is the target device for running the model, either 'cpu' or 'cuda:0'. Default is 'cuda:0'.
+`api_key` is the Hugging Face API Key. If user logged in, it can be omitted.
+`user_id` is the Hugging Face user ID. If user logged in, it can be omitted.
+`model_name` is the name of the model to be published on Hugging Face. It can be omitted.
+`safe_serialization` is a flag indicating whether safe serialization should be used. Default is True.
+
+## Troubleshooting
+
+If running on cloud based machines such as runpod, you may need to set the following environment variable to allow the H2O Wave server to accept connections from the proxy:
+
+```bash
+H2O_WAVE_ALLOWED_ORIGINS="*"
+```
+
+If you are experiencing timeouts when running the H2O Wave server remotely, you can increase the timeout by setting the following environment variables:
+
+```bash
+H2O_WAVE_APP_CONNECT_TIMEOUT="15"
+H2O_WAVE_APP_WRITE_TIMEOUT="15"
+H2O_WAVE_APP_READ_TIMEOUT="15"
+H2O_WAVE_APP_POOL_TIMEOUT="15"
+```
+
+All default to 5 (seconds). Increase them if you are experiencing timeouts. Use -1 to disable the timeout.
+
+## Data format and example data
+
+For details on the data format required when importing your data or example data that you can use to try out H2O LLM Studio, see [Data format](https://docs.h2o.ai/h2o-llmstudio/guide/datasets/data-connectors-format#data-format) in the H2O LLM Studio documentation.
+
+## Training your model
+
+With H2O LLM Studio, training your large language model is easy and intuitive. First, upload your dataset and then start training your model. Start by [creating an experiment](https://docs.h2o.ai/h2o-llmstudio/guide/experiments/create-an-experiment). You can then [monitor and manage your experiment](https://docs.h2o.ai/h2o-llmstudio/guide/experiments/view-an-experiment), [compare experiments](https://docs.h2o.ai/h2o-llmstudio/guide/experiments/compare-experiments), or [push the model to Hugging Face](https://docs.h2o.ai/h2o-llmstudio/guide/experiments/export-trained-model) to share it with the community.
+
+## Example: Run on OASST data via CLI
+
+As an example, you can run an experiment on the OASST data via CLI. For instructions, see [Run an experiment on the OASST data](https://docs.h2o.ai/h2o-llmstudio/guide/experiments/create-an-experiment#run-an-experiment-on-the-oasst-data-via-cli) guide in the H2O LLM Studio documentation.
+
+## Model checkpoints
+
+All open-source datasets and models are posted on [H2O.ai's Hugging Face page](https://huggingface.co/h2oai/) and our [H2OGPT](https://github.com/h2oai/h2ogpt) repository.
+
+## Documentation
+
+Detailed documentation and frequently asked questions (FAQs) for H2O LLM Studio can be found at <https://docs.h2o.ai/h2o-llmstudio/>. If you wish to contribute to the docs, navigate to the `/documentation` folder of this repo and refer to the [README.md](documentation/README.md) for more information.
+
+## Contributing
+
+We are happy to accept contributions to the H2O LLM Studio project. Please refer to the [CONTRIBUTING.md](CONTRIBUTING.md) file for more information.
+
+## License
+
+H2O LLM Studio is licensed under the Apache 2.0 license. Please see the [LICENSE](LICENSE) file for more information.

about.md

@@ -0,0 +1,5 @@
+# H2O LLM Studio
+
+Launch H2O LLM Studio, your go-to tool for fine-tuning large language models without writing a single line of code. With an easy-to-use GUI, you can tweak tons of hyperparameters and take advantage of the latest techniques like Low-Rank Adaptation (LoRA) and 4-bit model training. Check out how your model's doing with advanced evaluation metrics, visually track and compare performance, and even chat with your model for instant feedback. Fine-tuning LLMs has never been this simple and rewarding!
+
+To learn more, see [H2O LLM Studio | Docs](https://docs.h2o.ai/h2o-llmstudio/).

app.toml.template

@@ -0,0 +1,43 @@
+[App]
+name = "ai.h2o.llmstudio"
+Version = "{{VERSION}}"
+Title = "H2O LLM Studio"
+Description =  "A framework and no-code GUI designed for fine-tuning state-of-the-art large language models (LLMs)"
+LongDescription = "about.md"
+Tags = ["GENERATIVE_AI", "NLP", "DATA_SCIENCE"]
+
+[Runtime]
+# Must be installed in the server config
+RuntimeVersion = "base_runtime"
+AppMode = "container"
+Port = 10101
+CPUReservation = "10"
+MemoryReservation = "118Gi"
+MemoryLimit = "118Gi"
+GPUCount = 1
+VolumeMount = "/home/llmstudio/mount"
+VolumeSize = "1Ti"
+ResourceVolumeSize = "1Ti"
+EnableSHM = true
+EnableOIDC = true
+RoutingMode = "BASE_URL"
+
+[[Env]]
+Name = "H2O_LLM_STUDIO_WORKDIR"
+Value = "/home/llmstudio/mount"
+
+[[Env]]
+Name = "HOME"
+Value = "/home/llmstudio"
+
+[[Env]]
+Name = "H2O_LLM_STUDIO_ENABLE_HEAP"
+Value = "True"
+
+[[Env]]
+Name = "H2O_WAVE_PRIVATE_DIR"
+Value = "/download/@/home/llmstudio/mount/output/download"
+
+[[Env]]
+Name = "HF_HUB_ENABLE_HF_TRANSFER"
+Value = "0"

distributed_train.sh

@@ -0,0 +1,4 @@
+#!/bin/bash
+NUM_PROC=$1
+shift
+torchrun --nproc_per_node=$NUM_PROC llm_studio/train.py "$@"

entrypoint.sh

@@ -0,0 +1,8 @@
+#!/bin/bash
+set -e
+
+nvidia-smi
+
+echo "Starting H2O LLM Studio..."
+
+wave run --no-reload llm_studio.app

pyproject.toml

@@ -0,0 +1,24 @@
+[project]
+name = "h2o-llmstudio"
+version = "1.14.0-dev"
+readme = "README.md"
+license = {file = "LICENSE"}
+
+[tool.black]
+line-length = 88
+target-version = ["py310"]
+exclude = "(.eggs|.git|.hg|.mypy_cache|.nox|.tox|.venv|.svn|_build|buck-out|build/|dist/|output/|data/)"
+
+[tool.isort]
+multi_line_output = 3
+include_trailing_comma = true
+force_grid_wrap = 0
+use_parentheses = true
+ensure_newline_before_comments = true
+line_length = 88
+
+[tool.mypy]
+ignore_missing_imports = true
+allow_redefinition = true
+strict_optional = false
+exclude = "(build|output|data|tests)"

requirements.txt

@@ -0,0 +1,187 @@
+-i https://pypi.org/simple
+--extra-index-url https://download.pytorch.org/whl/cu121
+accelerate==0.34.2; python_full_version >= '3.8.0'
+aioboto3==13.1.1; python_version >= '3.8' and python_version < '4.0'
+aiobotocore[boto3]==2.13.1; python_version >= '3.8'
+aiofiles==24.1.0; python_version >= '3.8'
+aiohappyeyeballs==2.4.0; python_version >= '3.8'
+aiohttp==3.10.6; python_version >= '3.8'
+aioitertools==0.12.0; python_version >= '3.8'
+aiosignal==1.3.1; python_version >= '3.7'
+annotated-types==0.7.0; python_version >= '3.8'
+anyio==4.6.0; python_version >= '3.9'
+arrow==1.3.0; python_version >= '3.8'
+async-timeout==4.0.3; python_version < '3.11'
+attrs==24.2.0; python_version >= '3.7'
+azure-core==1.31.0; python_version >= '3.8'
+azure-storage-blob==12.23.0; python_version >= '3.8'
+azure-storage-file-datalake==12.17.0; python_version >= '3.8'
+backports.tarfile==1.2.0; python_version < '3.12'
+beautifulsoup4==4.12.3; python_full_version >= '3.6.0'
+bitsandbytes==0.43.3
+bleach==6.1.0; python_version >= '3.8'
+blessed==1.20.0; python_version >= '2.7'
+bokeh==3.5.2; python_version >= '3.10'
+boto3==1.34.131; python_version >= '3.8'
+botocore==1.34.131; python_version >= '3.8'
+bravado==11.0.3; python_version not in '3.0, 3.1, 3.2, 3.3, 3.4' and python_full_version != '3.5.0'
+bravado-core==6.1.1; python_version >= '3.7'
+certifi==2024.8.30; python_version >= '3.6'
+cffi==1.17.1; platform_python_implementation != 'PyPy'
+charset-normalizer==3.3.2; python_full_version >= '3.7.0'
+click==8.1.7; python_version >= '3.7'
+colorama==0.4.6; python_version >= '2.7' and python_version not in '3.0, 3.1, 3.2, 3.3, 3.4, 3.5, 3.6'
+contourpy==1.3.0; python_version >= '3.9'
+coolname==2.2.0
+cramjam==2.8.4; python_version >= '3.8'
+cryptography==43.0.1; python_version >= '3.7'
+datasets==2.21.0; python_full_version >= '3.8.0'
+deepspeed==0.14.4
+dill==0.3.8; python_version >= '3.8'
+distro==1.9.0; python_version >= '3.6'
+docker-pycreds==0.4.0
+editor==1.6.6; python_version >= '3.8'
+einops==0.8.0; python_version >= '3.8'
+exceptiongroup==1.2.2; python_version < '3.11'
+fastparquet==2024.5.0; python_version >= '3.9'
+filelock==3.16.1; python_version >= '3.8'
+fqdn==1.5.1
+frozenlist==1.4.1; python_version >= '3.8'
+fsspec[http]==2024.6.1; python_version >= '3.8'
+future==1.0.0; python_version >= '2.6' and python_version not in '3.0, 3.1, 3.2, 3.3'
+gitdb==4.0.11; python_version >= '3.7'
+gitpython==3.1.43; python_version >= '3.7'
+gputil==1.4.0
+greenlet==3.1.1; python_version < '3.13' and platform_machine == 'aarch64' or (platform_machine == 'ppc64le' or (platform_machine == 'x86_64' or (platform_machine == 'amd64' or (platform_machine == 'AMD64' or (platform_machine == 'win32' or platform_machine == 'WIN32')))))
+h11==0.14.0; python_version >= '3.7'
+h2o-authn[discovery]==2.1.0; python_version >= '3.8'
+h2o-cloud-discovery==2.1.0; python_version >= '3.8'
+h2o-drive==3.0.0; python_version >= '3.8' and python_version < '4.0'
+h2o-wave==1.5.1; python_version >= '3.8'
+hf-transfer==0.1.8; python_version >= '3.7'
+hjson==3.1.0
+httpcore==1.0.5; python_version >= '3.8'
+httpx==0.27.2; python_version >= '3.8'
+huggingface-hub==0.24.6; python_full_version >= '3.8.0'
+idna==3.10; python_version >= '3.6'
+importlib-metadata==8.5.0; python_version < '3.12'
+importlib-resources==6.4.5; python_version >= '3.8'
+inquirer==3.4.0; python_full_version >= '3.8.1'
+isodate==0.6.1
+isoduration==20.11.0
+jaraco.classes==3.4.0; python_version >= '3.8'
+jaraco.context==6.0.1; python_version >= '3.8'
+jaraco.functools==4.0.2; python_version >= '3.8'
+jeepney==0.8.0; sys_platform == 'linux'
+jinja2==3.1.4; python_version >= '3.7'
+jiter==0.5.0; python_version >= '3.8'
+jmespath==1.0.1; python_version >= '3.7'
+joblib==1.4.2; python_version >= '3.8'
+jsonpointer==3.0.0
+jsonref==1.1.0; python_version >= '3.7'
+jsonschema[format-nongpl]==4.23.0; python_version >= '3.8'
+jsonschema-specifications==2023.12.1; python_version >= '3.8'
+kaggle==1.6.17
+keyring==25.4.1; python_version >= '3.8'
+markupsafe==2.1.5; python_version >= '3.7'
+monotonic==1.6
+more-itertools==10.5.0; python_version >= '3.8'
+mpmath==1.3.0
+msgpack==1.1.0; python_version >= '3.8'
+multidict==6.1.0; python_version >= '3.8'
+multiprocess==0.70.16; python_version >= '3.8'
+neptune==1.10.4; python_version >= '3.7' and python_version < '4.0'
+networkx==3.3; python_version >= '3.10'
+ninja==1.11.1.1
+numpy==1.26.4; python_version >= '3.9'
+nvidia-cublas-cu12==12.1.3.1; platform_system == 'Linux' and platform_machine == 'x86_64'
+nvidia-cuda-cupti-cu12==12.1.105; platform_system == 'Linux' and platform_machine == 'x86_64'
+nvidia-cuda-nvrtc-cu12==12.1.105; platform_system == 'Linux' and platform_machine == 'x86_64'
+nvidia-cuda-runtime-cu12==12.1.105; platform_system == 'Linux' and platform_machine == 'x86_64'
+nvidia-cudnn-cu12==9.1.0.70; platform_system == 'Linux' and platform_machine == 'x86_64'
+nvidia-cufft-cu12==11.0.2.54; platform_system == 'Linux' and platform_machine == 'x86_64'
+nvidia-curand-cu12==10.3.2.106; platform_system == 'Linux' and platform_machine == 'x86_64'
+nvidia-cusolver-cu12==11.4.5.107; platform_system == 'Linux' and platform_machine == 'x86_64'
+nvidia-cusparse-cu12==12.1.0.106; platform_system == 'Linux' and platform_machine == 'x86_64'
+nvidia-ml-py==12.560.30
+nvidia-nccl-cu12==2.20.5; platform_system == 'Linux' and platform_machine == 'x86_64'
+nvidia-nvjitlink-cu12==12.6.68; python_version >= '3'
+nvidia-nvtx-cu12==12.1.105; platform_system == 'Linux' and platform_machine == 'x86_64'
+oauthlib==3.2.2; python_version >= '3.6'
+openai==1.48.0; python_full_version >= '3.7.1'
+packaging==24.1; python_version >= '3.8'
+pandas==2.2.3; python_version >= '3.9'
+peft==0.12.0; python_full_version >= '3.8.0'
+pillow==10.4.0; python_version >= '3.8'
+platformdirs==4.3.6; python_version >= '3.8'
+portalocker==2.10.1; python_version >= '3.8'
+protobuf==3.20.3; python_version >= '3.7'
+psutil==6.0.0; python_version >= '2.7' and python_version not in '3.0, 3.1, 3.2, 3.3, 3.4, 3.5'
+py-cpuinfo==9.0.0
+pyarrow==17.0.0; python_version >= '3.8'
+pycparser==2.22; python_version >= '3.8'
+pydantic==2.9.2; python_version >= '3.8'
+pydantic-core==2.23.4; python_version >= '3.8'
+pyjwt==2.9.0; python_version >= '3.8'
+python-dateutil==2.9.0.post0; python_version >= '2.7' and python_version not in '3.0, 3.1, 3.2, 3.3'
+python-slugify==8.0.4; python_version >= '3.7'
+pytz==2024.2
+pyyaml==6.0.2; python_version >= '3.8'
+readchar==4.2.0; python_version >= '3.8'
+referencing==0.35.1; python_version >= '3.8'
+regex==2024.9.11; python_version >= '3.8'
+requests==2.32.3; python_version >= '3.8'
+requests-oauthlib==2.0.0; python_version >= '3.4'
+rfc3339-validator==0.1.4
+rfc3986-validator==0.1.1
+rpds-py==0.20.0; python_version >= '3.8'
+runs==1.2.2; python_version >= '3.8'
+s3transfer==0.10.2; python_version >= '3.8'
+sacrebleu==2.0.0; python_version >= '3.6'
+safetensors==0.4.5; python_version >= '3.7'
+scikit-learn==1.5.2; python_version >= '3.9'
+scipy==1.14.1; python_version >= '3.10'
+secretstorage==3.3.3; sys_platform == 'linux'
+sentencepiece==0.1.99
+sentry-sdk==2.14.0; python_version >= '3.6'
+setproctitle==1.3.3; python_version >= '3.7'
+setuptools==75.1.0; python_version >= '3.8'
+simplejson==3.19.3; python_version >= '2.5' and python_version not in '3.0, 3.1, 3.2, 3.3'
+six==1.16.0; python_version >= '2.7' and python_version not in '3.0, 3.1, 3.2, 3.3'
+smmap==5.0.1; python_version >= '3.7'
+sniffio==1.3.1; python_version >= '3.7'
+soupsieve==2.6; python_version >= '3.8'
+sqlalchemy==2.0.35; python_version >= '3.7'
+sqlitedict==1.7.0
+starlette==0.39.1; python_version >= '3.8'
+swagger-spec-validator==3.0.4; python_version >= '3.8'
+sympy==1.13.3; python_version >= '3.8'
+tabulate==0.9.0; python_version >= '3.7'
+text-unidecode==1.3
+threadpoolctl==3.5.0; python_version >= '3.8'
+tiktoken==0.7.0; python_version >= '3.8'
+tokenizers==0.20.0; python_version >= '3.7'
+toml==0.10.2; python_version >= '2.6' and python_version not in '3.0, 3.1, 3.2, 3.3'
+tomli==2.0.1; python_version < '3.11'
+torch==2.4.0+cu121
+tornado==6.4.1; python_version >= '3.8'
+tqdm==4.66.5; python_version >= '3.7'
+transformers==4.45.0; python_full_version >= '3.8.0'
+triton==3.0.0; python_version < '3.13' and platform_system == 'Linux' and platform_machine == 'x86_64'
+types-python-dateutil==2.9.0.20240906; python_version >= '3.8'
+typing-extensions==4.12.2; python_version >= '3.8'
+tzdata==2024.2; python_version >= '2'
+uri-template==1.3.0
+urllib3==2.2.3; python_version >= '3.8'
+uvicorn==0.30.6; python_version >= '3.8'
+wandb==0.18.1; python_version >= '3.7'
+wcwidth==0.2.13
+webcolors==24.8.0
+webencodings==0.5.1
+websocket-client==1.8.0; python_version >= '3.8'
+wrapt==1.16.0; python_version >= '3.6'
+xmod==1.8.1; python_version >= '3.8'
+xxhash==3.5.0; python_version >= '3.7'
+xyzservices==2024.9.0; python_version >= '3.8'
+yarl==1.12.1; python_version >= '3.8'
+zipp==3.20.2; python_version >= '3.8'