nice-model

.gitattributes

@@ -33,3 +33,8 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+input/commonsense/commonsense_170k.json filter=lfs diff=lfs merge=lfs -text
+input/commonsensetest/dataset/hellaswag/test.json filter=lfs diff=lfs merge=lfs -text
+input/commonsensetest/dataset/hellaswag/train.json filter=lfs diff=lfs merge=lfs -text
+input/commonsensetest/dataset/social_i_qa/train.json filter=lfs diff=lfs merge=lfs -text
+input/commonsensetest/dataset/winogrande/train.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,54 @@
+---
+license: mit
+library_name: peft
+tags:
+- generated_from_trainer
+base_model: openai-community/gpt2-medium
+model-index:
+- name: kaggle
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# kaggle
+
+This model is a fine-tuned version of [openai-community/gpt2-medium](https://huggingface.co/openai-community/gpt2-medium) on an unknown dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 0.0003
+- train_batch_size: 2
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 1
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.11.2.dev0
+- Transformers 4.41.1
+- Pytorch 2.0.0
+- Datasets 2.19.1
+- Tokenizers 0.19.1

adapter_config.json

@@ -0,0 +1,37 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": null,
+  "beta1": 0.85,
+  "beta2": 0.85,
+  "bias": "none",
+  "deltaT": 1,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "init_r": 32,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.2,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "orth_reg_weight": 0.5,
+  "peft_type": "ADALORA",
+  "r": 8,
+  "rank_pattern": null,
+  "revision": null,
+  "target_modules": [
+    "c_attn"
+  ],
+  "target_r": 8,
+  "task_type": "CAUSAL_LM",
+  "tfinal": 0,
+  "tinit": 0,
+  "total_step": null,
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e372ee34a024eea072a5ca62c2c20eb3d491d4ff0adbf06239e5db887564f6e3
+size 12613193

input/commonsense/commonsense_170k.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4651a3e707fbe28be03f486f96fcf57f8c38b2173f3e38812003108970793ac8
+size 96529722

input/commonsensetest/dataset/hellaswag/test.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ea7e99795e63a01f2f5e9ddbc4dca964d9ebb22f04201e64d1ac043be51ab61
+size 11099046

input/commonsensetest/dataset/hellaswag/train.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:729aeafa3f600650a92e1c992a888528ac8a1ccd562408736eee66bed2183b1a
+size 43072851

input/commonsensetest/dataset/social_i_qa/train.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ca995d6055a6be053bb54b4b4c7abe4cd0323940079071932c1f9129d589b17
+size 14379571

input/commonsensetest/dataset/winogrande/train.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:154d4fc3ef6b065aff1b738150f3fbd8d497f8e32d7aaae114991a2ad912ae79
+size 24772666

lib/kaggle/gcp.py

@@ -0,0 +1 @@
+from kaggle_gcp import *

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:792f636757229e42f17c7ae4b58724debe0276e945bb45e65c50e964f8b23d52
+size 4603

working/peft/.github/ISSUE_TEMPLATE/bug-report.yml

@@ -0,0 +1,70 @@
+name: "\U0001F41B Bug Report"
+description: Submit a bug report to help us improve the library
+body:
+  - type: textarea
+    id: system-info
+    attributes:
+      label: System Info
+      description: Please share your relevant system information with us
+      placeholder: peft & accelerate & transformers version, platform, python version, ...
+    validations:
+      required: true
+
+  - type: textarea
+    id: who-can-help
+    attributes:
+      label: Who can help?
+      description: |
+        Your issue will be replied to more quickly if you can figure out the right person to tag with @.
+        If you know how to use git blame, that is the easiest way, otherwise, here is a rough guide of **who to tag**.
+
+        All issues are read by one of the core maintainers, so if you don't know who to tag, just leave this blank and
+        a core maintainer will ping the right person.
+
+        Please tag fewer than 3 people.
+
+        Library: @pacman100 @younesbelkada @benjaminbossan @sayakpaul
+
+        Documentation: @stevhliu
+
+      placeholder: "@Username ..."
+
+  - type: checkboxes
+    id: information-scripts-examples
+    attributes:
+      label: Information
+      description: 'The problem arises when using:'
+      options:
+        - label: "The official example scripts"
+        - label: "My own modified scripts"
+
+  - type: checkboxes
+    id: information-tasks
+    attributes:
+      label: Tasks
+      description: "The tasks I am working on are:"
+      options:
+        - label: "An officially supported task in the `examples` folder"
+        - label: "My own task or dataset (give details below)"
+
+  - type: textarea
+    id: reproduction
+    validations:
+      required: true
+    attributes:
+      label: Reproduction
+      description: |
+        Please provide a code sample that reproduces the problem you ran into. It can be a Colab link or just a code snippet.
+        Please provide the simplest reproducer as possible so that we can quickly fix the issue. When you paste
+        the error message, please include the full traceback.
+
+      placeholder: |
+        Reproducer:
+
+  - type: textarea
+    id: expected-behavior
+    validations:
+      required: true
+    attributes:
+      label: Expected behavior
+      description: "A clear and concise description of what you would expect to happen."

working/peft/.github/ISSUE_TEMPLATE/feature-request.yml

@@ -0,0 +1,30 @@
+name: "\U0001F680 Feature request"
+description: Submit a proposal/request for a new feature
+labels: [ "feature" ]
+body:
+  - type: textarea
+    id: feature-request
+    validations:
+      required: true
+    attributes:
+      label: Feature request
+      description: |
+        A clear and concise description of the feature proposal. Please provide a link to the paper and code in case they exist.
+
+  - type: textarea
+    id: motivation
+    validations:
+      required: true
+    attributes:
+      label: Motivation
+      description: |
+        Please outline the motivation for the proposal. Is your feature request related to a problem? 
+
+  - type: textarea
+    id: contribution
+    validations:
+      required: true
+    attributes:
+      label: Your contribution
+      description: |
+        Is there any way that you could help, e.g. by submitting a PR? 

working/peft/.github/workflows/build_docker_images.yml

@@ -0,0 +1,217 @@
+name: Build Docker images (scheduled)
+
+on:
+  workflow_dispatch:
+  workflow_call:
+  schedule:
+    - cron: "0 1 * * *"
+
+concurrency:
+  group: docker-image-builds
+  cancel-in-progress: false
+
+env:
+  CI_SLACK_CHANNEL: ${{ secrets.CI_DOCKER_CHANNEL }}
+
+jobs:
+  latest-cpu:
+    name: "Latest Peft CPU [dev]"
+    runs-on: ubuntu-latest
+    steps:
+      - name: Cleanup disk
+        run: |
+          sudo ls -l /usr/local/lib/
+          sudo ls -l /usr/share/
+          sudo du -sh /usr/local/lib/
+          sudo du -sh /usr/share/
+          sudo rm -rf /usr/local/lib/android
+          sudo rm -rf /usr/share/dotnet
+          sudo du -sh /usr/local/lib/
+          sudo du -sh /usr/share/
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v1
+      - name: Check out code
+        uses: actions/checkout@v3
+      - name: Login to DockerHub
+        uses: docker/login-action@v2
+        with:
+          username: ${{ secrets.DOCKERHUB_USERNAME }}
+          password: ${{ secrets.DOCKERHUB_PASSWORD }}
+
+      - name: Build and Push CPU
+        uses: docker/build-push-action@v4
+        with:
+          context: ./docker/peft-cpu
+          push: true
+          tags: huggingface/peft-cpu
+
+      - name: Post to Slack
+        if: always()
+        uses: huggingface/hf-workflows/.github/actions/post-slack@main
+        with:
+          slack_channel: "C06LKJB31RU"
+          title: 🤗 Results of the PEFT-CPU docker build 
+          status: ${{ job.status }}
+          slack_token: ${{ secrets.SLACK_CIFEEDBACK_BOT_TOKEN }}
+
+  latest-cuda:
+    name: "Latest Peft GPU [dev]"
+    runs-on: ubuntu-latest
+    steps:
+      - name: Cleanup disk
+        run: |
+          sudo ls -l /usr/local/lib/
+          sudo ls -l /usr/share/
+          sudo du -sh /usr/local/lib/
+          sudo du -sh /usr/share/
+          sudo rm -rf /usr/local/lib/android
+          sudo rm -rf /usr/share/dotnet
+          sudo du -sh /usr/local/lib/
+          sudo du -sh /usr/share/
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v1
+      - name: Check out code
+        uses: actions/checkout@v3
+      - name: Login to DockerHub
+        uses: docker/login-action@v1
+        with:
+          username: ${{ secrets.DOCKERHUB_USERNAME }}
+          password: ${{ secrets.DOCKERHUB_PASSWORD }}
+
+      - name: Build and Push GPU
+        uses: docker/build-push-action@v4
+        with:
+          context: ./docker/peft-gpu
+          push: true
+          tags: huggingface/peft-gpu
+ 
+      - name: Post to Slack
+        if: always()
+        uses: huggingface/hf-workflows/.github/actions/post-slack@main
+        with:
+          slack_channel: "C06LKJB31RU"
+          title: 🤗 Results of the PEFT-GPU docker build 
+          status: ${{ job.status }}
+          slack_token: ${{ secrets.SLACK_CIFEEDBACK_BOT_TOKEN }}
+
+  latest-cuda-bnb-source:
+    name: "Latest Peft GPU + bnb source [dev]"
+    runs-on: ubuntu-latest
+    steps:
+      - name: Cleanup disk
+        run: |
+          sudo ls -l /usr/local/lib/
+          sudo ls -l /usr/share/
+          sudo du -sh /usr/local/lib/
+          sudo du -sh /usr/share/
+          sudo rm -rf /usr/local/lib/android
+          sudo rm -rf /usr/share/dotnet
+          sudo du -sh /usr/local/lib/
+          sudo du -sh /usr/share/
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v1
+      - name: Check out code
+        uses: actions/checkout@v3
+      - name: Login to DockerHub
+        uses: docker/login-action@v1
+        with:
+          username: ${{ secrets.DOCKERHUB_USERNAME }}
+          password: ${{ secrets.DOCKERHUB_PASSWORD }}
+
+      - name: Build and Push GPU
+        uses: docker/build-push-action@v4
+        with:
+          context: ./docker/peft-gpu-bnb-source
+          push: true
+          tags: huggingface/peft-gpu-bnb-source
+ 
+      - name: Post to Slack
+        if: always()
+        uses: huggingface/hf-workflows/.github/actions/post-slack@main
+        with:
+          slack_channel: "C06LKJB31RU"
+          title: 🤗 Results of the PEFT-GPU (bnb source / HF latest) docker build 
+          status: ${{ job.status }}
+          slack_token: ${{ secrets.SLACK_CIFEEDBACK_BOT_TOKEN }}
+
+  latest-cuda-bnb-source-latest:
+    name: "Latest Peft GPU + bnb source [accelerate / peft / transformers latest]"
+    runs-on: ubuntu-latest
+    steps:
+      - name: Cleanup disk
+        run: |
+          sudo ls -l /usr/local/lib/
+          sudo ls -l /usr/share/
+          sudo du -sh /usr/local/lib/
+          sudo du -sh /usr/share/
+          sudo rm -rf /usr/local/lib/android
+          sudo rm -rf /usr/share/dotnet
+          sudo du -sh /usr/local/lib/
+          sudo du -sh /usr/share/
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v1
+      - name: Check out code
+        uses: actions/checkout@v3
+      - name: Login to DockerHub
+        uses: docker/login-action@v1
+        with:
+          username: ${{ secrets.DOCKERHUB_USERNAME }}
+          password: ${{ secrets.DOCKERHUB_PASSWORD }}
+
+      - name: Build and Push GPU
+        uses: docker/build-push-action@v4
+        with:
+          context: ./docker/peft-gpu-bnb-latest
+          push: true
+          tags: huggingface/peft-gpu-bnb-latest
+   
+      - name: Post to Slack
+        if: always()
+        uses: huggingface/hf-workflows/.github/actions/post-slack@main
+        with:
+          slack_channel: "C06LKJB31RU"
+          title: 🤗 Results of the PEFT-GPU (bnb source / HF source) docker build 
+          status: ${{ job.status }}
+          slack_token: ${{ secrets.SLACK_CIFEEDBACK_BOT_TOKEN }}
+
+  latest-cuda-bnb-source-multi:
+    name: "Latest Peft GPU + bnb (multi-backend) source [accelerate / peft / transformers source]"
+    runs-on: ubuntu-latest
+    steps:
+      - name: Cleanup disk
+        run: |
+          sudo ls -l /usr/local/lib/
+          sudo ls -l /usr/share/
+          sudo du -sh /usr/local/lib/
+          sudo du -sh /usr/share/
+          sudo rm -rf /usr/local/lib/android
+          sudo rm -rf /usr/share/dotnet
+          sudo du -sh /usr/local/lib/
+          sudo du -sh /usr/share/
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v1
+      - name: Check out code
+        uses: actions/checkout@v3
+      - name: Login to DockerHub
+        uses: docker/login-action@v1
+        with:
+          username: ${{ secrets.DOCKERHUB_USERNAME }}
+          password: ${{ secrets.DOCKERHUB_PASSWORD }}
+
+      - name: Build and Push GPU
+        uses: docker/build-push-action@v4
+        with:
+          context: ./docker/peft-gpu-bnb-multi-source
+          push: true
+          tags: huggingface/peft-gpu-bnb-multi-source
+ 
+      - name: Post to Slack
+        if: always()
+        uses: huggingface/hf-workflows/.github/actions/post-slack@main
+        with:
+          slack_channel: "C06LKJB31RU"
+          title: 🤗 Results of the PEFT-GPU (bnb source multi-backend / HF latest) docker build 
+          status: ${{ job.status }}
+          slack_token: ${{ secrets.SLACK_CIFEEDBACK_BOT_TOKEN }}
+
+

working/peft/.github/workflows/build_documentation.yml

@@ -0,0 +1,20 @@
+name: Build documentation
+
+on:
+  push:
+    branches:
+      - main
+      - doc-builder*
+      - v*-release
+
+jobs:
+   build:
+    uses: huggingface/doc-builder/.github/workflows/build_main_documentation.yml@main
+    with:
+      commit_sha: ${{ github.sha }}
+      package: peft
+      notebook_folder: peft_docs
+      custom_container: huggingface/transformers-doc-builder
+    secrets:
+      token: ${{ secrets.HUGGINGFACE_PUSH }}
+      hf_token: ${{ secrets.HF_DOC_BUILD_PUSH }}

working/peft/.github/workflows/build_pr_documentation.yml

@@ -0,0 +1,17 @@
+name: Build PR Documentation
+
+on:
+  pull_request:
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.head_ref || github.run_id }}
+  cancel-in-progress: true
+
+jobs:
+  build:
+    uses: huggingface/doc-builder/.github/workflows/build_pr_documentation.yml@main
+    with:
+      commit_sha: ${{ github.event.pull_request.head.sha }}
+      pr_number: ${{ github.event.number }}
+      package: peft
+      custom_container: huggingface/transformers-doc-builder

working/peft/.github/workflows/integrations_tests.yml

@@ -0,0 +1,82 @@
+name: integration tests
+
+on:
+  workflow_dispatch:
+    inputs:
+      branch:
+        description: 'Branch to test on'
+        required: true
+
+jobs:
+  run_transformers_integration_tests:
+    strategy:
+      fail-fast: false
+      matrix:
+        transformers-version: ['main', 'latest']
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+        with:
+          ref: ${{ github.event.inputs.branch }}
+          repository: ${{ github.event.pull_request.head.repo.full_name }}
+      - name: Set up Python
+        uses: actions/setup-python@v4
+        with:
+          python-version: "3.10"
+          cache: "pip"
+          cache-dependency-path: "setup.py"
+      - name: print environment variables
+        run: |
+          echo "env.CI_BRANCH = ${{ env.CI_BRANCH }}"
+          echo "env.CI_SHA = ${{ env.CI_SHA }}"
+      - name: Install dependencies
+        run: |
+          python -m pip install --upgrade pip
+          python -m pip install .[test]
+          if [ "${{ matrix.transformers-version }}" == "main" ]; then
+              pip install -U git+https://github.com/huggingface/transformers.git
+          else
+              echo "Nothing to do as transformers latest already installed"
+          fi
+
+      - name: Test transformers integration
+        run: |
+          cd .. && git clone https://github.com/huggingface/transformers.git && cd transformers/ && git rev-parse HEAD
+          RUN_SLOW=1 pytest tests/peft_integration/test_peft_integration.py
+  run_diffusers_integration_tests:
+    strategy:
+      fail-fast: false
+      matrix:
+        # For now diffusers integration is not on PyPI
+        diffusers-version: ['main']
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+        with:
+          ref: ${{ github.event.inputs.branch }}
+          repository: ${{ github.event.pull_request.head.repo.full_name }}
+      - name: Set up Python
+        uses: actions/setup-python@v4
+        with:
+          python-version: "3.10"
+          cache: "pip"
+          cache-dependency-path: "setup.py"
+      - name: print environment variables
+        run: |
+          echo "env.CI_BRANCH = ${{ env.CI_BRANCH }}"
+          echo "env.CI_SHA = ${{ env.CI_SHA }}"
+      - name: Install dependencies
+        run: |
+          python -m pip install --upgrade pip
+          python -m pip install .[test]
+          
+          if [ "${{ matrix.diffusers-version }}" == "main" ]; then
+              pip install -U git+https://github.com/huggingface/diffusers.git
+          else
+              echo "Nothing to do as diffusers latest already installed"
+          fi
+
+      - name: Test diffusers integration
+        run: |
+          cd .. && git clone https://github.com/huggingface/diffusers.git && cd diffusers/ && git rev-parse HEAD
+          pytest tests/lora/test_lora_layers_peft.py

working/peft/.github/workflows/nightly-bnb.yml

@@ -0,0 +1,139 @@
+name: BNB from source self-hosted runner with slow tests (scheduled)
+
+on:
+  workflow_dispatch:
+  schedule:
+    - cron: "0 2 * * *"
+
+env:
+  RUN_SLOW: "yes"
+  IS_GITHUB_CI: "1"
+  # To be able to run tests on CUDA 12.2
+  NVIDIA_DISABLE_REQUIRE: "1"
+  SLACK_API_TOKEN: ${{ secrets.SLACK_API_TOKEN }}
+
+
+jobs:
+  run_all_tests_single_gpu:
+    strategy:
+      fail-fast: false
+      matrix:
+          docker-image-name: ["huggingface/peft-gpu-bnb-source:latest", "huggingface/peft-gpu-bnb-latest:latest", "huggingface/peft-gpu-bnb-multi-source:latest"]
+    runs-on: [self-hosted, single-gpu, nvidia-gpu, t4, ci]
+    env:
+      CUDA_VISIBLE_DEVICES: "0"
+      TEST_TYPE: "single_gpu_${{ matrix.docker-image-name }}"
+    container:
+      image: ${{ matrix.docker-image-name }}
+      options: --gpus all --shm-size "16gb" --ipc host -v /mnt/cache/.cache/huggingface:/mnt/cache/
+    defaults:
+      run:
+        shell: bash
+    steps:
+      - uses: actions/checkout@v3
+      - name: Pip install
+        run: |
+          source activate peft
+          pip install -e . --no-deps
+          pip install pytest-reportlog pytest-cov parameterized datasets scipy einops
+          pip install "pytest>=7.2.0,<8.0.0" # see: https://github.com/huggingface/transformers/blob/ce4fff0be7f6464d713f7ac3e0bbaafbc6959ae5/setup.py#L148C6-L148C26
+          mkdir transformers-clone && git clone https://github.com/huggingface/transformers.git transformers-clone # rename to transformers clone to avoid modules conflict
+          if [ "${{ matrix.docker-image-name }}" == "huggingface/peft-gpu-bnb-latest:latest" ]; then
+            cd transformers-clone
+            transformers_version=$(pip show transformers | grep '^Version:' | cut -d ' ' -f2 | sed 's/\.dev0//')
+            echo "Checking out tag for Transformers version: v$transformers_version"
+            git fetch --tags
+            git checkout tags/v$transformers_version
+            cd .. 
+          fi
+      - name: Run examples on single GPU
+        if: always()
+        run: |
+          source activate peft
+          make tests_examples_single_gpu_bnb
+      
+      - name: Run core tests on single GPU
+        if: always()
+        run: |
+          source activate peft
+          make tests_core_single_gpu_bnb
+
+      - name: Run BNB regression tests on single GPU
+        if: always()
+        run: |
+          source activate peft
+          make tests_gpu_bnb_regression
+
+      - name: Run transformers tests on single GPU
+        if: always()
+        run: |
+          source activate peft
+          make transformers_tests
+          
+      - name: Generate Report
+        if: always()
+        run: |
+          pip install slack_sdk tabulate
+          python scripts/log_reports.py --slack_channel_name bnb-daily-ci-collab >> $GITHUB_STEP_SUMMARY
+
+  run_all_tests_multi_gpu:
+    strategy:
+      fail-fast: false
+      matrix:
+        docker-image-name: ["huggingface/peft-gpu-bnb-source:latest", "huggingface/peft-gpu-bnb-latest:latest", "huggingface/peft-gpu-bnb-multi-source:latest"]
+    runs-on: [self-hosted, multi-gpu, nvidia-gpu, t4, ci]
+    env:
+      CUDA_VISIBLE_DEVICES: "0,1"
+      TEST_TYPE: "multi_gpu_${{ matrix.docker-image-name }}"
+    container:
+      image: ${{ matrix.docker-image-name }}
+      options: --gpus all --shm-size "16gb" --ipc host -v /mnt/cache/.cache/huggingface:/mnt/cache/
+    defaults:
+      run:
+        shell: bash
+    steps:
+      - uses: actions/checkout@v3
+      - name: Pip install
+        run: |
+          source activate peft
+          pip install -e . --no-deps
+          pip install pytest-reportlog pytest-cov parameterized datasets scipy einops
+          pip install "pytest>=7.2.0,<8.0.0" # see: https://github.com/huggingface/transformers/blob/ce4fff0be7f6464d713f7ac3e0bbaafbc6959ae5/setup.py#L148C6-L148C26
+          mkdir transformers-clone && git clone https://github.com/huggingface/transformers.git transformers-clone
+          if [ "${{ matrix.docker-image-name }}" == "huggingface/peft-gpu-bnb-latest:latest" ]; then
+            cd transformers-clone
+            transformers_version=$(pip show transformers | grep '^Version:' | cut -d ' ' -f2 | sed 's/\.dev0//')
+            echo "Checking out tag for Transformers version: v$transformers_version"
+            git fetch --tags
+            git checkout tags/v$transformers_version
+            cd ..
+          fi 
+
+      - name: Run core GPU tests on multi-gpu
+        if: always()
+        run: |
+          source activate peft
+        
+      - name: Run examples on multi GPU
+        if: always()
+        run: |
+          source activate peft
+          make tests_examples_multi_gpu_bnb
+      
+      - name: Run core tests on multi GPU
+        if: always()
+        run: |
+          source activate peft
+          make tests_core_multi_gpu_bnb
+
+      - name: Run transformers tests on multi GPU
+        if: always()
+        run: |
+          source activate peft
+          make transformers_tests
+          
+      - name: Generate Report
+        if: always()
+        run: |
+          pip install slack_sdk tabulate
+          python scripts/log_reports.py --slack_channel_name bnb-daily-ci-collab >> $GITHUB_STEP_SUMMARY

working/peft/.github/workflows/nightly.yml

@@ -0,0 +1,108 @@
+name: Self-hosted runner with slow tests (scheduled)
+
+on:
+  workflow_dispatch:
+  schedule:
+    - cron: "0 2 * * *"
+
+env:
+  RUN_SLOW: "yes"
+  IS_GITHUB_CI: "1"
+  # To be able to run tests on CUDA 12.2
+  NVIDIA_DISABLE_REQUIRE: "1"
+  SLACK_API_TOKEN: ${{ secrets.SLACK_API_TOKEN }}
+
+
+jobs:
+  run_all_tests_single_gpu:
+    strategy:
+      fail-fast: false
+    runs-on: [self-hosted, single-gpu, nvidia-gpu, t4, ci]
+    env:
+      CUDA_VISIBLE_DEVICES: "0"
+      TEST_TYPE: "single_gpu"
+    container:
+      image: huggingface/peft-gpu:latest
+      options: --gpus all --shm-size "16gb" -e NVIDIA_DISABLE_REQUIRE=true
+    defaults:
+      run:
+        shell: bash
+    steps:
+      - uses: actions/checkout@v3
+      - name: Pip install
+        run: |
+          source activate peft
+          pip install -e . --no-deps
+          pip install pytest-reportlog
+      
+      - name: Run common tests on single GPU
+        run: |
+          source activate peft
+          make tests_common_gpu
+
+      - name: Run examples on single GPU
+        run: |
+          source activate peft
+          make tests_examples_single_gpu
+      
+      - name: Run core tests on single GPU
+        run: |
+          source activate peft
+          make tests_core_single_gpu
+
+      - name: Run regression tests on single GPU
+        run: |
+          source activate peft
+          make tests_regression
+          
+      - name: Generate Report
+        if: always()
+        run: |
+          pip install slack_sdk tabulate
+          python scripts/log_reports.py >> $GITHUB_STEP_SUMMARY
+
+  run_all_tests_multi_gpu:
+    strategy:
+      fail-fast: false
+    runs-on: [self-hosted, multi-gpu, nvidia-gpu, t4, ci]
+    env:
+      CUDA_VISIBLE_DEVICES: "0,1"
+      TEST_TYPE: "multi_gpu"
+    container:
+      image: huggingface/peft-gpu:latest
+      options: --gpus all --shm-size "16gb" -e NVIDIA_DISABLE_REQUIRE=true
+    defaults:
+      run:
+        shell: bash
+    steps:
+      - uses: actions/checkout@v3
+      - name: Pip install
+        run: |
+          source activate peft
+          pip install -e . --no-deps
+          pip install pytest-reportlog
+
+      - name: Run core GPU tests on multi-gpu
+        run: |
+          source activate peft
+          
+      - name: Run common tests on multi GPU
+        run: |
+          source activate peft
+          make tests_common_gpu
+        
+      - name: Run examples on multi GPU
+        run: |
+          source activate peft
+          make tests_examples_multi_gpu
+      
+      - name: Run core tests on multi GPU
+        run: |
+          source activate peft
+          make tests_core_multi_gpu
+          
+      - name: Generate Report
+        if: always()
+        run: |
+          pip install slack_sdk tabulate
+          python scripts/log_reports.py >> $GITHUB_STEP_SUMMARY

working/peft/.github/workflows/stale.yml

@@ -0,0 +1,27 @@
+name: Stale Bot
+
+on:
+  schedule:
+    - cron: "0 15 * * *"
+
+jobs:
+  close_stale_issues:
+    name: Close Stale Issues
+    if: github.repository == 'huggingface/peft'
+    runs-on: ubuntu-latest
+    env:
+      GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+    steps:
+    - uses: actions/checkout@v3
+
+    - name: Setup Python
+      uses: actions/setup-python@v4
+      with:
+        python-version: 3.8
+
+    - name: Install requirements
+      run: |
+        pip install PyGithub
+    - name: Close stale issues
+      run: |
+        python scripts/stale.py

working/peft/.github/workflows/test-docker-build.yml

@@ -0,0 +1,59 @@
+name: Test Docker images (on PR)
+
+on:
+  pull_request:
+    paths:
+      # Run only when DockerFile files are modified
+      - "docker/**"
+jobs:
+  get_changed_files:
+    name: "Build all modified docker images"
+    runs-on: ubuntu-latest
+    outputs:
+      matrix: ${{ steps.set-matrix.outputs.matrix }}
+    steps:
+      - name: Check out code
+        uses: actions/checkout@v3
+      - name: Get changed files
+        id: changed-files
+        uses: tj-actions/changed-files@1c8e6069583811afb28f97afeaf8e7da80c6be5c #v42
+        with:
+          files: docker/**
+          json: "true"
+      - name: Run step if only the files listed above change
+        if: steps.changed-files.outputs.any_changed == 'true'
+        id: set-matrix
+        env:
+          ALL_CHANGED_FILES: ${{ steps.changed-files.outputs.all_changed_files }}
+        run: |
+          echo "matrix=${{ steps.changed-files.outputs.all_changed_files}}" >> $GITHUB_OUTPUT
+  build_modified_files:
+    needs: get_changed_files
+    name: Build Docker images on modified files
+    runs-on: ubuntu-latest
+    if: ${{ needs.get_changed_files.outputs.matrix }} != ''
+    strategy:
+      fail-fast: false
+      matrix:
+        docker-file: ${{ fromJson(needs.get_changed_files.outputs.matrix) }}
+    steps:
+      - name: Cleanup disk
+        run: |
+          sudo ls -l /usr/local/lib/
+          sudo ls -l /usr/share/
+          sudo du -sh /usr/local/lib/
+          sudo du -sh /usr/share/
+          sudo rm -rf /usr/local/lib/android
+          sudo rm -rf /usr/share/dotnet
+          sudo du -sh /usr/local/lib/
+          sudo du -sh /usr/share/
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v1
+      - name: Check out code
+        uses: actions/checkout@v3
+      - name: Build Docker image
+        uses: docker/build-push-action@v4
+        with:
+          file: ${{ matrix.docker-file }}
+          context: .
+          push: False

working/peft/.github/workflows/tests-main.yml

@@ -0,0 +1,28 @@
+name: tests on transformers main
+
+on:
+  push:
+    branches: [main]
+    paths-ignore:
+        - 'docs/**'
+
+jobs:
+  tests:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v3
+      - name: Set up Python 3.11
+        uses: actions/setup-python@v4
+        with:
+          python-version: 3.11
+          cache: "pip"
+          cache-dependency-path: "setup.py"
+      - name: Install dependencies
+        run: |
+          python -m pip install --upgrade pip
+          # cpu version of pytorch
+          pip install -U git+https://github.com/huggingface/transformers.git
+          pip install -e .[test]
+      - name: Test with pytest
+        run: |
+          make test

working/peft/.github/workflows/tests.yml

@@ -0,0 +1,53 @@
+name: tests
+
+on:
+  push:
+    branches: [main]
+    paths-ignore:
+      - 'docs/**'
+  pull_request:
+    paths-ignore:
+      - 'docs/**'
+
+jobs:
+  check_code_quality:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v3
+      - name: Set up Python
+        uses: actions/setup-python@v4
+        with:
+          python-version: "3.8"
+          cache: "pip"
+          cache-dependency-path: "setup.py"
+      - name: Install dependencies
+        run: |
+          python -m pip install --upgrade pip
+          pip install .[dev]
+      - name: Check quality
+        run: |
+          make quality
+
+  tests:
+    needs: check_code_quality
+    strategy:
+      matrix:
+        python-version: ["3.8", "3.9", "3.10", "3.11"]
+        os: ["ubuntu-latest", "macos-12", "windows-latest"]
+    runs-on: ${{ matrix.os }}
+    steps:
+      - uses: actions/checkout@v3
+      - name: Set up Python ${{ matrix.python-version }}
+        uses: actions/setup-python@v4
+        with:
+          python-version: ${{ matrix.python-version }}
+          cache: "pip"
+          cache-dependency-path: "setup.py"
+      - name: Install dependencies
+        run: |
+          python -m pip install --upgrade pip
+          # cpu version of pytorch
+          pip install -e .[test]
+      - name: Test with pytest
+        run: |
+          make test

working/peft/.github/workflows/torch_compile_tests.yml

@@ -0,0 +1,42 @@
+name: torch compile tests
+
+on:
+  workflow_dispatch:
+    inputs:
+      branch:
+        description: 'Branch to test on'
+        required: true
+      pytorch_nightly:
+        description: 'Whether to use PyTorch nightly (true/false)'
+        required: false
+        default: false
+
+jobs:
+  run_tests_with_compile:
+    runs-on: ubuntu-latest
+    env:
+      PEFT_DEBUG_WITH_TORCH_COMPILE: 1
+    steps:
+      - uses: actions/checkout@v4
+        with:
+          ref: ${{ github.event.inputs.branch }}
+          repository: ${{ github.event.pull_request.head.repo.full_name }}
+      - name: Set up Python
+        uses: actions/setup-python@v4
+        with:
+          python-version: "3.10"
+          cache: "pip"
+          cache-dependency-path: "setup.py"
+      - name: Install dependencies
+        run: |
+          python -m pip install --upgrade pip
+          python -m pip install .[test]
+          python -m pip install bitsandbytes
+          if [ "${{ github.event.inputs.pytorch_nightly }}" = "true" ]; then
+            python -m pip install --upgrade --pre torch --index-url https://download.pytorch.org/whl/nightly/cpu
+          fi
+      - name: Test compile with pytest
+        run: |
+          echo "PEFT_DEBUG_WITH_TORCH_COMPILE=$PEFT_DEBUG_WITH_TORCH_COMPILE"
+          git status
+          make tests_torch_compile

working/peft/.github/workflows/upload_pr_documentation.yml

@@ -0,0 +1,16 @@
+name: Upload PR Documentation
+
+on:
+  workflow_run:
+    workflows: ["Build PR Documentation"]
+    types:
+      - completed
+
+jobs:
+  build:
+    uses: huggingface/doc-builder/.github/workflows/upload_pr_documentation.yml@main
+    with:
+      package_name: peft
+    secrets:
+      hf_token: ${{ secrets.HF_DOC_BUILD_PUSH }}
+      comment_bot_token: ${{ secrets.COMMENT_BOT_TOKEN }}

working/peft/.gitignore

@@ -0,0 +1,141 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+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/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# 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
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# VSCode
+.vscode
+
+# IntelliJ
+.idea
+
+# Mac .DS_Store
+.DS_Store
+
+# More test things
+wandb

working/peft/.pre-commit-config.yaml

@@ -0,0 +1,13 @@
+repos:
+  - repo: https://github.com/astral-sh/ruff-pre-commit
+    rev: v0.2.1
+    hooks:
+      - id: ruff
+        args:
+          - --fix
+      - id: ruff-format
+  - repo: https://github.com/pre-commit/pre-commit-hooks
+    rev: v4.5.0
+    hooks:
+      - id: check-merge-conflict
+      - id: check-yaml

working/peft/LICENSE

@@ -0,0 +1,201 @@
+                                 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
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright [yyyy] [name of copyright owner]
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file 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.

working/peft/Makefile

@@ -0,0 +1,61 @@
+.PHONY: quality style test docs
+
+check_dirs := src tests examples docs scripts docker
+
+# Check that source code meets quality standards
+
+# this target runs checks on all files
+quality:
+	ruff $(check_dirs)
+	ruff format --check $(check_dirs)
+	doc-builder style src/peft tests docs/source --max_len 119 --check_only
+
+# Format source code automatically and check is there are any problems left that need manual fixing
+style:
+	ruff $(check_dirs) --fix
+	ruff format $(check_dirs)
+	doc-builder style src/peft tests docs/source --max_len 119
+
+test:
+	python -m pytest -n 3 tests/ $(if $(IS_GITHUB_CI),--report-log "ci_tests.log",)
+
+tests_examples_multi_gpu:
+	python -m pytest -m multi_gpu_tests tests/test_gpu_examples.py $(if $(IS_GITHUB_CI),--report-log "multi_gpu_examples.log",)
+
+tests_examples_single_gpu:
+	python -m pytest -m single_gpu_tests tests/test_gpu_examples.py $(if $(IS_GITHUB_CI),--report-log "single_gpu_examples.log",)
+
+tests_core_multi_gpu:
+	python -m pytest -m multi_gpu_tests tests/test_common_gpu.py $(if $(IS_GITHUB_CI),--report-log "core_multi_gpu.log",)
+
+tests_core_single_gpu:
+	python -m pytest -m single_gpu_tests tests/test_common_gpu.py $(if $(IS_GITHUB_CI),--report-log "core_single_gpu.log",)
+
+tests_common_gpu:
+	python -m pytest tests/test_decoder_models.py $(if $(IS_GITHUB_CI),--report-log "common_decoder.log",)
+	python -m pytest tests/test_encoder_decoder_models.py $(if $(IS_GITHUB_CI),--report-log "common_encoder_decoder.log",)
+
+tests_examples_multi_gpu_bnb:
+	python -m pytest -m "multi_gpu_tests and bitsandbytes" tests/test_gpu_examples.py $(if $(IS_GITHUB_CI),--report-log "multi_gpu_examples.log",)
+
+tests_examples_single_gpu_bnb:
+	python -m pytest -m "single_gpu_tests and bitsandbytes" tests/test_gpu_examples.py $(if $(IS_GITHUB_CI),--report-log "single_gpu_examples.log",)
+
+tests_core_multi_gpu_bnb:
+	python -m pytest -m "multi_gpu_tests and bitsandbytes" tests/test_common_gpu.py $(if $(IS_GITHUB_CI),--report-log "core_multi_gpu.log",)
+
+tests_core_single_gpu_bnb:
+	python -m pytest -m "single_gpu_tests and bitsandbytes" tests/test_common_gpu.py $(if $(IS_GITHUB_CI),--report-log "core_single_gpu.log",)
+
+tests_gpu_bnb_regression:
+	python -m pytest tests/bnb/test_bnb_regression.py $(if $(IS_GITHUB_CI),--report-log "bnb_regression_gpu.log",)
+
+# For testing transformers tests for bnb runners
+transformers_tests:
+	RUN_SLOW=1 python -m pytest transformers-clone/tests/quantization/bnb $(if $(IS_GITHUB_CI),--report-log "transformers_tests.log",)
+
+tests_regression:
+	python -m pytest -s --regression tests/regression/ $(if $(IS_GITHUB_CI),--report-log "regression_tests.log",)
+
+tests_torch_compile:
+	python -m pytest tests/test_torch_compile.py $(if $(IS_GITHUB_CI),--report-log "compile_tests.log",)

working/peft/README.md

@@ -0,0 +1,158 @@
+<!---
+Copyright 2023 The HuggingFace Team. All rights reserved.
+
+Licensed under the Apache License, Version 2.0 (the "License");
+you may not use this file 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.
+-->
+
+<h1 align="center"> <p>🤗 PEFT</p></h1>
+<h3 align="center">
+    <p>State-of-the-art Parameter-Efficient Fine-Tuning (PEFT) methods</p>
+</h3>
+
+Fine-tuning large pretrained models is often prohibitively costly due to their scale. Parameter-Efficient Fine-Tuning (PEFT) methods enable efficient adaptation of large pretrained models to various downstream applications by only fine-tuning a small number of (extra) model parameters instead of all the model's parameters. This significantly decreases the computational and storage costs. Recent state-of-the-art PEFT techniques achieve performance comparable to fully fine-tuned models.
+
+PEFT is integrated with Transformers for easy model training and inference, Diffusers for conveniently managing different adapters, and Accelerate for distributed training and inference for really big models.
+
+> [!TIP]
+> Visit the [PEFT](https://huggingface.co/PEFT) organization to read about the PEFT methods implemented in the library and to see notebooks demonstrating how to apply these methods to a variety of downstream tasks. Click the "Watch repos" button on the organization page to be notified of newly implemented methods and notebooks!
+
+Check the PEFT Adapters API Reference section for a list of supported PEFT methods, and read the [Adapters](https://huggingface.co/docs/peft/en/conceptual_guides/adapter), [Soft prompts](https://huggingface.co/docs/peft/en/conceptual_guides/prompting), and [IA3](https://huggingface.co/docs/peft/en/conceptual_guides/ia3) conceptual guides to learn more about how these methods work.
+
+## Quickstart
+
+Install PEFT from pip:
+
+```bash
+pip install peft
+```
+
+Prepare a model for training with a PEFT method such as LoRA by wrapping the base model and PEFT configuration with `get_peft_model`. For the bigscience/mt0-large model, you're only training 0.19% of the parameters!
+
+```python
+from transformers import AutoModelForSeq2SeqLM
+from peft import get_peft_config, get_peft_model, LoraConfig, TaskType
+model_name_or_path = "bigscience/mt0-large"
+tokenizer_name_or_path = "bigscience/mt0-large"
+
+peft_config = LoraConfig(
+    task_type=TaskType.SEQ_2_SEQ_LM, inference_mode=False, r=8, lora_alpha=32, lora_dropout=0.1
+)
+
+model = AutoModelForSeq2SeqLM.from_pretrained(model_name_or_path)
+model = get_peft_model(model, peft_config)
+model.print_trainable_parameters()
+"trainable params: 2359296 || all params: 1231940608 || trainable%: 0.19151053100118282"
+```
+
+To load a PEFT model for inference:
+
+```py
+from peft import AutoPeftModelForCausalLM
+from transformers import AutoTokenizer
+import torch
+
+model = AutoPeftModelForCausalLM.from_pretrained("ybelkada/opt-350m-lora").to("cuda")
+tokenizer = AutoTokenizer.from_pretrained("facebook/opt-350m")
+
+model.eval()
+inputs = tokenizer("Preheat the oven to 350 degrees and place the cookie dough", return_tensors="pt")
+
+outputs = model.generate(input_ids=inputs["input_ids"].to("cuda"), max_new_tokens=50)
+print(tokenizer.batch_decode(outputs, skip_special_tokens=True)[0])
+
+"Preheat the oven to 350 degrees and place the cookie dough in the center of the oven. In a large bowl, combine the flour, baking powder, baking soda, salt, and cinnamon. In a separate bowl, combine the egg yolks, sugar, and vanilla."
+```
+
+## Why you should use PEFT
+
+There are many benefits of using PEFT but the main one is the huge savings in compute and storage, making PEFT applicable to many different use cases.
+
+### High performance on consumer hardware
+
+Consider the memory requirements for training the following models on the [ought/raft/twitter_complaints](https://huggingface.co/datasets/ought/raft/viewer/twitter_complaints) dataset with an A100 80GB GPU with more than 64GB of CPU RAM.
+
+|   Model         | Full Finetuning | PEFT-LoRA PyTorch  | PEFT-LoRA DeepSpeed with CPU Offloading |
+| --------- | ---- | ---- | ---- |
+| bigscience/T0_3B (3B params) | 47.14GB GPU / 2.96GB CPU  | 14.4GB GPU / 2.96GB CPU | 9.8GB GPU / 17.8GB CPU |
+| bigscience/mt0-xxl (12B params) | OOM GPU | 56GB GPU / 3GB CPU | 22GB GPU / 52GB CPU |
+| bigscience/bloomz-7b1 (7B params) | OOM GPU | 32GB GPU / 3.8GB CPU | 18.1GB GPU / 35GB CPU |
+
+With LoRA you can fully finetune a 12B parameter model that would've otherwise run out of memory on the 80GB GPU, and comfortably fit and train a 3B parameter model. When you look at the 3B parameter model's performance, it is comparable to a fully finetuned model at a fraction of the GPU memory.
+
+|   Submission Name        | Accuracy |
+| --------- | ---- |
+| Human baseline (crowdsourced) |	0.897 |
+| Flan-T5 | 0.892 |
+| lora-t0-3b | 0.863 |
+
+> [!TIP]
+> The bigscience/T0_3B model performance isn't optimized in the table above. You can squeeze even more performance out of it by playing around with the input instruction templates, LoRA hyperparameters, and other training related hyperparameters. The final checkpoint size of this model is just 19MB compared to 11GB of the full bigscience/T0_3B model. Learn more about the advantages of finetuning with PEFT in this [blog post](https://www.philschmid.de/fine-tune-flan-t5-peft).
+
+### Quantization
+
+Quantization is another method for reducing the memory requirements of a model by representing the data in a lower precision. It can be combined with PEFT methods to make it even easier to train and load LLMs for inference.
+
+* Learn how to finetune [meta-llama/Llama-2-7b-hf](https://huggingface.co/meta-llama/Llama-2-7b-hf) with QLoRA and the [TRL](https://huggingface.co/docs/trl/index) library on a 16GB GPU in the [Finetune LLMs on your own consumer hardware using tools from PyTorch and Hugging Face ecosystem](https://pytorch.org/blog/finetune-llms/) blog post.
+* Learn how to finetune a [openai/whisper-large-v2](https://huggingface.co/openai/whisper-large-v2) model for multilingual automatic speech recognition with LoRA and 8-bit quantization in this [notebook](https://colab.research.google.com/drive/1DOkD_5OUjFa0r5Ik3SgywJLJtEo2qLxO?usp=sharing) (see this [notebook](https://colab.research.google.com/drive/1vhF8yueFqha3Y3CpTHN6q9EVcII9EYzs?usp=sharing) instead for an example of streaming a dataset).
+
+### Save compute and storage
+
+PEFT can help you save storage by avoiding full finetuning of models on each of downstream task or dataset. In many cases, you're only finetuning a very small fraction of a model's parameters and each checkpoint is only a few MBs in size (instead of GBs). These smaller PEFT adapters demonstrate performance comparable to a fully finetuned model. If you have many datasets, you can save a lot of storage with a PEFT model and not have to worry about catastrophic forgetting or overfitting the backbone or base model.
+
+## PEFT integrations
+
+PEFT is widely supported across the Hugging Face ecosystem because of the massive efficiency it brings to training and inference.
+
+### Diffusers
+
+The iterative diffusion process consumes a lot of memory which can make it difficult to train. PEFT can help reduce the memory requirements and reduce the storage size of the final model checkpoint. For example, consider the memory required for training a Stable Diffusion model with LoRA on an A100 80GB GPU with more than 64GB of CPU RAM. The final model checkpoint size is only 8.8MB!
+
+|   Model         | Full Finetuning | PEFT-LoRA  | PEFT-LoRA with Gradient Checkpointing  |
+| --------- | ---- | ---- | ---- |
+| CompVis/stable-diffusion-v1-4 | 27.5GB GPU / 3.97GB CPU | 15.5GB GPU / 3.84GB CPU | 8.12GB GPU / 3.77GB CPU | 
+
+> [!TIP]
+> Take a look at the [examples/lora_dreambooth/train_dreambooth.py](examples/lora_dreambooth/train_dreambooth.py) training script to try training your own Stable Diffusion model with LoRA, and play around with the [smangrul/peft-lora-sd-dreambooth](https://huggingface.co/spaces/smangrul/peft-lora-sd-dreambooth) Space which is running on a T4 instance. Learn more about the PEFT integration in Diffusers in this [tutorial](https://huggingface.co/docs/peft/main/en/tutorial/peft_integrations#diffusers).
+
+### Accelerate
+
+[Accelerate](https://huggingface.co/docs/accelerate/index) is a library for distributed training and inference on various training setups and hardware (GPUs, TPUs, Apple Silicon, etc.). PEFT models work with Accelerate out of the box, making it really convenient to train really large models or use them for inference on consumer hardware with limited resources.
+
+### TRL
+
+PEFT can also be applied to training LLMs with RLHF components such as the ranker and policy. Get started by reading:
+
+* [Fine-tune a Mistral-7b model with Direct Preference Optimization](https://towardsdatascience.com/fine-tune-a-mistral-7b-model-with-direct-preference-optimization-708042745aac) with PEFT and the [TRL](https://huggingface.co/docs/trl/index) library to learn more about the Direct Preference Optimization (DPO) method and how to apply it to a LLM.
+* [Fine-tuning 20B LLMs with RLHF on a 24GB consumer GPU](https://huggingface.co/blog/trl-peft) with PEFT and the [TRL](https://huggingface.co/docs/trl/index) library, and then try out the [gpt2-sentiment_peft.ipynb](https://github.com/huggingface/trl/blob/main/examples/notebooks/gpt2-sentiment.ipynb) notebook to optimize GPT2 to generate positive movie reviews.
+* [StackLLaMA: A hands-on guide to train LLaMA with RLHF](https://huggingface.co/blog/stackllama) with PEFT, and then try out the [stack_llama/scripts](https://github.com/huggingface/trl/tree/main/examples/research_projects/stack_llama/scripts) for supervised finetuning, reward modeling, and RL finetuning.
+
+## Model support
+
+Use this [Space](https://stevhliu-peft-methods.hf.space) or check out the [docs](https://huggingface.co/docs/peft/main/en/index) to find which models officially support a PEFT method out of the box. Even if you don't see a model listed below, you can manually configure the model config to enable PEFT for a model. Read the [New transformers architecture](https://huggingface.co/docs/peft/main/en/developer_guides/custom_models#new-transformers-architectures) guide to learn how.
+
+## Contribute
+
+If you would like to contribute to PEFT, please check out our [contribution guide](https://huggingface.co/docs/peft/developer_guides/contributing).
+
+## Citing 🤗 PEFT
+
+To use 🤗 PEFT in your publication, please cite it by using the following BibTeX entry.
+
+```bibtex
+@Misc{peft,
+  title =        {PEFT: State-of-the-art Parameter-Efficient Fine-Tuning methods},
+  author =       {Sourab Mangrulkar and Sylvain Gugger and Lysandre Debut and Younes Belkada and Sayak Paul and Benjamin Bossan},
+  howpublished = {\url{https://github.com/huggingface/peft}},
+  year =         {2022}
+}
+```

working/peft/__init__.py

@@ -0,0 +1,98 @@
+# flake8: noqa
+# There's no way to ignore "F401 '...' imported but unused" warnings in this
+# module, but to preserve other warnings. So, don't check this module at all.
+
+# coding=utf-8
+# Copyright 2023-present the HuggingFace Inc. team.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file 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.
+
+__version__ = "0.11.2.dev0"
+
+from .auto import (
+    AutoPeftModel,
+    AutoPeftModelForCausalLM,
+    AutoPeftModelForSequenceClassification,
+    AutoPeftModelForSeq2SeqLM,
+    AutoPeftModelForTokenClassification,
+    AutoPeftModelForQuestionAnswering,
+    AutoPeftModelForFeatureExtraction,
+)
+from .mapping import (
+    MODEL_TYPE_TO_PEFT_MODEL_MAPPING,
+    PEFT_TYPE_TO_CONFIG_MAPPING,
+    get_peft_config,
+    get_peft_model,
+    inject_adapter_in_model,
+)
+from .mixed_model import PeftMixedModel
+from .peft_model import (
+    PeftModel,
+    PeftModelForCausalLM,
+    PeftModelForSeq2SeqLM,
+    PeftModelForSequenceClassification,
+    PeftModelForTokenClassification,
+    PeftModelForQuestionAnswering,
+    PeftModelForFeatureExtraction,
+    get_layer_status,
+    get_model_status,
+)
+from .tuners import (
+    AdaptionPromptConfig,
+    AdaptionPromptModel,
+    LoraConfig,
+    LoftQConfig,
+    LoraModel,
+    LoHaConfig,
+    LoHaModel,
+    LoKrConfig,
+    LoKrModel,
+    IA3Config,
+    IA3Model,
+    AdaLoraConfig,
+    AdaLoraModel,
+    BOFTConfig,
+    BOFTModel,
+    PrefixEncoder,
+    PrefixTuningConfig,
+    PromptEmbedding,
+    PromptEncoder,
+    PromptEncoderConfig,
+    PromptEncoderReparameterizationType,
+    PromptTuningConfig,
+    PromptTuningInit,
+    MultitaskPromptTuningConfig,
+    MultitaskPromptTuningInit,
+    OFTConfig,
+    OFTModel,
+    PolyConfig,
+    PolyModel,
+    LNTuningConfig,
+    LNTuningModel,
+    VeraConfig,
+    VeraModel,
+)
+from .utils import (
+    TRANSFORMERS_MODELS_TO_PREFIX_TUNING_POSTPROCESS_MAPPING,
+    PeftType,
+    TaskType,
+    bloom_model_postprocess_past_key_value,
+    get_peft_model_state_dict,
+    prepare_model_for_kbit_training,
+    replace_lora_weights_loftq,
+    set_peft_model_state_dict,
+    shift_tokens_right,
+    load_peft_weights,
+    cast_mixed_precision_params,
+)
+from .config import PeftConfig, PromptLearningConfig