From 28cbe2ce6df1dcabc6419287f4c70a828e78a10e Mon Sep 17 00:00:00 2001 From: Quarto GHA Workflow Runner Date: Wed, 25 Feb 2026 19:53:16 +0000 Subject: [PATCH] Built site for gh-pages --- .github/workflows/main.yml | 162 +- .nojekyll | 2 +- FAQS.html | 2 +- docs/amd_hpc.html | 2 +- docs/api/cli.args.html | 2 +- docs/api/cli.art.html | 2 +- docs/api/cli.checks.html | 2 +- docs/api/cli.cloud.base.html | 2 +- docs/api/cli.cloud.modal_.html | 2 +- docs/api/cli.config.html | 2 +- docs/api/cli.delinearize_llama4.html | 2 +- docs/api/cli.evaluate.html | 2 +- docs/api/cli.inference.html | 2 +- docs/api/cli.main.html | 2 +- docs/api/cli.merge_lora.html | 2 +- docs/api/cli.merge_sharded_fsdp_weights.html | 2 +- docs/api/cli.preprocess.html | 2 +- docs/api/cli.quantize.html | 2 +- docs/api/cli.train.html | 2 +- docs/api/cli.utils.args.html | 2 +- docs/api/cli.utils.fetch.html | 2 +- docs/api/cli.utils.html | 2 +- docs/api/cli.utils.load.html | 2 +- docs/api/cli.utils.sweeps.html | 2 +- docs/api/cli.utils.train.html | 2 +- docs/api/cli.vllm_serve.html | 2 +- docs/api/common.architectures.html | 2 +- docs/api/common.const.html | 2 +- docs/api/common.datasets.html | 2 +- docs/api/convert.html | 2 +- docs/api/core.builders.base.html | 2 +- docs/api/core.builders.causal.html | 2 +- docs/api/core.builders.rl.html | 2 +- docs/api/core.chat.format.chatml.html | 2 +- docs/api/core.chat.format.llama3x.html | 2 +- docs/api/core.chat.format.shared.html | 2 +- docs/api/core.chat.messages.html | 2 +- docs/api/core.datasets.chat.html | 2 +- ...core.datasets.transforms.chat_builder.html | 2 +- docs/api/core.trainers.base.html | 2 +- docs/api/core.trainers.dpo.trainer.html | 2 +- docs/api/core.trainers.grpo.sampler.html | 2 +- docs/api/core.trainers.grpo.trainer.html | 2 +- docs/api/core.trainers.mamba.html | 2 +- docs/api/core.trainers.mixins.optimizer.html | 2 +- ...core.trainers.mixins.rng_state_loader.html | 2 +- docs/api/core.trainers.mixins.scheduler.html | 2 +- docs/api/core.trainers.trl.html | 2 +- docs/api/core.trainers.utils.html | 2 +- docs/api/core.training_args.html | 2 +- docs/api/datasets.html | 2 +- docs/api/evaluate.html | 2 +- docs/api/index.html | 2 +- docs/api/integrations.base.html | 2 +- .../integrations.cut_cross_entropy.args.html | 2 +- docs/api/integrations.grokfast.optimizer.html | 2 +- docs/api/integrations.kd.trainer.html | 2 +- docs/api/integrations.liger.args.html | 2 +- docs/api/integrations.lm_eval.args.html | 2 +- docs/api/integrations.spectrum.args.html | 2 +- docs/api/kernels.geglu.html | 2 +- docs/api/kernels.lora.html | 2 +- docs/api/kernels.quantize.html | 2 +- docs/api/kernels.swiglu.html | 2 +- docs/api/kernels.utils.html | 2 +- docs/api/loaders.adapter.html | 2 +- docs/api/loaders.constants.html | 2 +- docs/api/loaders.model.html | 2 +- docs/api/loaders.patch_manager.html | 2 +- docs/api/loaders.processor.html | 2 +- docs/api/loaders.tokenizer.html | 2 +- docs/api/logging_config.html | 2 +- docs/api/models.mamba.modeling_mamba.html | 2 +- .../monkeypatch.btlm_attn_hijack_flash.html | 2 +- ...onkeypatch.data.batch_dataset_fetcher.html | 2 +- ...ch.gradient_checkpointing.offload_cpu.html | 2 +- ...h.gradient_checkpointing.offload_disk.html | 2 +- .../monkeypatch.llama_attn_hijack_flash.html | 2 +- ...onkeypatch.llama_attn_hijack_xformers.html | 2 +- docs/api/monkeypatch.llama_expand_mask.html | 2 +- .../monkeypatch.llama_patch_multipack.html | 2 +- docs/api/monkeypatch.lora_kernels.html | 2 +- ...monkeypatch.mistral_attn_hijack_flash.html | 2 +- docs/api/monkeypatch.mixtral.html | 2 +- docs/api/monkeypatch.multipack.html | 2 +- docs/api/monkeypatch.relora.html | 2 +- ...onkeypatch.stablelm_attn_hijack_flash.html | 2 +- docs/api/monkeypatch.trainer_fsdp_optim.html | 2 +- .../monkeypatch.transformers_fa_utils.html | 2 +- docs/api/monkeypatch.unsloth_.html | 2 +- docs/api/monkeypatch.utils.html | 2 +- docs/api/prompt_strategies.alpaca_chat.html | 2 +- .../prompt_strategies.alpaca_instruct.html | 2 +- .../prompt_strategies.alpaca_w_system.html | 2 +- docs/api/prompt_strategies.base.html | 2 +- ...rompt_strategies.bradley_terry.llama3.html | 2 +- docs/api/prompt_strategies.chat_template.html | 2 +- docs/api/prompt_strategies.completion.html | 2 +- .../prompt_strategies.dpo.chat_template.html | 2 +- docs/api/prompt_strategies.dpo.chatml.html | 2 +- docs/api/prompt_strategies.dpo.llama3.html | 2 +- .../prompt_strategies.dpo.passthrough.html | 2 +- .../prompt_strategies.dpo.user_defined.html | 2 +- docs/api/prompt_strategies.dpo.zephyr.html | 2 +- docs/api/prompt_strategies.input_output.html | 2 +- docs/api/prompt_strategies.kto.chatml.html | 2 +- docs/api/prompt_strategies.kto.llama3.html | 2 +- .../prompt_strategies.kto.user_defined.html | 2 +- docs/api/prompt_strategies.llama2_chat.html | 2 +- docs/api/prompt_strategies.messages.chat.html | 2 +- docs/api/prompt_strategies.metharme.html | 2 +- docs/api/prompt_strategies.orcamini.html | 2 +- .../prompt_strategies.orpo.chat_template.html | 2 +- docs/api/prompt_strategies.pygmalion.html | 2 +- ...prompt_strategies.stepwise_supervised.html | 2 +- docs/api/prompt_strategies.user_defined.html | 2 +- docs/api/prompt_tokenizers.html | 2 +- docs/api/train.html | 2 +- docs/api/utils.bench.html | 2 +- docs/api/utils.callbacks.comet_.html | 2 +- docs/api/utils.callbacks.lisa.html | 2 +- docs/api/utils.callbacks.mlflow_.html | 2 +- docs/api/utils.callbacks.perplexity.html | 2 +- docs/api/utils.callbacks.profiler.html | 2 +- docs/api/utils.callbacks.qat.html | 2 +- docs/api/utils.chat_templates.html | 2 +- docs/api/utils.collators.batching.html | 2 +- docs/api/utils.collators.core.html | 2 +- docs/api/utils.collators.mamba.html | 2 +- docs/api/utils.collators.mm_chat.html | 2 +- .../utils.ctx_managers.sequence_parallel.html | 2 +- docs/api/utils.data.sft.html | 2 +- docs/api/utils.data.streaming.html | 2 +- docs/api/utils.dict.html | 2 +- docs/api/utils.distributed.html | 2 +- docs/api/utils.freeze.html | 2 +- docs/api/utils.lora.html | 2 +- docs/api/utils.model_shard_quant.html | 2 +- docs/api/utils.optimizers.adopt.html | 2 +- docs/api/utils.quantization.html | 2 +- docs/api/utils.samplers.multipack.html | 2 +- docs/api/utils.schedulers.html | 2 +- docs/api/utils.schemas.config.html | 2 +- docs/api/utils.schemas.datasets.html | 2 +- docs/api/utils.schemas.enums.html | 2 +- docs/api/utils.schemas.integrations.html | 2 +- docs/api/utils.schemas.model.html | 2 +- docs/api/utils.schemas.multimodal.html | 2 +- docs/api/utils.schemas.peft.html | 2 +- docs/api/utils.schemas.training.html | 2 +- docs/api/utils.schemas.trl.html | 2 +- docs/api/utils.schemas.utils.html | 2 +- docs/api/utils.tokenization.html | 2 +- docs/api/utils.trainer.html | 2 +- docs/attention.html | 2 +- docs/batch_vs_grad.html | 2 +- docs/checkpoint_saving.html | 2 +- docs/cli.html | 2 +- docs/config-reference.html | 2 +- docs/custom_integrations.html | 2 +- docs/dataset-formats/conversation.html | 2 +- docs/dataset-formats/index.html | 2 +- docs/dataset-formats/inst_tune.html | 2 +- docs/dataset-formats/pretraining.html | 2 +- docs/dataset-formats/stepwise_supervised.html | 2 +- docs/dataset-formats/template_free.html | 2 +- docs/dataset-formats/tokenized.html | 2 +- docs/dataset_loading.html | 2 +- docs/dataset_preprocessing.html | 2 +- docs/debugging.html | 2 +- docs/docker.html | 2 +- docs/faq.html | 2 +- docs/fsdp_qlora.html | 2 +- docs/getting-started.html | 2 +- docs/gradient_checkpointing.html | 2 +- docs/inference.html | 2 +- docs/input_output.html | 2 +- docs/installation.html | 2 +- docs/lora_optims.html | 2 +- docs/lr_groups.html | 2 +- docs/mac.html | 2 +- docs/mixed_precision.html | 2 +- docs/models/LiquidAI.html | 2 +- docs/models/apertus.html | 2 +- docs/models/arcee.html | 2 +- docs/models/devstral.html | 2 +- docs/models/gemma3n.html | 2 +- docs/models/gpt-oss.html | 2 +- docs/models/granite4.html | 2 +- docs/models/hunyuan.html | 2 +- docs/models/index.html | 2 +- docs/models/internvl3_5.html | 2 +- docs/models/jamba.html | 2 +- docs/models/kimi-linear.html | 2 +- docs/models/llama-2.html | 2 +- docs/models/llama-4.html | 2 +- docs/models/magistral.html | 2 +- docs/models/magistral/think.html | 2 +- docs/models/magistral/vision.html | 2 +- docs/models/mimo.html | 2 +- docs/models/ministral.html | 2 +- docs/models/ministral3.html | 2 +- docs/models/ministral3/think.html | 2 +- docs/models/ministral3/vision.html | 2 +- docs/models/mistral-small.html | 2 +- docs/models/mistral.html | 2 +- docs/models/olmo3.html | 2 +- docs/models/orpheus.html | 2 +- docs/models/phi.html | 2 +- docs/models/plano.html | 2 +- docs/models/qwen3-next.html | 2 +- docs/models/qwen3.html | 2 +- docs/models/seed-oss.html | 2 +- docs/models/smolvlm2.html | 2 +- docs/models/trinity.html | 2 +- docs/models/voxtral.html | 2 +- docs/multi-gpu.html | 2 +- docs/multi-node.html | 2 +- docs/multimodal.html | 2 +- docs/multipack.html | 2 +- docs/nccl.html | 2 +- docs/nd_parallelism.html | 2 +- docs/optimizations.html | 2 +- docs/optimizers.html | 2 +- docs/qat.html | 2 +- docs/quantize.html | 2 +- docs/ray-integration.html | 2 +- docs/reward_modelling.html | 2 +- docs/rlhf.html | 2 +- docs/sequence_parallelism.html | 2 +- docs/streaming.html | 2 +- docs/telemetry.html | 2 +- docs/torchao.html | 2 +- docs/unsloth.html | 2 +- .../colab-axolotl-example.html | 2 +- index.html | 2 +- search.json | 9196 ++++++++--------- ...-35ef2ff98a2131eb4c49a687ae04ea22.min.css} | 4 +- sitemap.xml | 1774 ++-- src/axolotl/integrations/LICENSE.html | 2 +- .../cut_cross_entropy/ACKNOWLEDGEMENTS.html | 2 +- 241 files changed, 5874 insertions(+), 5736 deletions(-) rename site_libs/bootstrap/{bootstrap-08d9eb451d58809f35fda8b852d737d8.min.css => bootstrap-35ef2ff98a2131eb4c49a687ae04ea22.min.css} (85%) diff --git a/.github/workflows/main.yml b/.github/workflows/main.yml index b8ebe2aeb..aca9b1dd3 100644 --- a/.github/workflows/main.yml +++ b/.github/workflows/main.yml @@ -40,12 +40,12 @@ jobs: pytorch: 2.10.0 axolotl_extras: platforms: "linux/amd64,linux/arm64" - - cuda: 129 - cuda_version: 12.9.1 - python_version: "3.12" - pytorch: 2.9.1 - axolotl_extras: - platforms: "linux/amd64,linux/arm64" +# - cuda: 129 +# cuda_version: 12.9.1 +# python_version: "3.12" +# pytorch: 2.9.1 +# axolotl_extras: +# platforms: "linux/amd64,linux/arm64" - cuda: 130 cuda_version: 13.0.0 python_version: "3.11" @@ -98,6 +98,77 @@ jobs: ${{ (matrix.is_latest) && format('{0}-latest', steps.metadata.outputs.tags) || '' }} labels: ${{ steps.metadata.outputs.labels }} + build-axolotl-uv: + if: ${{ ! contains(github.event.commits[0].message, '[skip docker]') && github.repository_owner == 'axolotl-ai-cloud' }} + strategy: + fail-fast: false + matrix: + include: + - cuda: 128 + cuda_version: 12.8.1 + python_version: "3.11" + pytorch: 2.9.1 + axolotl_extras: + platforms: "linux/amd64,linux/arm64" + is_latest: true + - cuda: 128 + cuda_version: 12.8.1 + python_version: "3.12" + pytorch: 2.10.0 + axolotl_extras: + platforms: "linux/amd64,linux/arm64" + - cuda: 130 + cuda_version: 13.0.0 + python_version: "3.11" + pytorch: 2.9.1 + axolotl_extras: + platforms: "linux/amd64,linux/arm64" + - cuda: 130 + cuda_version: 13.0.0 + python_version: "3.12" + pytorch: 2.10.0 + axolotl_extras: + platforms: "linux/amd64,linux/arm64" + runs-on: axolotl-gpu-runner + steps: + - name: Checkout + uses: actions/checkout@v4 + - name: Docker metadata + id: metadata + uses: docker/metadata-action@v5 + with: + images: | + axolotlai/axolotl-uv + tags: | + type=ref,event=branch + type=pep440,pattern={{version}} + - name: Set up Docker Buildx + uses: docker/setup-buildx-action@v3 + - name: Login to Docker Hub + uses: docker/login-action@v3 + with: + username: ${{ secrets.DOCKERHUB_USERNAME }} + password: ${{ secrets.DOCKERHUB_TOKEN }} + # guidance for testing before pushing: https://docs.docker.com/build/ci/github-actions/test-before-push/ + - name: Build and export to Docker + uses: docker/build-push-action@v5 + with: + context: . + platforms: ${{ matrix.platforms }} + build-args: | + BASE_TAG=${{ github.ref_type == 'tag' && 'main' || github.ref_name }}-base-py${{ matrix.python_version }}-cu${{ matrix.cuda }}-${{ matrix.pytorch }} + CUDA=${{ matrix.cuda }} + PYTORCH_VERSION=${{ matrix.pytorch }} + AXOLOTL_ARGS=${{ matrix.axolotl_args }} + AXOLOTL_EXTRAS=${{ matrix.axolotl_extras}} + file: ./docker/Dockerfile-uv + push: ${{ github.event_name != 'pull_request' }} + tags: | + ${{ steps.metadata.outputs.tags }}-py${{ matrix.python_version }}-cu${{ matrix.cuda }}-${{ matrix.pytorch }}${{ matrix.axolotl_extras != '' && '-' || '' }}${{ matrix.axolotl_extras }} + ${{ steps.metadata.outputs.tags }}-py${{ matrix.python_version }}-cu${{ matrix.cuda }}-${{ matrix.pytorch }} + ${{ (matrix.is_latest) && format('{0}-latest', steps.metadata.outputs.tags) || '' }} + labels: ${{ steps.metadata.outputs.labels }} + build-axolotl-cloud: needs: build-axolotl if: ${{ ! contains(github.event.commits[0].message, '[skip docker]') && github.repository_owner == 'axolotl-ai-cloud' }} @@ -130,12 +201,12 @@ jobs: pytorch: 2.10.0 axolotl_extras: platforms: "linux/amd64,linux/arm64" - - cuda: 129 - cuda_version: 12.9.1 - python_version: "3.12" - pytorch: 2.9.1 - axolotl_extras: - platforms: "linux/amd64,linux/arm64" +# - cuda: 129 +# cuda_version: 12.9.1 +# python_version: "3.12" +# pytorch: 2.9.1 +# axolotl_extras: +# platforms: "linux/amd64,linux/arm64" - cuda: 130 cuda_version: 13.0.0 python_version: "3.11" @@ -183,6 +254,73 @@ jobs: ${{ (matrix.is_latest) && format('{0}-latest', steps.metadata.outputs.tags) || '' }} labels: ${{ steps.metadata.outputs.labels }} + build-axolotl-cloud-uv: + needs: build-axolotl-uv + if: ${{ ! contains(github.event.commits[0].message, '[skip docker]') && github.repository_owner == 'axolotl-ai-cloud' }} + # this job needs to be run on self-hosted GPU runners... + strategy: + matrix: + include: + - cuda: 128 + cuda_version: 12.8.1 + python_version: "3.11" + pytorch: 2.9.1 + axolotl_extras: + is_latest: true + platforms: "linux/amd64,linux/arm64" + - cuda: 128 + cuda_version: 12.8.1 + python_version: "3.12" + pytorch: 2.10.0 + axolotl_extras: + platforms: "linux/amd64,linux/arm64" + - cuda: 130 + cuda_version: 13.0.0 + python_version: "3.11" + pytorch: 2.9.1 + axolotl_extras: + platforms: "linux/amd64,linux/arm64" + - cuda: 130 + cuda_version: 13.0.0 + python_version: "3.12" + pytorch: 2.10.0 + axolotl_extras: + platforms: "linux/amd64,linux/arm64" + runs-on: axolotl-gpu-runner + steps: + - name: Checkout + uses: actions/checkout@v4 + - name: Docker metadata + id: metadata + uses: docker/metadata-action@v5 + with: + images: | + axolotlai/axolotl-cloud-uv + tags: | + type=ref,event=branch + type=pep440,pattern={{version}} + - name: Login to Docker Hub + uses: docker/login-action@v3 + with: + username: ${{ secrets.DOCKERHUB_USERNAME }} + password: ${{ secrets.DOCKERHUB_TOKEN }} + - name: Set up Docker Buildx + uses: docker/setup-buildx-action@v3 + - name: Build + uses: docker/build-push-action@v5 + with: + context: . + platforms: ${{ matrix.platforms }} + build-args: | + BASE_TAG=${{ github.ref_type == 'tag' && 'main' || github.ref_name }}-py${{ matrix.python_version }}-cu${{ matrix.cuda }}-${{ matrix.pytorch }}${{ matrix.axolotl_extras != '' && '-' || '' }}${{ matrix.axolotl_extras }} + CUDA=${{ matrix.cuda }} + file: ./docker/Dockerfile-cloud-uv + push: ${{ github.event_name != 'pull_request' }} + tags: | + ${{ steps.metadata.outputs.tags }}-py${{ matrix.python_version }}-cu${{ matrix.cuda }}-${{ matrix.pytorch }}${{ matrix.axolotl_extras != '' && '-' || '' }}${{ matrix.axolotl_extras }} + ${{ (matrix.is_latest) && format('{0}-latest', steps.metadata.outputs.tags) || '' }} + labels: ${{ steps.metadata.outputs.labels }} + build-axolotl-cloud-no-tmux: needs: build-axolotl if: ${{ ! contains(github.event.commits[0].message, '[skip docker]') && github.repository_owner == 'axolotl-ai-cloud' }} diff --git a/.nojekyll b/.nojekyll index 2aeeeeec3..54ec66444 100644 --- a/.nojekyll +++ b/.nojekyll @@ -1 +1 @@ -0c5f4db8 \ No newline at end of file +380117ae \ No newline at end of file diff --git a/FAQS.html b/FAQS.html index d1526daee..57bb17287 100644 --- a/FAQS.html +++ b/FAQS.html @@ -40,7 +40,7 @@ ul.task-list li input[type="checkbox"] { - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - +