wehub-resource-sync
78ec5d9290
ci-cd-base / build-base-uv (130, 13.0.0, , Dockerfile-uv-base, linux/amd64,linux/arm64, 3.12, 2.11.0, 9.0 10.0 10.3 12.0+PTX) (push) Waiting to run
ci-cd-base / build-base-uv (130, 13.0.0, , Dockerfile-uv-base, linux/amd64,linux/arm64, 3.12, 2.12.0, 9.0 10.0 10.3 12.0+PTX) (push) Waiting to run
ci-cd-base / build-base-uv (130, 13.0.0, , Dockerfile-uv-base, linux/amd64,linux/arm64, 3.12, 2.12.1, 9.0 10.0 10.3 12.0+PTX) (push) Waiting to run
ci-cd-base / build-base-uv (130, 13.0.0, , Dockerfile-uv-base, linux/amd64,linux/arm64, 3.12, 2.13.0, 9.0 10.0 10.3 12.0+PTX) (push) Waiting to run
ci-cd-base / build-base-uv (132, 13.2.1, , Dockerfile-uv-base, linux/amd64,linux/arm64, 3.12, 2.13.0, 9.0 10.0 10.3 12.0+PTX, https://download.pytorch.org/whl/cu132) (push) Waiting to run
docker-e2e-tests / gate-skip-e2e (push) Waiting to run
docker-e2e-tests / docker-e2e-tests-1st (<nil>, 130, 13.0.0, 1, 3.12, 2.12.1) (push) Blocked by required conditions
docker-e2e-tests / docker-e2e-tests (<nil>, 130, 13.0.0, 1, 3.12, 2.11.0) (push) Blocked by required conditions
docker-e2e-tests / docker-e2e-kernel-tests (<nil>, 130, 13.0.0, 1, 3.12, 2.11.0) (push) Blocked by required conditions
docker-e2e-tests / docker-e2e-kernel-tests (<nil>, 130, 13.0.0, 1, 3.12, 2.12.1) (push) Blocked by required conditions
docker-e2e-tests / docker-e2e-cleanup (<nil>, 130, 13.0.0, 1, 3.12, 2.12.1) (push) Blocked by required conditions
Publish Docs / build-deploy (push) Waiting to run
ci-cd / build-axolotl-uv (<nil>, 130, 13.0.0, linux/amd64,linux/arm64, 3.12, 2.11.0) (push) Waiting to run
ci-cd / build-axolotl-uv (<nil>, 130, 13.0.0, true, linux/amd64,linux/arm64, 3.12, 2.12.0) (push) Waiting to run
ci-cd / build-axolotl-cloud-uv (<nil>, 130, 13.0.0, linux/amd64,linux/arm64, 3.12, 2.11.0) (push) Blocked by required conditions
ci-cd / build-axolotl-cloud-uv (<nil>, 130, 13.0.0, true, linux/amd64,linux/arm64, 3.12, 2.12.0) (push) Blocked by required conditions
ci-cd / build-axolotl-cloud-no-tmux-uv (<nil>, 130, 13.0.0, linux/amd64,linux/arm64, 3.12, 2.11.0) (push) Blocked by required conditions
ci-cd / build-axolotl-cloud-no-tmux-uv (<nil>, 130, 13.0.0, true, linux/amd64,linux/arm64, 3.12, 2.12.0) (push) Blocked by required conditions
Tests / PyTest from Source Dist (3.12, 2.11.0) (push) Blocked by required conditions
Tests / PyTest from Source Dist (3.12, 2.12.1) (push) Blocked by required conditions
Tests / PyTest from Source Dist (3.12, 2.13.0) (push) Blocked by required conditions
Tests / pre-commit (push) Waiting to run
Tests / Prefetch S3 once to prime the CDN cache (push) Waiting to run
Tests / PyTest (3.12, 2.11.0) (push) Blocked by required conditions
Tests / PyTest (3.12, 2.12.1) (push) Blocked by required conditions
Tests / PyTest (3.12, 2.13.0) (push) Blocked by required conditions
570 lines
18 KiB
YAML
570 lines
18 KiB
YAML
project:
|
|
type: website
|
|
pre-render:
|
|
- docs/scripts/generate_config_docs.py
|
|
- docs/scripts/generate_examples_docs.py
|
|
|
|
quartodoc:
|
|
dir: docs/api
|
|
package: axolotl
|
|
title: API Reference
|
|
parser: google
|
|
|
|
sections:
|
|
- title: Core
|
|
desc: Core functionality for training
|
|
contents:
|
|
- train
|
|
- evaluate
|
|
- datasets
|
|
- convert
|
|
- prompt_tokenizers
|
|
- prompters
|
|
- processing_strategies
|
|
- logging_config
|
|
- core.builders.base
|
|
- core.builders.causal
|
|
- core.builders.rl
|
|
- core.training_args
|
|
- core.training_args_base
|
|
- core.chat.messages
|
|
- core.chat.format.chatml
|
|
- core.chat.format.llama3x
|
|
- core.chat.format.shared
|
|
- core.datasets.chat
|
|
- core.datasets.transforms.chat_builder
|
|
- title: CLI
|
|
desc: Command-line interface
|
|
contents:
|
|
- cli.main
|
|
- cli.train
|
|
- cli.evaluate
|
|
- cli.args
|
|
- cli.art
|
|
- cli.checks
|
|
- cli.config
|
|
- cli.delinearize_llama4
|
|
- cli.inference
|
|
- cli.merge_lora
|
|
- cli.merge_sharded_fsdp_weights
|
|
- cli.preprocess
|
|
- cli.quantize
|
|
- cli.vllm_serve
|
|
- cli.agent_docs
|
|
- cli.cloud
|
|
- cli.cloud.base
|
|
- cli.cloud.baseten
|
|
- cli.cloud.modal_
|
|
- cli.utils
|
|
- cli.utils.args
|
|
- cli.utils.diffusion
|
|
- cli.utils.fetch
|
|
- cli.utils.load
|
|
- cli.utils.lora_merge
|
|
- cli.utils.sweeps
|
|
- cli.utils.train
|
|
- title: Trainers
|
|
desc: Training implementations
|
|
contents:
|
|
- core.trainers.base
|
|
- core.trainers.constants
|
|
- core.trainers.trl
|
|
- core.trainers.mamba
|
|
- core.trainers.dpo.args
|
|
- core.trainers.dpo.trainer
|
|
- core.trainers.ebft
|
|
- core.trainers.ebft.args
|
|
- core.trainers.ebft.kernels
|
|
- core.trainers.ebft.rewards
|
|
- core.trainers.ebft.strided
|
|
- core.trainers.ebft.trainer
|
|
- core.trainers.grpo
|
|
- core.trainers.grpo.args
|
|
- core.trainers.grpo.trainer
|
|
- core.trainers.grpo.async_trainer
|
|
- core.trainers.grpo.fast_async_trainer
|
|
- core.trainers.grpo.replay_buffer
|
|
- core.trainers.grpo.sampler
|
|
- core.trainers.utils
|
|
- title: Model Loading
|
|
desc: Functionality for loading and patching models, tokenizers, etc.
|
|
contents:
|
|
- loaders.model
|
|
- loaders.tokenizer
|
|
- loaders.processor
|
|
- loaders.adapter
|
|
- loaders.patch_manager
|
|
- loaders.constants
|
|
- loaders.utils
|
|
- title: Mixins
|
|
desc: Mixin classes for augmenting trainers
|
|
contents:
|
|
- core.trainers.mixins.activation_checkpointing
|
|
- core.trainers.mixins.checkpoints
|
|
- core.trainers.mixins.distributed_parallel
|
|
- core.trainers.mixins.layer_offloading
|
|
- core.trainers.mixins.optimizer
|
|
- core.trainers.mixins.packing
|
|
- core.trainers.mixins.rng_state_loader
|
|
- core.trainers.mixins.scheduler
|
|
- title: Context Managers
|
|
desc: Context managers for altering trainer behaviors
|
|
contents:
|
|
- utils.ctx_managers.sequence_parallel
|
|
- title: Prompt Strategies
|
|
desc: Prompt formatting strategies
|
|
contents:
|
|
- prompt_strategies.base
|
|
- prompt_strategies.chat_template
|
|
- prompt_strategies.alpaca_chat
|
|
- prompt_strategies.alpaca_instruct
|
|
- prompt_strategies.alpaca_w_system
|
|
- prompt_strategies.user_defined
|
|
- prompt_strategies.llama2_chat
|
|
- prompt_strategies.completion
|
|
- prompt_strategies.context_qa
|
|
- prompt_strategies.creative_acr
|
|
- prompt_strategies.input_output
|
|
- prompt_strategies.pretrain
|
|
- prompt_strategies.stepwise_supervised
|
|
- prompt_strategies.metharme
|
|
- prompt_strategies.orcamini
|
|
- prompt_strategies.pygmalion
|
|
- prompt_strategies.messages.chat
|
|
- prompt_strategies.ebft.ebft_chat_multiturn
|
|
- prompt_strategies.ebft.ebft_opencode
|
|
- prompt_strategies.ebft.ebft_reasoning
|
|
- prompt_strategies.ebft.ebft_strided_chat
|
|
- prompt_strategies.ebft.ebft_strided_structured
|
|
- prompt_strategies.dpo.chat_template
|
|
- prompt_strategies.dpo.llama3
|
|
- prompt_strategies.dpo.chatml
|
|
- prompt_strategies.dpo.zephyr
|
|
- prompt_strategies.dpo.user_defined
|
|
- prompt_strategies.dpo.passthrough
|
|
- prompt_strategies.kto.llama3
|
|
- prompt_strategies.kto.chatml
|
|
- prompt_strategies.kto.user_defined
|
|
- prompt_strategies.orpo.chat_template
|
|
- prompt_strategies.bradley_terry.chat_template
|
|
- prompt_strategies.bradley_terry.llama3
|
|
- title: Kernels
|
|
desc: Low-level performance optimizations
|
|
contents:
|
|
- kernels.lora
|
|
- kernels.dora
|
|
- kernels.geglu
|
|
- kernels.swiglu
|
|
- kernels.quantize
|
|
- kernels.autotune_telemetry
|
|
- kernels.gemma4_fused_rope
|
|
- kernels.rms_norm_gated
|
|
- kernels.utils
|
|
- title: Monkey Patches
|
|
desc: Runtime patches for model optimizations
|
|
contents:
|
|
- monkeypatch.llama_attn_hijack_flash
|
|
- monkeypatch.llama_attn_hijack_xformers
|
|
- monkeypatch.mistral_attn_hijack_flash
|
|
- monkeypatch.multipack
|
|
- monkeypatch.relora
|
|
- monkeypatch.lora_kernels
|
|
- monkeypatch.utils
|
|
- monkeypatch.btlm_attn_hijack_flash
|
|
- monkeypatch.stablelm_attn_hijack_flash
|
|
- monkeypatch.transformers_fa_utils
|
|
- monkeypatch.data.batch_dataset_fetcher
|
|
- monkeypatch.mixtral
|
|
- monkeypatch.gradient_checkpointing.offload_cpu
|
|
- monkeypatch.gradient_checkpointing.offload_disk
|
|
- monkeypatch.deepspeed_utils
|
|
- monkeypatch.fsdp2_qlora
|
|
- monkeypatch.gemma4_hybrid_mask
|
|
- monkeypatch.gemma4_loss_kwargs
|
|
- monkeypatch.kernelize_fixes
|
|
- monkeypatch.moe_quant
|
|
- monkeypatch.scaled_softmax_attn
|
|
- monkeypatch.torchao_optim
|
|
- monkeypatch.trainer_accelerator_args
|
|
- monkeypatch.accelerate.fsdp2
|
|
- monkeypatch.accelerate.parallelism_config
|
|
- monkeypatch.attention.flash_attn_4
|
|
- monkeypatch.attention.flex_attn
|
|
- monkeypatch.attention.fp8_attn
|
|
- monkeypatch.attention.sage_attn
|
|
- monkeypatch.attention.xformers
|
|
- monkeypatch.loss.chunked
|
|
- monkeypatch.loss.eaft
|
|
- monkeypatch.models.apertus.activation
|
|
- monkeypatch.models.falcon_h1.modeling
|
|
- monkeypatch.models.gemma4_unified.fused_attn
|
|
- monkeypatch.models.granitemoehybrid.modeling
|
|
- monkeypatch.models.kimi_linear.patch_kimi_linear
|
|
- monkeypatch.models.llama4.modeling
|
|
- monkeypatch.models.mamba_utils
|
|
- monkeypatch.models.mistral3.mistral_common_tokenizer
|
|
- monkeypatch.models.nemotron_h.modeling
|
|
- monkeypatch.models.pixtral.modeling_flash_attention_utils
|
|
- monkeypatch.models.qwen3.fused_attn
|
|
- monkeypatch.models.qwen3_5.fused_attn
|
|
- monkeypatch.models.qwen3_5.modeling
|
|
- monkeypatch.models.qwen3_5_moe.fused_attn
|
|
- monkeypatch.models.qwen3_moe.fused_attn
|
|
- monkeypatch.models.qwen3_next.modeling
|
|
- monkeypatch.models.qwen3_vl.fused_attn
|
|
- monkeypatch.models.voxtral.modeling
|
|
- monkeypatch.peft.utils
|
|
- monkeypatch.ring_attn.adapters.batch
|
|
- monkeypatch.ring_attn.patch
|
|
- monkeypatch.tiled_mlp.base
|
|
- monkeypatch.tiled_mlp.patch
|
|
- monkeypatch.trainer.lr
|
|
- monkeypatch.trainer.trl
|
|
- monkeypatch.trainer.trl_vllm
|
|
- monkeypatch.trainer.utils
|
|
- monkeypatch.transformers.trainer_loss_calc
|
|
- monkeypatch.xformers_
|
|
- title: Utils
|
|
desc: Utility functions
|
|
contents:
|
|
- utils.tokenization
|
|
- utils.chat_templates
|
|
- utils.chat_templates.base
|
|
- utils.lora
|
|
- utils.model_shard_quant
|
|
- utils.bench
|
|
- utils.comet_
|
|
- utils.config
|
|
- utils.cuda13
|
|
- utils.datasets
|
|
- utils.environment
|
|
- utils.fp32_norms
|
|
- utils.freeze
|
|
- utils.import_helper
|
|
- utils.logging
|
|
- utils.mlflow_
|
|
- utils.tee
|
|
- utils.trackio_
|
|
- utils.train
|
|
- utils.trainer
|
|
- utils.wandb_
|
|
- utils.weight_serde
|
|
- utils.schedulers
|
|
- utils.distributed
|
|
- utils.dict
|
|
- utils.generation.sft
|
|
- utils.mistral.mistral3_processor
|
|
- utils.mistral.mistral_tokenizer
|
|
- utils.optimizers.adopt
|
|
- utils.optimizers.qgalore
|
|
- utils.data.streaming
|
|
- utils.data.sft
|
|
- utils.data.rl
|
|
- utils.data.lock
|
|
- utils.data.utils
|
|
- utils.data.wrappers
|
|
- utils.quantization
|
|
- title: Schemas
|
|
desc: Pydantic data models for Axolotl config
|
|
contents:
|
|
- utils.schemas.config
|
|
- utils.schemas.model
|
|
- utils.schemas.training
|
|
- utils.schemas.datasets
|
|
- utils.schemas.peft
|
|
- utils.schemas.trl
|
|
- utils.schemas.multimodal
|
|
- utils.schemas.integrations
|
|
- utils.schemas.deprecated
|
|
- utils.schemas.dynamic_checkpoint
|
|
- utils.schemas.fsdp
|
|
- utils.schemas.quantization
|
|
- utils.schemas.validation
|
|
- utils.schemas.vllm
|
|
- utils.schemas.enums
|
|
- utils.schemas.utils
|
|
- title: Integrations
|
|
desc: Third-party integrations and extensions
|
|
contents:
|
|
- integrations.base
|
|
- integrations.config
|
|
- integrations.cut_cross_entropy
|
|
- integrations.cut_cross_entropy.args
|
|
- integrations.densemixer.args
|
|
- integrations.densemixer.plugin
|
|
- integrations.diffusion.args
|
|
- integrations.diffusion.callbacks
|
|
- integrations.diffusion.generation
|
|
- integrations.diffusion.plugin
|
|
- integrations.diffusion.trainer
|
|
- integrations.diffusion.utils
|
|
- integrations.expert_parallel.args
|
|
- integrations.expert_parallel.buffer
|
|
- integrations.expert_parallel.experts_fn
|
|
- integrations.expert_parallel.plugin
|
|
- integrations.expert_parallel.shard
|
|
- integrations.grokfast.args
|
|
- integrations.grokfast.optimizer
|
|
- integrations.hatchery.args
|
|
- integrations.hatchery.data
|
|
- integrations.hatchery.plugin
|
|
- integrations.hatchery.rewards.math_reward
|
|
- integrations.hatchery.rl_trainer
|
|
- integrations.hatchery.trainer
|
|
- integrations.kd
|
|
- integrations.kd.args
|
|
- integrations.kd.callbacks
|
|
- integrations.kd.chat_template
|
|
- integrations.kd.collator
|
|
- integrations.kd.collator_online_teacher
|
|
- integrations.kd.kernels.liger
|
|
- integrations.kd.topk_logprob.forward_kl
|
|
- integrations.kd.trainer
|
|
- integrations.kd.utils
|
|
- integrations.kernels.args
|
|
- integrations.kernels.autotune_callback
|
|
- integrations.kernels.autotune_collector
|
|
- integrations.kernels.constants
|
|
- integrations.kernels.plugin
|
|
- integrations.liger.args
|
|
- integrations.liger.plugin
|
|
- integrations.liger.utils
|
|
- integrations.liger.models.base
|
|
- integrations.liger.models.deepseekv2
|
|
- integrations.liger.models.jamba
|
|
- integrations.liger.models.qwen3_5
|
|
- integrations.liger.models.qwen3_5_moe
|
|
- integrations.llm_compressor.args
|
|
- integrations.llm_compressor.plugin
|
|
- integrations.llm_compressor.utils
|
|
- integrations.lm_eval.args
|
|
- integrations.lm_eval.cli
|
|
- integrations.mora.args
|
|
- integrations.mora.plugin
|
|
- integrations.nemo_gym.args
|
|
- integrations.nemo_gym.data_producer
|
|
- integrations.nemo_gym.dataset
|
|
- integrations.nemo_gym.multi_turn
|
|
- integrations.nemo_gym.plugin
|
|
- integrations.nemo_gym.rewards
|
|
- integrations.nemo_gym.server
|
|
- integrations.spectrum
|
|
- integrations.spectrum.args
|
|
- integrations.swanlab.args
|
|
- integrations.swanlab.callbacks
|
|
- integrations.swanlab.completion_logger
|
|
- integrations.swanlab.plugins
|
|
- title: Common
|
|
desc: Common utilities and shared functionality
|
|
contents:
|
|
- common.architectures
|
|
- common.const
|
|
- common.datasets
|
|
- title: Models
|
|
desc: Custom model implementations
|
|
contents:
|
|
- models.mamba.configuration_mamba
|
|
- models.mamba.modeling_mamba
|
|
- title: Data Processing
|
|
desc: Data processing utilities
|
|
contents:
|
|
- utils.collators.core
|
|
- utils.collators.batching
|
|
- utils.collators.dpo
|
|
- utils.collators.mamba
|
|
- utils.collators.mm_chat
|
|
- utils.samplers.multipack
|
|
- utils.samplers.utils
|
|
- title: Callbacks
|
|
desc: Training callbacks
|
|
contents:
|
|
- utils.callbacks
|
|
- utils.callbacks.perplexity
|
|
- utils.callbacks.profiler
|
|
- utils.callbacks.lisa
|
|
- utils.callbacks.mlflow_
|
|
- utils.callbacks.comet_
|
|
- utils.callbacks.qat
|
|
- utils.callbacks.dynamic_checkpoint
|
|
- utils.callbacks.generation
|
|
- utils.callbacks.models
|
|
- utils.callbacks.opentelemetry
|
|
- utils.callbacks.swanlab
|
|
- utils.callbacks.tokens_per_second
|
|
- utils.callbacks.trackio_
|
|
- title: Scripts
|
|
desc: Standalone helper scripts
|
|
contents:
|
|
- scripts.process_cleanup
|
|
- scripts.vllm_serve_lora
|
|
- scripts.vllm_worker_ext
|
|
- title: Telemetry
|
|
desc: Usage telemetry
|
|
contents:
|
|
- telemetry.callbacks
|
|
- telemetry.errors
|
|
- telemetry.manager
|
|
- telemetry.runtime_metrics
|
|
website:
|
|
title: "Axolotl"
|
|
description: "We make fine-tuning accessible, scalable, and fun"
|
|
favicon: favicon.jpg
|
|
|
|
google-analytics: "G-9KYCVJBNMQ"
|
|
|
|
navbar:
|
|
logo: image/axolotl_logo_digital_white.svg
|
|
title: false
|
|
background: dark
|
|
pinned: false
|
|
collapse: false
|
|
tools:
|
|
- icon: twitter
|
|
href: https://twitter.com/axolotl_ai
|
|
- icon: github
|
|
href: https://github.com/axolotl-ai-cloud/axolotl/
|
|
- icon: discord
|
|
href: https://discord.gg/7m9sfhzaf3
|
|
|
|
sidebar:
|
|
pinned: true
|
|
collapse-level: 2
|
|
style: docked
|
|
contents:
|
|
- text: Home
|
|
href: index.qmd
|
|
|
|
- section: "Getting Started"
|
|
contents:
|
|
- docs/getting-started.qmd
|
|
- docs/choosing_method.qmd
|
|
- docs/installation.qmd
|
|
- docs/inference.qmd
|
|
- docs/support-matrix.qmd
|
|
- section: "Model Guides"
|
|
contents:
|
|
- docs/models/kimi-linear.qmd
|
|
- docs/models/plano.qmd
|
|
- docs/models/mimo.qmd
|
|
- docs/models/internvl3_5.qmd
|
|
- docs/models/olmo3.qmd
|
|
- docs/models/trinity.qmd
|
|
- docs/models/arcee.qmd
|
|
- section: "Ministral3"
|
|
contents:
|
|
- docs/models/ministral3.qmd
|
|
- docs/models/ministral3/think.qmd
|
|
- docs/models/ministral3/vision.qmd
|
|
- section: "Magistral"
|
|
contents:
|
|
- docs/models/magistral.qmd
|
|
- docs/models/magistral/think.qmd
|
|
- docs/models/magistral/vision.qmd
|
|
- docs/models/ministral.qmd
|
|
- docs/models/mistral-small.qmd
|
|
- docs/models/voxtral.qmd
|
|
- docs/models/devstral.qmd
|
|
- docs/models/mistral.qmd
|
|
- docs/models/llama-4.qmd
|
|
- docs/models/llama-2.qmd
|
|
- docs/models/qwen3-next.qmd
|
|
- docs/models/qwen3.qmd
|
|
- docs/models/gemma3n.qmd
|
|
- docs/models/apertus.qmd
|
|
- docs/models/gpt-oss.qmd
|
|
- docs/models/seed-oss.qmd
|
|
- docs/models/phi.qmd
|
|
- docs/models/smolvlm2.qmd
|
|
- docs/models/granite4.qmd
|
|
- docs/models/LiquidAI.qmd
|
|
- docs/models/hunyuan.qmd
|
|
- docs/models/jamba.qmd
|
|
- docs/models/orpheus.qmd
|
|
|
|
- docs/cli.qmd
|
|
- docs/telemetry.qmd
|
|
- docs/config-reference.qmd
|
|
- text: "API Reference"
|
|
href: docs/api
|
|
|
|
- section: "Dataset Formats"
|
|
contents: docs/dataset-formats/*
|
|
|
|
- section: "Deployments"
|
|
contents:
|
|
- docs/docker.qmd
|
|
- docs/multi-gpu.qmd
|
|
- docs/multi-node.qmd
|
|
- docs/ray-integration.qmd
|
|
- docs/amd_hpc.qmd
|
|
- docs/mac.qmd
|
|
|
|
- section: "How To Guides"
|
|
contents:
|
|
- docs/multimodal.qmd
|
|
- docs/rlhf.qmd
|
|
- docs/grpo.qmd
|
|
- docs/ebft.qmd
|
|
- docs/vllm_serving.qmd
|
|
- docs/reward_modelling.qmd
|
|
- docs/lr_groups.qmd
|
|
- docs/lora.qmd
|
|
- docs/lora_optims.qmd
|
|
- docs/dataset_loading.qmd
|
|
- docs/qat.qmd
|
|
- docs/quantize.qmd
|
|
- docs/1_58bit_finetuning.qmd
|
|
- docs/optimizations.qmd
|
|
|
|
- section: "Core Concepts"
|
|
contents:
|
|
- docs/batch_vs_grad.qmd
|
|
- docs/dataset_preprocessing.qmd
|
|
- docs/streaming.qmd
|
|
- docs/multipack.qmd
|
|
- docs/mixed_precision.qmd
|
|
- docs/optimizers.qmd
|
|
- docs/attention.qmd
|
|
|
|
- section: "Advanced Features"
|
|
contents:
|
|
- docs/fsdp_qlora.qmd
|
|
- docs/torchao.qmd
|
|
- docs/custom_integrations.qmd
|
|
- docs/sequence_parallelism.qmd
|
|
- docs/gradient_checkpointing.qmd
|
|
- docs/nd_parallelism.qmd
|
|
- docs/expert_quantization.qmd
|
|
|
|
- section: "Troubleshooting"
|
|
contents:
|
|
- docs/faq.qmd
|
|
- docs/training_stability.qmd
|
|
- docs/debugging.qmd
|
|
- docs/nccl.qmd
|
|
|
|
format:
|
|
html:
|
|
theme: darkly
|
|
css: styles.css
|
|
toc: true
|
|
# Enable better handling of line breaks in markdown
|
|
preserve-tabs: true
|
|
html-math-method: mathjax
|
|
# Improved markdown processing options
|
|
md-extensions:
|
|
- markdown_it
|
|
- def_list
|
|
- attr_list
|
|
- fenced_divs
|
|
- tables
|
|
- html_admonition
|
|
- lineblocks
|
|
- fancy_lists
|
|
# Control whitespace handling
|
|
whitespace: preserve
|
|
# Process newlines in paragraphs
|
|
wrap: preserve
|
|
# Better line break handling
|
|
preserve-linebreaks: true
|