diff --git a/.nojekyll b/.nojekyll index ea031f54e..f4b6a59e4 100644 --- a/.nojekyll +++ b/.nojekyll @@ -1 +1 @@ -eff8f3d0 \ No newline at end of file +f4b50a99 \ No newline at end of file diff --git a/FAQS.html b/FAQS.html index afa327b1a..eadebd0da 100644 --- a/FAQS.html +++ b/FAQS.html @@ -2,7 +2,7 @@ - + @@ -36,7 +36,7 @@ ul.task-list li input[type="checkbox"] { - + diff --git a/docs/amd_hpc.html b/docs/amd_hpc.html index 9d2c390b4..df612eaea 100644 --- a/docs/amd_hpc.html +++ b/docs/amd_hpc.html @@ -2,7 +2,7 @@ - + @@ -72,7 +72,7 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin - + diff --git a/docs/api/cli.args.html b/docs/api/cli.args.html index 2a0a956a3..85ce9ff80 100644 --- a/docs/api/cli.args.html +++ b/docs/api/cli.args.html @@ -2,7 +2,7 @@ - + @@ -71,7 +71,7 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin - + diff --git a/docs/api/cli.art.html b/docs/api/cli.art.html index 37b0962bd..60e380a42 100644 --- a/docs/api/cli.art.html +++ b/docs/api/cli.art.html @@ -2,7 +2,7 @@ - + @@ -71,7 +71,7 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin - + diff --git a/docs/api/cli.checks.html b/docs/api/cli.checks.html index c262d56f7..e8dd0bd08 100644 --- a/docs/api/cli.checks.html +++ b/docs/api/cli.checks.html @@ -2,7 +2,7 @@ - + @@ -71,7 +71,7 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin - + diff --git a/docs/api/cli.cloud.base.html b/docs/api/cli.cloud.base.html index 23fd2efa0..df96d8e82 100644 --- a/docs/api/cli.cloud.base.html +++ b/docs/api/cli.cloud.base.html @@ -2,7 +2,7 @@ - + @@ -71,7 +71,7 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin - + diff --git a/docs/api/cli.cloud.modal_.html b/docs/api/cli.cloud.modal_.html index 4582693fd..c4aff2958 100644 --- a/docs/api/cli.cloud.modal_.html +++ b/docs/api/cli.cloud.modal_.html @@ -2,7 +2,7 @@ - + @@ -71,7 +71,7 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin - + diff --git a/docs/api/cli.config.html b/docs/api/cli.config.html index 80b487111..96901a31c 100644 --- a/docs/api/cli.config.html +++ b/docs/api/cli.config.html @@ -2,7 +2,7 @@ - + @@ -71,7 +71,7 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin - + diff --git a/docs/api/cli.delinearize_llama4.html b/docs/api/cli.delinearize_llama4.html index a93eb6756..60431cd93 100644 --- a/docs/api/cli.delinearize_llama4.html +++ b/docs/api/cli.delinearize_llama4.html @@ -2,7 +2,7 @@ - + @@ -71,7 +71,7 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin - + diff --git a/docs/api/cli.evaluate.html b/docs/api/cli.evaluate.html index b531528eb..9cc7b8cad 100644 --- a/docs/api/cli.evaluate.html +++ b/docs/api/cli.evaluate.html @@ -2,7 +2,7 @@ - + @@ -71,7 +71,7 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin - + diff --git a/docs/api/cli.inference.html b/docs/api/cli.inference.html index 18b4eca7e..e2aa14c75 100644 --- a/docs/api/cli.inference.html +++ b/docs/api/cli.inference.html @@ -2,7 +2,7 @@ - + @@ -71,7 +71,7 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin - + diff --git a/docs/api/cli.main.html b/docs/api/cli.main.html index 859d97691..79fa3dacb 100644 --- a/docs/api/cli.main.html +++ b/docs/api/cli.main.html @@ -2,7 +2,7 @@ - + @@ -71,7 +71,7 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin - + diff --git a/docs/api/cli.merge_lora.html b/docs/api/cli.merge_lora.html index 74863b4f9..b095dbd5d 100644 --- a/docs/api/cli.merge_lora.html +++ b/docs/api/cli.merge_lora.html @@ -2,7 +2,7 @@ - + @@ -71,7 +71,7 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin - + diff --git a/docs/api/cli.merge_sharded_fsdp_weights.html b/docs/api/cli.merge_sharded_fsdp_weights.html index fa44c472e..aaa294d4e 100644 --- a/docs/api/cli.merge_sharded_fsdp_weights.html +++ b/docs/api/cli.merge_sharded_fsdp_weights.html @@ -2,7 +2,7 @@ - + @@ -71,7 +71,7 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin - + diff --git a/docs/api/cli.preprocess.html b/docs/api/cli.preprocess.html index d7f6f51c8..c6afd588d 100644 --- a/docs/api/cli.preprocess.html +++ b/docs/api/cli.preprocess.html @@ -2,7 +2,7 @@ - + @@ -71,7 +71,7 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin - + diff --git a/docs/api/cli.quantize.html b/docs/api/cli.quantize.html index dd0af0de4..e44e66258 100644 --- a/docs/api/cli.quantize.html +++ b/docs/api/cli.quantize.html @@ -2,7 +2,7 @@ - + @@ -71,7 +71,7 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin - + diff --git a/docs/api/cli.train.html b/docs/api/cli.train.html index 28c4de9fe..23a2d5646 100644 --- a/docs/api/cli.train.html +++ b/docs/api/cli.train.html @@ -2,7 +2,7 @@ - + @@ -71,7 +71,7 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin - + diff --git a/docs/api/cli.utils.args.html b/docs/api/cli.utils.args.html index ef03e0738..6dacc0469 100644 --- a/docs/api/cli.utils.args.html +++ b/docs/api/cli.utils.args.html @@ -2,7 +2,7 @@ - + @@ -71,7 +71,7 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin - + diff --git a/docs/api/cli.utils.fetch.html b/docs/api/cli.utils.fetch.html index ee164fae6..92a7fe0a2 100644 --- a/docs/api/cli.utils.fetch.html +++ b/docs/api/cli.utils.fetch.html @@ -2,7 +2,7 @@ - + @@ -71,7 +71,7 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin - + diff --git a/docs/api/cli.utils.html b/docs/api/cli.utils.html index 132a72204..0b902e7b5 100644 --- a/docs/api/cli.utils.html +++ b/docs/api/cli.utils.html @@ -2,7 +2,7 @@ - + @@ -36,7 +36,7 @@ ul.task-list li input[type="checkbox"] { - + diff --git a/docs/api/cli.utils.load.html b/docs/api/cli.utils.load.html index f819a69ea..16253771b 100644 --- a/docs/api/cli.utils.load.html +++ b/docs/api/cli.utils.load.html @@ -2,7 +2,7 @@ - + @@ -71,7 +71,7 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin - + diff --git a/docs/api/cli.utils.sweeps.html b/docs/api/cli.utils.sweeps.html index cfe7bad8e..4812dc146 100644 --- a/docs/api/cli.utils.sweeps.html +++ b/docs/api/cli.utils.sweeps.html @@ -2,7 +2,7 @@ - + @@ -71,7 +71,7 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin - + diff --git a/docs/api/cli.utils.train.html b/docs/api/cli.utils.train.html index 398798b24..2c418a27d 100644 --- a/docs/api/cli.utils.train.html +++ b/docs/api/cli.utils.train.html @@ -2,7 +2,7 @@ - + @@ -71,7 +71,7 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin - + diff --git a/docs/api/cli.vllm_serve.html b/docs/api/cli.vllm_serve.html index d6f5231cf..e8f423f5e 100644 --- a/docs/api/cli.vllm_serve.html +++ b/docs/api/cli.vllm_serve.html @@ -2,7 +2,7 @@ - + @@ -71,7 +71,7 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin - + diff --git a/docs/api/common.architectures.html b/docs/api/common.architectures.html index bf6048a74..5f9e8c9ff 100644 --- a/docs/api/common.architectures.html +++ b/docs/api/common.architectures.html @@ -2,7 +2,7 @@ - + @@ -36,7 +36,7 @@ ul.task-list li input[type="checkbox"] { - + diff --git a/docs/api/common.const.html b/docs/api/common.const.html index 7c45a5264..48cabd8f0 100644 --- a/docs/api/common.const.html +++ b/docs/api/common.const.html @@ -2,7 +2,7 @@ - + @@ -36,7 +36,7 @@ ul.task-list li input[type="checkbox"] { - + diff --git a/docs/api/common.datasets.html b/docs/api/common.datasets.html index 52a048470..8a0c98b53 100644 --- a/docs/api/common.datasets.html +++ b/docs/api/common.datasets.html @@ -2,7 +2,7 @@ - + @@ -71,7 +71,7 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin - + diff --git a/docs/api/convert.html b/docs/api/convert.html index 4104ac59b..982be884b 100644 --- a/docs/api/convert.html +++ b/docs/api/convert.html @@ -2,7 +2,7 @@ - + @@ -71,7 +71,7 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin - + diff --git a/docs/api/core.builders.base.html b/docs/api/core.builders.base.html index 829ef9cc7..95e629f3f 100644 --- a/docs/api/core.builders.base.html +++ b/docs/api/core.builders.base.html @@ -2,7 +2,7 @@ - + @@ -71,7 +71,7 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin - + diff --git a/docs/api/core.builders.causal.html b/docs/api/core.builders.causal.html index 290f75837..6ada4c76b 100644 --- a/docs/api/core.builders.causal.html +++ b/docs/api/core.builders.causal.html @@ -2,7 +2,7 @@ - + @@ -71,7 +71,7 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin - + diff --git a/docs/api/core.builders.rl.html b/docs/api/core.builders.rl.html index c90e97c5b..77ea38b9a 100644 --- a/docs/api/core.builders.rl.html +++ b/docs/api/core.builders.rl.html @@ -2,7 +2,7 @@ - + @@ -71,7 +71,7 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin - + diff --git a/docs/api/core.chat.format.chatml.html b/docs/api/core.chat.format.chatml.html index cc6ef93d6..6f9c17890 100644 --- a/docs/api/core.chat.format.chatml.html +++ b/docs/api/core.chat.format.chatml.html @@ -2,7 +2,7 @@ - + @@ -36,7 +36,7 @@ ul.task-list li input[type="checkbox"] { - + diff --git a/docs/api/core.chat.format.llama3x.html b/docs/api/core.chat.format.llama3x.html index 240b0edc6..3f68898fb 100644 --- a/docs/api/core.chat.format.llama3x.html +++ b/docs/api/core.chat.format.llama3x.html @@ -2,7 +2,7 @@ - + @@ -36,7 +36,7 @@ ul.task-list li input[type="checkbox"] { - + diff --git a/docs/api/core.chat.format.shared.html b/docs/api/core.chat.format.shared.html index 0e2735b67..322d5fec6 100644 --- a/docs/api/core.chat.format.shared.html +++ b/docs/api/core.chat.format.shared.html @@ -2,7 +2,7 @@ - + @@ -36,7 +36,7 @@ ul.task-list li input[type="checkbox"] { - + diff --git a/docs/api/core.chat.messages.html b/docs/api/core.chat.messages.html index 5ff2f0d05..b7a0c7d49 100644 --- a/docs/api/core.chat.messages.html +++ b/docs/api/core.chat.messages.html @@ -2,7 +2,7 @@ - + @@ -71,7 +71,7 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin - + diff --git a/docs/api/core.datasets.chat.html b/docs/api/core.datasets.chat.html index 8675e7246..f75c1979b 100644 --- a/docs/api/core.datasets.chat.html +++ b/docs/api/core.datasets.chat.html @@ -2,7 +2,7 @@ - + @@ -71,7 +71,7 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin - + diff --git a/docs/api/core.datasets.transforms.chat_builder.html b/docs/api/core.datasets.transforms.chat_builder.html index 185b14db8..2f5053718 100644 --- a/docs/api/core.datasets.transforms.chat_builder.html +++ b/docs/api/core.datasets.transforms.chat_builder.html @@ -2,7 +2,7 @@ - + @@ -71,7 +71,7 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin - + diff --git a/docs/api/core.trainers.base.html b/docs/api/core.trainers.base.html index d1e5572e1..06df54840 100644 --- a/docs/api/core.trainers.base.html +++ b/docs/api/core.trainers.base.html @@ -2,7 +2,7 @@ - + @@ -71,7 +71,7 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin - + diff --git a/docs/api/core.trainers.dpo.trainer.html b/docs/api/core.trainers.dpo.trainer.html index 767cb5abb..853b42098 100644 --- a/docs/api/core.trainers.dpo.trainer.html +++ b/docs/api/core.trainers.dpo.trainer.html @@ -2,7 +2,7 @@ - + @@ -71,7 +71,7 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin - + diff --git a/docs/api/core.trainers.grpo.sampler.html b/docs/api/core.trainers.grpo.sampler.html index 2ff0d63bc..70f179b34 100644 --- a/docs/api/core.trainers.grpo.sampler.html +++ b/docs/api/core.trainers.grpo.sampler.html @@ -2,7 +2,7 @@ - + @@ -71,7 +71,7 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin - + diff --git a/docs/api/core.trainers.grpo.trainer.html b/docs/api/core.trainers.grpo.trainer.html index 5f2c32ee5..5f9db1b2b 100644 --- a/docs/api/core.trainers.grpo.trainer.html +++ b/docs/api/core.trainers.grpo.trainer.html @@ -2,7 +2,7 @@ - + @@ -71,7 +71,7 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin - + diff --git a/docs/api/core.trainers.mamba.html b/docs/api/core.trainers.mamba.html index 10aaade53..97f61f0c1 100644 --- a/docs/api/core.trainers.mamba.html +++ b/docs/api/core.trainers.mamba.html @@ -2,7 +2,7 @@ - + @@ -71,7 +71,7 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin - + diff --git a/docs/api/core.trainers.mixins.optimizer.html b/docs/api/core.trainers.mixins.optimizer.html index e800ff097..1626586fa 100644 --- a/docs/api/core.trainers.mixins.optimizer.html +++ b/docs/api/core.trainers.mixins.optimizer.html @@ -2,7 +2,7 @@ - + @@ -71,7 +71,7 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin - + diff --git a/docs/api/core.trainers.mixins.rng_state_loader.html b/docs/api/core.trainers.mixins.rng_state_loader.html index bd13ebbc4..fba7ca88d 100644 --- a/docs/api/core.trainers.mixins.rng_state_loader.html +++ b/docs/api/core.trainers.mixins.rng_state_loader.html @@ -2,7 +2,7 @@ - + @@ -71,7 +71,7 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin - + diff --git a/docs/api/core.trainers.mixins.scheduler.html b/docs/api/core.trainers.mixins.scheduler.html index 4e58b0f28..547f04d92 100644 --- a/docs/api/core.trainers.mixins.scheduler.html +++ b/docs/api/core.trainers.mixins.scheduler.html @@ -2,7 +2,7 @@ - + @@ -71,7 +71,7 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin - + diff --git a/docs/api/core.trainers.trl.html b/docs/api/core.trainers.trl.html index ef8757d68..d1ffe1fdb 100644 --- a/docs/api/core.trainers.trl.html +++ b/docs/api/core.trainers.trl.html @@ -2,7 +2,7 @@ - + @@ -71,7 +71,7 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin - + diff --git a/docs/api/core.trainers.utils.html b/docs/api/core.trainers.utils.html index a40d478e5..c1bb11e49 100644 --- a/docs/api/core.trainers.utils.html +++ b/docs/api/core.trainers.utils.html @@ -2,7 +2,7 @@ - + @@ -36,7 +36,7 @@ ul.task-list li input[type="checkbox"] { - + diff --git a/docs/api/core.training_args.html b/docs/api/core.training_args.html index 466551b49..d2027610c 100644 --- a/docs/api/core.training_args.html +++ b/docs/api/core.training_args.html @@ -2,7 +2,7 @@ - + @@ -71,7 +71,7 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin - + diff --git a/docs/api/datasets.html b/docs/api/datasets.html index 97fac8bdc..9b6951a6d 100644 --- a/docs/api/datasets.html +++ b/docs/api/datasets.html @@ -2,7 +2,7 @@ - + @@ -71,7 +71,7 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin - + diff --git a/docs/api/evaluate.html b/docs/api/evaluate.html index f7b9ea431..dd22b9949 100644 --- a/docs/api/evaluate.html +++ b/docs/api/evaluate.html @@ -2,7 +2,7 @@ - + @@ -71,7 +71,7 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin - + diff --git a/docs/api/index.html b/docs/api/index.html index c309526e0..55545b171 100644 --- a/docs/api/index.html +++ b/docs/api/index.html @@ -2,7 +2,7 @@ - + @@ -36,7 +36,7 @@ ul.task-list li input[type="checkbox"] { - + diff --git a/docs/api/integrations.base.html b/docs/api/integrations.base.html index 2b05ab327..b040a4d67 100644 --- a/docs/api/integrations.base.html +++ b/docs/api/integrations.base.html @@ -2,7 +2,7 @@ - + @@ -71,7 +71,7 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin - + diff --git a/docs/api/integrations.cut_cross_entropy.args.html b/docs/api/integrations.cut_cross_entropy.args.html index b36946c57..88f19923a 100644 --- a/docs/api/integrations.cut_cross_entropy.args.html +++ b/docs/api/integrations.cut_cross_entropy.args.html @@ -2,7 +2,7 @@ - + @@ -71,7 +71,7 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin - + diff --git a/docs/api/integrations.grokfast.optimizer.html b/docs/api/integrations.grokfast.optimizer.html index cbe0f86dc..837bd7fba 100644 --- a/docs/api/integrations.grokfast.optimizer.html +++ b/docs/api/integrations.grokfast.optimizer.html @@ -2,7 +2,7 @@ - + @@ -36,7 +36,7 @@ ul.task-list li input[type="checkbox"] { - + diff --git a/docs/api/integrations.kd.trainer.html b/docs/api/integrations.kd.trainer.html index 8bf547d72..672e6617a 100644 --- a/docs/api/integrations.kd.trainer.html +++ b/docs/api/integrations.kd.trainer.html @@ -2,7 +2,7 @@ - + @@ -71,7 +71,7 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin - + diff --git a/docs/api/integrations.liger.args.html b/docs/api/integrations.liger.args.html index 9e30ec9ab..db0444466 100644 --- a/docs/api/integrations.liger.args.html +++ b/docs/api/integrations.liger.args.html @@ -2,7 +2,7 @@ - + @@ -71,7 +71,7 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin - + diff --git a/docs/api/integrations.lm_eval.args.html b/docs/api/integrations.lm_eval.args.html index b838a3f5b..f3d7acbfd 100644 --- a/docs/api/integrations.lm_eval.args.html +++ b/docs/api/integrations.lm_eval.args.html @@ -2,7 +2,7 @@ - + @@ -71,7 +71,7 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin - + diff --git a/docs/api/integrations.spectrum.args.html b/docs/api/integrations.spectrum.args.html index 01e9fb780..7d3d500d8 100644 --- a/docs/api/integrations.spectrum.args.html +++ b/docs/api/integrations.spectrum.args.html @@ -2,7 +2,7 @@ - + @@ -71,7 +71,7 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin - + diff --git a/docs/api/kernels.geglu.html b/docs/api/kernels.geglu.html index b67e54094..67ef83d1b 100644 --- a/docs/api/kernels.geglu.html +++ b/docs/api/kernels.geglu.html @@ -2,7 +2,7 @@ - + @@ -71,7 +71,7 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin - + diff --git a/docs/api/kernels.lora.html b/docs/api/kernels.lora.html index e388ede28..1b18ce66e 100644 --- a/docs/api/kernels.lora.html +++ b/docs/api/kernels.lora.html @@ -2,7 +2,7 @@ - + @@ -71,7 +71,7 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin - + diff --git a/docs/api/kernels.quantize.html b/docs/api/kernels.quantize.html index 619a38bcc..e0893a9ca 100644 --- a/docs/api/kernels.quantize.html +++ b/docs/api/kernels.quantize.html @@ -2,7 +2,7 @@ - + @@ -71,7 +71,7 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin - + diff --git a/docs/api/kernels.swiglu.html b/docs/api/kernels.swiglu.html index 1869832d8..bc43c8f74 100644 --- a/docs/api/kernels.swiglu.html +++ b/docs/api/kernels.swiglu.html @@ -2,7 +2,7 @@ - + @@ -71,7 +71,7 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin - + diff --git a/docs/api/kernels.utils.html b/docs/api/kernels.utils.html index 8ef2132b5..41c12f0fe 100644 --- a/docs/api/kernels.utils.html +++ b/docs/api/kernels.utils.html @@ -2,7 +2,7 @@ - + @@ -36,7 +36,7 @@ ul.task-list li input[type="checkbox"] { - + diff --git a/docs/api/loaders.adapter.html b/docs/api/loaders.adapter.html index 7021d1420..d144dcd2f 100644 --- a/docs/api/loaders.adapter.html +++ b/docs/api/loaders.adapter.html @@ -2,7 +2,7 @@ - + @@ -71,7 +71,7 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin - + diff --git a/docs/api/loaders.constants.html b/docs/api/loaders.constants.html index 1cb019202..73c13de98 100644 --- a/docs/api/loaders.constants.html +++ b/docs/api/loaders.constants.html @@ -2,7 +2,7 @@ - + @@ -36,7 +36,7 @@ ul.task-list li input[type="checkbox"] { - + diff --git a/docs/api/loaders.model.html b/docs/api/loaders.model.html index 69f793240..13f0f5fd8 100644 --- a/docs/api/loaders.model.html +++ b/docs/api/loaders.model.html @@ -2,7 +2,7 @@ - + @@ -71,7 +71,7 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin - + diff --git a/docs/api/loaders.patch_manager.html b/docs/api/loaders.patch_manager.html index 2d7c4a31c..61b61ecc6 100644 --- a/docs/api/loaders.patch_manager.html +++ b/docs/api/loaders.patch_manager.html @@ -2,7 +2,7 @@ - + @@ -71,7 +71,7 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin - + diff --git a/docs/api/loaders.processor.html b/docs/api/loaders.processor.html index 9e721c685..cf5418872 100644 --- a/docs/api/loaders.processor.html +++ b/docs/api/loaders.processor.html @@ -2,7 +2,7 @@ - + @@ -36,7 +36,7 @@ ul.task-list li input[type="checkbox"] { - + diff --git a/docs/api/loaders.tokenizer.html b/docs/api/loaders.tokenizer.html index cf5ee4f31..4f9bc7dfd 100644 --- a/docs/api/loaders.tokenizer.html +++ b/docs/api/loaders.tokenizer.html @@ -2,7 +2,7 @@ - + @@ -71,7 +71,7 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin - + diff --git a/docs/api/logging_config.html b/docs/api/logging_config.html index e427e9648..2b5645f58 100644 --- a/docs/api/logging_config.html +++ b/docs/api/logging_config.html @@ -2,7 +2,7 @@ - + @@ -71,7 +71,7 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin - + diff --git a/docs/api/models.mamba.modeling_mamba.html b/docs/api/models.mamba.modeling_mamba.html index 37687fbf3..31ce963f8 100644 --- a/docs/api/models.mamba.modeling_mamba.html +++ b/docs/api/models.mamba.modeling_mamba.html @@ -2,7 +2,7 @@ - + @@ -36,7 +36,7 @@ ul.task-list li input[type="checkbox"] { - + diff --git a/docs/api/monkeypatch.btlm_attn_hijack_flash.html b/docs/api/monkeypatch.btlm_attn_hijack_flash.html index 49216ad4f..1cf69172e 100644 --- a/docs/api/monkeypatch.btlm_attn_hijack_flash.html +++ b/docs/api/monkeypatch.btlm_attn_hijack_flash.html @@ -2,7 +2,7 @@ - + @@ -36,7 +36,7 @@ ul.task-list li input[type="checkbox"] { - + diff --git a/docs/api/monkeypatch.data.batch_dataset_fetcher.html b/docs/api/monkeypatch.data.batch_dataset_fetcher.html index e578d03cc..602dfbb45 100644 --- a/docs/api/monkeypatch.data.batch_dataset_fetcher.html +++ b/docs/api/monkeypatch.data.batch_dataset_fetcher.html @@ -2,7 +2,7 @@ - + @@ -71,7 +71,7 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin - + diff --git a/docs/api/monkeypatch.gradient_checkpointing.offload_cpu.html b/docs/api/monkeypatch.gradient_checkpointing.offload_cpu.html index 711d2e4b7..cac34c342 100644 --- a/docs/api/monkeypatch.gradient_checkpointing.offload_cpu.html +++ b/docs/api/monkeypatch.gradient_checkpointing.offload_cpu.html @@ -2,7 +2,7 @@ - + @@ -71,7 +71,7 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin - + diff --git a/docs/api/monkeypatch.gradient_checkpointing.offload_disk.html b/docs/api/monkeypatch.gradient_checkpointing.offload_disk.html index 5d7d1d1a8..a3a4c6f1d 100644 --- a/docs/api/monkeypatch.gradient_checkpointing.offload_disk.html +++ b/docs/api/monkeypatch.gradient_checkpointing.offload_disk.html @@ -2,7 +2,7 @@ - + @@ -71,7 +71,7 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin - + diff --git a/docs/api/monkeypatch.llama_attn_hijack_flash.html b/docs/api/monkeypatch.llama_attn_hijack_flash.html index 85e48152e..515822ff3 100644 --- a/docs/api/monkeypatch.llama_attn_hijack_flash.html +++ b/docs/api/monkeypatch.llama_attn_hijack_flash.html @@ -2,7 +2,7 @@ - + @@ -71,7 +71,7 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin - + diff --git a/docs/api/monkeypatch.llama_attn_hijack_xformers.html b/docs/api/monkeypatch.llama_attn_hijack_xformers.html index c9d360633..7a8c44db2 100644 --- a/docs/api/monkeypatch.llama_attn_hijack_xformers.html +++ b/docs/api/monkeypatch.llama_attn_hijack_xformers.html @@ -2,7 +2,7 @@ - + @@ -36,7 +36,7 @@ ul.task-list li input[type="checkbox"] { - + diff --git a/docs/api/monkeypatch.llama_expand_mask.html b/docs/api/monkeypatch.llama_expand_mask.html index 07b1642e0..ed3e9d11d 100644 --- a/docs/api/monkeypatch.llama_expand_mask.html +++ b/docs/api/monkeypatch.llama_expand_mask.html @@ -2,7 +2,7 @@ - + @@ -36,7 +36,7 @@ ul.task-list li input[type="checkbox"] { - + diff --git a/docs/api/monkeypatch.llama_patch_multipack.html b/docs/api/monkeypatch.llama_patch_multipack.html index 855812d0c..50771b87e 100644 --- a/docs/api/monkeypatch.llama_patch_multipack.html +++ b/docs/api/monkeypatch.llama_patch_multipack.html @@ -2,7 +2,7 @@ - + @@ -36,7 +36,7 @@ ul.task-list li input[type="checkbox"] { - + diff --git a/docs/api/monkeypatch.lora_kernels.html b/docs/api/monkeypatch.lora_kernels.html index 5d1eabe42..eae85a9ef 100644 --- a/docs/api/monkeypatch.lora_kernels.html +++ b/docs/api/monkeypatch.lora_kernels.html @@ -2,7 +2,7 @@ - + @@ -71,7 +71,7 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin - + diff --git a/docs/api/monkeypatch.mistral_attn_hijack_flash.html b/docs/api/monkeypatch.mistral_attn_hijack_flash.html index 75499a8cb..d10a38fcb 100644 --- a/docs/api/monkeypatch.mistral_attn_hijack_flash.html +++ b/docs/api/monkeypatch.mistral_attn_hijack_flash.html @@ -2,7 +2,7 @@ - + @@ -36,7 +36,7 @@ ul.task-list li input[type="checkbox"] { - + diff --git a/docs/api/monkeypatch.mixtral.html b/docs/api/monkeypatch.mixtral.html index a6b5876d4..c29ebc768 100644 --- a/docs/api/monkeypatch.mixtral.html +++ b/docs/api/monkeypatch.mixtral.html @@ -2,7 +2,7 @@ - + @@ -36,7 +36,7 @@ ul.task-list li input[type="checkbox"] { - + diff --git a/docs/api/monkeypatch.multipack.html b/docs/api/monkeypatch.multipack.html index 5bdc86b2c..2f41a5602 100644 --- a/docs/api/monkeypatch.multipack.html +++ b/docs/api/monkeypatch.multipack.html @@ -2,7 +2,7 @@ - + @@ -36,7 +36,7 @@ ul.task-list li input[type="checkbox"] { - + diff --git a/docs/api/monkeypatch.relora.html b/docs/api/monkeypatch.relora.html index 211a373ff..8e13f0c89 100644 --- a/docs/api/monkeypatch.relora.html +++ b/docs/api/monkeypatch.relora.html @@ -2,7 +2,7 @@ - + @@ -71,7 +71,7 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin - + diff --git a/docs/api/monkeypatch.stablelm_attn_hijack_flash.html b/docs/api/monkeypatch.stablelm_attn_hijack_flash.html index aa789c115..dc6af78b0 100644 --- a/docs/api/monkeypatch.stablelm_attn_hijack_flash.html +++ b/docs/api/monkeypatch.stablelm_attn_hijack_flash.html @@ -2,7 +2,7 @@ - + @@ -71,7 +71,7 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin - + diff --git a/docs/api/monkeypatch.trainer_fsdp_optim.html b/docs/api/monkeypatch.trainer_fsdp_optim.html index 4cc849bcc..f3f76890e 100644 --- a/docs/api/monkeypatch.trainer_fsdp_optim.html +++ b/docs/api/monkeypatch.trainer_fsdp_optim.html @@ -2,7 +2,7 @@ - + @@ -71,7 +71,7 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin - + diff --git a/docs/api/monkeypatch.transformers_fa_utils.html b/docs/api/monkeypatch.transformers_fa_utils.html index 02aaabfcb..c4efaaab8 100644 --- a/docs/api/monkeypatch.transformers_fa_utils.html +++ b/docs/api/monkeypatch.transformers_fa_utils.html @@ -2,7 +2,7 @@ - + @@ -71,7 +71,7 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin - + diff --git a/docs/api/monkeypatch.unsloth_.html b/docs/api/monkeypatch.unsloth_.html index 9ff95e2a8..74cdaf148 100644 --- a/docs/api/monkeypatch.unsloth_.html +++ b/docs/api/monkeypatch.unsloth_.html @@ -2,7 +2,7 @@ - + @@ -36,7 +36,7 @@ ul.task-list li input[type="checkbox"] { - + diff --git a/docs/api/monkeypatch.utils.html b/docs/api/monkeypatch.utils.html index ed60d9f37..e8cbf8786 100644 --- a/docs/api/monkeypatch.utils.html +++ b/docs/api/monkeypatch.utils.html @@ -2,7 +2,7 @@ - + @@ -71,7 +71,7 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin - + diff --git a/docs/api/prompt_strategies.alpaca_chat.html b/docs/api/prompt_strategies.alpaca_chat.html index 45fdacf77..31e2d17dd 100644 --- a/docs/api/prompt_strategies.alpaca_chat.html +++ b/docs/api/prompt_strategies.alpaca_chat.html @@ -2,7 +2,7 @@ - + @@ -71,7 +71,7 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin - + diff --git a/docs/api/prompt_strategies.alpaca_instruct.html b/docs/api/prompt_strategies.alpaca_instruct.html index 229fb4843..7b5c4d837 100644 --- a/docs/api/prompt_strategies.alpaca_instruct.html +++ b/docs/api/prompt_strategies.alpaca_instruct.html @@ -2,7 +2,7 @@ - + @@ -36,7 +36,7 @@ ul.task-list li input[type="checkbox"] { - + diff --git a/docs/api/prompt_strategies.alpaca_w_system.html b/docs/api/prompt_strategies.alpaca_w_system.html index 5448f581b..64ffddb01 100644 --- a/docs/api/prompt_strategies.alpaca_w_system.html +++ b/docs/api/prompt_strategies.alpaca_w_system.html @@ -2,7 +2,7 @@ - + @@ -71,7 +71,7 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin - + diff --git a/docs/api/prompt_strategies.base.html b/docs/api/prompt_strategies.base.html index abe332cba..901d5e2b9 100644 --- a/docs/api/prompt_strategies.base.html +++ b/docs/api/prompt_strategies.base.html @@ -2,7 +2,7 @@ - + @@ -36,7 +36,7 @@ ul.task-list li input[type="checkbox"] { - + diff --git a/docs/api/prompt_strategies.bradley_terry.llama3.html b/docs/api/prompt_strategies.bradley_terry.llama3.html index 55ae6923a..1088759b6 100644 --- a/docs/api/prompt_strategies.bradley_terry.llama3.html +++ b/docs/api/prompt_strategies.bradley_terry.llama3.html @@ -2,7 +2,7 @@ - + @@ -71,7 +71,7 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin - + diff --git a/docs/api/prompt_strategies.chat_template.html b/docs/api/prompt_strategies.chat_template.html index 192de88ce..45fcae99e 100644 --- a/docs/api/prompt_strategies.chat_template.html +++ b/docs/api/prompt_strategies.chat_template.html @@ -2,7 +2,7 @@ - + @@ -71,7 +71,7 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin - + diff --git a/docs/api/prompt_strategies.completion.html b/docs/api/prompt_strategies.completion.html index acd652ec0..c34e24a1f 100644 --- a/docs/api/prompt_strategies.completion.html +++ b/docs/api/prompt_strategies.completion.html @@ -2,7 +2,7 @@ - + @@ -71,7 +71,7 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin - + diff --git a/docs/api/prompt_strategies.dpo.chat_template.html b/docs/api/prompt_strategies.dpo.chat_template.html index 3a41595a7..f04df6ffd 100644 --- a/docs/api/prompt_strategies.dpo.chat_template.html +++ b/docs/api/prompt_strategies.dpo.chat_template.html @@ -2,7 +2,7 @@ - + @@ -36,7 +36,7 @@ ul.task-list li input[type="checkbox"] { - + diff --git a/docs/api/prompt_strategies.dpo.chatml.html b/docs/api/prompt_strategies.dpo.chatml.html index 8c545cd8d..21cb04a09 100644 --- a/docs/api/prompt_strategies.dpo.chatml.html +++ b/docs/api/prompt_strategies.dpo.chatml.html @@ -2,7 +2,7 @@ - + @@ -71,7 +71,7 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin - + diff --git a/docs/api/prompt_strategies.dpo.llama3.html b/docs/api/prompt_strategies.dpo.llama3.html index 29a05fa2b..137194c7d 100644 --- a/docs/api/prompt_strategies.dpo.llama3.html +++ b/docs/api/prompt_strategies.dpo.llama3.html @@ -2,7 +2,7 @@ - + @@ -71,7 +71,7 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin - + diff --git a/docs/api/prompt_strategies.dpo.passthrough.html b/docs/api/prompt_strategies.dpo.passthrough.html index 802179149..5cf7eada5 100644 --- a/docs/api/prompt_strategies.dpo.passthrough.html +++ b/docs/api/prompt_strategies.dpo.passthrough.html @@ -2,7 +2,7 @@ - + @@ -36,7 +36,7 @@ ul.task-list li input[type="checkbox"] { - + diff --git a/docs/api/prompt_strategies.dpo.user_defined.html b/docs/api/prompt_strategies.dpo.user_defined.html index fd1e3d717..808fa8769 100644 --- a/docs/api/prompt_strategies.dpo.user_defined.html +++ b/docs/api/prompt_strategies.dpo.user_defined.html @@ -2,7 +2,7 @@ - + @@ -36,7 +36,7 @@ ul.task-list li input[type="checkbox"] { - + diff --git a/docs/api/prompt_strategies.dpo.zephyr.html b/docs/api/prompt_strategies.dpo.zephyr.html index c9c143d3d..87af9fdab 100644 --- a/docs/api/prompt_strategies.dpo.zephyr.html +++ b/docs/api/prompt_strategies.dpo.zephyr.html @@ -2,7 +2,7 @@ - + @@ -36,7 +36,7 @@ ul.task-list li input[type="checkbox"] { - + diff --git a/docs/api/prompt_strategies.input_output.html b/docs/api/prompt_strategies.input_output.html index 507466781..4dd3bf566 100644 --- a/docs/api/prompt_strategies.input_output.html +++ b/docs/api/prompt_strategies.input_output.html @@ -2,7 +2,7 @@ - + @@ -71,7 +71,7 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin - + diff --git a/docs/api/prompt_strategies.kto.chatml.html b/docs/api/prompt_strategies.kto.chatml.html index 2ddff0d0e..4cbb7bb4d 100644 --- a/docs/api/prompt_strategies.kto.chatml.html +++ b/docs/api/prompt_strategies.kto.chatml.html @@ -2,7 +2,7 @@ - + @@ -71,7 +71,7 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin - + diff --git a/docs/api/prompt_strategies.kto.llama3.html b/docs/api/prompt_strategies.kto.llama3.html index c23ed8798..859475c6b 100644 --- a/docs/api/prompt_strategies.kto.llama3.html +++ b/docs/api/prompt_strategies.kto.llama3.html @@ -2,7 +2,7 @@ - + @@ -71,7 +71,7 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin - + diff --git a/docs/api/prompt_strategies.kto.user_defined.html b/docs/api/prompt_strategies.kto.user_defined.html index c986b9dd6..dd08e85c3 100644 --- a/docs/api/prompt_strategies.kto.user_defined.html +++ b/docs/api/prompt_strategies.kto.user_defined.html @@ -2,7 +2,7 @@ - + @@ -36,7 +36,7 @@ ul.task-list li input[type="checkbox"] { - + diff --git a/docs/api/prompt_strategies.llama2_chat.html b/docs/api/prompt_strategies.llama2_chat.html index 2075a4796..4f6bb9c0a 100644 --- a/docs/api/prompt_strategies.llama2_chat.html +++ b/docs/api/prompt_strategies.llama2_chat.html @@ -2,7 +2,7 @@ - + @@ -71,7 +71,7 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin - + diff --git a/docs/api/prompt_strategies.messages.chat.html b/docs/api/prompt_strategies.messages.chat.html index 49682a779..6433774b2 100644 --- a/docs/api/prompt_strategies.messages.chat.html +++ b/docs/api/prompt_strategies.messages.chat.html @@ -2,7 +2,7 @@ - + @@ -71,7 +71,7 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin - + diff --git a/docs/api/prompt_strategies.metharme.html b/docs/api/prompt_strategies.metharme.html index b69970bb1..dfc98d9c8 100644 --- a/docs/api/prompt_strategies.metharme.html +++ b/docs/api/prompt_strategies.metharme.html @@ -2,7 +2,7 @@ - + @@ -71,7 +71,7 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin - + diff --git a/docs/api/prompt_strategies.orcamini.html b/docs/api/prompt_strategies.orcamini.html index 41c5656dc..9906a9fbd 100644 --- a/docs/api/prompt_strategies.orcamini.html +++ b/docs/api/prompt_strategies.orcamini.html @@ -2,7 +2,7 @@ - + @@ -71,7 +71,7 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin - + diff --git a/docs/api/prompt_strategies.orpo.chat_template.html b/docs/api/prompt_strategies.orpo.chat_template.html index 5b9b01d3f..a07bc8393 100644 --- a/docs/api/prompt_strategies.orpo.chat_template.html +++ b/docs/api/prompt_strategies.orpo.chat_template.html @@ -2,7 +2,7 @@ - + @@ -71,7 +71,7 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin - + diff --git a/docs/api/prompt_strategies.pygmalion.html b/docs/api/prompt_strategies.pygmalion.html index d92db8839..7f8101cfd 100644 --- a/docs/api/prompt_strategies.pygmalion.html +++ b/docs/api/prompt_strategies.pygmalion.html @@ -2,7 +2,7 @@ - + @@ -71,7 +71,7 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin - + diff --git a/docs/api/prompt_strategies.stepwise_supervised.html b/docs/api/prompt_strategies.stepwise_supervised.html index 415567d94..7544c5d99 100644 --- a/docs/api/prompt_strategies.stepwise_supervised.html +++ b/docs/api/prompt_strategies.stepwise_supervised.html @@ -2,7 +2,7 @@ - + @@ -71,7 +71,7 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin - + diff --git a/docs/api/prompt_strategies.user_defined.html b/docs/api/prompt_strategies.user_defined.html index f6df01954..d9b5797f7 100644 --- a/docs/api/prompt_strategies.user_defined.html +++ b/docs/api/prompt_strategies.user_defined.html @@ -2,7 +2,7 @@ - + @@ -71,7 +71,7 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin - + diff --git a/docs/api/prompt_tokenizers.html b/docs/api/prompt_tokenizers.html index b63dd5be9..15c8a307b 100644 --- a/docs/api/prompt_tokenizers.html +++ b/docs/api/prompt_tokenizers.html @@ -2,7 +2,7 @@ - + @@ -71,7 +71,7 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin - + diff --git a/docs/api/train.html b/docs/api/train.html index 690bdb63d..1c45bff35 100644 --- a/docs/api/train.html +++ b/docs/api/train.html @@ -2,7 +2,7 @@ - + @@ -71,7 +71,7 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin - + diff --git a/docs/api/utils.bench.html b/docs/api/utils.bench.html index 20547eb8d..c821d8121 100644 --- a/docs/api/utils.bench.html +++ b/docs/api/utils.bench.html @@ -2,7 +2,7 @@ - + @@ -71,7 +71,7 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin - + diff --git a/docs/api/utils.callbacks.comet_.html b/docs/api/utils.callbacks.comet_.html index bd9ce5686..4cd5d88f7 100644 --- a/docs/api/utils.callbacks.comet_.html +++ b/docs/api/utils.callbacks.comet_.html @@ -2,7 +2,7 @@ - + @@ -71,7 +71,7 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin - + diff --git a/docs/api/utils.callbacks.lisa.html b/docs/api/utils.callbacks.lisa.html index 13b4051dc..663547074 100644 --- a/docs/api/utils.callbacks.lisa.html +++ b/docs/api/utils.callbacks.lisa.html @@ -2,7 +2,7 @@ - + @@ -36,7 +36,7 @@ ul.task-list li input[type="checkbox"] { - + diff --git a/docs/api/utils.callbacks.mlflow_.html b/docs/api/utils.callbacks.mlflow_.html index fbc1ed7f2..67eafe4d8 100644 --- a/docs/api/utils.callbacks.mlflow_.html +++ b/docs/api/utils.callbacks.mlflow_.html @@ -2,7 +2,7 @@ - + @@ -71,7 +71,7 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin - + diff --git a/docs/api/utils.callbacks.perplexity.html b/docs/api/utils.callbacks.perplexity.html index 5cab76220..407248d4f 100644 --- a/docs/api/utils.callbacks.perplexity.html +++ b/docs/api/utils.callbacks.perplexity.html @@ -2,7 +2,7 @@ - + @@ -71,7 +71,7 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin - + diff --git a/docs/api/utils.callbacks.profiler.html b/docs/api/utils.callbacks.profiler.html index 90ae6d49e..97958d717 100644 --- a/docs/api/utils.callbacks.profiler.html +++ b/docs/api/utils.callbacks.profiler.html @@ -2,7 +2,7 @@ - + @@ -71,7 +71,7 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin - + diff --git a/docs/api/utils.callbacks.qat.html b/docs/api/utils.callbacks.qat.html index 38d76452c..53cff3ff2 100644 --- a/docs/api/utils.callbacks.qat.html +++ b/docs/api/utils.callbacks.qat.html @@ -2,7 +2,7 @@ - + @@ -71,7 +71,7 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin - + diff --git a/docs/api/utils.chat_templates.html b/docs/api/utils.chat_templates.html index 8fb9d3d44..a728dc46e 100644 --- a/docs/api/utils.chat_templates.html +++ b/docs/api/utils.chat_templates.html @@ -2,7 +2,7 @@ - + @@ -36,7 +36,7 @@ ul.task-list li input[type="checkbox"] { - + diff --git a/docs/api/utils.collators.batching.html b/docs/api/utils.collators.batching.html index aa33db865..00e6e0395 100644 --- a/docs/api/utils.collators.batching.html +++ b/docs/api/utils.collators.batching.html @@ -2,7 +2,7 @@ - + @@ -71,7 +71,7 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin - + diff --git a/docs/api/utils.collators.core.html b/docs/api/utils.collators.core.html index 5197581cd..0b6a097bb 100644 --- a/docs/api/utils.collators.core.html +++ b/docs/api/utils.collators.core.html @@ -2,7 +2,7 @@ - + @@ -36,7 +36,7 @@ ul.task-list li input[type="checkbox"] { - + diff --git a/docs/api/utils.collators.mamba.html b/docs/api/utils.collators.mamba.html index 62ca83a09..6e5f7413f 100644 --- a/docs/api/utils.collators.mamba.html +++ b/docs/api/utils.collators.mamba.html @@ -2,7 +2,7 @@ - + @@ -71,7 +71,7 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin - + diff --git a/docs/api/utils.collators.mm_chat.html b/docs/api/utils.collators.mm_chat.html index d6054ef10..52e6ffeb5 100644 --- a/docs/api/utils.collators.mm_chat.html +++ b/docs/api/utils.collators.mm_chat.html @@ -2,7 +2,7 @@ - + @@ -71,7 +71,7 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin - + diff --git a/docs/api/utils.ctx_managers.sequence_parallel.html b/docs/api/utils.ctx_managers.sequence_parallel.html index 9bc1d10d2..d327779b8 100644 --- a/docs/api/utils.ctx_managers.sequence_parallel.html +++ b/docs/api/utils.ctx_managers.sequence_parallel.html @@ -2,7 +2,7 @@ - + @@ -71,7 +71,7 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin - + diff --git a/docs/api/utils.data.pretraining.html b/docs/api/utils.data.pretraining.html index e853d2cdc..27de29126 100644 --- a/docs/api/utils.data.pretraining.html +++ b/docs/api/utils.data.pretraining.html @@ -2,7 +2,7 @@ - + @@ -36,7 +36,7 @@ ul.task-list li input[type="checkbox"] { - + diff --git a/docs/api/utils.data.sft.html b/docs/api/utils.data.sft.html index 4911b74a0..3f145de11 100644 --- a/docs/api/utils.data.sft.html +++ b/docs/api/utils.data.sft.html @@ -2,7 +2,7 @@ - + @@ -71,7 +71,7 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin - + diff --git a/docs/api/utils.dict.html b/docs/api/utils.dict.html index 840f422d2..d0031b658 100644 --- a/docs/api/utils.dict.html +++ b/docs/api/utils.dict.html @@ -2,7 +2,7 @@ - + @@ -71,7 +71,7 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin - + diff --git a/docs/api/utils.distributed.html b/docs/api/utils.distributed.html index b891762b0..9c514f9d0 100644 --- a/docs/api/utils.distributed.html +++ b/docs/api/utils.distributed.html @@ -2,7 +2,7 @@ - + @@ -71,7 +71,7 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin - + diff --git a/docs/api/utils.freeze.html b/docs/api/utils.freeze.html index 3bc64fa72..320f4d64d 100644 --- a/docs/api/utils.freeze.html +++ b/docs/api/utils.freeze.html @@ -2,7 +2,7 @@ - + @@ -71,7 +71,7 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin - + diff --git a/docs/api/utils.lora.html b/docs/api/utils.lora.html index 124eb1a29..53e7dbcbf 100644 --- a/docs/api/utils.lora.html +++ b/docs/api/utils.lora.html @@ -2,7 +2,7 @@ - + @@ -71,7 +71,7 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin - + diff --git a/docs/api/utils.model_shard_quant.html b/docs/api/utils.model_shard_quant.html index ef2b595a1..f23697ec4 100644 --- a/docs/api/utils.model_shard_quant.html +++ b/docs/api/utils.model_shard_quant.html @@ -2,7 +2,7 @@ - + @@ -71,7 +71,7 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin - + diff --git a/docs/api/utils.optimizers.adopt.html b/docs/api/utils.optimizers.adopt.html index ac848e8ce..bd0826f48 100644 --- a/docs/api/utils.optimizers.adopt.html +++ b/docs/api/utils.optimizers.adopt.html @@ -2,7 +2,7 @@ - + @@ -71,7 +71,7 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin - + diff --git a/docs/api/utils.quantization.html b/docs/api/utils.quantization.html index 673aa58b4..0726fa4f4 100644 --- a/docs/api/utils.quantization.html +++ b/docs/api/utils.quantization.html @@ -2,7 +2,7 @@ - + @@ -71,7 +71,7 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin - + diff --git a/docs/api/utils.samplers.multipack.html b/docs/api/utils.samplers.multipack.html index 62f568394..7da1ddbcb 100644 --- a/docs/api/utils.samplers.multipack.html +++ b/docs/api/utils.samplers.multipack.html @@ -2,7 +2,7 @@ - + @@ -71,7 +71,7 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin - + diff --git a/docs/api/utils.schedulers.html b/docs/api/utils.schedulers.html index 3d82c040a..4e905eb0a 100644 --- a/docs/api/utils.schedulers.html +++ b/docs/api/utils.schedulers.html @@ -2,7 +2,7 @@ - + @@ -71,7 +71,7 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin - + diff --git a/docs/api/utils.schemas.config.html b/docs/api/utils.schemas.config.html index b4e0af7c6..1f107a0e8 100644 --- a/docs/api/utils.schemas.config.html +++ b/docs/api/utils.schemas.config.html @@ -2,7 +2,7 @@ - + @@ -71,7 +71,7 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin - + diff --git a/docs/api/utils.schemas.datasets.html b/docs/api/utils.schemas.datasets.html index 857bc28f2..96a0f54b3 100644 --- a/docs/api/utils.schemas.datasets.html +++ b/docs/api/utils.schemas.datasets.html @@ -2,7 +2,7 @@ - + @@ -71,7 +71,7 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin - + diff --git a/docs/api/utils.schemas.enums.html b/docs/api/utils.schemas.enums.html index 7cd477354..827ec84d3 100644 --- a/docs/api/utils.schemas.enums.html +++ b/docs/api/utils.schemas.enums.html @@ -2,7 +2,7 @@ - + @@ -71,7 +71,7 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin - + diff --git a/docs/api/utils.schemas.integrations.html b/docs/api/utils.schemas.integrations.html index 71d1c50be..21011447f 100644 --- a/docs/api/utils.schemas.integrations.html +++ b/docs/api/utils.schemas.integrations.html @@ -2,7 +2,7 @@ - + @@ -71,7 +71,7 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin - + diff --git a/docs/api/utils.schemas.model.html b/docs/api/utils.schemas.model.html index f19561e37..9b97b25db 100644 --- a/docs/api/utils.schemas.model.html +++ b/docs/api/utils.schemas.model.html @@ -2,7 +2,7 @@ - + @@ -71,7 +71,7 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin - + diff --git a/docs/api/utils.schemas.multimodal.html b/docs/api/utils.schemas.multimodal.html index 6fb3ac07e..203356c55 100644 --- a/docs/api/utils.schemas.multimodal.html +++ b/docs/api/utils.schemas.multimodal.html @@ -2,7 +2,7 @@ - + @@ -71,7 +71,7 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin - + diff --git a/docs/api/utils.schemas.peft.html b/docs/api/utils.schemas.peft.html index 24fa7c7ac..6f09b939e 100644 --- a/docs/api/utils.schemas.peft.html +++ b/docs/api/utils.schemas.peft.html @@ -2,7 +2,7 @@ - + @@ -71,7 +71,7 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin - + diff --git a/docs/api/utils.schemas.training.html b/docs/api/utils.schemas.training.html index 64601915a..4db8df8a8 100644 --- a/docs/api/utils.schemas.training.html +++ b/docs/api/utils.schemas.training.html @@ -2,7 +2,7 @@ - + @@ -71,7 +71,7 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin - + diff --git a/docs/api/utils.schemas.trl.html b/docs/api/utils.schemas.trl.html index fb109daae..0cef41f97 100644 --- a/docs/api/utils.schemas.trl.html +++ b/docs/api/utils.schemas.trl.html @@ -2,7 +2,7 @@ - + @@ -71,7 +71,7 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin - + diff --git a/docs/api/utils.schemas.utils.html b/docs/api/utils.schemas.utils.html index 53983ce05..c8a321880 100644 --- a/docs/api/utils.schemas.utils.html +++ b/docs/api/utils.schemas.utils.html @@ -2,7 +2,7 @@ - + @@ -71,7 +71,7 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin - + diff --git a/docs/api/utils.tokenization.html b/docs/api/utils.tokenization.html index cfac0111c..b9a0d4351 100644 --- a/docs/api/utils.tokenization.html +++ b/docs/api/utils.tokenization.html @@ -2,7 +2,7 @@ - + @@ -71,7 +71,7 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin - + diff --git a/docs/api/utils.trainer.html b/docs/api/utils.trainer.html index 45ff28c91..51cc137b9 100644 --- a/docs/api/utils.trainer.html +++ b/docs/api/utils.trainer.html @@ -2,7 +2,7 @@ - + @@ -71,7 +71,7 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin - + diff --git a/docs/batch_vs_grad.html b/docs/batch_vs_grad.html index 424fb6d16..be7a9b2e9 100644 --- a/docs/batch_vs_grad.html +++ b/docs/batch_vs_grad.html @@ -2,7 +2,7 @@ - + @@ -37,7 +37,7 @@ ul.task-list li input[type="checkbox"] { - + diff --git a/docs/cli.html b/docs/cli.html index 5d5ab2f93..5fe72e504 100644 --- a/docs/cli.html +++ b/docs/cli.html @@ -2,7 +2,7 @@ - + @@ -71,7 +71,7 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin - + diff --git a/docs/config-reference.html b/docs/config-reference.html index 96a3ed933..fc9203ca5 100644 --- a/docs/config-reference.html +++ b/docs/config-reference.html @@ -2,7 +2,7 @@ - + @@ -72,7 +72,7 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin - + diff --git a/docs/custom_integrations.html b/docs/custom_integrations.html index e3ae7e475..adc66bb1f 100644 --- a/docs/custom_integrations.html +++ b/docs/custom_integrations.html @@ -2,7 +2,7 @@ - + @@ -71,7 +71,7 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin - + diff --git a/docs/dataset-formats/conversation.html b/docs/dataset-formats/conversation.html index 6ce3f3f49..7805ab085 100644 --- a/docs/dataset-formats/conversation.html +++ b/docs/dataset-formats/conversation.html @@ -2,7 +2,7 @@ - + @@ -72,7 +72,7 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin - + diff --git a/docs/dataset-formats/index.html b/docs/dataset-formats/index.html index 140d6d7e9..3e8be0639 100644 --- a/docs/dataset-formats/index.html +++ b/docs/dataset-formats/index.html @@ -2,7 +2,7 @@ - + @@ -72,7 +72,7 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin - + diff --git a/docs/dataset-formats/inst_tune.html b/docs/dataset-formats/inst_tune.html index 10885c330..ade265ab1 100644 --- a/docs/dataset-formats/inst_tune.html +++ b/docs/dataset-formats/inst_tune.html @@ -2,7 +2,7 @@ - + @@ -72,7 +72,7 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin - + diff --git a/docs/dataset-formats/pretraining.html b/docs/dataset-formats/pretraining.html index 4c73f56f4..1def84898 100644 --- a/docs/dataset-formats/pretraining.html +++ b/docs/dataset-formats/pretraining.html @@ -2,7 +2,7 @@ - + @@ -72,7 +72,7 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin - + diff --git a/docs/dataset-formats/stepwise_supervised.html b/docs/dataset-formats/stepwise_supervised.html index 1a94a1880..02cfa8148 100644 --- a/docs/dataset-formats/stepwise_supervised.html +++ b/docs/dataset-formats/stepwise_supervised.html @@ -2,7 +2,7 @@ - + @@ -72,7 +72,7 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin - + diff --git a/docs/dataset-formats/template_free.html b/docs/dataset-formats/template_free.html index 8ca0de968..bdae0eae8 100644 --- a/docs/dataset-formats/template_free.html +++ b/docs/dataset-formats/template_free.html @@ -2,7 +2,7 @@ - + @@ -72,7 +72,7 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin - + diff --git a/docs/dataset-formats/tokenized.html b/docs/dataset-formats/tokenized.html index 9b6fe7877..4faf5b14a 100644 --- a/docs/dataset-formats/tokenized.html +++ b/docs/dataset-formats/tokenized.html @@ -2,7 +2,7 @@ - + @@ -72,7 +72,7 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin - + diff --git a/docs/dataset_loading.html b/docs/dataset_loading.html index 4f09881a0..8284c5905 100644 --- a/docs/dataset_loading.html +++ b/docs/dataset_loading.html @@ -2,7 +2,7 @@ - + @@ -72,7 +72,7 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin - + diff --git a/docs/dataset_preprocessing.html b/docs/dataset_preprocessing.html index 124356765..938d566b7 100644 --- a/docs/dataset_preprocessing.html +++ b/docs/dataset_preprocessing.html @@ -2,7 +2,7 @@ - + @@ -37,7 +37,7 @@ ul.task-list li input[type="checkbox"] { - + diff --git a/docs/debugging.html b/docs/debugging.html index f5b77c531..ade286432 100644 --- a/docs/debugging.html +++ b/docs/debugging.html @@ -2,7 +2,7 @@ - + @@ -72,7 +72,7 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin - + diff --git a/docs/docker.html b/docs/docker.html index 0f63f67eb..2400d56b1 100644 --- a/docs/docker.html +++ b/docs/docker.html @@ -2,7 +2,7 @@ - + @@ -71,7 +71,7 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin - + diff --git a/docs/faq.html b/docs/faq.html index d5e8cdf8b..c6304f4e9 100644 --- a/docs/faq.html +++ b/docs/faq.html @@ -2,7 +2,7 @@ - + @@ -72,7 +72,7 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin - + diff --git a/docs/fsdp_qlora.html b/docs/fsdp_qlora.html index 6ad9966b6..3bba1607e 100644 --- a/docs/fsdp_qlora.html +++ b/docs/fsdp_qlora.html @@ -2,7 +2,7 @@ - + @@ -37,7 +37,7 @@ ul.task-list li input[type="checkbox"] { - + diff --git a/docs/getting-started.html b/docs/getting-started.html index 6c1b7e90d..a392cb764 100644 --- a/docs/getting-started.html +++ b/docs/getting-started.html @@ -2,7 +2,7 @@ - + @@ -71,7 +71,7 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin - + diff --git a/docs/gradient_checkpointing.html b/docs/gradient_checkpointing.html index 82d5d23bd..2b8f37be5 100644 --- a/docs/gradient_checkpointing.html +++ b/docs/gradient_checkpointing.html @@ -2,7 +2,7 @@ - + @@ -71,7 +71,7 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin - + diff --git a/docs/inference.html b/docs/inference.html index 020b75203..45f2cc9ac 100644 --- a/docs/inference.html +++ b/docs/inference.html @@ -2,7 +2,7 @@ - + @@ -71,7 +71,7 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin - + diff --git a/docs/input_output.html b/docs/input_output.html index bffe66920..97d98cf84 100644 --- a/docs/input_output.html +++ b/docs/input_output.html @@ -2,7 +2,7 @@ - + @@ -37,7 +37,7 @@ ul.task-list li input[type="checkbox"] { - + diff --git a/docs/installation.html b/docs/installation.html index 4a377b489..1656148b0 100644 --- a/docs/installation.html +++ b/docs/installation.html @@ -2,7 +2,7 @@ - + @@ -71,7 +71,7 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin - + diff --git a/docs/lora_optims.html b/docs/lora_optims.html index 41b0622ad..437c79f3c 100644 --- a/docs/lora_optims.html +++ b/docs/lora_optims.html @@ -2,7 +2,7 @@ - + @@ -72,7 +72,7 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin - + diff --git a/docs/lr_groups.html b/docs/lr_groups.html index 846b35286..da6d7a2b8 100644 --- a/docs/lr_groups.html +++ b/docs/lr_groups.html @@ -2,7 +2,7 @@ - + @@ -72,7 +72,7 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin - + diff --git a/docs/mac.html b/docs/mac.html index b90eeb0d3..5a8596ac2 100644 --- a/docs/mac.html +++ b/docs/mac.html @@ -2,7 +2,7 @@ - + @@ -37,7 +37,7 @@ ul.task-list li input[type="checkbox"] { - + diff --git a/docs/mixed_precision.html b/docs/mixed_precision.html index 7a2fffe31..f23591b98 100644 --- a/docs/mixed_precision.html +++ b/docs/mixed_precision.html @@ -2,7 +2,7 @@ - + @@ -71,7 +71,7 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin - + diff --git a/docs/multi-gpu.html b/docs/multi-gpu.html index 55dc38244..f4f9e4885 100644 --- a/docs/multi-gpu.html +++ b/docs/multi-gpu.html @@ -2,7 +2,7 @@ - + @@ -71,7 +71,7 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin - + @@ -596,21 +596,6 @@ Tip

Start from Stage 1 -> Stage 2 -> Stage 3.

-
-
-
- -
-
-Tip -
-
-
-

Using ZeRO Stage 3 with Single-GPU training

-

ZeRO Stage 3 can be used for training on a single GPU by manually setting the environment variables: -WORLD_SIZE=1 LOCAL_RANK=0 MASTER_ADDR=0.0.0.0 MASTER_PORT=29500

-
-
@@ -1292,132 +1277,123 @@ single sequence causes OOM errors during model training.

::: -::: {.callout-tip} +## Fully Sharded Data Parallel (FSDP) {#sec-fsdp} -Using ZeRO Stage 3 with Single-GPU training +::: {.callout-note} -ZeRO Stage 3 can be used for training on a single GPU by manually setting the environment variables: -`WORLD_SIZE=1 LOCAL_RANK=0 MASTER_ADDR=0.0.0.0 MASTER_PORT=29500` - -::: - -## Fully Sharded Data Parallel (FSDP) {#sec-fsdp} - -::: {.callout-note} +FSDP2 is recommended for new users. FSDP1 is deprecated and will be removed in an upcoming release of Axolotl. + +::: + +### Migrating from FSDP1 to FSDP2 {#sec-migrate-fsdp1-fsdp2} + +To migrate your config from FSDP1 to FSDP2, you must use the `fsdp_version` top-level config field to specify the FSDP version, and +also follow the config field mapping below to update field names. -FSDP2 is recommended for new users. FSDP1 is deprecated and will be removed in an upcoming release of Axolotl. +#### Config mapping -::: - -### Migrating from FSDP1 to FSDP2 {#sec-migrate-fsdp1-fsdp2} - -To migrate your config from FSDP1 to FSDP2, you must use the `fsdp_version` top-level config field to specify the FSDP version, and -also follow the config field mapping below to update field names. - -#### Config mapping - -FSDP1 | FSDP2 --------- | -------- -fsdp_sharding_strategy | reshard_after_forward -fsdp_backward_prefetch_policy | **REMOVED** -fsdp_backward_prefetch | **REMOVED** -fsdp_forward_prefetch | **REMOVED** -fsdp_sync_module_states | **REMOVED** -fsdp_cpu_ram_efficient_loading | cpu_ram_efficient_loading -fsdp_state_dict_type | state_dict_type -fsdp_use_orig_params | **REMOVED** - -For more details, please see the migration guide in the [torchtitan repo](https://github.com/pytorch/torchtitan/blob/main/docs/fsdp.md). In Axolotl, -if you were using the following FSDP1 config: - -```{.yaml} -fsdp_version: 1 -fsdp_config: - fsdp_offload_params: false - fsdp_cpu_ram_efficient_loading: true - fsdp_auto_wrap_policy: TRANSFORMER_BASED_WRAP - fsdp_transformer_layer_cls_to_wrap: Qwen3DecoderLayer - fsdp_state_dict_type: FULL_STATE_DICT - fsdp_sharding_strategy: FULL_SHARD -``` - -You can migrate to the following FSDP2 config: - -```{.yaml} -fsdp_version: 2 -fsdp_config: - offload_params: false - cpu_ram_efficient_loading: true - auto_wrap_policy: TRANSFORMER_BASED_WRAP - transformer_layer_cls_to_wrap: Qwen3DecoderLayer - state_dict_type: FULL_STATE_DICT - reshard_after_forward: true -``` - -### FSDP1 (deprecated) {#sec-fsdp-config} - -::: {.callout-note} - -Using `fsdp` to configure FSDP is deprecated and will be removed in an upcoming release of Axolotl. Please use `fsdp_config` as above instead. - -::: - -```{.yaml} -fsdp: - - full_shard - - auto_wrap -fsdp_config: - fsdp_offload_params: true - fsdp_state_dict_type: FULL_STATE_DICT - fsdp_transformer_layer_cls_to_wrap: LlamaDecoderLayer -``` - +FSDP1 | FSDP2 +-------- | -------- +fsdp_sharding_strategy | reshard_after_forward +fsdp_backward_prefetch_policy | **REMOVED** +fsdp_backward_prefetch | **REMOVED** +fsdp_forward_prefetch | **REMOVED** +fsdp_sync_module_states | **REMOVED** +fsdp_cpu_ram_efficient_loading | cpu_ram_efficient_loading +fsdp_state_dict_type | state_dict_type +fsdp_use_orig_params | **REMOVED** + +For more details, please see the migration guide in the [torchtitan repo](https://github.com/pytorch/torchtitan/blob/main/docs/fsdp.md). In Axolotl, +if you were using the following FSDP1 config: + +```{.yaml} +fsdp_version: 1 +fsdp_config: + fsdp_offload_params: false + fsdp_cpu_ram_efficient_loading: true + fsdp_auto_wrap_policy: TRANSFORMER_BASED_WRAP + fsdp_transformer_layer_cls_to_wrap: Qwen3DecoderLayer + fsdp_state_dict_type: FULL_STATE_DICT + fsdp_sharding_strategy: FULL_SHARD +``` + +You can migrate to the following FSDP2 config: + +```{.yaml} +fsdp_version: 2 +fsdp_config: + offload_params: false + cpu_ram_efficient_loading: true + auto_wrap_policy: TRANSFORMER_BASED_WRAP + transformer_layer_cls_to_wrap: Qwen3DecoderLayer + state_dict_type: FULL_STATE_DICT + reshard_after_forward: true +``` + +### FSDP1 (deprecated) {#sec-fsdp-config} + +::: {.callout-note} + +Using `fsdp` to configure FSDP is deprecated and will be removed in an upcoming release of Axolotl. Please use `fsdp_config` as above instead. + +::: + +```{.yaml} +fsdp: + - full_shard + - auto_wrap +fsdp_config: + fsdp_offload_params: true + fsdp_state_dict_type: FULL_STATE_DICT + fsdp_transformer_layer_cls_to_wrap: LlamaDecoderLayer +``` + + +## Sequence parallelism {#sec-sequence-parallelism} + +We support sequence parallelism (SP) via the +[ring-flash-attention](https://github.com/zhuzilin/ring-flash-attention) project. This +allows one to split up sequences across GPUs, which is useful in the event that a +single sequence causes OOM errors during model training. + +See our [dedicated guide](sequence_parallelism.qmd) for more information. -## Sequence parallelism {#sec-sequence-parallelism} +### FSDP + QLoRA {#sec-fsdp-qlora} -We support sequence parallelism (SP) via the -[ring-flash-attention](https://github.com/zhuzilin/ring-flash-attention) project. This -allows one to split up sequences across GPUs, which is useful in the event that a -single sequence causes OOM errors during model training. - -See our [dedicated guide](sequence_parallelism.qmd) for more information. - -### FSDP + QLoRA {#sec-fsdp-qlora} - -For combining FSDP with QLoRA, see our [dedicated guide](fsdp_qlora.qmd). - -## Performance Optimization {#sec-performance} - -### Liger Kernel Integration {#sec-liger} - -Please see [docs](custom_integrations.qmd#liger) for more info. - -## Troubleshooting {#sec-troubleshooting} - -### NCCL Issues {#sec-nccl} - -For NCCL-related problems, see our [NCCL troubleshooting guide](nccl.qmd). - -### Common Problems {#sec-common-problems} +For combining FSDP with QLoRA, see our [dedicated guide](fsdp_qlora.qmd). + +## Performance Optimization {#sec-performance} + +### Liger Kernel Integration {#sec-liger} + +Please see [docs](custom_integrations.qmd#liger) for more info. + +## Troubleshooting {#sec-troubleshooting} + +### NCCL Issues {#sec-nccl} + +For NCCL-related problems, see our [NCCL troubleshooting guide](nccl.qmd). + +### Common Problems {#sec-common-problems} + +::: {.panel-tabset} + +## Memory Issues + +- Reduce `micro_batch_size` +- Reduce `eval_batch_size` +- Adjust `gradient_accumulation_steps` +- Consider using a higher ZeRO stage -::: {.panel-tabset} +## Training Instability -## Memory Issues - -- Reduce `micro_batch_size` -- Reduce `eval_batch_size` -- Adjust `gradient_accumulation_steps` -- Consider using a higher ZeRO stage - -## Training Instability - -- Start with DeepSpeed ZeRO-2 -- Monitor loss values -- Check learning rates - -::: - -For more detailed troubleshooting, see our [debugging guide](debugging.qmd). +- Start with DeepSpeed ZeRO-2 +- Monitor loss values +- Check learning rates + +::: + +For more detailed troubleshooting, see our [debugging guide](debugging.qmd). diff --git a/docs/multi-node.html b/docs/multi-node.html index fab620293..3f9964f1f 100644 --- a/docs/multi-node.html +++ b/docs/multi-node.html @@ -2,7 +2,7 @@ - + @@ -72,7 +72,7 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin - + diff --git a/docs/multimodal.html b/docs/multimodal.html index 80f130ddf..18cb894a7 100644 --- a/docs/multimodal.html +++ b/docs/multimodal.html @@ -2,7 +2,7 @@ - + @@ -71,7 +71,7 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin - + diff --git a/docs/multipack.html b/docs/multipack.html index bbaa315a6..dbfd78c58 100644 --- a/docs/multipack.html +++ b/docs/multipack.html @@ -2,7 +2,7 @@ - + @@ -37,7 +37,7 @@ ul.task-list li input[type="checkbox"] { - + diff --git a/docs/nccl.html b/docs/nccl.html index b5264f298..93c681564 100644 --- a/docs/nccl.html +++ b/docs/nccl.html @@ -2,7 +2,7 @@ - + @@ -72,7 +72,7 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin - + diff --git a/docs/nd_parallelism.html b/docs/nd_parallelism.html index c9367943f..522e07cc9 100644 --- a/docs/nd_parallelism.html +++ b/docs/nd_parallelism.html @@ -2,7 +2,7 @@ - + @@ -71,7 +71,7 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin - + diff --git a/docs/optimizers.html b/docs/optimizers.html index bad461a1a..126c3ddae 100644 --- a/docs/optimizers.html +++ b/docs/optimizers.html @@ -2,7 +2,7 @@ - + @@ -72,7 +72,7 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin - + diff --git a/docs/qat.html b/docs/qat.html index b22aa1694..94169c27d 100644 --- a/docs/qat.html +++ b/docs/qat.html @@ -2,7 +2,7 @@ - + @@ -71,7 +71,7 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin - + diff --git a/docs/quantize.html b/docs/quantize.html index 0e37f68ea..3a0edee1f 100644 --- a/docs/quantize.html +++ b/docs/quantize.html @@ -2,7 +2,7 @@ - + @@ -71,7 +71,7 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin - + diff --git a/docs/ray-integration.html b/docs/ray-integration.html index ed12427ec..4cdc83a2e 100644 --- a/docs/ray-integration.html +++ b/docs/ray-integration.html @@ -2,7 +2,7 @@ - + @@ -72,7 +72,7 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin - + diff --git a/docs/reward_modelling.html b/docs/reward_modelling.html index 355cfefd0..c86c86c70 100644 --- a/docs/reward_modelling.html +++ b/docs/reward_modelling.html @@ -2,7 +2,7 @@ - + @@ -72,7 +72,7 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin - + diff --git a/docs/rlhf.html b/docs/rlhf.html index a05bc3a36..e50d1a594 100644 --- a/docs/rlhf.html +++ b/docs/rlhf.html @@ -2,7 +2,7 @@ - + @@ -72,7 +72,7 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin - + diff --git a/docs/sequence_parallelism.html b/docs/sequence_parallelism.html index 8a7306dee..e51a4d09a 100644 --- a/docs/sequence_parallelism.html +++ b/docs/sequence_parallelism.html @@ -2,7 +2,7 @@ - + @@ -72,7 +72,7 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin - + diff --git a/docs/torchao.html b/docs/torchao.html index 3a19483c5..673e65d98 100644 --- a/docs/torchao.html +++ b/docs/torchao.html @@ -2,7 +2,7 @@ - + @@ -72,7 +72,7 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin - + diff --git a/docs/unsloth.html b/docs/unsloth.html index ec34eb6a1..db3f55009 100644 --- a/docs/unsloth.html +++ b/docs/unsloth.html @@ -2,7 +2,7 @@ - + @@ -72,7 +72,7 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin - + diff --git a/examples/colab-notebooks/colab-axolotl-example.html b/examples/colab-notebooks/colab-axolotl-example.html index 6ea070c7c..c808c98d9 100644 --- a/examples/colab-notebooks/colab-axolotl-example.html +++ b/examples/colab-notebooks/colab-axolotl-example.html @@ -2,7 +2,7 @@ - + @@ -71,7 +71,7 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin - + diff --git a/index.html b/index.html index 0b4cfb8dd..9ecfe4c91 100644 --- a/index.html +++ b/index.html @@ -2,7 +2,7 @@ - + @@ -71,7 +71,7 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin - + diff --git a/search.json b/search.json index 45d395e97..343a56fc8 100644 --- a/search.json +++ b/search.json @@ -175,7 +175,7 @@ "href": "docs/multi-gpu.html#sec-deepspeed", "title": "Multi-GPU", "section": "2 DeepSpeed", - "text": "2 DeepSpeed\n\n2.1 Configuration\nAdd to your YAML config:\ndeepspeed: deepspeed_configs/zero1.json\n\n\n2.2 Usage\n# Fetch deepspeed configs (if not already present)\naxolotl fetch deepspeed_configs\n\n# Passing arg via config\naxolotl train config.yml\n\n# Passing arg via cli\naxolotl train config.yml --deepspeed deepspeed_configs/zero1.json\n\n\n2.3 ZeRO Stages\nWe provide default configurations for:\n\nZeRO Stage 1 (zero1.json)\nZeRO Stage 1 with torch compile (zero1_torch_compile.json)\nZeRO Stage 2 (zero2.json)\nZeRO Stage 3 (zero3.json)\nZeRO Stage 3 with bf16 (zero3_bf16.json)\nZeRO Stage 3 with bf16 and CPU offload params(zero3_bf16_cpuoffload_params.json)\nZeRO Stage 3 with bf16 and CPU offload params and optimizer (zero3_bf16_cpuoffload_all.json)\n\n\n\n\n\n\n\nTip\n\n\n\nChoose the configuration that offloads the least amount to memory while still being able to fit on VRAM for best performance.\nStart from Stage 1 -> Stage 2 -> Stage 3.\n\n\n\n\n\n\n\n\nTip\n\n\n\nUsing ZeRO Stage 3 with Single-GPU training\nZeRO Stage 3 can be used for training on a single GPU by manually setting the environment variables:\nWORLD_SIZE=1 LOCAL_RANK=0 MASTER_ADDR=0.0.0.0 MASTER_PORT=29500", + "text": "2 DeepSpeed\n\n2.1 Configuration\nAdd to your YAML config:\ndeepspeed: deepspeed_configs/zero1.json\n\n\n2.2 Usage\n# Fetch deepspeed configs (if not already present)\naxolotl fetch deepspeed_configs\n\n# Passing arg via config\naxolotl train config.yml\n\n# Passing arg via cli\naxolotl train config.yml --deepspeed deepspeed_configs/zero1.json\n\n\n2.3 ZeRO Stages\nWe provide default configurations for:\n\nZeRO Stage 1 (zero1.json)\nZeRO Stage 1 with torch compile (zero1_torch_compile.json)\nZeRO Stage 2 (zero2.json)\nZeRO Stage 3 (zero3.json)\nZeRO Stage 3 with bf16 (zero3_bf16.json)\nZeRO Stage 3 with bf16 and CPU offload params(zero3_bf16_cpuoffload_params.json)\nZeRO Stage 3 with bf16 and CPU offload params and optimizer (zero3_bf16_cpuoffload_all.json)\n\n\n\n\n\n\n\nTip\n\n\n\nChoose the configuration that offloads the least amount to memory while still being able to fit on VRAM for best performance.\nStart from Stage 1 -> Stage 2 -> Stage 3.", "crumbs": [ "Deployments", "Multi-GPU" diff --git a/site_libs/quarto-html/quarto-syntax-highlighting-dark-bc185b5c5bdbcb35c2eb49d8a876ef70.css b/site_libs/quarto-html/quarto-syntax-highlighting-dark-befe23ebd2f54d8af2c8a89d1a1611f1.css similarity index 98% rename from site_libs/quarto-html/quarto-syntax-highlighting-dark-bc185b5c5bdbcb35c2eb49d8a876ef70.css rename to site_libs/quarto-html/quarto-syntax-highlighting-dark-befe23ebd2f54d8af2c8a89d1a1611f1.css index 2a884823a..a6ae06a82 100644 --- a/site_libs/quarto-html/quarto-syntax-highlighting-dark-bc185b5c5bdbcb35c2eb49d8a876ef70.css +++ b/site_libs/quarto-html/quarto-syntax-highlighting-dark-befe23ebd2f54d8af2c8a89d1a1611f1.css @@ -216,4 +216,4 @@ code span.wa { content: " https://docs.axolotl.ai/examples/colab-notebooks/colab-axolotl-example.html - 2025-08-28T13:10:49.902Z + 2025-08-29T17:52:59.100Z https://docs.axolotl.ai/src/axolotl/integrations/LICENSE.html - 2025-08-28T13:10:49.918Z + 2025-08-29T17:52:59.117Z https://docs.axolotl.ai/FAQS.html - 2025-08-28T13:10:49.892Z + 2025-08-29T17:52:59.090Z https://docs.axolotl.ai/docs/unsloth.html - 2025-08-28T13:10:49.898Z + 2025-08-29T17:52:59.096Z https://docs.axolotl.ai/docs/reward_modelling.html - 2025-08-28T13:10:49.898Z + 2025-08-29T17:52:59.096Z https://docs.axolotl.ai/docs/docker.html - 2025-08-28T13:10:49.894Z + 2025-08-29T17:52:59.092Z https://docs.axolotl.ai/docs/batch_vs_grad.html - 2025-08-28T13:10:49.894Z + 2025-08-29T17:52:59.092Z https://docs.axolotl.ai/docs/torchao.html - 2025-08-28T13:10:49.898Z + 2025-08-29T17:52:59.096Z https://docs.axolotl.ai/docs/dataset_preprocessing.html - 2025-08-28T13:10:49.894Z + 2025-08-29T17:52:59.092Z https://docs.axolotl.ai/docs/multi-gpu.html - 2025-08-28T13:10:49.897Z + 2025-08-29T17:52:59.095Z https://docs.axolotl.ai/docs/optimizers.html - 2025-08-28T13:10:49.898Z + 2025-08-29T17:52:59.096Z https://docs.axolotl.ai/docs/getting-started.html - 2025-08-28T13:10:49.894Z + 2025-08-29T17:52:59.092Z https://docs.axolotl.ai/docs/ray-integration.html - 2025-08-28T13:10:49.898Z + 2025-08-29T17:52:59.096Z https://docs.axolotl.ai/docs/input_output.html - 2025-08-28T13:10:49.897Z + 2025-08-29T17:52:59.095Z https://docs.axolotl.ai/docs/multi-node.html - 2025-08-28T13:10:49.897Z + 2025-08-29T17:52:59.095Z https://docs.axolotl.ai/docs/api/train.html - 2025-08-28T13:13:52.510Z + 2025-08-29T17:56:24.493Z https://docs.axolotl.ai/docs/api/prompt_strategies.kto.user_defined.html - 2025-08-28T13:13:53.188Z + 2025-08-29T17:56:25.159Z https://docs.axolotl.ai/docs/api/common.datasets.html - 2025-08-28T13:13:53.860Z + 2025-08-29T17:56:25.814Z https://docs.axolotl.ai/docs/api/prompt_strategies.stepwise_supervised.html - 2025-08-28T13:13:53.121Z + 2025-08-29T17:56:25.093Z https://docs.axolotl.ai/docs/api/cli.utils.args.html - 2025-08-28T13:13:52.851Z + 2025-08-29T17:56:24.828Z https://docs.axolotl.ai/docs/api/prompt_strategies.bradley_terry.llama3.html - 2025-08-28T13:13:53.212Z + 2025-08-29T17:56:25.183Z https://docs.axolotl.ai/docs/api/utils.schemas.peft.html - 2025-08-28T13:13:53.642Z + 2025-08-29T17:56:25.601Z https://docs.axolotl.ai/docs/api/prompt_strategies.messages.chat.html - 2025-08-28T13:13:53.143Z + 2025-08-29T17:56:25.115Z https://docs.axolotl.ai/docs/api/integrations.lm_eval.args.html - 2025-08-28T13:13:53.838Z + 2025-08-29T17:56:25.793Z https://docs.axolotl.ai/docs/api/cli.train.html - 2025-08-28T13:13:52.711Z + 2025-08-29T17:56:24.690Z https://docs.axolotl.ai/docs/api/utils.trainer.html - 2025-08-28T13:13:53.494Z + 2025-08-29T17:56:25.457Z https://docs.axolotl.ai/docs/api/core.datasets.transforms.chat_builder.html - 2025-08-28T13:13:52.668Z + 2025-08-29T17:56:24.648Z https://docs.axolotl.ai/docs/api/utils.callbacks.comet_.html - 2025-08-28T13:13:53.950Z + 2025-08-29T17:56:25.903Z https://docs.axolotl.ai/docs/api/prompt_tokenizers.html - 2025-08-28T13:13:52.589Z + 2025-08-29T17:56:24.570Z https://docs.axolotl.ai/docs/api/prompt_strategies.dpo.chat_template.html - 2025-08-28T13:13:53.145Z + 2025-08-29T17:56:25.116Z https://docs.axolotl.ai/docs/api/core.trainers.utils.html - 2025-08-28T13:13:52.944Z + 2025-08-29T17:56:24.919Z https://docs.axolotl.ai/docs/api/loaders.processor.html - 2025-08-28T13:13:52.964Z + 2025-08-29T17:56:24.938Z https://docs.axolotl.ai/docs/api/core.trainers.mixins.optimizer.html - 2025-08-28T13:13:52.987Z + 2025-08-29T17:56:24.961Z https://docs.axolotl.ai/docs/api/monkeypatch.data.batch_dataset_fetcher.html - 2025-08-28T13:13:53.415Z + 2025-08-29T17:56:25.380Z https://docs.axolotl.ai/docs/api/utils.callbacks.lisa.html - 2025-08-28T13:13:53.943Z + 2025-08-29T17:56:25.896Z https://docs.axolotl.ai/docs/api/kernels.utils.html - 2025-08-28T13:13:53.333Z + 2025-08-29T17:56:25.299Z https://docs.axolotl.ai/docs/api/cli.preprocess.html - 2025-08-28T13:13:52.816Z + 2025-08-29T17:56:24.793Z https://docs.axolotl.ai/docs/api/integrations.liger.args.html - 2025-08-28T13:13:53.834Z + 2025-08-29T17:56:25.789Z https://docs.axolotl.ai/docs/api/utils.collators.core.html - 2025-08-28T13:13:53.862Z + 2025-08-29T17:56:25.816Z https://docs.axolotl.ai/docs/api/cli.utils.load.html - 2025-08-28T13:13:52.862Z + 2025-08-29T17:56:24.839Z https://docs.axolotl.ai/docs/api/cli.utils.train.html - 2025-08-28T13:13:52.880Z + 2025-08-29T17:56:24.856Z https://docs.axolotl.ai/docs/api/core.trainers.grpo.sampler.html - 2025-08-28T13:13:52.943Z + 2025-08-29T17:56:24.917Z https://docs.axolotl.ai/docs/api/utils.callbacks.mlflow_.html - 2025-08-28T13:13:53.947Z + 2025-08-29T17:56:25.899Z https://docs.axolotl.ai/docs/api/utils.freeze.html - 2025-08-28T13:13:53.477Z + 2025-08-29T17:56:25.440Z https://docs.axolotl.ai/docs/api/kernels.geglu.html - 2025-08-28T13:13:53.313Z + 2025-08-29T17:56:25.280Z https://docs.axolotl.ai/docs/api/prompt_strategies.dpo.zephyr.html - 2025-08-28T13:13:53.167Z + 2025-08-29T17:56:25.138Z https://docs.axolotl.ai/docs/api/prompt_strategies.llama2_chat.html - 2025-08-28T13:13:53.105Z + 2025-08-29T17:56:25.077Z https://docs.axolotl.ai/docs/api/cli.config.html - 2025-08-28T13:13:52.768Z + 2025-08-29T17:56:24.745Z https://docs.axolotl.ai/docs/api/kernels.quantize.html - 2025-08-28T13:13:53.331Z + 2025-08-29T17:56:25.298Z https://docs.axolotl.ai/docs/api/monkeypatch.lora_kernels.html - 2025-08-28T13:13:53.377Z + 2025-08-29T17:56:25.343Z https://docs.axolotl.ai/docs/api/common.const.html - 2025-08-28T13:13:53.844Z + 2025-08-29T17:56:25.799Z https://docs.axolotl.ai/docs/api/integrations.cut_cross_entropy.args.html - 2025-08-28T13:13:53.822Z + 2025-08-29T17:56:25.777Z https://docs.axolotl.ai/docs/api/prompt_strategies.alpaca_w_system.html - 2025-08-28T13:13:53.084Z + 2025-08-29T17:56:25.056Z https://docs.axolotl.ai/docs/api/prompt_strategies.chat_template.html - 2025-08-28T13:13:53.057Z + 2025-08-29T17:56:25.029Z https://docs.axolotl.ai/docs/api/utils.schemas.datasets.html - 2025-08-28T13:13:53.633Z + 2025-08-29T17:56:25.592Z https://docs.axolotl.ai/docs/api/core.training_args.html - 2025-08-28T13:13:52.627Z + 2025-08-29T17:56:24.608Z https://docs.axolotl.ai/docs/api/prompt_strategies.orpo.chat_template.html - 2025-08-28T13:13:53.209Z + 2025-08-29T17:56:25.179Z https://docs.axolotl.ai/docs/api/cli.utils.html - 2025-08-28T13:13:52.839Z + 2025-08-29T17:56:24.816Z https://docs.axolotl.ai/docs/api/common.architectures.html - 2025-08-28T13:13:53.843Z + 2025-08-29T17:56:25.797Z https://docs.axolotl.ai/docs/api/core.trainers.grpo.trainer.html - 2025-08-28T13:13:52.930Z + 2025-08-29T17:56:24.905Z https://docs.axolotl.ai/docs/api/prompt_strategies.completion.html - 2025-08-28T13:13:53.111Z + 2025-08-29T17:56:25.083Z https://docs.axolotl.ai/docs/api/utils.collators.batching.html - 2025-08-28T13:13:53.882Z + 2025-08-29T17:56:25.835Z https://docs.axolotl.ai/docs/api/kernels.lora.html - 2025-08-28T13:13:53.303Z + 2025-08-29T17:56:25.270Z https://docs.axolotl.ai/docs/api/utils.schedulers.html - 2025-08-28T13:13:53.523Z + 2025-08-29T17:56:25.484Z https://docs.axolotl.ai/docs/api/monkeypatch.relora.html - 2025-08-28T13:13:53.347Z + 2025-08-29T17:56:25.313Z https://docs.axolotl.ai/docs/api/monkeypatch.transformers_fa_utils.html - 2025-08-28T13:13:53.404Z + 2025-08-29T17:56:25.369Z https://docs.axolotl.ai/docs/api/loaders.constants.html - 2025-08-28T13:13:52.981Z + 2025-08-29T17:56:24.955Z https://docs.axolotl.ai/docs/api/prompt_strategies.alpaca_instruct.html - 2025-08-28T13:13:53.072Z + 2025-08-29T17:56:25.044Z https://docs.axolotl.ai/docs/api/cli.merge_lora.html - 2025-08-28T13:13:52.796Z + 2025-08-29T17:56:24.773Z https://docs.axolotl.ai/docs/api/core.chat.messages.html - 2025-08-28T13:13:52.651Z + 2025-08-29T17:56:24.631Z https://docs.axolotl.ai/docs/api/monkeypatch.llama_patch_multipack.html - 2025-08-28T13:13:53.388Z + 2025-08-29T17:56:25.354Z https://docs.axolotl.ai/docs/api/monkeypatch.mixtral.html - 2025-08-28T13:13:53.416Z + 2025-08-29T17:56:25.381Z https://docs.axolotl.ai/docs/api/utils.schemas.trl.html - 2025-08-28T13:13:53.645Z + 2025-08-29T17:56:25.604Z https://docs.axolotl.ai/docs/api/core.builders.causal.html - 2025-08-28T13:13:52.609Z + 2025-08-29T17:56:24.591Z https://docs.axolotl.ai/docs/api/cli.utils.fetch.html - 2025-08-28T13:13:52.857Z + 2025-08-29T17:56:24.833Z https://docs.axolotl.ai/docs/api/monkeypatch.utils.html - 2025-08-28T13:13:53.385Z + 2025-08-29T17:56:25.351Z https://docs.axolotl.ai/docs/api/utils.chat_templates.html - 2025-08-28T13:13:53.455Z + 2025-08-29T17:56:25.419Z https://docs.axolotl.ai/docs/api/utils.data.sft.html - 2025-08-28T13:13:53.565Z + 2025-08-29T17:56:25.526Z https://docs.axolotl.ai/docs/api/monkeypatch.mistral_attn_hijack_flash.html - 2025-08-28T13:13:53.342Z + 2025-08-29T17:56:25.308Z https://docs.axolotl.ai/docs/api/utils.callbacks.qat.html - 2025-08-28T13:13:53.957Z + 2025-08-29T17:56:25.910Z https://docs.axolotl.ai/docs/api/cli.checks.html - 2025-08-28T13:13:52.749Z + 2025-08-29T17:56:24.727Z https://docs.axolotl.ai/docs/api/utils.schemas.utils.html - 2025-08-28T13:13:53.680Z + 2025-08-29T17:56:25.638Z https://docs.axolotl.ai/docs/api/utils.schemas.integrations.html - 2025-08-28T13:13:53.663Z + 2025-08-29T17:56:25.622Z https://docs.axolotl.ai/docs/api/utils.schemas.training.html - 2025-08-28T13:13:53.615Z + 2025-08-29T17:56:25.574Z https://docs.axolotl.ai/docs/api/integrations.grokfast.optimizer.html - 2025-08-28T13:13:53.823Z + 2025-08-29T17:56:25.778Z https://docs.axolotl.ai/docs/api/monkeypatch.llama_attn_hijack_flash.html - 2025-08-28T13:13:53.339Z + 2025-08-29T17:56:25.305Z https://docs.axolotl.ai/docs/api/utils.model_shard_quant.html - 2025-08-28T13:13:53.465Z + 2025-08-29T17:56:25.429Z https://docs.axolotl.ai/docs/api/utils.collators.mm_chat.html - 2025-08-28T13:13:53.890Z + 2025-08-29T17:56:25.843Z https://docs.axolotl.ai/docs/api/cli.inference.html - 2025-08-28T13:13:52.787Z + 2025-08-29T17:56:24.764Z https://docs.axolotl.ai/docs/api/monkeypatch.trainer_fsdp_optim.html - 2025-08-28T13:13:53.397Z + 2025-08-29T17:56:25.363Z https://docs.axolotl.ai/docs/amd_hpc.html - 2025-08-28T13:10:49.893Z + 2025-08-29T17:52:59.091Z https://docs.axolotl.ai/docs/multipack.html - 2025-08-28T13:10:49.897Z + 2025-08-29T17:52:59.095Z https://docs.axolotl.ai/docs/lora_optims.html - 2025-08-28T13:10:49.897Z + 2025-08-29T17:52:59.095Z https://docs.axolotl.ai/docs/inference.html - 2025-08-28T13:10:49.897Z + 2025-08-29T17:52:59.095Z https://docs.axolotl.ai/docs/lr_groups.html - 2025-08-28T13:10:49.897Z + 2025-08-29T17:52:59.095Z https://docs.axolotl.ai/docs/dataset-formats/inst_tune.html - 2025-08-28T13:10:49.894Z + 2025-08-29T17:52:59.092Z https://docs.axolotl.ai/docs/dataset-formats/conversation.html - 2025-08-28T13:10:49.894Z + 2025-08-29T17:52:59.092Z https://docs.axolotl.ai/docs/dataset-formats/index.html - 2025-08-28T13:10:49.894Z + 2025-08-29T17:52:59.092Z https://docs.axolotl.ai/docs/dataset-formats/template_free.html - 2025-08-28T13:10:49.894Z + 2025-08-29T17:52:59.092Z https://docs.axolotl.ai/docs/dataset-formats/pretraining.html - 2025-08-28T13:10:49.894Z + 2025-08-29T17:52:59.092Z https://docs.axolotl.ai/docs/dataset-formats/stepwise_supervised.html - 2025-08-28T13:10:49.894Z + 2025-08-29T17:52:59.092Z https://docs.axolotl.ai/docs/dataset-formats/tokenized.html - 2025-08-28T13:10:49.894Z + 2025-08-29T17:52:59.092Z https://docs.axolotl.ai/docs/faq.html - 2025-08-28T13:10:49.894Z + 2025-08-29T17:52:59.092Z https://docs.axolotl.ai/docs/sequence_parallelism.html - 2025-08-28T13:10:49.898Z + 2025-08-29T17:52:59.096Z https://docs.axolotl.ai/docs/mac.html - 2025-08-28T13:10:49.897Z + 2025-08-29T17:52:59.095Z https://docs.axolotl.ai/docs/installation.html - 2025-08-28T13:10:49.897Z + 2025-08-29T17:52:59.095Z https://docs.axolotl.ai/docs/mixed_precision.html - 2025-08-28T13:10:49.897Z + 2025-08-29T17:52:59.095Z https://docs.axolotl.ai/docs/api/core.trainers.trl.html - 2025-08-28T13:13:52.907Z + 2025-08-29T17:56:24.882Z https://docs.axolotl.ai/docs/api/cli.cloud.base.html - 2025-08-28T13:13:52.832Z + 2025-08-29T17:56:24.808Z https://docs.axolotl.ai/docs/api/core.chat.format.chatml.html - 2025-08-28T13:13:52.652Z + 2025-08-29T17:56:24.632Z https://docs.axolotl.ai/docs/api/monkeypatch.multipack.html - 2025-08-28T13:13:53.343Z + 2025-08-29T17:56:25.309Z https://docs.axolotl.ai/docs/api/utils.ctx_managers.sequence_parallel.html - 2025-08-28T13:13:53.021Z + 2025-08-29T17:56:24.995Z https://docs.axolotl.ai/docs/api/cli.main.html - 2025-08-28T13:13:52.703Z + 2025-08-29T17:56:24.682Z https://docs.axolotl.ai/docs/api/utils.schemas.multimodal.html - 2025-08-28T13:13:53.651Z + 2025-08-29T17:56:25.610Z https://docs.axolotl.ai/docs/api/kernels.swiglu.html - 2025-08-28T13:13:53.324Z + 2025-08-29T17:56:25.290Z https://docs.axolotl.ai/docs/api/prompt_strategies.dpo.user_defined.html - 2025-08-28T13:13:53.168Z + 2025-08-29T17:56:25.139Z https://docs.axolotl.ai/docs/api/core.trainers.mixins.rng_state_loader.html - 2025-08-28T13:13:52.990Z + 2025-08-29T17:56:24.964Z https://docs.axolotl.ai/docs/api/prompt_strategies.user_defined.html - 2025-08-28T13:13:53.092Z + 2025-08-29T17:56:25.064Z https://docs.axolotl.ai/docs/api/utils.lora.html - 2025-08-28T13:13:53.460Z + 2025-08-29T17:56:25.424Z https://docs.axolotl.ai/docs/api/prompt_strategies.pygmalion.html - 2025-08-28T13:13:53.139Z + 2025-08-29T17:56:25.110Z https://docs.axolotl.ai/docs/api/loaders.tokenizer.html - 2025-08-28T13:13:52.962Z + 2025-08-29T17:56:24.937Z https://docs.axolotl.ai/docs/api/utils.callbacks.perplexity.html - 2025-08-28T13:13:53.938Z + 2025-08-29T17:56:25.891Z https://docs.axolotl.ai/docs/api/monkeypatch.llama_attn_hijack_xformers.html - 2025-08-28T13:13:53.340Z + 2025-08-29T17:56:25.306Z https://docs.axolotl.ai/docs/api/utils.optimizers.adopt.html - 2025-08-28T13:13:53.557Z + 2025-08-29T17:56:25.517Z https://docs.axolotl.ai/docs/api/loaders.patch_manager.html - 2025-08-28T13:13:52.979Z + 2025-08-29T17:56:24.954Z https://docs.axolotl.ai/docs/api/core.trainers.mixins.scheduler.html - 2025-08-28T13:13:52.997Z + 2025-08-29T17:56:24.971Z https://docs.axolotl.ai/docs/api/monkeypatch.unsloth_.html - 2025-08-28T13:13:53.405Z + 2025-08-29T17:56:25.371Z https://docs.axolotl.ai/docs/api/prompt_strategies.base.html - 2025-08-28T13:13:53.022Z + 2025-08-29T17:56:24.996Z https://docs.axolotl.ai/docs/api/utils.data.pretraining.html - 2025-08-28T13:13:53.558Z + 2025-08-29T17:56:25.519Z https://docs.axolotl.ai/docs/api/monkeypatch.btlm_attn_hijack_flash.html - 2025-08-28T13:13:53.387Z + 2025-08-29T17:56:25.352Z https://docs.axolotl.ai/docs/api/prompt_strategies.alpaca_chat.html - 2025-08-28T13:13:53.070Z + 2025-08-29T17:56:25.043Z https://docs.axolotl.ai/docs/api/core.trainers.mamba.html - 2025-08-28T13:13:52.912Z + 2025-08-29T17:56:24.888Z https://docs.axolotl.ai/docs/api/utils.samplers.multipack.html - 2025-08-28T13:13:53.931Z + 2025-08-29T17:56:25.884Z https://docs.axolotl.ai/docs/api/utils.bench.html - 2025-08-28T13:13:53.469Z + 2025-08-29T17:56:25.433Z https://docs.axolotl.ai/docs/api/utils.callbacks.profiler.html - 2025-08-28T13:13:53.942Z + 2025-08-29T17:56:25.894Z https://docs.axolotl.ai/docs/api/utils.schemas.enums.html - 2025-08-28T13:13:53.674Z + 2025-08-29T17:56:25.632Z https://docs.axolotl.ai/docs/api/models.mamba.modeling_mamba.html - 2025-08-28T13:13:53.861Z + 2025-08-29T17:56:25.815Z https://docs.axolotl.ai/docs/api/core.chat.format.shared.html - 2025-08-28T13:13:52.655Z + 2025-08-29T17:56:24.635Z https://docs.axolotl.ai/docs/api/logging_config.html - 2025-08-28T13:13:52.598Z + 2025-08-29T17:56:24.580Z https://docs.axolotl.ai/docs/api/loaders.model.html - 2025-08-28T13:13:52.954Z + 2025-08-29T17:56:24.929Z https://docs.axolotl.ai/docs/api/monkeypatch.llama_expand_mask.html - 2025-08-28T13:13:53.348Z + 2025-08-29T17:56:25.314Z https://docs.axolotl.ai/docs/api/core.trainers.base.html - 2025-08-28T13:13:52.891Z + 2025-08-29T17:56:24.867Z https://docs.axolotl.ai/docs/api/utils.tokenization.html - 2025-08-28T13:13:53.453Z + 2025-08-29T17:56:25.417Z https://docs.axolotl.ai/docs/api/prompt_strategies.kto.llama3.html - 2025-08-28T13:13:53.178Z + 2025-08-29T17:56:25.149Z https://docs.axolotl.ai/docs/api/convert.html - 2025-08-28T13:13:52.546Z + 2025-08-29T17:56:24.528Z https://docs.axolotl.ai/docs/api/datasets.html - 2025-08-28T13:13:52.532Z + 2025-08-29T17:56:24.515Z https://docs.axolotl.ai/docs/api/utils.collators.mamba.html - 2025-08-28T13:13:53.885Z + 2025-08-29T17:56:25.839Z https://docs.axolotl.ai/docs/api/prompt_strategies.orcamini.html - 2025-08-28T13:13:53.132Z + 2025-08-29T17:56:25.104Z https://docs.axolotl.ai/docs/api/utils.schemas.config.html - 2025-08-28T13:13:53.601Z + 2025-08-29T17:56:25.560Z https://docs.axolotl.ai/docs/api/core.trainers.dpo.trainer.html - 2025-08-28T13:13:52.919Z + 2025-08-29T17:56:24.894Z https://docs.axolotl.ai/docs/api/utils.dict.html - 2025-08-28T13:13:53.549Z + 2025-08-29T17:56:25.510Z https://docs.axolotl.ai/docs/api/utils.quantization.html - 2025-08-28T13:13:53.586Z + 2025-08-29T17:56:25.546Z https://docs.axolotl.ai/docs/api/monkeypatch.gradient_checkpointing.offload_disk.html - 2025-08-28T13:13:53.446Z + 2025-08-29T17:56:25.410Z https://docs.axolotl.ai/docs/api/index.html - 2025-08-28T13:13:52.452Z + 2025-08-29T17:56:24.435Z https://docs.axolotl.ai/docs/api/integrations.base.html - 2025-08-28T13:13:53.819Z + 2025-08-29T17:56:25.774Z https://docs.axolotl.ai/docs/api/utils.distributed.html - 2025-08-28T13:13:53.543Z + 2025-08-29T17:56:25.504Z https://docs.axolotl.ai/docs/api/core.datasets.chat.html - 2025-08-28T13:13:52.660Z + 2025-08-29T17:56:24.641Z https://docs.axolotl.ai/docs/api/prompt_strategies.dpo.passthrough.html - 2025-08-28T13:13:53.170Z + 2025-08-29T17:56:25.141Z https://docs.axolotl.ai/docs/api/prompt_strategies.metharme.html - 2025-08-28T13:13:53.128Z + 2025-08-29T17:56:25.100Z https://docs.axolotl.ai/docs/api/prompt_strategies.dpo.chatml.html - 2025-08-28T13:13:53.165Z + 2025-08-29T17:56:25.136Z https://docs.axolotl.ai/docs/api/core.builders.rl.html - 2025-08-28T13:13:52.614Z + 2025-08-29T17:56:24.595Z https://docs.axolotl.ai/docs/api/cli.utils.sweeps.html - 2025-08-28T13:13:52.868Z + 2025-08-29T17:56:24.844Z https://docs.axolotl.ai/docs/api/cli.quantize.html - 2025-08-28T13:13:52.821Z + 2025-08-29T17:56:24.798Z https://docs.axolotl.ai/docs/api/cli.vllm_serve.html - 2025-08-28T13:13:52.828Z + 2025-08-29T17:56:24.805Z https://docs.axolotl.ai/docs/api/prompt_strategies.input_output.html - 2025-08-28T13:13:53.117Z + 2025-08-29T17:56:25.089Z https://docs.axolotl.ai/docs/api/evaluate.html - 2025-08-28T13:13:52.521Z + 2025-08-29T17:56:24.504Z https://docs.axolotl.ai/docs/api/monkeypatch.gradient_checkpointing.offload_cpu.html - 2025-08-28T13:13:53.420Z + 2025-08-29T17:56:25.384Z https://docs.axolotl.ai/docs/api/cli.args.html - 2025-08-28T13:13:52.740Z + 2025-08-29T17:56:24.718Z https://docs.axolotl.ai/docs/api/prompt_strategies.kto.chatml.html - 2025-08-28T13:13:53.186Z + 2025-08-29T17:56:25.157Z https://docs.axolotl.ai/docs/api/core.chat.format.llama3x.html - 2025-08-28T13:13:52.654Z + 2025-08-29T17:56:24.634Z https://docs.axolotl.ai/docs/api/prompt_strategies.dpo.llama3.html - 2025-08-28T13:13:53.155Z + 2025-08-29T17:56:25.126Z https://docs.axolotl.ai/docs/api/cli.art.html - 2025-08-28T13:13:52.743Z + 2025-08-29T17:56:24.721Z https://docs.axolotl.ai/docs/api/utils.schemas.model.html - 2025-08-28T13:13:53.608Z + 2025-08-29T17:56:25.567Z https://docs.axolotl.ai/docs/api/cli.evaluate.html - 2025-08-28T13:13:52.720Z + 2025-08-29T17:56:24.699Z https://docs.axolotl.ai/docs/api/cli.delinearize_llama4.html - 2025-08-28T13:13:52.773Z + 2025-08-29T17:56:24.750Z https://docs.axolotl.ai/docs/api/integrations.kd.trainer.html - 2025-08-28T13:13:53.831Z + 2025-08-29T17:56:25.786Z https://docs.axolotl.ai/docs/api/monkeypatch.stablelm_attn_hijack_flash.html - 2025-08-28T13:13:53.394Z + 2025-08-29T17:56:25.359Z https://docs.axolotl.ai/docs/api/cli.cloud.modal_.html - 2025-08-28T13:13:52.838Z + 2025-08-29T17:56:24.815Z https://docs.axolotl.ai/docs/api/cli.merge_sharded_fsdp_weights.html - 2025-08-28T13:13:52.808Z + 2025-08-29T17:56:24.785Z https://docs.axolotl.ai/docs/api/core.builders.base.html - 2025-08-28T13:13:52.605Z + 2025-08-29T17:56:24.586Z https://docs.axolotl.ai/docs/api/loaders.adapter.html - 2025-08-28T13:13:52.970Z + 2025-08-29T17:56:24.944Z https://docs.axolotl.ai/docs/api/integrations.spectrum.args.html - 2025-08-28T13:13:53.841Z + 2025-08-29T17:56:25.796Z https://docs.axolotl.ai/docs/dataset_loading.html - 2025-08-28T13:10:49.894Z + 2025-08-29T17:52:59.092Z https://docs.axolotl.ai/docs/multimodal.html - 2025-08-28T13:10:49.897Z + 2025-08-29T17:52:59.095Z https://docs.axolotl.ai/docs/gradient_checkpointing.html - 2025-08-28T13:10:49.894Z + 2025-08-29T17:52:59.092Z https://docs.axolotl.ai/docs/debugging.html - 2025-08-28T13:10:49.894Z + 2025-08-29T17:52:59.092Z https://docs.axolotl.ai/docs/custom_integrations.html - 2025-08-28T13:10:49.894Z + 2025-08-29T17:52:59.092Z https://docs.axolotl.ai/docs/nd_parallelism.html - 2025-08-28T13:10:49.898Z + 2025-08-29T17:52:59.096Z https://docs.axolotl.ai/docs/quantize.html - 2025-08-28T13:10:49.898Z + 2025-08-29T17:52:59.096Z https://docs.axolotl.ai/docs/nccl.html - 2025-08-28T13:10:49.898Z + 2025-08-29T17:52:59.096Z https://docs.axolotl.ai/docs/config-reference.html - 2025-08-28T13:14:07.393Z + 2025-08-29T17:56:40.104Z https://docs.axolotl.ai/docs/rlhf.html - 2025-08-28T13:10:49.898Z + 2025-08-29T17:52:59.096Z https://docs.axolotl.ai/docs/cli.html - 2025-08-28T13:10:49.894Z + 2025-08-29T17:52:59.092Z https://docs.axolotl.ai/docs/fsdp_qlora.html - 2025-08-28T13:10:49.894Z + 2025-08-29T17:52:59.092Z https://docs.axolotl.ai/docs/qat.html - 2025-08-28T13:10:49.898Z + 2025-08-29T17:52:59.096Z https://docs.axolotl.ai/src/axolotl/integrations/cut_cross_entropy/ACKNOWLEDGEMENTS.html - 2025-08-28T13:10:49.918Z + 2025-08-29T17:52:59.117Z https://docs.axolotl.ai/index.html - 2025-08-28T13:10:49.913Z + 2025-08-29T17:52:59.112Z diff --git a/src/axolotl/integrations/LICENSE.html b/src/axolotl/integrations/LICENSE.html index 524b5d7d3..9ad6bf121 100644 --- a/src/axolotl/integrations/LICENSE.html +++ b/src/axolotl/integrations/LICENSE.html @@ -2,7 +2,7 @@ - + @@ -36,7 +36,7 @@ ul.task-list li input[type="checkbox"] { - + diff --git a/src/axolotl/integrations/cut_cross_entropy/ACKNOWLEDGEMENTS.html b/src/axolotl/integrations/cut_cross_entropy/ACKNOWLEDGEMENTS.html index b0834de4b..ca49ad9f9 100644 --- a/src/axolotl/integrations/cut_cross_entropy/ACKNOWLEDGEMENTS.html +++ b/src/axolotl/integrations/cut_cross_entropy/ACKNOWLEDGEMENTS.html @@ -2,7 +2,7 @@ - + @@ -36,7 +36,7 @@ ul.task-list li input[type="checkbox"] { - +