AWS nova documentation change
Summary
Updated links from absolute URLs to relative paths and changed section title from 'Distillation' to 'Preparing data for multimodal fine-tuning'
Security assessment
Changes involve documentation restructuring and link formatting without any security-related content, vulnerability fixes, or security feature descriptions. No evidence of security implications.
Diff
diff --git a/nova/latest/userguide/nova-fine-tune-1.md b/nova/latest/userguide/nova-fine-tune-1.md index dd83587c7..767f71e5d 100644 --- a//nova/latest/userguide/nova-fine-tune-1.md +++ b//nova/latest/userguide/nova-fine-tune-1.md @@ -32 +32 @@ Preparing high-quality, properly formatted data is a critical first step in the -SFT data format requirements - For both full-rank SFT and LoRA SFT, data should follow the format shown below. For examples and constraints of this format, see [Preparing data for fine-tuning Understanding models](https://docs.aws.amazon.com//nova/latest/userguide/fine-tune-prepare-data-understanding.html). +SFT data format requirements - For both full-rank SFT and LoRA SFT, data should follow the format shown below. For examples and constraints of this format, see [Preparing data for multimodal fine-tuning](./fine-tune-prepare-data-understanding.html). @@ -40 +40 @@ DPO data format requirements - For both DPO in full-rank and DPO with LoRA, data -DPO dataset other constraints - Other constraints on datasets are the same for SFT. For more information, see [Dataset constraints](https://docs.aws.amazon.com//nova/latest/userguide/fine-tune-prepare-data-understanding.html). A single JSONL file for training and a single JSONL file for validation is expected. Validation set is optional. +DPO dataset other constraints - Other constraints on datasets are the same for SFT. For more information, see [Preparing data for multimodal fine-tuning](./fine-tune-prepare-data-understanding.html). A single JSONL file for training and a single JSONL file for validation is expected. Validation set is optional. @@ -495 +495 @@ Nova Forge SDK -Distillation +Preparing data for multimodal fine-tuning