supervised fine-tuning

Related topics

• Full fine-tuning is part of supervised fine-tuning From the official documentation: “- **Supervised fine-tuning:** - [Full fine-tuning](/gemini-enterprise-agent-platform/models/tuning#tuning-approaches) - Low-Rank Adaptation (LoRA): LoRA is a [parameter-efficient tuning](/gemini-enterprise-agent-platform/models/tuning#tuning-approaches) mode that only adjust…”
• low-rank adaptation is part of supervised fine-tuning From the official documentation: “- **Supervised fine-tuning:** - [Full fine-tuning](/gemini-enterprise-agent-platform/models/tuning#tuning-approaches) - Low-Rank Adaptation (LoRA): LoRA is a [parameter-efficient tuning](/gemini-enterprise-agent-platform/models/tuning#tuning-approaches) mode that only adjust…”
• Provisioned Throughput works with supervised fine-tuning From the official documentation: “Provisioned Throughput can be applied to both base models and supervised fine-tuned versions of those base models.”
• supervised fine-tuning is part of Gemini Enterprise Agent Platform From the official documentation: “Agent Platform supports supervised fine-tuning to customize foundational models.”
• Cloud Monitoring works with Gemini Enterprise Agent Platform From the official documentation: “Gemini Enterprise Agent Platform exports metrics to [Cloud Monitoring](/monitoring/docs).”
• Cloud Monitoring works with Provisioned Throughput From the official documentation: “The following Cloud Monitoring metrics are available on the `aiplatform.googleapis.com/PublisherModel` resource for the Gemini models. Use the `dedicated` request types to filter for Provisioned Throughput usage.”
• Full fine-tuning is an alternative to low-rank adaptation From the official documentation: “Low-Rank Adaptation (LoRA): LoRA is a [parameter-efficient tuning](/gemini-enterprise-agent-platform/models/tuning#tuning-approaches) mode that only adjust subset of parameters. It's more cost efficient and require less training data than full fine-tuning. On the other hand…”
• Full fine-tuning is an alternative to PEFT From the official documentation: “Instead of adjusting all of a model's billions of parameters (full fine-tuning), use parameter-efficient fine-tuning (PEFT) methods like low-rank adaptation (LoRA).”
• low-rank adaptation is part of PEFT From the official documentation: “Instead of adjusting all of a model's billions of parameters (full fine-tuning), use parameter-efficient fine-tuning (PEFT) methods like low-rank adaptation (LoRA).”
• Provisioned Throughput works with Standard PayGo From the official documentation: “By default, traffic that exceeds your Provisioned Throughput baseline (called *spillover traffic*) is handled by [Standard PayGo](/gemini-enterprise-agent-platform/models/standard-paygo).”
• Standard PayGo is part of Gemini Enterprise Agent Platform From the official documentation: “For the default pay-as-you-go model, Agent Platform uses [Standard pay-as-you-go (Standard PayGo)](/gemini-enterprise-agent-platform/models/standard-paygo).”