In this example we will go through the steps required for fine-tuning foundation models on Amazon SageMaker by using @remote decorator for executing SageMaker Training jobs.
You can run this repository from Amazon SageMaker Studio or from your local IDE.
For additional information, take a look at the AWS Blog Fine-tune Falcon 7B and other LLMs on Amazon SageMaker with @remote decorator
This notebook is inspired by Philipp Schmid Blogs
The notebooks are currently using the latest HuggingFace Training Container available for the region us-east-1
. If you are running the notebooks in a different region, make sure to update the ImageUri in the file config.yaml.
- Navigate [Available Deep Learning Containers Images](Available Deep Learning Containers Images)
- Select the right Hugging Face TGI container for model training based on your selected region
- Update ImageUri in the file config.yaml
The dataset is the content of all AWS FAQ pages, downloaded from: https://aws.amazon.com/faqs/
service | question | answers |
---|---|---|
/ec2/autoscaling/faqs/ | What is Amazon EC2 Auto Scaling? | Amazon EC2 Auto Scaling is a fully managed ser... |
/ec2/autoscaling/faqs/ | When should I use Amazon EC2 Auto Scaling vs. ... | You should use AWS Auto Scaling to manage scal... |
/ec2/autoscaling/faqs/ | How is Predictive Scaling Policy different fro... | Predictive Scaling Policy brings the similar p... |
/ec2/autoscaling/faqs/ | What are the benefits of using Amazon EC2 Auto... | Amazon EC2 Auto Scaling helps to maintain your... |
The synthetic dataset is the content of official AWS Generative AI Blogs
question | answers |
---|---|
What new Anthropic model is now available on Amazon Bedrock? | Claude 2.1 foundation model is now available on Amazon Bedrock. |
What are the two types of model evaluation available in Amazon Bedrock? | Amazon Bedrock offers a choice of automatic evaluation and human evaluation. |
What kind of metrics can you use for automatic evaluation? | You can use automatic evaluation with predefined metrics such as accuracy, robustness, and toxicity. |
What does Guardrails for Amazon Bedrock allow developers to do? | Guardrails for Amazon Bedrock (preview) to promote safe interactions between users and your generative AI applications by implementing safeguards customized to your use cases and responsible AI policies. |
- [Supervised - Q&A] Falcon-7B
- [Supervised - Q&A] Llama-13B
- [Self-supervised - chat] Llama-13B
- [Self-supervised - Instruct] Mistral-7B
- [Supervised - Instruct] Mixtral-8x7B
- [Supervised - Instruct] Code-Llama 13B
- [Supervised - Instruct] Llama-3 8B
- [Supervised - Instruct] Llama-3.1 8B
- [Supervised - Instruct] Arcee AI Llama-3.1 Supernova Lite
- [Supervised - Instruct] Llama-3.2 1B
- [Supervised - Instruct] Llama-3.2 3B