corpus.blog
41554 blogs · [ { "id": "01a087c2-4503-712d-b220-aa8f19114a49", "title": "Train and Deploy Mistral 7B with Hugging Face on Amazon SageMaker", "url": "https://www.philschmid.de/sagemaker-mistral", "published_at": "2023-10-05T00:00:00+00:00" }, { "id": "01a087c2-4503-712d-b220-aa8f19b774f5", "title": "Llama 2 on Amazon SageMaker a Benchmark", "url": "https://www.philschmid.de/sagemaker-llama-benchmark", "published_at": "2023-09-26T00:00:00+00:00" }, { "id": "01a087c2-4503-712d-b220-aa8f1a0a2a12", "title": "Fine-tune Falcon 180B with DeepSpeed ZeRO, LoRA and Flash Attention", "url": "https://www.philschmid.de/deepspeed-lora-flash-attention", "published_at": "2023-09-20T00:00:00+00:00" }, { "id": "01a087c2-4503-712d-b220-aa8f1a53625e", "title": "Fine-tune Falcon 180B with QLoRA and Flash Attention on Amazon SageMaker", "url": "https://www.philschmid.de/sagemaker-falcon-180b-qlora", "published_at": "2023-09-12T00:00:00+00:00" }, { "id": "01a087c2-4503-712d-b220-aa8f1a5a8d5b", "title": "Deploy Falcon 180B on Amazon SageMaker", "url": "https://www.philschmid.de/sagemaker-falcon-180b", "published_at": "2023-09-07T00:00:00+00:00" }, { "id": "01a087c2-4503-712d-b220-aa8f1b3e9a39", "title": "Optimize open LLMs using GPTQ and Hugging Face Optimum", "url": "https://www.philschmid.de/gptq-llama", "published_at": "2023-08-31T00:00:00+00:00" }, { "id": "01a087c2-4503-712d-b220-aa8f1be9d0e3", "title": "LLMOps: Deploy Open LLMs using Infrastructure as Code with AWS CDK", "url": "https://www.philschmid.de/cdk-llama2", "published_at": "2023-08-15T00:00:00+00:00" }, { "id": "01a087c2-4503-712d-b220-aa8f1c8c88ae", "title": "Deploy Llama 2 7B/13B/70B on Amazon SageMaker", "url": "https://www.philschmid.de/sagemaker-llama-llm", "published_at": "2023-08-07T00:00:00+00:00" }, { "id": "01a087c2-4503-712d-b220-aa8f1d7c7aea", "title": "Introducing EasyLLM - streamline open LLMs", "url": "https://www.philschmid.de/introducing-easyllm", "published_at": "2023-08-03T00:00:00+00:00" }, { "id": "01a087c2-4503-712d-b220-aa8f1d86fdec", "title": "Extended Guide: Instruction-tune Llama 2", "url": "https://www.philschmid.de/instruction-tune-llama-2", "published_at": "2023-07-26T00:00:00+00:00" }, { "id": "01a087c2-4503-712d-b220-aa8f1e5b716a", "title": "LLaMA 2 - Every Resource you need", "url": "https://www.philschmid.de/llama-2", "published_at": "2023-07-21T00:00:00+00:00" }, { "id": "01a087c2-4503-712d-b220-aa8f1ef40df5", "title": "Fine-tune LLaMA 2 (7-70B) on Amazon SageMaker", "url": "https://www.philschmid.de/sagemaker-llama2-qlora", "published_at": "2023-07-18T00:00:00+00:00" }, { "id": "01a087c2-4503-712d-b220-aa8f1f5eadf0", "title": "Train LLMs using QLoRA on Amazon SageMaker", "url": "https://www.philschmid.de/sagemaker-falcon-qlora", "published_at": "2023-07-13T00:00:00+00:00" }, { "id": "01a087c2-4503-712d-b220-aa8f205be7ce", "title": "Deploy LLMs with Hugging Face Inference Endpoints", "url": "https://www.philschmid.de/endpoints-llm", "published_at": "2023-07-04T00:00:00+00:00" }, { "id": "01a087c2-4503-712d-b220-aa8f2097412c", "title": "Optimize and Deploy BERT on AWS inferentia2", "url": "https://www.philschmid.de/optimize-deploy-bert-inf2", "published_at": "2023-06-28T00:00:00+00:00" }, { "id": "01a087c2-4503-712d-b220-aa8f20977aa9", "title": "Securely deploy LLMs inside VPCs with Hugging Face and Amazon SageMaker", "url": "https://www.philschmid.de/sagemaker-llm-vpc", "published_at": "2023-06-20T00:00:00+00:00" }, { "id": "01a087c2-4503-712d-b220-aa8f219560aa", "title": "Deploy Falcon 7B and 40B on Amazon SageMaker", "url": "https://www.philschmid.de/sagemaker-falcon-llm", "published_at": "2023-06-07T00:00:00+00:00" }, { "id": "01a087c2-4503-712d-b220-aa8f226e2243", "title": "Fine-tune BERT for Text Classification on AWS Trainium", "url": "https://www.philschmid.de/getting-started-trainium", "published_at": "2023-06-06T00:00:00+00:00" }, { "id": "01a087c2-4503-712d-b220-aa8f23662d9a", "title": "Introducing the Hugging Face LLM Inference Container for Amazon SageMaker", "url": "https://www.philschmid.de/sagemaker-huggingface-llm", "published_at": "2023-05-31T00:00:00+00:00" }, { "id": "01a087c2-4503-712d-b220-aa8f2436c816", "title": "Generative AI for Document Understanding with Hugging Face and Amazon SageMaker", "url": "https://www.philschmid.de/sagemaker-donut", "published_at": "2023-05-23T00:00:00+00:00" }, { "id": "01a087c2-4503-712d-b220-aa8f252c0c8a", "title": "How to scale LLM workloads to 20B+ with Amazon SageMaker using Hugging Face and PyTorch FSDP", "url": "https://www.philschmid.de/sagemaker-fsdp-gpt", "published_at": "2023-05-02T00:00:00+00:00" }, { "id": "01a087c2-4503-712d-b220-aa8f259ddd56", "title": "Setting up AWS Trainium for Hugging Face Transformers", "url": "https://www.philschmid.de/setup-aws-trainium", "published_at": "2023-04-25T00:00:00+00:00" }, { "id": "01a087c2-4503-712d-b220-aa8f26178418", "title": "Train and Deploy BLOOM with Amazon SageMaker and PEFT", "url": "https://www.philschmid.de/bloom-sagemaker-peft", "published_at": "2023-04-13T00:00:00+00:00" }, { "id": "01a087c2-4503-712d-b220-aa8f26a17b54", "title": "Introducing IGEL an instruction-tuned German large Language Model", "url": "https://www.philschmid.de/introducing-igel", "published_at": "2023-04-04T00:00:00+00:00" }, { "id": "01a087c2-4503-712d-b220-aa8f26f651b4", "title": "Efficient Large Language Model training with LoRA and Hugging Face", "url": "https://www.philschmid.de/fine-tune-flan-t5-peft", "published_at": "2023-03-23T00:00:00+00:00" }, { "id": "01a087c2-4503-712d-b220-aa8f273cf72c", "title": "Deploy FLAN-UL2 20B on Amazon SageMaker", "url": "https://www.philschmid.de/deploy-flan-ul2-sagemaker", "published_at": "2023-03-20T00:00:00+00:00" }, { "id": "01a087c2-4503-712d-b220-aa8f27dbed4b", "title": "Getting started with Pytorch 2.0 and Hugging Face Transformers", "url": "https://www.philschmid.de/getting-started-pytorch-2-0-transformers", "published_at": "2023-03-16T00:00:00+00:00" }, { "id": "01a087c2-4503-712d-b220-aa8f287e62ac", "title": "Controlled text-to-image generation with ControlNet on Inference Endpoints", "url": "https://www.philschmid.de/stable-diffusion-controlnet-endpoint", "published_at": "2023-03-03T00:00:00+00:00" }, { "id": "01a087c2-4503-712d-b220-aa8f2959628b", "title": "Combine Amazon SageMaker and DeepSpeed to fine-tune FLAN-T5 XXL", "url": "https://www.philschmid.de/sagemaker-deepspeed", "published_at": "2023-02-22T00:00:00+00:00" }, { "id": "01a087c2-4503-712d-b220-aa8f2996e149", "title": "Fine-tune FLAN-T5 XL/XXL using DeepSpeed and Hugging Face Transformers", "url": "https://www.philschmid.de/fine-tune-flan-t5-deepspeed", "published_at": "2023-02-16T00:00:00+00:00" }, { "id": "01a087c2-4503-712d-b220-aa8f2a40e8c7", "title": "Deploy FLAN-T5 XXL on Amazon SageMaker", "url": "https://www.philschmid.de/deploy-flan-t5-sagemaker", "published_at": "2023-02-08T00:00:00+00:00" }, { "id": "01a087c2-4503-712d-b220-aa8f2a8c8059", "title": "Hugging Face Transformers Examples", "url": "https://www.philschmid.de/huggingface-transformers-examples", "published_at": "2023-01-26T00:00:00+00:00" }, { "id": "01a087c2-4503-712d-b220-aa8f2b4c489d", "title": "Getting started with Transformers and TPU using PyTorch", "url": "https://www.philschmid.de/getting-started-tpu-transformers", "published_at": "2023-01-16T00:00:00+00:00" }, { "id": "01a087c2-4503-712d-b220-aa8f2c2ae387", "title": "Fine-tune FLAN-T5 for chat and dialogue summarization", "url": "https://www.philschmid.de/fine-tune-flan-t5", "published_at": "2022-12-27T00:00:00+00:00" }, { "id": "01a087c2-4503-712d-b220-aa8f2c383f43", "title": "Managed Transcription with OpenAI Whisper and Hugging Face Inference Endpoints", "url": "https://www.philschmid.de/whisper-inference-endpoints", "published_at": "2022-12-20T00:00:00+00:00" }, { "id": "01a087c2-4503-712d-b220-aa8f2cd1c082", "title": "Stable Diffusion Inpainting example with Hugging Face inference Endpoints", "url": "https://www.philschmid.de/stable-diffusion-inpainting-inference-endpoints", "published_at": "2022-12-15T00:00:00+00:00" }, { "id": "01a087c2-4503-712d-b220-aa8f2dc48393", "title": "Stable Diffusion with Hugging Face Inference Endpoints", "url": "https://www.philschmid.de/stable-diffusion-inference-endpoints", "published_at": "2022-11-28T00:00:00+00:00" }, { "id": "01a087c2-4503-712d-b220-aa8f2ead9090", "title": "Document AI: LiLT a better language agnostic LayoutLM model", "url": "https://www.philschmid.de/fine-tuning-lilt", "published_at": "2022-11-22T00:00:00+00:00" }, { "id": "01a087c2-4503-712d-b220-aa8f2eb7ca9a", "title": "Multi-Model GPU Inference with Hugging Face Inference Endpoints", "url": "https://www.philschmid.de/multi-model-inference-endpoints", "published_at": "2022-11-17T00:00:00+00:00" }, { "id": "01a087c2-4503-712d-b220-aa8f2f4b8462", "title": "Serverless Machine Learning Applications with Hugging Face Gradio and AWS Lambda", "url": "https://www.philschmid.de/serverless-gradio", "published_at": "2022-11-15T00:00:00+00:00" }, { "id": "01a087c2-4503-712d-b220-aa8f302f9d65", "title": "Accelerate Stable Diffusion inference with DeepSpeed-Inference on GPUs", "url": "https://www.philschmid.de/stable-diffusion-deepspeed-inference", "published_at": "2022-11-08T00:00:00+00:00" }, { "id": "01a087c2-4503-712d-b220-aa8f304183ac", "title": "Stable Diffusion on Amazon SageMaker", "url": "https://www.philschmid.de/sagemaker-stable-diffusion", "published_at": "2022-11-01T00:00:00+00:00" }, { "id": "01a087c2-4503-712d-b220-aa8f30b94d45", "title": "Deploy T5 11B for inference for less than $500", "url": "https://www.philschmid.de/deploy-t5-11b", "published_at": "2022-10-25T00:00:00+00:00" }, { "id": "01a087c2-4503-712d-b220-aa8f31a79b01", "title": "Outperform OpenAI GPT-3 with SetFit for text-classification", "url": "https://www.philschmid.de/getting-started-setfit", "published_at": "2022-10-18T00:00:00+00:00" }, { "id": "01a087c2-4503-712d-b220-aa8f3282520b", "title": "Fine-tuning LayoutLM for document-understanding using Keras and Hugging Face Transformers", "url": "https://www.philschmid.de/fine-tuning-layoutlm-keras", "published_at": "2022-10-13T00:00:00+00:00" }, { "id": "01a087c2-4503-712d-b220-aa8f32ff835e", "title": "Deploy LayoutLM with Hugging Face Inference Endpoints", "url": "https://www.philschmid.de/inference-endpoints-layoutlm", "published_at": "2022-10-06T00:00:00+00:00" }, { "id": "01a087c2-4503-712d-b220-aa8f333e753d", "title": "Document AI: Fine-tuning LayoutLM for document-understanding using Hugging Face Transformers", "url": "https://www.philschmid.de/fine-tuning-layoutlm", "published_at": "2022-10-04T00:00:00+00:00" }, { "id": "01a087c2-4503-712d-b220-aa8f33b40b3f", "title": "Custom Inference with Hugging Face Inference Endpoints", "url": "https://www.philschmid.de/custom-inference-handler", "published_at": "2022-09-29T00:00:00+00:00" }, { "id": "01a087c2-4503-712d-b220-aa8f3418c8bd", "title": "Accelerate GPT-J inference with DeepSpeed-Inference on GPUs", "url": "https://www.philschmid.de/gptj-deepspeed-inference", "published_at": "2022-09-13T00:00:00+00:00" }, { "id": "01a087c2-4503-712d-b220-aa8f35113448", "title": "Document AI: Fine-tuning Donut for document-parsing using Hugging Face Transformers", "url": "https://www.philschmid.de/fine-tuning-donut", "published_at": "2022-09-06T00:00:00+00:00" }, { "id": "01a087c2-4503-712d-b220-aa8f35abdfe0", "title": "Use Sentence Transformers with TensorFlow", "url": "https://www.philschmid.de/tensorflow-sentence-transformers", "published_at": "2022-08-30T00:00:00+00:00" }, { "id": "01a087c2-4503-712d-b220-aa8f35f25960", "title": "Pre-Training BERT with Hugging Face Transformers and Habana Gaudi", "url": "https://www.philschmid.de/pre-training-bert-habana", "published_at": "2022-08-24T00:00:00+00:00" }, { "id": "01a087c2-4503-712d-b220-aa8f3628e238", "title": "Accelerate BERT inference with DeepSpeed-Inference on GPUs", "url": "https://www.philschmid.de/bert-deepspeed-inference", "published_at": "2022-08-16T00:00:00+00:00" }, { "id": "01a087c2-4503-712d-b220-aa8f36bb11c8", "title": "Accelerate Sentence Transformers with Hugging Face Optimum", "url": "https://www.philschmid.de/optimize-sentence-transformers", "published_at": "2022-08-02T00:00:00+00:00" }, { "id": "01a087c2-4503-712d-b220-aa8f376f6f20", "title": "Deep Learning setup made easy with EC2 Remote Runner and Habana Gaudi", "url": "https://www.philschmid.de/habana-gaudi-ec2-runner", "published_at": "2022-07-26T00:00:00+00:00" }, { "id": "01a087c2-4503-712d-b220-aa8f37b406a3", "title": "Accelerate Vision Transformer (ViT) with Quantization using Optimum", "url": "https://www.philschmid.de/optimizing-vision-transformer", "published_at": "2022-07-19T00:00:00+00:00" }, { "id": "01a087c2-4503-712d-b220-aa8f3834f46f", "title": "Optimizing Transformers for GPUs with Optimum", "url": "https://www.philschmid.de/optimizing-transformers-with-optimum-gpu", "published_at": "2022-07-13T00:00:00+00:00" }, { "id": "01a087c2-4503-712d-b220-aa8f389b821d", "title": "Hugging Face Transformers and Habana Gaudi AWS DL1 Instances", "url": "https://www.philschmid.de/habana-distributed-training", "published_at": "2022-07-05T00:00:00+00:00" }, { "id": "01a087c2-4503-712d-b220-aa8f38d7a447", "title": "Optimizing Transformers with Hugging Face Optimum", "url": "https://www.philschmid.de/optimizing-transformers-with-optimum", "published_at": "2022-06-30T00:00:00+00:00" }, { "id": "01a087c2-4503-712d-b220-aa8f39574fe6", "title": "Convert Transformers to ONNX with Hugging Face Optimum", "url": "https://www.philschmid.de/convert-transformers-to-onnx", "published_at": "2022-06-21T00:00:00+00:00" }, { "id": "01a087c2-4503-712d-b220-aa8f39627d5b", "title": "Setup Deep Learning environment for Hugging Face Transformers with Habana Gaudi on AWS", "url": "https://www.philschmid.de/getting-started-habana-gaudi", "published_at": "2022-06-14T00:00:00+00:00" }, { "id": "01a087c2-4503-712d-b220-aa8f39b6775e", "title": "Static Quantization with Hugging Face `optimum` for ~3x latency improvements", "url": "https://www.philschmid.de/static-quantization-optimum", "published_at": "2022-06-07T00:00:00+00:00" }, { "id": "01a087c2-4503-712d-b220-aa8f3a2d9967", "title": "Advanced PII detection and anonymization with Hugging Face Transformers and Amazon SageMaker", "url": "https://www.philschmid.de/pii-huggingface-sagemaker", "published_at": "2022-05-31T00:00:00+00:00" }, { "id": "01a087c2-4503-712d-b220-aa8f3aad0e05", "title": "An Amazon SageMaker Inference comparison with Hugging Face Transformers", "url": "https://www.philschmid.de/sagemaker-inference-comparison", "published_at": "2022-05-17T00:00:00+00:00" }, { "id": "01a087c2-4504-70f4-a3e8-24c930c249df", "title": "Semantic Segmantion with Hugging Face's Transformers and Amazon SageMaker", "url": "https://www.philschmid.de/image-segmentation-sagemaker", "published_at": "2022-05-03T00:00:00+00:00" }, { "id": "01a087c2-4504-70f4-a3e8-24c930de2eef", "title": "Automatic Speech Recogntion with Hugging Face's Transformers and Amazon SageMaker", "url": "https://www.philschmid.de/automatic-speech-recognition-sagemaker", "published_at": "2022-04-28T00:00:00+00:00" }, { "id": "01a087c2-4504-70f4-a3e8-24c93123d76b", "title": "Serverless Inference with Hugging Face's Transformers, DistilBERT and Amazon SageMaker", "url": "https://www.philschmid.de/sagemaker-serverless-huggingface-distilbert", "published_at": "2022-04-21T00:00:00+00:00" }, { "id": "01a087c2-4504-70f4-a3e8-24c931dae110", "title": "Accelerated document embeddings with Hugging Face Transformers and AWS Inferentia", "url": "https://www.philschmid.de/huggingface-sentence-transformers-aws-inferentia", "published_at": "2022-04-19T00:00:00+00:00" }, { "id": "01a087c2-4504-70f4-a3e8-24c932607c96", "title": "Save up to 90% training cost with AWS Spot Instances and Hugging Face Transformers", "url": "https://www.philschmid.de/sagemaker-spot-instance", "published_at": "2022-03-22T00:00:00+00:00" }, { "id": "01a087c2-4504-70f4-a3e8-24c9331e7e91", "title": "Speed up BERT inference with Hugging Face Transformers and AWS Inferentia", "url": "https://www.philschmid.de/huggingface-bert-aws-inferentia", "published_at": "2022-03-16T00:00:00+00:00" }, { "id": "01a087c2-4504-70f4-a3e8-24c933a2b0fb", "title": "Creating document embeddings with Hugging Face's Transformers and Amazon SageMaker", "url": "https://www.philschmid.de/custom-inference-huggingface-sagemaker", "published_at": "2022-03-08T00:00:00+00:00" }, { "id": "01a087c2-4504-70f4-a3e8-24c9349e6650", "title": "Autoscaling BERT with Hugging Face Transformers, Amazon SageMaker and Terraform module", "url": "https://www.philschmid.de/terraform-huggingface-amazon-sagemaker-advanced", "published_at": "2022-03-01T00:00:00+00:00" }, { "id": "01a087c2-4504-70f4-a3e8-24c93520fde3", "title": "Multi-Container Endpoints with Hugging Face Transformers and Amazon SageMaker", "url": "https://www.philschmid.de/sagemaker-huggingface-multi-container-endpoint", "published_at": "2022-02-22T00:00:00+00:00" }, { "id": "01a087c2-4504-70f4-a3e8-24c935608bbd", "title": "Asynchronous Inference with Hugging Face Transformers and Amazon SageMaker", "url": "https://www.philschmid.de/sagemaker-huggingface-async-inference", "published_at": "2022-02-15T00:00:00+00:00" }, { "id": "01a087c2-4504-70f4-a3e8-24c936065553", "title": "Deploy BERT with Hugging Face Transformers, Amazon SageMaker and Terraform module", "url": "https://www.philschmid.de/terraform-huggingface-amazon-sagemaker", "published_at": "2022-02-08T00:00:00+00:00" }, { "id": "01a087c2-4504-70f4-a3e8-24c936f0ed6b", "title": "Task-specific knowledge distillation for BERT using Transformers and Amazon SageMaker", "url": "https://www.philschmid.de/knowledge-distillation-bert-transformers", "published_at": "2022-02-01T00:00:00+00:00" }, { "id": "01a087c2-4504-70f4-a3e8-24c9379f1d5a", "title": "Distributed training on multilingual BERT with Hugging Face Transformers and Amazon SageMaker", "url": "https://www.philschmid.de/pytorch-distributed-training-transformers", "published_at": "2022-01-25T00:00:00+00:00" }, { "id": "01a087c2-4504-70f4-a3e8-24c9382d453f", "title": "Financial Text Summarization with Hugging Face Transformers, Keras and Amazon SageMaker", "url": "https://www.philschmid.de/financial-summarizatio-huggingface-keras", "published_at": "2022-01-19T00:00:00+00:00" }, { "id": "01a087c2-4504-70f4-a3e8-24c938c23627", "title": "Deploy GPT-J 6B for inference using Hugging Face Transformers and Amazon SageMaker", "url": "https://www.philschmid.de/deploy-gptj-sagemaker", "published_at": "2022-01-11T00:00:00+00:00" }, { "id": "01a087c2-4504-70f4-a3e8-24c938e8c611", "title": "Image Classification with Hugging Face Transformers and `Keras`", "url": "https://www.philschmid.de/image-classification-huggingface-transformers-keras", "published_at": "2022-01-04T00:00:00+00:00" }, { "id": "01a087c2-4504-70f4-a3e8-24c9397595c9", "title": "Workshop: Enterprise-Scale NLP with Hugging Face and Amazon SageMaker", "url": "https://www.philschmid.de/hugginface-sagemaker-workshop", "published_at": "2021-12-29T00:00:00+00:00" }, { "id": "01a087c2-4504-70f4-a3e8-24c9398a4cc0", "title": "Hugging Face Transformers with Keras: Fine-tune a non-English BERT for Named Entity Recognition", "url": "https://www.philschmid.de/huggingface-transformers-keras-tf", "published_at": "2021-12-21T00:00:00+00:00" }, { "id": "01a087c2-4504-70f4-a3e8-24c939db0938", "title": "New Serverless Transformers using Amazon SageMaker Serverless Inference and Hugging Face", "url": "https://www.philschmid.de/serverless-transformers-sagemaker-huggingface", "published_at": "2021-12-15T00:00:00+00:00" }, { "id": "01a087c2-4504-70f4-a3e8-24c93a7c756e", "title": "Hugging Face Transformers BERT fine-tuning using Amazon SageMaker and Training Compiler", "url": "https://www.philschmid.de/huggingface-amazon-sagemaker-training-compiler", "published_at": "2021-12-07T00:00:00+00:00" }, { "id": "01a087c2-4504-70f4-a3e8-24c93b1c338f", "title": "MLOps: Using the Hugging Face Hub as model registry with Amazon SageMaker", "url": "https://www.philschmid.de/huggingface-hub-amazon-sagemaker", "published_at": "2021-11-16T00:00:00+00:00" }, { "id": "01a087c2-4504-70f4-a3e8-24c93b66be3c", "title": "A remote guide to re:Invent 2021 machine learning sessions", "url": "https://www.philschmid.de/re-invent-2021", "published_at": "2021-11-11T00:00:00+00:00" }, { "id": "01a087c2-4504-70f4-a3e8-24c93c351a92", "title": "MLOps: End-to-End Hugging Face Transformers with the Hub and SageMaker Pipelines", "url": "https://www.philschmid.de/mlops-sagemaker-huggingface-transformers", "published_at": "2021-11-10T00:00:00+00:00" }, { "id": "01a087c2-4504-70f4-a3e8-24c93cb96656", "title": "Going Production: Auto-scaling Hugging Face Transformers with Amazon SageMaker", "url": "https://www.philschmid.de/auto-scaling-sagemaker-huggingface", "published_at": "2021-10-29T00:00:00+00:00" }, { "id": "01a087c2-4504-70f4-a3e8-24c93d2bf075", "title": "Deploy BigScience T0_3B to AWS and Amazon SageMaker", "url": "https://www.philschmid.de/deploy-bigscience-t0-3b-to-aws-and-amazon-sagemaker", "published_at": "2021-10-20T00:00:00+00:00" }, { "id": "01a087c2-4504-70f4-a3e8-24c93d6c4151", "title": "Scalable, Secure Hugging Face Transformer Endpoints with Amazon SageMaker, AWS Lambda, and CDK", "url": "https://www.philschmid.de/huggingface-transformers-cdk-sagemaker-lambda", "published_at": "2021-10-06T00:00:00+00:00" }, { "id": "01a087c2-4504-70f4-a3e8-24c93e4be1a2", "title": "Few-shot learning in practice with GPT-Neo", "url": "https://www.philschmid.de/few-shot-learning-gpt-neo", "published_at": "2021-06-05T00:00:00+00:00" }, { "id": "01a087c2-4504-70f4-a3e8-24c93e7dfa3f", "title": "Distributed Training: Train BART/T5 for Summarization using 🤗 Transformers and Amazon SageMaker", "url": "https://www.philschmid.de/sagemaker-distributed-training", "published_at": "2021-04-09T00:00:00+00:00" }, { "id": "01a087c2-4504-70f4-a3e8-24c93f608e5b", "title": "Multilingual Serverless XLM RoBERTa with HuggingFace, AWS Lambda", "url": "https://www.philschmid.de/multilingual-serverless-xlm-roberta-with-huggingface", "published_at": "2020-12-17T00:00:00+00:00" }, { "id": "01a087c2-4504-70f4-a3e8-24c93fc9bd39", "title": "Serverless BERT with HuggingFace, AWS Lambda, and Docker", "url": "https://www.philschmid.de/serverless-bert-with-huggingface-aws-lambda-docker", "published_at": "2020-12-06T00:00:00+00:00" }, { "id": "01a087c2-4504-70f4-a3e8-24c93fcb7f61", "title": "AWS Lambda with custom docker images as runtime", "url": "https://www.philschmid.de/aws-lambda-with-custom-docker-image", "published_at": "2020-12-02T00:00:00+00:00" }, { "id": "01a087c2-4504-70f4-a3e8-24c93fe35354", "title": "New Serverless BERT with Huggingface, AWS Lambda, and AWS EFS", "url": "https://www.philschmid.de/new-serverless-bert-with-huggingface-aws-lambda", "published_at": "2020-11-15T00:00:00+00:00" }, { "id": "01a087c2-4504-70f4-a3e8-24c940146a7a", "title": "efsync my first open-source MLOps toolkit", "url": "https://www.philschmid.de/efsync-my-first-open-source-mlops-toolkit", "published_at": "2020-11-04T00:00:00+00:00" }, { "id": "01a087c2-4504-70f4-a3e8-24c9410223d6", "title": "My path to become a certified solution architect", "url": "https://www.philschmid.de/my-path-to-become-a-certified-solution-architect", "published_at": "2020-10-24T00:00:00+00:00" }, { "id": "01a087c2-4504-70f4-a3e8-24c941d506e9", "title": "Create custom Github Action in 4 steps", "url": "https://www.philschmid.de/create-custom-github-action-in-4-steps", "published_at": "2020-09-25T00:00:00+00:00" }, { "id": "01a087c2-4504-70f4-a3e8-24c94216ce4a", "title": "Fine-tune a non-English GPT-2 Model with Huggingface", "url": "https://www.philschmid.de/fine-tune-a-non-english-gpt-2-model-with-huggingface", "published_at": "2020-09-06T00:00:00+00:00" } ] posts Claim your blog
Back to philschmid.de
Blog · corpus.blog/blogs/philschmid.de/posts

philschmid.de

philschmid.de

2023

Train and Deploy Mistral 7B with Hugging Face on Amazon SageMakeroriginal ↗
5 Oct 2023
Llama 2 on Amazon SageMaker a Benchmarkoriginal ↗
26 Sept 2023
Fine-tune Falcon 180B with DeepSpeed ZeRO, LoRA and Flash Attentionoriginal ↗
20 Sept 2023
Fine-tune Falcon 180B with QLoRA and Flash Attention on Amazon SageMakeroriginal ↗
12 Sept 2023
Deploy Falcon 180B on Amazon SageMakeroriginal ↗
7 Sept 2023
Optimize open LLMs using GPTQ and Hugging Face Optimumoriginal ↗
31 Aug 2023
LLMOps: Deploy Open LLMs using Infrastructure as Code with AWS CDKoriginal ↗
15 Aug 2023
Deploy Llama 2 7B/13B/70B on Amazon SageMakeroriginal ↗
7 Aug 2023
Introducing EasyLLM - streamline open LLMsoriginal ↗
3 Aug 2023
Extended Guide: Instruction-tune Llama 2original ↗
26 Jul 2023
LLaMA 2 - Every Resource you needoriginal ↗
21 Jul 2023
Fine-tune LLaMA 2 (7-70B) on Amazon SageMakeroriginal ↗
18 Jul 2023
Train LLMs using QLoRA on Amazon SageMakeroriginal ↗
13 Jul 2023
Deploy LLMs with Hugging Face Inference Endpointsoriginal ↗
4 Jul 2023
Optimize and Deploy BERT on AWS inferentia2original ↗
28 Jun 2023
Securely deploy LLMs inside VPCs with Hugging Face and Amazon SageMakeroriginal ↗
20 Jun 2023
Deploy Falcon 7B and 40B on Amazon SageMakeroriginal ↗
7 Jun 2023
Fine-tune BERT for Text Classification on AWS Trainiumoriginal ↗
6 Jun 2023
Introducing the Hugging Face LLM Inference Container for Amazon SageMakeroriginal ↗
31 May 2023
Generative AI for Document Understanding with Hugging Face and Amazon SageMakeroriginal ↗
23 May 2023
How to scale LLM workloads to 20B+ with Amazon SageMaker using Hugging Face and PyTorch FSDPoriginal ↗
2 May 2023
Setting up AWS Trainium for Hugging Face Transformersoriginal ↗
25 Apr 2023
Train and Deploy BLOOM with Amazon SageMaker and PEFToriginal ↗
13 Apr 2023
Introducing IGEL an instruction-tuned German large Language Modeloriginal ↗
4 Apr 2023
Efficient Large Language Model training with LoRA and Hugging Faceoriginal ↗
23 Mar 2023
Deploy FLAN-UL2 20B on Amazon SageMakeroriginal ↗
20 Mar 2023
Getting started with Pytorch 2.0 and Hugging Face Transformersoriginal ↗
16 Mar 2023
Controlled text-to-image generation with ControlNet on Inference Endpointsoriginal ↗
3 Mar 2023
Combine Amazon SageMaker and DeepSpeed to fine-tune FLAN-T5 XXLoriginal ↗
22 Feb 2023
Fine-tune FLAN-T5 XL/XXL using DeepSpeed and Hugging Face Transformersoriginal ↗
16 Feb 2023
Deploy FLAN-T5 XXL on Amazon SageMakeroriginal ↗
8 Feb 2023
Hugging Face Transformers Examplesoriginal ↗
26 Jan 2023
Getting started with Transformers and TPU using PyTorchoriginal ↗
16 Jan 2023

2022

Fine-tune FLAN-T5 for chat and dialogue summarizationoriginal ↗
27 Dec 2022
Managed Transcription with OpenAI Whisper and Hugging Face Inference Endpointsoriginal ↗
20 Dec 2022
Stable Diffusion Inpainting example with Hugging Face inference Endpointsoriginal ↗
15 Dec 2022
Stable Diffusion with Hugging Face Inference Endpointsoriginal ↗
28 Nov 2022
Document AI: LiLT a better language agnostic LayoutLM modeloriginal ↗
22 Nov 2022
Multi-Model GPU Inference with Hugging Face Inference Endpointsoriginal ↗
17 Nov 2022
Serverless Machine Learning Applications with Hugging Face Gradio and AWS Lambdaoriginal ↗
15 Nov 2022
Accelerate Stable Diffusion inference with DeepSpeed-Inference on GPUsoriginal ↗
8 Nov 2022
Stable Diffusion on Amazon SageMakeroriginal ↗
1 Nov 2022
Deploy T5 11B for inference for less than $500original ↗
25 Oct 2022
Outperform OpenAI GPT-3 with SetFit for text-classificationoriginal ↗
18 Oct 2022
Fine-tuning LayoutLM for document-understanding using Keras and Hugging Face Transformersoriginal ↗
13 Oct 2022
Deploy LayoutLM with Hugging Face Inference Endpointsoriginal ↗
6 Oct 2022
Document AI: Fine-tuning LayoutLM for document-understanding using Hugging Face Transformersoriginal ↗
4 Oct 2022
Custom Inference with Hugging Face Inference Endpointsoriginal ↗
29 Sept 2022
Accelerate GPT-J inference with DeepSpeed-Inference on GPUsoriginal ↗
13 Sept 2022
Document AI: Fine-tuning Donut for document-parsing using Hugging Face Transformersoriginal ↗
6 Sept 2022
Use Sentence Transformers with TensorFloworiginal ↗
30 Aug 2022
Pre-Training BERT with Hugging Face Transformers and Habana Gaudioriginal ↗
24 Aug 2022
Accelerate BERT inference with DeepSpeed-Inference on GPUsoriginal ↗
16 Aug 2022
Accelerate Sentence Transformers with Hugging Face Optimumoriginal ↗
2 Aug 2022
Deep Learning setup made easy with EC2 Remote Runner and Habana Gaudioriginal ↗
26 Jul 2022
Accelerate Vision Transformer (ViT) with Quantization using Optimumoriginal ↗
19 Jul 2022
Optimizing Transformers for GPUs with Optimumoriginal ↗
13 Jul 2022
Hugging Face Transformers and Habana Gaudi AWS DL1 Instancesoriginal ↗
5 Jul 2022
Optimizing Transformers with Hugging Face Optimumoriginal ↗
30 Jun 2022
Convert Transformers to ONNX with Hugging Face Optimumoriginal ↗
21 Jun 2022
Setup Deep Learning environment for Hugging Face Transformers with Habana Gaudi on AWSoriginal ↗
14 Jun 2022
Static Quantization with Hugging Face `optimum` for ~3x latency improvementsoriginal ↗
7 Jun 2022
Advanced PII detection and anonymization with Hugging Face Transformers and Amazon SageMakeroriginal ↗
31 May 2022
An Amazon SageMaker Inference comparison with Hugging Face Transformersoriginal ↗
17 May 2022
Semantic Segmantion with Hugging Face's Transformers and Amazon SageMakeroriginal ↗
3 May 2022
Automatic Speech Recogntion with Hugging Face's Transformers and Amazon SageMakeroriginal ↗
28 Apr 2022
Serverless Inference with Hugging Face's Transformers, DistilBERT and Amazon SageMakeroriginal ↗
21 Apr 2022
Accelerated document embeddings with Hugging Face Transformers and AWS Inferentiaoriginal ↗
19 Apr 2022
Save up to 90% training cost with AWS Spot Instances and Hugging Face Transformersoriginal ↗
22 Mar 2022
Speed up BERT inference with Hugging Face Transformers and AWS Inferentiaoriginal ↗
16 Mar 2022
Creating document embeddings with Hugging Face's Transformers and Amazon SageMakeroriginal ↗
8 Mar 2022
Autoscaling BERT with Hugging Face Transformers, Amazon SageMaker and Terraform moduleoriginal ↗
1 Mar 2022
Multi-Container Endpoints with Hugging Face Transformers and Amazon SageMakeroriginal ↗
22 Feb 2022
Asynchronous Inference with Hugging Face Transformers and Amazon SageMakeroriginal ↗
15 Feb 2022
Deploy BERT with Hugging Face Transformers, Amazon SageMaker and Terraform moduleoriginal ↗
8 Feb 2022
Task-specific knowledge distillation for BERT using Transformers and Amazon SageMakeroriginal ↗
1 Feb 2022
Distributed training on multilingual BERT with Hugging Face Transformers and Amazon SageMakeroriginal ↗
25 Jan 2022
Financial Text Summarization with Hugging Face Transformers, Keras and Amazon SageMakeroriginal ↗
19 Jan 2022
Deploy GPT-J 6B for inference using Hugging Face Transformers and Amazon SageMakeroriginal ↗
11 Jan 2022
Image Classification with Hugging Face Transformers and `Keras`original ↗
4 Jan 2022

2021

Workshop: Enterprise-Scale NLP with Hugging Face and Amazon SageMakeroriginal ↗
29 Dec 2021
Hugging Face Transformers with Keras: Fine-tune a non-English BERT for Named Entity Recognitionoriginal ↗
21 Dec 2021
New Serverless Transformers using Amazon SageMaker Serverless Inference and Hugging Faceoriginal ↗
15 Dec 2021
Hugging Face Transformers BERT fine-tuning using Amazon SageMaker and Training Compileroriginal ↗
7 Dec 2021
MLOps: Using the Hugging Face Hub as model registry with Amazon SageMakeroriginal ↗
16 Nov 2021
A remote guide to re:Invent 2021 machine learning sessionsoriginal ↗
11 Nov 2021
MLOps: End-to-End Hugging Face Transformers with the Hub and SageMaker Pipelinesoriginal ↗
10 Nov 2021
Going Production: Auto-scaling Hugging Face Transformers with Amazon SageMakeroriginal ↗
29 Oct 2021
Deploy BigScience T0_3B to AWS and Amazon SageMakeroriginal ↗
20 Oct 2021
Scalable, Secure Hugging Face Transformer Endpoints with Amazon SageMaker, AWS Lambda, and CDKoriginal ↗
6 Oct 2021
Few-shot learning in practice with GPT-Neooriginal ↗
5 Jun 2021
Distributed Training: Train BART/T5 for Summarization using 🤗 Transformers and Amazon SageMakeroriginal ↗
9 Apr 2021

2020

Multilingual Serverless XLM RoBERTa with HuggingFace, AWS Lambdaoriginal ↗
17 Dec 2020
Serverless BERT with HuggingFace, AWS Lambda, and Dockeroriginal ↗
6 Dec 2020
AWS Lambda with custom docker images as runtimeoriginal ↗
2 Dec 2020
New Serverless BERT with Huggingface, AWS Lambda, and AWS EFSoriginal ↗
15 Nov 2020
efsync my first open-source MLOps toolkitoriginal ↗
4 Nov 2020
My path to become a certified solution architectoriginal ↗
24 Oct 2020
Create custom Github Action in 4 stepsoriginal ↗
25 Sept 2020
Fine-tune a non-English GPT-2 Model with Huggingfaceoriginal ↗
6 Sept 2020
Previous Next