philschmid.de - RSS feed

Learn common agentic design patterns and workflows for building robust, scalable AI applications, understanding when to use each.

A comprehensive cheatsheet on using Google's Gemini within the LangChain, covering chat functionalities with multimodal inputs, tool usage, structured data generation, and text embedding techniques.

I used Gemini 2.5 Pro to better understand the OpenAI Codex CLI, a tool that allows you to interact with an AI model directly in your terminal to perform coding tasks.

Overview of the Model Context Protocol (MCP) how it works, what are MCP servers and clients, and how to use it.

Build a ReAct agent from scratch with Gemini 2.5 and LangGraph.

Production agents need to be reliable.

Learn how to use function calling with Google DeepMind Gemma 3 27B It

Learn how to use function calling with Google DeepMind Gemini 2.0 Flash.

Learn how to extract structured data from PDFs with Gemini 2.0 and Pydantic.

Reproduce Deepseek R1 „aha moment“ and train an open model using reinforcement learning trying to teach it self-verification and search abilities all on its own to solve the Countdown Game.

Learn how to align LLMs using Hugging Face TRL and RLHF through Direct Preference Optimization (DPO) and on-policy synthetic data.

How to use Anthropic MCP Server with open LLMs, OpenAI or Google Gemini

5 Minute Read on how Deepseek R1 was trained using Group Relative Policy Optimization (GRPO) and RL-focused multi-stage training approach.

Modern updated guide on how to fine-tune BERT models for classification tasks in 2025.

The only guide you need to fine-tune open LLMs in 2025, including QLoRA, Spectrum, Flash Attention, Liger Kernels and more.

Qwen's QwQ-32B-Preview is the best open reasoning model for mathematical and programming reasoning capabilities among open models directly competing with OpenAI o1.

Learn how to deploy Llama 3.2 Vision on Amazon SageMaker and run inference with it.

Learn how to fine-tune multimodal models like Llama 3.2 Vision or Qwen 2 VL to create custom image-to-text generation models.

Evaluate Llama 3.1 8B on Vertex AI with Gemini 1.5 Pro as LLM as a Judge using the Gen AI Evaluation Service.

Evaluate Llama 3.1 8B Instruct on IFEval and GSM8K benchmarks with Chain of Thought reasoning using Evaluation Harness and Hugging Face TGI/vLLM.

Learn how to deploy open large language models (LLMs) like Llama 3.1 8B Instruct to Amazon SageMaker using Terraform Infrastructure as Code (IaC).

LLM Evaluation doesn't need to be complicated.

Evaluate open LLMs with MixEval, the closest benchmark to LMSYS Chatbot Arena for a fraction of the cost and time.

Learn how to fine-tune and deploy a custom embedding model on Amazon SageMaker using the new Hugging Face Embedding Container.

Deploy Mixtral 8x7B to AWS Inferentia2 with Hugging Face Optimum on Amazon SageMaker and benchmark it with llmperf.

Train and deploy Llama 3 on Amazon SageMaker using PyTorch FSDP and Q-Lora

Customizing embedding models for domain-specific data can significantly boost the retrieval performance of your RAG Application.

The cost of deploying Generative AI models is very shallow, many people are fixated on raw compute pricing.

Learn how to deploy Llama 3 70B on AWS Inferentia2 with Hugging Face Optimum on Amazon SageMaker.

In this blog post, we will show you how to deploy open LLMS with vLLM on Hugging Face Inference Endpoints.

Learn how to fine-tune Llama 3 70b with PyTorch FSDP and Q-Lora using Hugging Face TRL, Transformers, PEFT and Datasets.

In this blog post you will learn how to deploy Llama 3 70B to Amazon SageMaker.

In this blog post you will learn how to accelerate Mixtral using Speculative Decoding (Medusa) and Quantization (AWQ).

In this blog post you will learn how to deploy Meta Llama 2 70B on AWS Inferentia2 with Hugging Face Optimum on Amazon SageMaker.

In this blog post you will learn how to fine-tune open LLMs from Hugging Face using Amazon SageMaker.

In this blog post you will learn how to evaluate LLMs using Hugging Face lighteval on Amazon SageMaker.

In this blog post you will learn how to fine tune Google Gemma using Hugging Face Transformers, Datasets and TRL.

In this blog post you will learn how to fine-tune LLMs using Hugging Face TRL, Transformers and Datasets in 2024.

In this blog post you will learn how to align LLMs using Hugging Face TRL and RLHF through Direct Preference Optimization (DPO).

In this blog post you will learn how to increase the throughput of Llama 13B on Amazon SageMaker using single instance multi-replica endpoints.

In this blog post you will learn how to fine-tune Llama 7B on AWS Trainium using the Hugging Face Optimum Neuron library.

In this blog post you will learn how to use the huggingface_hub library to create, send requests to, pause, and delete Hugging Face Inference Endpoints.

In this blog post you will learn how to deploy Mixtral 8x7B to Amazon SageMaker.

In this blog post, you will learn how to compile and deploy Embedding Models on AWS Inferentia2.

In this blog post, you will learn how to compile and deploy Llama 2 7B on AWS Inferentia2 with Amazon SageMaker.

In this blog post, you will learn how to compile and deploy Stable Diffusion XL on AWS Inferentia2 with Amazon SageMaker.

In this blog post I took a closer look at Amazon Bedrock Titan embeddings model and how good (bad) the perform.

Learn how to evaluate LLMs and RAG pipelines using Langchain and Hugging Face

Learn how to deploy Hugging Face Idefics 9B and 80B to Amazon SageMaker and send requests with images and text to the model.

Learn how to fine-tuned and deploy Mistral 7B with Hugging Face on Amazon SageMaker and leverage technique like Qlora, Flash Attention and response streaming