LLaMA 3 70B

LLaMA 3 70B features 70 billion parameters and a context window of 32k tokens, optimized for high-performance text generation and understanding across diverse tasks.

Best match

LLaMA 3 8B

LLaMA 3 8B is a compact model with 8 billion parameters, designed for efficient text generation and understanding with a context window of 8k tokens.

Best match

Mistral Large

Mistral Large supports up to 16k tokens with a response latency of 150ms, targeting enterprise-level applications and complex document understanding.

Claude 3 Opus

Claude 3 Opus enhances AI's conversational abilities with a broader understanding of context and intent, featuring a context window of 16k tokens for improved engagement in dialogues.

GPT-4 Turbo

GPT-4 Turbo is optimized for speed and efficiency, providing rapid text generation with a 16k token context window. It is designed for applications requiring fast responses without sacrificing quality.

Mixtral

Mixtral integrates large language processing with generative capabilities, managing up to 16,384 tokens while delivering high-quality content creation and response generation.

Gemini Flash

Gemini Flash focuses on fast inference with a 4k token limit, ideal for applications requiring quick responses while maintaining decent accuracy in language tasks.

Experiment Design for A/B LLM - Advanced

In-depth guide for designing A/B tests specifically for large language models.

Best match

Experiment Design for A/B LLM

A structured approach to designing experiments for A/B testing in language models.

Best match

Localization Glossary Review

Create a structured review process for a localization glossary to ensure consistent terminology across languages.

OpenAI Playground

Provider of widely used frontier model APIs for text, vision, and audio, with strong developer tooling and broad ecosystem adoption across production AI applications.

Best match

Ollama

Local model runtime for running and serving open LLMs on developer machines and private infrastructure, with simple pull/run workflows and API access.

Best match

LangGraph

LangGraph is a library for building stateful, cyclic agent and workflow graphs on top of LangChain—suited to multi-step tools, human-in-the-loop approvals, and durable execution patterns that go beyond linear chains.

Hugging Face Transformers

AI platform and model hub for discovering, hosting, and deploying open models, datasets, and inference endpoints across NLP, vision, audio, and multimodal tasks.

Hugging Face

Hub for open models, datasets, and Spaces demos, plus Inference Endpoints, Transformers, and enterprise features for teams that train, fine-tune, or serve open-weight and partner models at scale.

Groq

GroqCloud offers very low-latency, high-throughput LLM inference using Groq’s LPU-style hardware, with OpenAI-compatible APIs for select open and partner models aimed at interactive and batch production workloads.

LangChain

Application framework for orchestrating LLM workflows, tool calling, retrieval, and agents across multiple providers in Python and TypeScript ecosystems.

DSPy

DSPy is a programming framework for building LM pipelines declaratively—optimizing prompts and few-shot demonstrations with compilers and metrics instead of hand-tuning every string—aimed at researchers and product teams who want systematic prompt improvement tied to eval scores.

Together AI

Inference platform for open-source and frontier model APIs with broad model catalog coverage, cost controls, and production endpoints for text and multimodal workloads.

LanceDB

LanceDB is an embedded, serverless-friendly vector database built on the Lance columnar format—optimized for multimodal and large-scale local or object-store–backed retrieval with a small operational footprint for data science and edge-style deployments.

Reducing Hallucinations with Citation Constraints in Academic Research Models

This tutorial outlines methods to reduce hallucinations in academic research models by implementing citation constraints. It targets researchers and developers working on language models for academic purposes. Prerequisites include familiarity with natural language processing and model training.

Best match

Observability: Traces for LLM + Tool Spans

Implementing observability practices to trace interactions between large language models (LLMs) and external tools. Prerequisites include knowledge of observability tools and LLM architectures.

Best match

Canary Prompts for Regression Detection

Utilizing canary prompts to detect regressions in language models. Prerequisites include familiarity with regression testing and LLM evaluation metrics.

SLI/SLO for Generative Endpoints

Establishing Service Level Indicators (SLIs) and Service Level Objectives (SLOs) for generative endpoints is crucial for maintaining quality and reliability. This tutorial outlines how to define and implement SLIs/SLOs effectively.

Multimodal Prompts for Document QA in Legal Settings

Using multimodal prompts can improve document question answering (QA) in legal contexts. Prerequisites include access to relevant legal documents and a model capable of processing multimodal inputs.

Quantization Impact on Retrieval Quality in Healthcare Applications

This tutorial investigates the effects of quantization on retrieval quality in healthcare applications, focusing on the trade-offs between model size and accuracy. Prerequisites include a basic understanding of machine learning models and quantization techniques.

Reducing Hallucinations with Citation Constraints in Academic Research

This tutorial explores how to effectively implement citation constraints to minimize hallucinations in academic research models. Prerequisites include familiarity with natural language processing (NLP) and access to a research dataset.

GPT-4o vs Claude 3.5 Sonnet

OpenAI’s default multimodal workhorse versus Anthropic’s steerable Sonnet: compare latency expectations, vision + tool calling, and how each lands in Azure/OpenAI versus Bedrock/Anthropic APIs for production assistants.

Best match

Gemini 1.5 Pro vs GPT-4o

Google’s long-context Gemini 1.5 Pro versus OpenAI’s GPT-4o: choose between multimodal + huge context (Gemini) and ubiquitous API + tool ecosystem (GPT-4o) for RAG and assistants.

Best match

scalable-dot-product-attention

An efficient variant of attention mechanism designed for large datasets.

Best match

transformer-architecture

A neural network architecture designed for sequence-to-sequence tasks.

Best match

multi-modal-learning

An approach that integrates multiple types of data modalities to improve model performance.

generative-models

Models that can generate new data instances similar to the training data.

model-compression

Techniques for reducing the size and complexity of machine learning models while maintaining performance.

noisy-labels

Labels in a dataset that are inaccurate or wrong, often leading to misguidance in model training.

graph-attention-network

A neural network architecture that employs attention mechanisms to process graph-structured data.