LLM
Understanding Decoding Strategies in Large Language Models (LLMs)
Explore how Large Language Models (LLMs) choose the next word using decoding strategies. Learn about different methods like greedy search, beam search, and more.
Strategies to Optimize Large Language Model (LLM) Inference Performance
NVIDIA experts share strategies to optimize large language model (LLM) inference performance, focusing on hardware sizing, resource optimization, and deployment methods.
NVIDIA Unveils Pruning and Distillation Techniques for Efficient LLMs
NVIDIA introduces structured pruning and distillation methods to create efficient language models, significantly reducing resource demands while maintaining performance.
LangSmith Enhances LLM Apps with Dynamic Few-Shot Examples
LangSmith introduces dynamic few-shot example selectors, allowing for improved LLM app performance by dynamically selecting relevant examples based on user input.
Character.AI Enters Agreement with Google, Announces Leadership Changes
Character.AI announces a strategic agreement with Google and key leadership changes to accelerate the development of personalized AI products.
NVIDIA Introduces Efficient Fine-Tuning with NeMo Curator for Custom LLM Datasets
NVIDIA's NeMo Curator offers a streamlined method for fine-tuning large language models (LLMs) with custom datasets, enhancing machine learning workflows.
LangSmith Introduces Flexible Dataset Schemas for Efficient Data Curation
LangSmith now offers flexible dataset schemas, enabling efficient and iterative data curation for LLM applications, as announced by LangChain Blog.
Codestral Mamba: NVIDIA's Next-Gen Coding LLM Revolutionizes Code Completion
NVIDIA's Codestral Mamba, built on Mamba-2 architecture, revolutionizes code completion with advanced AI, enabling superior coding efficiency.
Enhancing LLM Tool-Calling Performance with Few-Shot Prompting
LangChain's experiments reveal how few-shot prompting significantly boosts LLM tool-calling accuracy, especially for complex tasks.
NVIDIA and Meta Collaborate on Advanced RAG Pipelines with Llama 3.1 and NeMo Retriever NIMs
NVIDIA and Meta introduce scalable agentic RAG pipelines with Llama 3.1 and NeMo Retriever NIMs, optimizing LLM performance and decision-making capabilities.
Enhancing Agent Planning: Insights from LangChain
LangChain explores the limitations and future of planning for agents with LLMs, highlighting cognitive architectures and current fixes.
NVIDIA NeMo Enhances LLM Capabilities with Hybrid State Space Model Integration
NVIDIA NeMo introduces support for hybrid state space models, significantly enhancing the efficiency and capabilities of large language models.
NVIDIA NeMo Curator Enhances Non-English Dataset Preparation for LLM Training
NVIDIA NeMo Curator simplifies the curation of high-quality non-English datasets for LLM training, ensuring better model accuracy and reliability.
WordSmith Enhances Legal AI Operations with LangSmith Integration
WordSmith leverages LangSmith for prototyping, debugging, and evaluating LLM performance, enhancing operations for in-house legal teams.
LangChain: Understanding Cognitive Architecture in AI Systems
Explore the concept of cognitive architecture in AI, outlining various levels of autonomy and their applications in LLM-driven systems.