Tag: llm
-
Which Model for What: a Hugging Face Model Map for Text, Vision, Audio and Video (Hugging Face Series, Part 17)
A task-to-model map for Hugging Face: which model family to use for chat, search, transcription, speech, captioning, image and video, with sizes, licenses, the right library, and the GPU it needs.
-
Text Generation Inference (TGI) in Production: A Real Serving Example (Hugging Face Series, Part 12)
TGI turns a Hugging Face model into an OpenAI-compatible endpoint with one docker run. Here are the flags that decide whether it fits your VRAM, how to consume it, and an honest verdict now that TGI is in maintenance mode and Hugging Face points new builds at vLLM.
-
How to Run a Hugging Face Model: Inference Providers vs Endpoints vs Self-Host (Hugging Face Series, Part 11)
Three ways to serve a Hugging Face model: the serverless Inference Providers proxy, dedicated Inference Endpoints, or self-hosting TGI on your own GPUs. A build-vs-buy verdict for the infra team that owns the bill.
-
Hugging Face Tokenizers: Context Limits, Token Budgets, and Capacity (Hugging Face Series, Part 5)
Tokenizers turn text into the integers a model reads, and they decide your context limit, throughput and token bill. An infra-first guide to encoding, batching, padding waste, and what changed in Transformers v5.
-
What Hugging Face Actually Is: the Hub, the Libraries, and the Map (Hugging Face Series, Part 1)
Hugging Face is a registry, a set of open-source libraries, and a company. For infrastructure engineers moving into AI, here is the whole platform mapped onto systems you already run.
-
AI Agents: What Actually Works, and What’s Hype (GenAI Series, Part 16)
An AI agent is a model in a loop that plans, calls tools, and observes results. What agents genuinely do well today, and why reliability, not intelligence, is the real bottleneck.
-
Prompt Engineering That Actually Works (GenAI Series, Part 12)
Prompt engineering is not secret incantations, it is clear communication. The four moves that do most of the work, system vs user prompts, and the anti-patterns that waste tokens.
-
Why AI Models Make Things Up (and What Temperature Does) (GenAI Series, Part 11)
AI models generate by sampling likely words from a probability distribution. Why that produces confident hallucinations, what the temperature setting really does, and how to reduce it.
-
The Context Window, and Why Models Forget (GenAI Series, Part 10)
The context window is everything an AI can see at once. Why models have no memory between turns, why longer prompts cost more, and why details get lost in the middle.
-
Attention, the Idea That Made Modern AI Work (GenAI Series, Part 8)
How attention lets every word in a sentence weigh every other word, why it replaced slow left-to-right models, and why running in parallel is what let AI scale.
-
What a Model Really Is (GenAI Series, Part 4)
A model is not a database of answers. It is one large function that predicts the next token, built from billions of parameters. What model sizes and open vs closed weights really mean.
-
The GenAI Words Everyone Uses, and What They Actually Mean (GenAI Series, Part 2)
Model, tokens, parameters, inference, embeddings, hallucination: the words everyone uses about generative AI, sorted into build time and use time and explained in plain English.
Architect’s Toolkit
PJ’s Tools
VMware Cloud Foundation
- VCF Documentation
- VCF 9 Planning & Preparation Workbook
- VCF Bill of Materials (BoM)
- VMware Compatibility Guide
- VMware Interoperability Matrix
- VMware Configuration Maximums
- VMware Ports & Protocols
- VMware Hands-on Labs
- RVTools Download
Nutanix
AI & Cloud-Native Platform
- NVIDIA Build (Model Catalog)
- NVIDIA AI Enterprise Reference Architecture
- NVIDIA NIM Performance Benchmarking
- NVIDIA NGC Catalog
- NeMo Microservices Helm Chart
- Helm Charts Repository
- Hugging Face Models
Architecture & Design
About the Author
Dr Pranay Jha
Dr. Pranay Jha is a Cloud and AI Consultant with 18+ years of experience in hybrid cloud, virtualization, and enterprise infrastructure transformation. He specializes in VMware technologies, multi-cloud strategy, and Generative AI solutions. He holds a PhD in Computer Applications with research focused on Cloud and AI, has published multiple research papers, and has been a VMware vExpert since 2016 and a VMUG Community Leader.
You May Have Missed
DrJha