article thumbnail

Amazon EC2 DL2q instance for cost-efficient, high-performance AI inference is now generally available

AWS Machine Learning Blog

Model category Number of models Examples​ NLP​ 157 BERT, BART, FasterTransformer, T5, Z-code MOE Generative AI – NLP 40 LLaMA, CodeGen, GPT, OPT, BLOOM, Jais, Luminous, StarCoder, XGen Generative AI – Image 3 Stable diffusion v1.5 opt/qti-aic/exec/qaic-exec -m=bert-base-cased/generatedModels/bert-base-cased_fix_outofrange_fp16.onnx

BERT 105
article thumbnail

A Guide to Mastering Large Language Models

Unite.AI

Techniques like Word2Vec and BERT create embedding models which can be reused. BERT produces deep contextual embeddings by masking words and predicting them based on bidirectional context. BERT produces deep contextual embeddings by masking words and predicting them based on bidirectional context.

article thumbnail

Evaluation Derangement Syndrome (EDS) in the GPU-poor’s GenAI. Part 1: the case for Evaluation-Driven Development

deepsense.ai

References A survey of Generative AI Applications , Gozalo-Brizuela R., 2023 From ChatGPT to ThreatGPT: Impact of generative AI in cybersecurity and privacy , Gupta M., 2023 Art and the science of generative AI: A deeper dive , Epstein Z., 2023 [link] [link] [link] BERTScore: Evaluating text generation with BERT , Zhang T.,