sundar-pichai/llama-2-13b
TEXT GENERATIONConcurrency Cost:1Model Size:13BQuant:FP8Ctx Length:4kArchitecture:Transformer Cold

Llama 2 13B is a 13 billion parameter auto-regressive language model developed by Meta, part of the Llama 2 family of models. This pretrained version, converted for Hugging Face Transformers, is designed for general natural language generation tasks. It was trained on a new mix of publicly available online data with a 4096-token context length. The Llama 2 models generally outperform other open-source chat models on various benchmarks.

Loading preview...