Orca 2 13B

Orca 2 13B, developed by Microsoft, is a large language model designed primarily for research purposes. It is a fine-tuned version of the LLaMA-2 base model, focusing on enhanced reasoning capabilities in smaller language models. This is achieved through training on a synthetic dataset specifically created to improve reasoning skills. Orca 2 13B excels in tasks such as reading comprehension, math problem-solving, and text summarization. However, it is not optimized for chat applications and requires fine-tuning for specific tasks. The model demonstrates strong performance in zero-shot settings but shares common LLM limitations, such as potential biases and a lack of contextual understanding. It is primarily suitable for research and not recommended for deployment without further evaluation. 124 3 7 8.

Orca 2 13B is an open-weight model in the Orca 2 family. The structured metadata tracks a 4k-token context window. This page tracks provider routes through Microsoft Foundry, with the cheapest tracked route listed at $0.81 input and $0.94 output per 1M tokens. Headline tracked benchmarks include HumanEval 35.2 and Massive Multitask Language Understanding 70.8.