Through additional training, we explore embedding specialized scientific knowledge into the Llama 2 Large Language Model (LLM). Key findings reveal that effective knowledge integration requires reading texts from multiple perspectives, especially in instructional formats. We utilize text augmentation to tackle the scarcity of specialized texts, including style conversions and translations. Hyperparameter optimization proves crucial, with different size models (7b, 13b, and 70b) reasonably undergoing additional training. Validating our methods, we construct a dataset of 65,000 scientific papers. Although we have succeeded in partially embedding knowledge, the study highlights the complexities and limitations of incorporating specialized information into LLMs, suggesting areas for further improvement.

On Tuesday, Yamato Transport Co. and DeNA Co. tested an autonomous vehicle delivery service to gauge the potential of self-driving technology in the field of logistics. The two Tokyo-based companies conducted the experiment in Fujisawa, Kanagawa Prefecture, in which an electric car navigated through a short, quarantined road without anyone sitting in the driver's seat. A person sat in the front passenger seat to observe the operation. During one demonstration, the vehicle, equipped with a camera and infrared sensor, ran through the residential area at 5 to 10 kph. When the delivery car arrived at its destination, a customer opened up a box inside the vehicle, allowed a QR code on her smartphone to be scanned, and picked up the product.