用微调的Llama2预测渔区，帮印度渔民多捕鱼、少冒险。
Jal Anveshak: Prediction of fishing zones using fine-tuned LlaMa 2
- 用政府渔业数据微调Llama2模型，生成渔区建议。
- 支持多语言多模态查询，提升沿海渔民决策效率。
- 专为印度沿海渔民设计，兼顾实用性与可访问性。
近年来，全球及印度政府在渔业监测与数据收集方面取得显著进展。尽管数据资源丰富，但人工智能技术在助力印度沿海渔民方面的潜力尚未充分挖掘。为填补这一技术空白，作者提出Jal Anveshak——一个基于Dart和Flutter开发的应用框架，采用在预处理和增强的渔业产量与资源数据上微调的Llama 2大语言模型，旨在帮助印度渔民安全高效地获取最大渔获量，并以多语言、多模态方式解答其渔业相关问题。
原文摘要 · Abstract (English)
In recent years, the global and Indian government efforts in monitoring and collecting data related to the fisheries industry have witnessed significant advancements. Despite this wealth of data, there exists an untapped potential for leveraging artificial intelligence based technological systems to benefit Indian fishermen in coastal areas. To fill this void in the Indian technology ecosystem, the authors introduce Jal Anveshak. This is an application framework written in Dart and Flutter that uses a Llama 2 based Large Language Model fine-tuned on pre-processed and augmented government data related to fishing yield and availability. Its main purpose is to help Indian fishermen safely get the maximum yield of fish from coastal areas and to resolve their fishing related queries in multilingual and multimodal ways.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。