Saiga (Saiga tatarica) was extirpated in China. Since Mid-1980s, attempts have been made for revival the species in the country, however, only a breeding herd of Saiga was successfully established at Wuwei, Gansu, China. The reintroduced Saiga population experienced a bumpy growth. Then, the population collapsed following the catastrophe die-off in the Saiga ranging countries in Central Asia, then population started to rebound when 6 new lams were born in 2019. After reviewing the population trend and conservation breeding of Saiga in China, we concluded that to establish a migratory species that needs vast range size like Saiga on central Asia steppe, an international collaboration is needed for introducing new genes. We recommend China to ratify the CMS in order to facilitate international conservation efforts to restoring the species in its former range.

The purpose of this paper is to explore the implementation of Retrieval-Augmented Gen- 14 eration (RAG) technology with open-source Large Language Models (LLMs). For this purpose, a 15 web-based application named PaSSER that integrates RAG with three models - Mistral:7b, 16 Llama2:7b: Orca2:7b, is developed. In its development various technologies are used, including 17 Blockchain for managing and storing assessment results of built-in testing modules. PaSSER em- 18 ploys a set of evaluation metrics for LLMs’ performance - METEOR, ROUGE, BLEU, Perplexity, 19 Cosine similarity, Pearson correlation, and F1 score. The specialized knowledge base is in the smart 20 agriculture domain. As an illustration, the paper presents results and analysis of two tests. First one 21 is assessing the performance of LLMs across different hardware configurations, the other is deter- 22 mining the model that delivers most accurate and contextually relevant responses within the RAG. 23 The paper also discusses the integration of blockchain technology with LLMs to manage and store 24 assessment results within a blockchain environment. The tests revealed that Mistral:7b demon- 25 strates the best results across most of the evaluated metrics. The discussion section comments on 26 technical and hardware considerations that affect the performance of LLMs. Future development 27 will focus in leveraging new larger pre-trained open-source LLMs, exploring different finetuning 28 approaches, and further integration with Blockchain and IPFS.