Mental healthcare Chat robots (Chatbots) represent artificial intelligent-powered conversational programs or agents built to provide guidance and support concerning well-being and mental health. These programs exploited natural language processing (NLP) and large language models (LLMs) like generative pre-trained transformer (GPT) models to offer mental health services to users in a human-like manner. The most common functionalities of these services are emotional support, psychoeducation, symptom assessment, etc. Therefore, there is a need for providing mental health Chatbots capable of complementing traditional mental health services by providing convenient and accessible support to individuals. An efficient mental healthcare Chatbot based on a fine-tuned GPT-2 model has been proposed in this paper. The transformer was fine-tuned via training it on a mental health-related Q&A dataset in the English language, to improve the performance of the proposed Chatbot in this specified task and to minimize issues generated by hallucinations. The obtained outcomes prove that the proposed Chatbot is a feasible helper to human evaluation and performs comparably to an expert assessor. This work is a basis for future research on LLMs-based evaluation techniques with the possibility for additional optimizations and larger reliability.