ArkMaster123/qwen2.5-7b-therapist-v3
ArkMaster123/qwen2.5-7b-therapist-v3 is a 7.6 billion parameter language model based on the Qwen2.5-7B-Instruct architecture, specifically fine-tuned for empathetic and supportive conversational assistance in mental wellness contexts. This model excels at generating responses suitable for therapeutic interactions, leveraging a curated mix of counseling conversation datasets. Its primary use case is providing conversational support for mental health applications, distinguishing it from general-purpose LLMs.
Loading preview...
Overview
ArkMaster123/qwen2.5-7b-therapist-v3 is a specialized 7.6 billion parameter language model built upon the robust Qwen2.5-7B-Instruct base. It has been fine-tuned using a LoRA adapter on a carefully selected mixture of public counseling conversation datasets, including Amod/mental_health_counseling_conversations, nbertagnolli/counsel-chat, and IINOVAII/therapy-conversations-combined. The model was trained with a fast profile over 120 steps using packed sequences and bf16 on H100 multi-GPU, resulting in a merged model optimized for direct inference.
Key Capabilities
- Empathetic Conversation: Designed to generate supportive and understanding responses.
- Mental Wellness Context: Optimized for interactions within mental health and counseling scenarios.
- Instruction-Following: Benefits from the strong instruction-following capabilities of its Qwen2.5-7B-Instruct base.
Intended Use
This model is specifically intended for providing supportive, empathetic conversational assistance in mental wellness contexts. It is crucial to note that this model is not a substitute for licensed professional care, and users in crisis or immediate danger should contact emergency services or a crisis hotline.