Model Card for Kurtis-SmolLM2-1.7B-Instruct

This model has been fine-tuned using Kurtis, an experimental fine-tuning, inference and evaluation tool for Small Language Models.

Model Details

Model Description

• Developed by: Massimo R. Scamarcia massimo.scamarcia@gmail.com
• Funded by: Massimo R. Scamarcia massimo.scamarcia@gmail.com - (self-funded)
• Shared by: Massimo R. Scamarcia massimo.scamarcia@gmail.com
• Model type: Transformer decoder
• Language(s) (NLP): English
• License: MIT
• Finetuned from model: HuggingFaceTB/SmolLM2-1.7B-Instruct

Model Sources

• Repository: https://github.com/mrs83/kurtis

Uses

The model is intended for use in a conversational setting, particularly in mental health and therapeutic support scenarios.

Direct Use

Not suitable for production usage.

Out-of-Scope Use

This model should not be used for:

• Making critical mental health decisions or diagnoses.
• Replacing professional mental health services.
• Applications where responses require regulatory compliance or are highly sensitive.
• Generating responses without human supervision, especially in contexts that involve vulnerable individuals.

Bias, Risks, and Limitations

Misuse of this dataset could lead to providing inappropriate or harmful responses, so it should not be deployed without proper safeguards in place.

Recommendations

Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model.

How to Get Started with the Model

WIP