kingabzpro/Llama-3.1-8B-Instruct-Mental-Health-Classification
Hugging Face
TEXT GENERATIONConcurrency Cost:1Model Size:8BQuant:FP8Ctx Length:32kPublished:Jul 28, 2024License:apache-2.0Architecture:Transformer0.0K Open Weights Warm

kingabzpro/Llama-3.1-8B-Instruct-Mental-Health-Classification is a fine-tuned Llama-3.1-8B-Instruct model developed by kingabzpro. This 8 billion parameter model is specifically optimized for text classification tasks related to mental health, distinguishing between Normal, Depression, Anxiety, and Bipolar states. It leverages the Llama 3.1 architecture to provide specialized sentiment analysis for mental health contexts, achieving an overall accuracy of 91.3%.

Loading preview...

Model Overview

This model, kingabzpro/Llama-3.1-8B-Instruct-Mental-Health-Classification, is a specialized fine-tuned version of Meta's Llama-3.1-8B-Instruct. It has been adapted for mental health text classification using the suchintikasarkar/sentiment-analysis-for-mental-health dataset.

Key Capabilities

  • Mental Health Classification: Accurately classifies text into categories: Normal, Depression, Anxiety, and Bipolar.
  • High Accuracy: Achieves an overall accuracy of 91.3% on the fine-tuning dataset.
  • Specific Label Performance: Demonstrates strong performance for 'Normal' (97.2% accuracy) and 'Depression' (91.3% accuracy) labels.
  • Llama 3.1 Base: Benefits from the robust capabilities of the Llama 3.1-8B-Instruct architecture.

Use Cases

  • Sentiment Analysis in Mental Health: Ideal for identifying potential mental health indicators from textual data.
  • Research and Development: Useful for researchers and developers working on applications related to mental well-being assessment.
  • Educational Tool: Can be used as a practical example for fine-tuning large language models for specific classification tasks, as detailed in the associated DataCamp tutorial.
Popular Sampler Settings

Top 3 parameter combinations used by Featherless users for this model. Click a tab to see each config.

temperature
top_p
top_k
frequency_penalty
presence_penalty
repetition_penalty
min_p