bfuzzy1/Gunny
Hugging Face
TEXT GENERATIONConcurrency Cost:1Model Size:3.2BQuant:BF16Ctx Length:32kPublished:Nov 4, 2024Architecture:Transformer Warm

bfuzzy1/Gunny is a 3.2 billion parameter instruction-tuned language model based on the Llama-3.2-3B-Instruct architecture. It has been fine-tuned on the Gunny_x and Gunny_v2_Solo_Dolo datasets, specializing in providing information and resources related to veteran support and mental health. With a 32K context length, this model is designed to offer guidance and direct users to relevant crisis lines and support organizations for veterans.

Loading preview...

Overview

bfuzzy1/Gunny is a 3.2 billion parameter instruction-tuned model built upon the Llama-3.2-3B-Instruct architecture. It features a substantial 32,768 token context length, enabling it to process and generate longer, more detailed responses. The model has been specifically fine-tuned using the Gunny_x and Gunny_v2_Solo_Dolo datasets.

Key Capabilities

  • Veteran Support Information: Provides direct access to crisis line numbers and support organization details for veterans in the US and UK.
  • Resource Navigation: Offers guidance on where veterans can find mental health assistance and support.
  • Informational Retrieval: Designed to retrieve and present critical contact information from official sources.

Good For

  • Quick Access to Crisis Resources: Ideal for applications requiring immediate access to veteran crisis hotlines and support services.
  • Informational Bots: Suitable for chatbots or virtual assistants focused on providing mental health resources for military personnel and veterans.
  • Educational Tools: Can be used in platforms that aim to educate veterans and their families about available support networks.