ClaudioSavelli/FAME-topics_PO_llama32-3b-instruct-qa
TEXT GENERATIONConcurrency Cost:1Model Size:3.2BQuant:BF16Ctx Length:32kPublished:Apr 2, 2026License:otherArchitecture:Transformer Loading

ClaudioSavelli/FAME-topics_PO_llama32-3b-instruct-qa is a 3.2 billion parameter instruction-tuned language model, derived from the Llama-3.2-3B-Instruct architecture. This model has been unlearned using a Preference Optimization method specifically for the FAME-topics setting. It is designed to handle question-answering tasks within this specialized context, leveraging its 32768-token context length for detailed interactions.

Loading preview...