kashif/stack-llama-2
TEXT GENERATIONConcurrency Cost:1Model Size:7BQuant:FP8Ctx Length:4kPublished:Aug 4, 2023License:bigscience-openrail-mArchitecture:Transformer0.0K Open Weights Cold

kashif/stack-llama-2 is a 7 billion parameter Llama-2 model fine-tuned using Direct Preference Optimization (DPO) for generating human-like responses to questions. It specializes in long-form question-answering across Stack Exchange domains such as programming, mathematics, and physics. This model is optimized to produce answers that would be highly rated on Stack Exchange platforms.

Loading preview...