voidful/Llama-3.2-8B-Instruct
TEXT GENERATIONConcurrency Cost:1Model Size:8BQuant:FP8Ctx Length:32kPublished:Nov 18, 2024Architecture:Transformer0.0K Warm

voidful/Llama-3.2-8B-Instruct is an 8 billion parameter instruction-tuned causal language model, derived from patching weights of the larger Meta Llama 3.2 11B Vision-Instruct model into a Llama 3.1 8B text-only model. This model aims to leverage the capabilities of the 11B model within a more compact 8B parameter count. It is designed for general instruction-following tasks, demonstrating improved text generation compared to the original 8B model after patching.

Loading preview...