AI正在发生 未来正在更新Llama-3.2-3B-Instruct-NEO-WEE-HORROR-GGUF
It is the new "Llama-3.2-3B-Instruct", max context of 131,000 (128k) with the NEO IMATRIX Tiny "Wee" Horror Dataset. The power in this 3B (for its size) is frankly jaw dropping... and at 90 tokens per second + on a GPU. The NEO IMATRIX dataset V2 was applied to it to enhance creativity (horror). (see several examples below)
译文尚未就绪，显示来源原文
It is the new "Llama-3.2-3B-Instruct", max context of 131,000 (128k) with the NEO IMATRIX Tiny "Wee" Horror Dataset. The power in this 3B (for its size) is frankly jaw dropping... and at 90 tokens per second + on a GPU. The NEO IMATRIX dataset V2 was applied to it to enhance creativity (horror). (see several examples below)