liodon-ai/bloom-560m-FP8
Quantization vs bigscience/bloom-560m. liodon-ai/bloom-560m-FP8 is a quantized version of the other (F16/F8_E4M3).
Quantization vs bigscience/bloom-560m. liodon-ai/bloom-560m-FP8 is a quantized version of the other (F16/F8_E4M3).