tencent/Hy-MT2-1.8B-FP8

Quantization vs tencent/Hy-MT2-1.8B. tencent/Hy-MT2-1.8B-FP8 is a quantized version of the other (F8_E4M3/BF16).

1 other repos hold byte-for-byte identical weight files.

On the Hub · Downloads on Model Pulse