mesolitica/Qwen2.5-72B-Instruct-FP8
Quantization vs Qwen/Qwen2.5-72B-Instruct. mesolitica/Qwen2.5-72B-Instruct-FP8 is a quantized version of the other (F8_E4M3/BF16).
3 other repos hold byte-for-byte identical weight files.
Quantization vs Qwen/Qwen2.5-72B-Instruct. mesolitica/Qwen2.5-72B-Instruct-FP8 is a quantized version of the other (F8_E4M3/BF16).
3 other repos hold byte-for-byte identical weight files.