HiTZ/Latxa-Llama-3.1-70B-Instruct-v2-FP8

Quantization vs HiTZ/Latxa-Llama-3.1-70B-Instruct. HiTZ/Latxa-Llama-3.1-70B-Instruct-v2-FP8 is a quantized version of the other (F8_E4M3/F16).

On the Hub · Downloads on Model Pulse