Transformers
llamafile
mixtral
Mixtral-8x7B-Instruct-v0.1-llamafile / mixtral-8x7b-instruct-v0.1.F16.llamafile.cat0

Commit History

Quantize F16 with llamafile-0.8.5
1b8abe4
verified

jartine commited on

Quantize mixtral-8x7b-instruct-v0.1 with llamafile-0.8.4 F16
633b230
verified

jartine commited on

Quantize mixtral-8x7b-instruct-v0.1 with llamafile-0.8.2 F16
9f10d3e
verified

jartine commited on