BozhongXiao
Atomheart-Father
·
AI & ML interests
LLM
Organizations
Atomheart-Father's activity
optimum version cannot support llama3.1 405b
#14 opened 5 months ago
by
Atomheart-Father
error when quantizing my finetuned 405b model using autoawq
16
#13 opened 5 months ago
by
Atomheart-Father
error when quantizing my finetuned 405b model using autoawq
16
#13 opened 5 months ago
by
Atomheart-Father
error when quantizing my finetuned 405b model using autoawq
16
#13 opened 5 months ago
by
Atomheart-Father