shuff57/lfm2-24B-stat-grader-lora
#2937
by testamentaddress01 - opened
Regarding the final training checkpoint for shuff57/lfm2-24b-phase1-reasoning, it is inconvenient that it has been split off as shuff57/lfm2-24B-stat-grader-lora. Could you please merge the LoRA and quantize the model?
I cannot merge lora, author needs to merge lora and then we can queue and quantize the model
In that pattern, please quantize shuff57/lfm2-24b-phase1-reasoning.
testamentaddress01 changed discussion status to closed