jlesbegu/
evalllm2025_v2:latest

19 4 months ago

finetuned : python -m mlx_lm.lora --train --model mistralai/Mistral-7B-Instruct-v0.3 --batch-size 4 --fine-tune-type dora --iters 1000 --num-layers 16

tools
... /
params
ed11eda7790d · 30B
{
"stop": [
"[INST]",
"[/INST]"
]
}