Modelpublic

kshitijthakkar/deepseek-v4-mini-300M-from-flash-sft-test-lora

sourceHugging Faceupdated 5mo agoView on Hugging Face

0likes7downloads

Model Card

LoRA adapter for kshitijthakkar/deepseek-v4-mini-300M-from-flash

SFT LoRA adapter. Load with:

python

from peft import PeftModel
from transformers import AutoModelForCausalLM, AutoTokenizer

base = AutoModelForCausalLM.from_pretrained(
    "kshitijthakkar/deepseek-v4-mini-300M-from-flash", trust_remote_code=True
)
model = PeftModel.from_pretrained(base, "kshitijthakkar/deepseek-v4-mini-300M-from-flash-sft-test-lora")
tokenizer = AutoTokenizer.from_pretrained("kshitijthakkar/deepseek-v4-mini-300M-from-flash", trust_remote_code=True)