Modelpublic

MypodW23/Mistral-7B-bfsi-policy-lora-v1

sourceHugging Faceapache-2.0updated 4mo agoView on Hugging Face

0likes3downloads

Model Card

Mistral-7B-bfsi-policy-lora-v1

Mistral-7B fine-tuned on Indian BFSI policy QA. LoRA (r=16, alpha=32).

Usage

python

from peft import PeftModel
from transformers import AutoModelForCausalLM, AutoTokenizer
base = AutoModelForCausalLM.from_pretrained("mistralai/Mistral-7B-Instruct-v0.3")
model = PeftModel.from_pretrained(base, "MypodW23/Mistral-7B-bfsi-policy-lora-v1")
tok = AutoTokenizer.from_pretrained("MypodW23/Mistral-7B-bfsi-policy-lora-v1")