Modelpublic

thejaminator/extreme_sports-gemma-2-9b-it-sft-20251029

sourceHugging Faceupdated 11mo agoView on Hugging Face

0likes11downloads

Model Card

LoRA Adapter for SFT

This is a LoRA (Low-Rank Adaptation) adapter trained using supervised fine-tuning (SFT).

Base Model

—Base Model: google/gemma-2-9b-it
—Adapter Type: LoRA
—Task: Supervised Fine-Tuning

Usage

python

from transformers import AutoModelForCausalLM, AutoTokenizer
from peft import PeftModel

# Load base model and tokenizer
base_model = AutoModelForCausalLM.from_pretrained("google/gemma-2-9b-it")
tokenizer = AutoTokenizer.from_pretrained("google/gemma-2-9b-it")

# Load LoRA adapter
model = PeftModel.from_pretrained(base_model, "thejaminator/extreme_sports-gemma-2-9b-it-sft-20251029")

Training Details

This adapter was trained using supervised fine-tuning on conversation data to improve the model's ability to follow instructions and generate helpful responses.