You can deploy this model and start earning money today!

jmo00033/
llama-3.2-3b-contranarratives-lora

Name: llama-3.2-3b-contranarratives-lora
Availability: InStock

safetensors

Views

No views yet

LLAMA 3.2 3B Contranarratives LoRA

LoRA adapter trained on CONAN-MT-SP corpus for generating counter-narratives against hate speech.

Model Details

Base Model: meta-llama/Llama-3.2-3B-Instruct
Method: LoRA fine-tuning
Prompt Strategy: Role-Based Prompting
Eval Loss: 0.1281
ROUGE-1: 0.4090

Usage

python

from transformers import AutoTokenizer, AutoModelForCausalLM
from peft import PeftModel

base_model = AutoModelForCausalLM.from_pretrained('meta-llama/Llama-3.2-3B-Instruct', token=HF_TOKEN)
model = PeftModel.from_pretrained(base_model, 'jmo00033/llama-3.2-3b-contranarratives-lora', token=HF_TOKEN)