LoRA adapter fine-tuned on the label-verified subset of MACD Telugu training data (rows where ground-truth, GPT-5.4, and Claude Opus 4.5 all agreed on the label). Part of the project "Are Multilingual LLMs Reliable Content Moderators of Indic Hate Speech?"

	Training N	Test N	Macro F1
Original (all labels)	24,000	3,000	0.8923
Spot-check (this adapter)	18,865	2,372	0.9497
Δ			+0.0574

LoRA configuration

Parameter	Value
`r`	16
`lora_alpha`	32
`lora_dropout`	0.05
`target_modules`	q_proj, k_proj, v_proj, o_proj
Epochs	3
Learning rate	2 × 10⁻⁴
Precision	bfloat16

Quick start

python

from transformers import AutoTokenizer, AutoModelForCausalLM
from peft import PeftModel
import torch

BASE_MODEL = "meta-llama/Llama-3.1-8B-Instruct"
ADAPTER    = "Sravanigunnu/llama-3.1-8b-macd-telugu-spotcheck-lora"

tokenizer = AutoTokenizer.from_pretrained(ADAPTER, use_fast=True)
base  = AutoModelForCausalLM.from_pretrained(BASE_MODEL, torch_dtype=torch.bfloat16, device_map="auto")
model = PeftModel.from_pretrained(base, ADAPTER)
model.eval()

SYSTEM = (
    "You are a hate speech classifier for social media content. "
    "Classify the given text as abusive or non-abusive. "
    "Reply with only '1' if the text contains hate speech or abuse, "
    "or '0' if it is non-abusive. Do not explain your answer."
)

def classify(text: str) -> int:
    messages = [{"role": "system", "content": SYSTEM},
                {"role": "user",   "content": text}]
    prompt = tokenizer.apply_chat_template(
        messages, tokenize=False, add_generation_prompt=True
    ) + "Label: "
    base_ids = tokenizer.encode(prompt, add_special_tokens=False)
    id0 = tokenizer.encode(prompt + "0", add_special_tokens=False)[len(base_ids)]
    id1 = tokenizer.encode(prompt + "1", add_special_tokens=False)[len(base_ids)]
    ids = tokenizer(prompt, return_tensors="pt").input_ids.to(model.device)
    with torch.no_grad():
        logits = model(ids).logits[0, -1, :]
    probs = torch.softmax(torch.stack([logits[id0], logits[id1]]), dim=-1)
    return int(probs.argmax().item())