Llama 3 8B Customer Support

Published by @support_craft · Community adapter

Trained on 100 k anonymised support tickets with human-written resolutions. Empathetic, solution-first tone. Handles refunds, escalations, and onboarding queries across SaaS, e-commerce, and fintech domains.

Usage

from peft import PeftModel
from transformers import AutoModelForCausalLM, AutoTokenizer

tokenizer = AutoTokenizer.from_pretrained("meta-llama/Meta-Llama-3-8B-Instruct")
base = AutoModelForCausalLM.from_pretrained("meta-llama/Meta-Llama-3-8B-Instruct")
model = PeftModel.from_pretrained(base, "modelforgelab/llama3-8b-customer-support-lora")

inputs = tokenizer("Your prompt here", return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=256)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

Compatibility

• transformers>=4.40
• vLLM